ARM: 9108/1: oabi-compat: rework epoll_wait/epoll_pwait emulation

The epoll_wait() system call wrapper is one of the remaining users of
the set_fs() infrasturcture for Arm. Changing it to not require set_fs()
is rather complex unfortunately.

The approach I'm taking here is to allow architectures to override
the code that copies the output to user space, and let the oabi-compat
implementation check whether it is getting called from an EABI or OABI
system call based on the thread_info->syscall value.

The in_oabi_syscall() check here mirrors the in_compat_syscall() and
in_x32_syscall() helpers for 32-bit compat implementations on other
architectures.

Overall, the amount of code goes down, at least with the newly added
sys_oabi_epoll_pwait() helper getting removed again. The downside
is added complexity in the source code for the native implementation.
There should be no difference in runtime performance except for Arm
kernels with CONFIG_OABI_COMPAT enabled that now have to go through
an external function call to check which of the two variants to use.

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
This commit is contained in:
Arnd Bergmann 2021-08-11 08:30:22 +01:00 committed by Russell King (Oracle)
parent 4e57a4ddf6
commit 249dbe74d3
5 changed files with 53 additions and 76 deletions

View File

@ -28,6 +28,17 @@ static inline int syscall_get_nr(struct task_struct *task,
return task_thread_info(task)->abi_syscall & __NR_SYSCALL_MASK;
}
static inline bool __in_oabi_syscall(struct task_struct *task)
{
return IS_ENABLED(CONFIG_OABI_COMPAT) &&
(task_thread_info(task)->abi_syscall & __NR_OABI_SYSCALL_BASE);
}
static inline bool in_oabi_syscall(void)
{
return __in_oabi_syscall(current);
}
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{

View File

@ -83,6 +83,8 @@
#include <linux/uaccess.h>
#include <linux/slab.h>
#include <asm/syscall.h>
struct oldabi_stat64 {
unsigned long long st_dev;
unsigned int __pad1;
@ -264,88 +266,35 @@ asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd,
return do_epoll_ctl(epfd, op, fd, &kernel, false);
}
static long do_oabi_epoll_wait(int epfd, struct oabi_epoll_event __user *events,
int maxevents, int timeout)
{
struct epoll_event *kbuf;
struct oabi_epoll_event e;
mm_segment_t fs;
long ret, err, i;
if (maxevents <= 0 ||
maxevents > (INT_MAX/sizeof(*kbuf)) ||
maxevents > (INT_MAX/sizeof(*events)))
return -EINVAL;
if (!access_ok(events, sizeof(*events) * maxevents))
return -EFAULT;
kbuf = kmalloc_array(maxevents, sizeof(*kbuf), GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
fs = get_fs();
set_fs(KERNEL_DS);
ret = sys_epoll_wait(epfd, kbuf, maxevents, timeout);
set_fs(fs);
err = 0;
for (i = 0; i < ret; i++) {
e.events = kbuf[i].events;
e.data = kbuf[i].data;
err = __copy_to_user(events, &e, sizeof(e));
if (err)
break;
events++;
}
kfree(kbuf);
return err ? -EFAULT : ret;
}
#else
asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd,
struct oabi_epoll_event __user *event)
{
return -EINVAL;
}
asmlinkage long sys_oabi_epoll_wait(int epfd,
struct oabi_epoll_event __user *events,
int maxevents, int timeout)
{
return -EINVAL;
}
#endif
SYSCALL_DEFINE4(oabi_epoll_wait, int, epfd,
struct oabi_epoll_event __user *, events,
int, maxevents, int, timeout)
struct epoll_event __user *
epoll_put_uevent(__poll_t revents, __u64 data,
struct epoll_event __user *uevent)
{
return do_oabi_epoll_wait(epfd, events, maxevents, timeout);
if (in_oabi_syscall()) {
struct oabi_epoll_event __user *oevent = (void __user *)uevent;
if (__put_user(revents, &oevent->events) ||
__put_user(data, &oevent->data))
return NULL;
return (void __user *)(oevent+1);
}
if (__put_user(revents, &uevent->events) ||
__put_user(data, &uevent->data))
return NULL;
return uevent+1;
}
/*
* Implement the event wait interface for the eventpoll file. It is the kernel
* part of the user space epoll_pwait(2).
*/
SYSCALL_DEFINE6(oabi_epoll_pwait, int, epfd,
struct oabi_epoll_event __user *, events, int, maxevents,
int, timeout, const sigset_t __user *, sigmask,
size_t, sigsetsize)
{
int error;
/*
* If the caller wants a certain signal mask to be set during the wait,
* we apply it here.
*/
error = set_user_sigmask(sigmask, sigsetsize);
if (error)
return error;
error = do_oabi_epoll_wait(epfd, events, maxevents, timeout);
restore_saved_sigmask_unless(error == -EINTR);
return error;
}
#endif
struct oabi_sembuf {
unsigned short sem_num;
short sem_op;

View File

@ -266,7 +266,7 @@
249 common lookup_dcookie sys_lookup_dcookie
250 common epoll_create sys_epoll_create
251 common epoll_ctl sys_epoll_ctl sys_oabi_epoll_ctl
252 common epoll_wait sys_epoll_wait sys_oabi_epoll_wait
252 common epoll_wait sys_epoll_wait
253 common remap_file_pages sys_remap_file_pages
# 254 for set_thread_area
# 255 for get_thread_area
@ -360,7 +360,7 @@
343 common vmsplice sys_vmsplice
344 common move_pages sys_move_pages
345 common getcpu sys_getcpu
346 common epoll_pwait sys_epoll_pwait sys_oabi_epoll_pwait
346 common epoll_pwait sys_epoll_pwait
347 common kexec_load sys_kexec_load
348 common utimensat sys_utimensat_time32
349 common signalfd sys_signalfd

View File

@ -1684,8 +1684,8 @@ static int ep_send_events(struct eventpoll *ep,
if (!revents)
continue;
if (__put_user(revents, &events->events) ||
__put_user(epi->event.data, &events->data)) {
events = epoll_put_uevent(revents, epi->event.data, events);
if (!events) {
list_add(&epi->rdllink, &txlist);
ep_pm_stay_awake(epi);
if (!res)
@ -1693,7 +1693,6 @@ static int ep_send_events(struct eventpoll *ep,
break;
}
res++;
events++;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
else if (!(epi->event.events & EPOLLET)) {

View File

@ -68,4 +68,22 @@ static inline void eventpoll_release(struct file *file) {}
#endif
#if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT)
/* ARM OABI has an incompatible struct layout and needs a special handler */
extern struct epoll_event __user *
epoll_put_uevent(__poll_t revents, __u64 data,
struct epoll_event __user *uevent);
#else
static inline struct epoll_event __user *
epoll_put_uevent(__poll_t revents, __u64 data,
struct epoll_event __user *uevent)
{
if (__put_user(revents, &uevent->events) ||
__put_user(data, &uevent->data))
return NULL;
return uevent+1;
}
#endif
#endif /* #ifndef _LINUX_EVENTPOLL_H */