This is another set of system call changes that were intended to get merged much earlier. I've rebased the patches on top of the latest kernel and Deepa's poll/select/io_pgetevents series now, and applied it to the same y2038 branch for inclusion in 4.21.
This is just a continuation of the earlier system call changes, so I expect no surprises here, unless I made a mistake in the rebase.
After this series, the only remaining system calls that need to be modified are:
- setsockopt/getsockopt, they do not need a new entry in the system call table, only new numbers assigned for their socket options. Deepa is finalizing her series to passing 64-bit timestamps in cmsg correctly for SO_TIMESTAMP{,NS,ING}. Further, we need a new SO_RCVTIMEO/SO_SNDTIMEO implementation here, which has not been implemented yet.
- waitid/getrusage, this needs a rewrite now from earlier versions based on recent feedback. The plan now is to incorporate nanosecond timestamps in a new revision of the 'rusage' structure. Possibly also include BSD wait6() semantics of passing back the child resource usage in waitid(), and/or a method to pass a signal mask as in io_pgetevents(). waitid/getrusage() are not required for correct behavior with 64-bit time_t and can be safely emulated on top of the existing syscalls by the C library beyond 2038. This needs more discussion.
- clock_adjtime, this is also optional and can be implemented by the C library if necessary. The plan is to do the same as x32 and use the 64-bit structure natively on both 32-bit and 64-bit architectures. The timex structure contains a 'timeval' at the moment, but also supports nanoseconds passed in it.
- getitimer/setitimer, these again can be trivially emulated by the C library.
Arnd
Arnd Bergmann (5): y2038: futex: Move compat implementation into futex.c y2038: futex: Add support for __kernel_timespec y2038: socket: Add compat_sys_recvmmsg_time64 y2038: signal: Add sys_rt_sigtimedwait_time32 y2038: signal: Add compat_sys_rt_sigtimedwait_time64
include/linux/compat.h | 8 +- include/linux/futex.h | 8 -- include/linux/socket.h | 9 +- include/linux/syscalls.h | 9 +- kernel/Makefile | 3 - kernel/futex.c | 207 +++++++++++++++++++++++++++++++++++++-- kernel/futex_compat.c | 202 -------------------------------------- kernel/signal.c | 65 ++++++++++++ kernel/sys_ni.c | 2 + net/compat.c | 34 +++---- net/socket.c | 62 +++++++++--- 11 files changed, 345 insertions(+), 264 deletions(-) delete mode 100644 kernel/futex_compat.c
We are going to share the compat_sys_futex() handler between 64-bit architectures and 32-bit architectures that need to deal with both 32-bit and 64-bit time_t, and this is easier if both entry points are in the same file.
In fact, most other system call handlers do the same thing these days, so let's follow the trend here and merge all of futex_compat.c into futex.c.
In the process, a few minor changes have to be done to make sure everything still makes sense: handle_futex_death() and futex_cmpxchg_enabled() become local symbol, and the compat version of the fetch_robust_entry() function gets renamed to compat_fetch_robust_entry() to avoid a symbol clash.
This is intended as a purely cosmetic patch, no behavior should change.
Signed-off-by: Arnd Bergmann arnd@arndb.de --- include/linux/futex.h | 8 -- kernel/Makefile | 3 - kernel/futex.c | 195 +++++++++++++++++++++++++++++++++++++++- kernel/futex_compat.c | 202 ------------------------------------------ 4 files changed, 192 insertions(+), 216 deletions(-) delete mode 100644 kernel/futex_compat.c
diff --git a/include/linux/futex.h b/include/linux/futex.h index 821ae502d3d8..ccaef0097785 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -9,9 +9,6 @@ struct inode; struct mm_struct; struct task_struct;
-extern int -handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi); - /* * Futexes are matched on equal values of this key. * The key type depends on whether it's a shared or private mapping. @@ -55,11 +52,6 @@ extern void exit_robust_list(struct task_struct *curr);
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3); -#ifdef CONFIG_HAVE_FUTEX_CMPXCHG -#define futex_cmpxchg_enabled 1 -#else -extern int futex_cmpxchg_enabled; -#endif #else static inline void exit_robust_list(struct task_struct *curr) { diff --git a/kernel/Makefile b/kernel/Makefile index 7343b3a9bff0..8e40a6742d23 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -49,9 +49,6 @@ obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ obj-$(CONFIG_FUTEX) += futex.o -ifeq ($(CONFIG_COMPAT),y) -obj-$(CONFIG_FUTEX) += futex_compat.o -endif obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) diff --git a/kernel/futex.c b/kernel/futex.c index f423f9b6577e..5cc7c3b098e9 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -44,6 +44,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/compat.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/fs.h> @@ -173,8 +174,10 @@ * double_lock_hb() and double_unlock_hb(), respectively. */
-#ifndef CONFIG_HAVE_FUTEX_CMPXCHG -int __read_mostly futex_cmpxchg_enabled; +#ifdef CONFIG_HAVE_FUTEX_CMPXCHG +#define futex_cmpxchg_enabled 1 +#else +static int __read_mostly futex_cmpxchg_enabled; #endif
/* @@ -3360,7 +3363,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid, * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ -int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) +static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) { u32 uval, uninitialized_var(nval), mval;
@@ -3589,6 +3592,192 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); }
+#ifdef CONFIG_COMPAT +/* + * Fetch a robust-list pointer. Bit 0 signals PI futexes: + */ +static inline int +compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, + compat_uptr_t __user *head, unsigned int *pi) +{ + if (get_user(*uentry, head)) + return -EFAULT; + + *entry = compat_ptr((*uentry) & ~1); + *pi = (unsigned int)(*uentry) & 1; + + return 0; +} + +static void __user *futex_uaddr(struct robust_list __user *entry, + compat_long_t futex_offset) +{ + compat_uptr_t base = ptr_to_compat(entry); + void __user *uaddr = compat_ptr(base + futex_offset); + + return uaddr; +} + +/* + * Walk curr->robust_list (very carefully, it's a userspace list!) + * and mark any locks found there dead, and notify any waiters. + * + * We silently return on any sign of list-walking problem. + */ +void compat_exit_robust_list(struct task_struct *curr) +{ + struct compat_robust_list_head __user *head = curr->compat_robust_list; + struct robust_list __user *entry, *next_entry, *pending; + unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; + unsigned int uninitialized_var(next_pi); + compat_uptr_t uentry, next_uentry, upending; + compat_long_t futex_offset; + int rc; + + if (!futex_cmpxchg_enabled) + return; + + /* + * Fetch the list head (which was registered earlier, via + * sys_set_robust_list()): + */ + if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) + return; + /* + * Fetch the relative futex offset: + */ + if (get_user(futex_offset, &head->futex_offset)) + return; + /* + * Fetch any possibly pending lock-add first, and handle it + * if it exists: + */ + if (compat_fetch_robust_entry(&upending, &pending, + &head->list_op_pending, &pip)) + return; + + next_entry = NULL; /* avoid warning with gcc */ + while (entry != (struct robust_list __user *) &head->list) { + /* + * Fetch the next entry in the list before calling + * handle_futex_death: + */ + rc = compat_fetch_robust_entry(&next_uentry, &next_entry, + (compat_uptr_t __user *)&entry->next, &next_pi); + /* + * A pending lock might already be on the list, so + * dont process it twice: + */ + if (entry != pending) { + void __user *uaddr = futex_uaddr(entry, futex_offset); + + if (handle_futex_death(uaddr, curr, pi)) + return; + } + if (rc) + return; + uentry = next_uentry; + entry = next_entry; + pi = next_pi; + /* + * Avoid excessively long or circular lists: + */ + if (!--limit) + break; + + cond_resched(); + } + if (pending) { + void __user *uaddr = futex_uaddr(pending, futex_offset); + + handle_futex_death(uaddr, curr, pip); + } +} + +COMPAT_SYSCALL_DEFINE2(set_robust_list, + struct compat_robust_list_head __user *, head, + compat_size_t, len) +{ + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + if (unlikely(len != sizeof(*head))) + return -EINVAL; + + current->compat_robust_list = head; + + return 0; +} + +COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, + compat_uptr_t __user *, head_ptr, + compat_size_t __user *, len_ptr) +{ + struct compat_robust_list_head __user *head; + unsigned long ret; + struct task_struct *p; + + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + rcu_read_lock(); + + ret = -ESRCH; + if (!pid) + p = current; + else { + p = find_task_by_vpid(pid); + if (!p) + goto err_unlock; + } + + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) + goto err_unlock; + + head = p->compat_robust_list; + rcu_read_unlock(); + + if (put_user(sizeof(*head), len_ptr)) + return -EFAULT; + return put_user(ptr_to_compat(head), head_ptr); + +err_unlock: + rcu_read_unlock(); + + return ret; +} + +COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, + struct old_timespec32 __user *, utime, u32 __user *, uaddr2, + u32, val3) +{ + struct timespec ts; + ktime_t t, *tp = NULL; + int val2 = 0; + int cmd = op & FUTEX_CMD_MASK; + + if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { + if (compat_get_timespec(&ts, utime)) + return -EFAULT; + if (!timespec_valid(&ts)) + return -EINVAL; + + t = timespec_to_ktime(ts); + if (cmd == FUTEX_WAIT) + t = ktime_add_safe(ktime_get(), t); + tp = &t; + } + if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || + cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) + val2 = (int) (unsigned long) utime; + + return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); +} +#endif /* CONFIG_COMPAT */ + static void __init futex_detect_cmpxchg(void) { #ifndef CONFIG_HAVE_FUTEX_CMPXCHG diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c deleted file mode 100644 index 410a77a8f6e2..000000000000 --- a/kernel/futex_compat.c +++ /dev/null @@ -1,202 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * linux/kernel/futex_compat.c - * - * Futex compatibililty routines. - * - * Copyright 2006, Red Hat, Inc., Ingo Molnar - */ - -#include <linux/linkage.h> -#include <linux/compat.h> -#include <linux/nsproxy.h> -#include <linux/futex.h> -#include <linux/ptrace.h> -#include <linux/syscalls.h> - -#include <linux/uaccess.h> - - -/* - * Fetch a robust-list pointer. Bit 0 signals PI futexes: - */ -static inline int -fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, - compat_uptr_t __user *head, unsigned int *pi) -{ - if (get_user(*uentry, head)) - return -EFAULT; - - *entry = compat_ptr((*uentry) & ~1); - *pi = (unsigned int)(*uentry) & 1; - - return 0; -} - -static void __user *futex_uaddr(struct robust_list __user *entry, - compat_long_t futex_offset) -{ - compat_uptr_t base = ptr_to_compat(entry); - void __user *uaddr = compat_ptr(base + futex_offset); - - return uaddr; -} - -/* - * Walk curr->robust_list (very carefully, it's a userspace list!) - * and mark any locks found there dead, and notify any waiters. - * - * We silently return on any sign of list-walking problem. - */ -void compat_exit_robust_list(struct task_struct *curr) -{ - struct compat_robust_list_head __user *head = curr->compat_robust_list; - struct robust_list __user *entry, *next_entry, *pending; - unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int uninitialized_var(next_pi); - compat_uptr_t uentry, next_uentry, upending; - compat_long_t futex_offset; - int rc; - - if (!futex_cmpxchg_enabled) - return; - - /* - * Fetch the list head (which was registered earlier, via - * sys_set_robust_list()): - */ - if (fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) - return; - /* - * Fetch the relative futex offset: - */ - if (get_user(futex_offset, &head->futex_offset)) - return; - /* - * Fetch any possibly pending lock-add first, and handle it - * if it exists: - */ - if (fetch_robust_entry(&upending, &pending, - &head->list_op_pending, &pip)) - return; - - next_entry = NULL; /* avoid warning with gcc */ - while (entry != (struct robust_list __user *) &head->list) { - /* - * Fetch the next entry in the list before calling - * handle_futex_death: - */ - rc = fetch_robust_entry(&next_uentry, &next_entry, - (compat_uptr_t __user *)&entry->next, &next_pi); - /* - * A pending lock might already be on the list, so - * dont process it twice: - */ - if (entry != pending) { - void __user *uaddr = futex_uaddr(entry, futex_offset); - - if (handle_futex_death(uaddr, curr, pi)) - return; - } - if (rc) - return; - uentry = next_uentry; - entry = next_entry; - pi = next_pi; - /* - * Avoid excessively long or circular lists: - */ - if (!--limit) - break; - - cond_resched(); - } - if (pending) { - void __user *uaddr = futex_uaddr(pending, futex_offset); - - handle_futex_death(uaddr, curr, pip); - } -} - -COMPAT_SYSCALL_DEFINE2(set_robust_list, - struct compat_robust_list_head __user *, head, - compat_size_t, len) -{ - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - if (unlikely(len != sizeof(*head))) - return -EINVAL; - - current->compat_robust_list = head; - - return 0; -} - -COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, - compat_uptr_t __user *, head_ptr, - compat_size_t __user *, len_ptr) -{ - struct compat_robust_list_head __user *head; - unsigned long ret; - struct task_struct *p; - - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - rcu_read_lock(); - - ret = -ESRCH; - if (!pid) - p = current; - else { - p = find_task_by_vpid(pid); - if (!p) - goto err_unlock; - } - - ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) - goto err_unlock; - - head = p->compat_robust_list; - rcu_read_unlock(); - - if (put_user(sizeof(*head), len_ptr)) - return -EFAULT; - return put_user(ptr_to_compat(head), head_ptr); - -err_unlock: - rcu_read_unlock(); - - return ret; -} - -COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, - struct old_timespec32 __user *, utime, u32 __user *, uaddr2, - u32, val3) -{ - struct timespec ts; - ktime_t t, *tp = NULL; - int val2 = 0; - int cmd = op & FUTEX_CMD_MASK; - - if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || - cmd == FUTEX_WAIT_BITSET || - cmd == FUTEX_WAIT_REQUEUE_PI)) { - if (compat_get_timespec(&ts, utime)) - return -EFAULT; - if (!timespec_valid(&ts)) - return -EINVAL; - - t = timespec_to_ktime(ts); - if (cmd == FUTEX_WAIT) - t = ktime_add_safe(ktime_get(), t); - tp = &t; - } - if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || - cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) - val2 = (int) (unsigned long) utime; - - return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); -}
This prepares sys_futex for y2038 safe calling: the native syscall is changed to receive a __kernel_timespec argument, which will be switched to 64-bit time_t in the future. All the internal time handling gets changed to timespec64, and the compat_sys_futex entry point is moved under the CONFIG_COMPAT_32BIT_TIME check to provide compatibility for existing 32-bit architectures.
Signed-off-by: Arnd Bergmann arnd@arndb.de --- include/linux/syscalls.h | 2 +- kernel/futex.c | 22 ++++++++++++---------- 2 files changed, 13 insertions(+), 11 deletions(-)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a27cf407de92..247ad9eca955 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -553,7 +553,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags);
/* kernel/futex.c */ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, - struct timespec __user *utime, u32 __user *uaddr2, + struct __kernel_timespec __user *utime, u32 __user *uaddr2, u32 val3); asmlinkage long sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, diff --git a/kernel/futex.c b/kernel/futex.c index 5cc7c3b098e9..b305beaab739 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3558,10 +3558,10 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, - struct timespec __user *, utime, u32 __user *, uaddr2, + struct __kernel_timespec __user *, utime, u32 __user *, uaddr2, u32, val3) { - struct timespec ts; + struct timespec64 ts; ktime_t t, *tp = NULL; u32 val2 = 0; int cmd = op & FUTEX_CMD_MASK; @@ -3571,12 +3571,12 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, cmd == FUTEX_WAIT_REQUEUE_PI)) { if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) return -EFAULT; - if (copy_from_user(&ts, utime, sizeof(ts)) != 0) + if (get_timespec64(&ts, utime)) return -EFAULT; - if (!timespec_valid(&ts)) + if (!timespec64_valid(&ts)) return -EINVAL;
- t = timespec_to_ktime(ts); + t = timespec64_to_ktime(ts); if (cmd == FUTEX_WAIT) t = ktime_add_safe(ktime_get(), t); tp = &t; @@ -3747,12 +3747,14 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
return ret; } +#endif /* CONFIG_COMPAT */
+#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { - struct timespec ts; + struct timespec64 ts; ktime_t t, *tp = NULL; int val2 = 0; int cmd = op & FUTEX_CMD_MASK; @@ -3760,12 +3762,12 @@ COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || cmd == FUTEX_WAIT_BITSET || cmd == FUTEX_WAIT_REQUEUE_PI)) { - if (compat_get_timespec(&ts, utime)) + if (get_old_timespec32(&ts, utime)) return -EFAULT; - if (!timespec_valid(&ts)) + if (!timespec64_valid(&ts)) return -EINVAL;
- t = timespec_to_ktime(ts); + t = timespec64_to_ktime(ts); if (cmd == FUTEX_WAIT) t = ktime_add_safe(ktime_get(), t); tp = &t; @@ -3776,7 +3778,7 @@ COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); } -#endif /* CONFIG_COMPAT */ +#endif /* CONFIG_COMPAT_32BIT_TIME */
static void __init futex_detect_cmpxchg(void) {
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 arnd@arndb.de --- include/linux/compat.h | 5 +++- include/linux/socket.h | 9 ++++-- include/linux/syscalls.h | 3 ++ kernel/sys_ni.c | 2 ++ net/compat.c | 34 ++++++++-------------- net/socket.c | 62 +++++++++++++++++++++++++++++----------- 6 files changed, 73 insertions(+), 42 deletions(-)
diff --git a/include/linux/compat.h b/include/linux/compat.h index 8be8daa38c9a..72969d303434 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -893,7 +893,10 @@ asmlinkage long compat_sys_move_pages(pid_t pid, compat_ulong_t nr_pages, asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); -asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, +asmlinkage long compat_sys_recvmmsg_time64(int fd, struct compat_mmsghdr __user *mmsg, + unsigned vlen, unsigned int flags, + struct __kernel_timespec __user *timeout); +asmlinkage long compat_sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct old_timespec32 __user *timeout); asmlinkage long compat_sys_wait4(compat_pid_t pid, 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); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 247ad9eca955..03cda6793be3 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -843,6 +843,9 @@ asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, int); asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, unsigned int vlen, unsigned flags, struct __kernel_timespec __user *timeout); +asmlinkage long sys_recvmmsg_time32(int fd, struct mmsghdr __user *msg, + unsigned int vlen, unsigned flags, + struct old_timespec32 __user *timeout);
asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, int options, struct rusage __user *ru); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index df556175be50..ab9d0e3c6d50 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -284,7 +284,9 @@ COND_SYSCALL_COMPAT(move_pages); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); COND_SYSCALL(recvmmsg); +COND_SYSCALL(recvmmsg_time32); COND_SYSCALL_COMPAT(recvmmsg); +COND_SYSCALL_COMPAT(recvmmsg_time64);
/* * Architecture specific syscalls: see further below diff --git a/net/compat.c b/net/compat.c index 47a614b370cd..f7084780a8f8 100644 --- a/net/compat.c +++ b/net/compat.c @@ -810,34 +810,23 @@ COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len return __compat_sys_recvfrom(fd, buf, len, flags, addr, addrlen); }
-static int __compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, - unsigned int vlen, unsigned int flags, - struct old_timespec32 __user *timeout) +COMPAT_SYSCALL_DEFINE5(recvmmsg_time64, int, fd, struct compat_mmsghdr __user *, mmsg, + unsigned int, vlen, unsigned int, flags, + struct __kernel_timespec __user *, timeout) { - int datagrams; - struct timespec64 ktspec; - - if (timeout == NULL) - return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, - flags | MSG_CMSG_COMPAT, NULL); - - if (compat_get_timespec64(&ktspec, timeout)) - return -EFAULT; - - datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, - flags | MSG_CMSG_COMPAT, &ktspec); - if (datagrams > 0 && compat_put_timespec64(&ktspec, timeout)) - datagrams = -EFAULT; - - return datagrams; + return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, + flags | MSG_CMSG_COMPAT, timeout, NULL); }
+#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct old_timespec32 __user *, timeout) { - return __compat_sys_recvmmsg(fd, mmsg, vlen, flags, timeout); + return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, + flags | MSG_CMSG_COMPAT, NULL, timeout); } +#endif
COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args) { @@ -925,8 +914,9 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args) ret = __compat_sys_recvmsg(a0, compat_ptr(a1), a[2]); break; case SYS_RECVMMSG: - ret = __compat_sys_recvmmsg(a0, compat_ptr(a1), a[2], a[3], - compat_ptr(a[4])); + ret = __sys_recvmmsg(a0, compat_ptr(a1), a[2], + a[3] | MSG_CMSG_COMPAT, NULL, + compat_ptr(a[4])); break; case SYS_ACCEPT4: ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]); diff --git a/net/socket.c b/net/socket.c index 593826e11a53..f6a2d3a7b611 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2341,8 +2341,9 @@ SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg, * Linux recvmmsg interface */
-int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags, struct timespec64 *timeout) +static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, + unsigned int vlen, unsigned int flags, + struct timespec64 *timeout) { int fput_needed, err, datagrams; struct socket *sock; @@ -2451,25 +2452,32 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, return datagrams; }
-static int do_sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, - unsigned int vlen, unsigned int flags, - struct __kernel_timespec __user *timeout) +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) { int datagrams; struct timespec64 timeout_sys;
- if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - - if (!timeout) - return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL); + if (timeout && get_timespec64(&timeout_sys, timeout)) + return -EFAULT;
- if (get_timespec64(&timeout_sys, timeout)) + if (timeout32 && get_old_timespec32(&timeout_sys, timeout32)) return -EFAULT;
- datagrams = __sys_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); + if (!timeout && !timeout32) + do_recvmmsg(fd, mmsg, vlen, flags, NULL); + + datagrams = do_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys);
- if (datagrams > 0 && put_timespec64(&timeout_sys, timeout)) + if (!datagrams) + return 0; + + if (timeout && put_timespec64(&timeout_sys, timeout)) + datagrams = -EFAULT; + + if (timeout32 && put_old_timespec32(&timeout_sys, timeout32)) datagrams = -EFAULT;
return datagrams; @@ -2479,8 +2487,23 @@ SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct __kernel_timespec __user *, timeout) { - return do_sys_recvmmsg(fd, mmsg, vlen, flags, timeout); + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + + return __sys_recvmmsg(fd, mmsg, vlen, flags, timeout, NULL); +} + +#ifdef CONFIG_COMPAT_32BIT_TIME +SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct mmsghdr __user *, mmsg, + unsigned int, vlen, unsigned int, flags, + struct old_timespec32 __user *, timeout) +{ + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + + return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL, timeout); } +#endif
#ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ @@ -2600,8 +2623,15 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) a[2], true); break; case SYS_RECVMMSG: - err = do_sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], - a[3], (struct __kernel_timespec __user *)a[4]); + if (IS_ENABLED(CONFIG_64BIT) || !IS_ENABLED(CONFIG_64BIT_TIME)) + err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, + a[2], a[3], + (struct __kernel_timespec __user *)a[4], + NULL); + else + err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, + a[2], a[3], NULL, + (struct old_timespec32 __user *)a[4]); break; case SYS_ACCEPT4: err = __sys_accept4(a0, (struct sockaddr __user *)a1,
Once sys_rt_sigtimedwait() gets changed to a 64-bit time_t, we have to provide compatibility support for existing binaries.
An earlier version of this patch reused the compat_sys_rt_sigtimedwait entry point to avoid code duplication, but this newer approach duplicates the existing native entry point instead, which seems a bit cleaner.
Signed-off-by: Arnd Bergmann arnd@arndb.de --- include/linux/syscalls.h | 4 ++++ kernel/signal.c | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 03cda6793be3..251979d2e709 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -649,6 +649,10 @@ asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, siginfo_t __user *uinfo, const struct __kernel_timespec __user *uts, size_t sigsetsize); +asmlinkage long sys_rt_sigtimedwait_time32(const sigset_t __user *uthese, + siginfo_t __user *uinfo, + const struct old_timespec32 __user *uts, + size_t sigsetsize); asmlinkage long sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo);
/* kernel/sys.c */ diff --git a/kernel/signal.c b/kernel/signal.c index 3c8ea7a328e0..be6744cd0a11 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3332,6 +3332,39 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, return ret; }
+#ifdef CONFIG_COMPAT_32BIT_TIME +SYSCALL_DEFINE4(rt_sigtimedwait_time32, const sigset_t __user *, uthese, + siginfo_t __user *, uinfo, + const struct old_timespec32 __user *, uts, + size_t, sigsetsize) +{ + sigset_t these; + struct timespec64 ts; + kernel_siginfo_t info; + int ret; + + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&these, uthese, sizeof(these))) + return -EFAULT; + + if (uts) { + if (get_old_timespec32(&ts, uts)) + return -EFAULT; + } + + ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL); + + if (ret > 0 && uinfo) { + if (copy_siginfo_to_user(uinfo, &info)) + ret = -EFAULT; + } + + return ret; +} +#endif + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo,
Now that 32-bit architectures have two variants of sys_rt_sigtimedwaid() for 32-bit and 64-bit time_t, we also need to have a second compat system call entry point on the corresponding 64-bit architectures.
The traditional system call keeps getting handled by compat_sys_rt_sigtimedwait(), and this adds a new compat_sys_rt_sigtimedwait_time64() that differs only in the timeout argument type.
The naming remains a bit asymmetric for the moment. Ideally we would want to have compat_sys_rt_sigtimedwait_time32() for the old version and compat_sys_rt_sigtimedwait() for the new one to mirror the names of the native entry points, but renaming the existing system call tables causes unnecessary churn. I would suggest renaming all such system calls together at a later point.
Signed-off-by: Arnd Bergmann arnd@arndb.de --- include/linux/compat.h | 3 +++ kernel/signal.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+)
diff --git a/include/linux/compat.h b/include/linux/compat.h index 72969d303434..3bc5f218efd8 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -788,6 +788,9 @@ asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, struct old_timespec32 __user *uts, compat_size_t sigsetsize); +asmlinkage long compat_sys_rt_sigtimedwait_time64(compat_sigset_t __user *uthese, + struct compat_siginfo __user *uinfo, + struct __kernel_timespec __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); /* No generic prototype for rt_sigreturn */ diff --git a/kernel/signal.c b/kernel/signal.c index be6744cd0a11..53e07d97ffe0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3366,6 +3366,37 @@ SYSCALL_DEFINE4(rt_sigtimedwait_time32, const sigset_t __user *, uthese, #endif
#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time64, compat_sigset_t __user *, uthese, + struct compat_siginfo __user *, uinfo, + struct __kernel_timespec __user *, uts, compat_size_t, sigsetsize) +{ + sigset_t s; + struct timespec64 t; + kernel_siginfo_t info; + long ret; + + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (get_compat_sigset(&s, uthese)) + return -EFAULT; + + if (uts) { + if (get_timespec64(&t, uts)) + return -EFAULT; + } + + ret = do_sigtimedwait(&s, &info, uts ? &t : NULL); + + if (ret > 0 && uinfo) { + if (copy_siginfo_to_user32(uinfo, &info)) + ret = -EFAULT; + } + + return ret; +} + +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo, struct old_timespec32 __user *, uts, compat_size_t, sigsetsize) @@ -3396,6 +3427,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, return ret; } #endif +#endif
/** * sys_kill - send a signal to a process
-
Arnd Bergmann