linux/fs/userfaultfd.c

1959 lines
50 KiB
C
Raw Normal View History

/*
* fs/userfaultfd.c
*
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
* Copyright (C) 2008-2009 Red Hat, Inc.
* Copyright (C) 2015 Red Hat, Inc.
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Some part derived from fs/eventfd.c (anon inode setup) and
* mm/ksm.c (mm hashing).
*/
#include <linux/list.h>
#include <linux/hashtable.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/mm.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/file.h>
#include <linux/bug.h>
#include <linux/anon_inodes.h>
#include <linux/syscalls.h>
#include <linux/userfaultfd_k.h>
#include <linux/mempolicy.h>
#include <linux/ioctl.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
enum userfaultfd_state {
UFFD_STATE_WAIT_API,
UFFD_STATE_RUNNING,
};
/*
* Start with fault_pending_wqh and fault_wqh so they're more likely
* to be in the same cacheline.
*/
struct userfaultfd_ctx {
/* waitqueue head for the pending (i.e. not read) userfaults */
wait_queue_head_t fault_pending_wqh;
/* waitqueue head for the userfaults */
wait_queue_head_t fault_wqh;
/* waitqueue head for the pseudo fd to wakeup poll/read */
wait_queue_head_t fd_wqh;
/* waitqueue head for events */
wait_queue_head_t event_wqh;
/* a refile sequence protected by fault_pending_wqh lock */
struct seqcount refile_seq;
/* pseudo fd refcounting */
atomic_t refcount;
/* userfaultfd syscall flags */
unsigned int flags;
/* features requested from the userspace */
unsigned int features;
/* state machine */
enum userfaultfd_state state;
/* released */
bool released;
/* mm with one ore more vmas attached to this userfaultfd_ctx */
struct mm_struct *mm;
};
2017-02-23 07:42:27 +08:00
struct userfaultfd_fork_ctx {
struct userfaultfd_ctx *orig;
struct userfaultfd_ctx *new;
struct list_head list;
};
struct userfaultfd_unmap_ctx {
struct userfaultfd_ctx *ctx;
unsigned long start;
unsigned long end;
struct list_head list;
};
struct userfaultfd_wait_queue {
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
struct uffd_msg msg;
wait_queue_entry_t wq;
struct userfaultfd_ctx *ctx;
userfaultfd: fix SIGBUS resulting from false rwsem wakeups With >=32 CPUs the userfaultfd selftest triggered a graceful but unexpected SIGBUS because VM_FAULT_RETRY was returned by handle_userfault() despite the UFFDIO_COPY wasn't completed. This seems caused by rwsem waking the thread blocked in handle_userfault() and we can't run up_read() before the wait_event sequence is complete. Keeping the wait_even sequence identical to the first one, would require running userfaultfd_must_wait() again to know if the loop should be repeated, and it would also require retaking the rwsem and revalidating the whole vma status. It seems simpler to wait the targeted wakeup so that if false wakeups materialize we still wait for our specific wakeup event, unless of course there are signals or the uffd was released. Debug code collecting the stack trace of the wakeup showed this: $ ./userfaultfd 100 99999 nr_pages: 25600, nr_pages_per_cpu: 800 bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2 bounces: 99997, mode: rnd ver poll, Bus error (core dumped) save_stack_trace+0x2b/0x50 try_to_wake_up+0x2a6/0x580 wake_up_q+0x32/0x70 rwsem_wake+0xe0/0x120 call_rwsem_wake+0x1b/0x30 up_write+0x3b/0x40 vm_mmap_pgoff+0x9c/0xc0 SyS_mmap_pgoff+0x1a9/0x240 SyS_mmap+0x22/0x30 entry_SYSCALL_64_fastpath+0x1f/0xbd 0xffffffffffffffff FAULT_FLAG_ALLOW_RETRY missing 70 CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xb8/0x112 handle_userfault+0x572/0x650 handle_mm_fault+0x12cb/0x1520 __do_page_fault+0x175/0x500 trace_do_page_fault+0x61/0x270 do_async_page_fault+0x19/0x90 async_page_fault+0x25/0x30 This always happens when the main userfault selftest thread is running clone() while glibc runs either mprotect or mmap (both taking mmap_sem down_write()) to allocate the thread stack of the background threads, while locking/userfault threads already run at full throttle and are susceptible to false wakeups that may cause handle_userfault() to return before than expected (which results in graceful SIGBUS at the next attempt). This was reproduced only with >=32 CPUs because the loop to start the thread where clone() is too quick with fewer CPUs, while with 32 CPUs there's already significant activity on ~32 locking and userfault threads when the last background threads are started with clone(). This >=32 CPUs SMP race condition is likely reproducible only with the selftest because of the much heavier userfault load it generates if compared to real apps. We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a patch floating around that provides it also hidden this problem but in reality only is successfully at hiding the problem. False wakeups could still happen again the second time handle_userfault() is invoked, even if it's a so rare race condition that getting false wakeups twice in a row is impossible to reproduce. This full fix is needed for correctness, the only alternative would be to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP support can stick to a strict "one more" VM_FAULT_RETRY logic (no need of returning it infinite times to avoid the SIGBUS). Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Michael Rapoport <RAPOPORT@il.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-25 07:17:59 +08:00
bool waken;
};
struct userfaultfd_wake_range {
unsigned long start;
unsigned long len;
};
static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
int wake_flags, void *key)
{
struct userfaultfd_wake_range *range = key;
int ret;
struct userfaultfd_wait_queue *uwq;
unsigned long start, len;
uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
ret = 0;
/* len == 0 means wake all */
start = range->start;
len = range->len;
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
if (len && (start > uwq->msg.arg.pagefault.address ||
start + len <= uwq->msg.arg.pagefault.address))
goto out;
userfaultfd: fix SIGBUS resulting from false rwsem wakeups With >=32 CPUs the userfaultfd selftest triggered a graceful but unexpected SIGBUS because VM_FAULT_RETRY was returned by handle_userfault() despite the UFFDIO_COPY wasn't completed. This seems caused by rwsem waking the thread blocked in handle_userfault() and we can't run up_read() before the wait_event sequence is complete. Keeping the wait_even sequence identical to the first one, would require running userfaultfd_must_wait() again to know if the loop should be repeated, and it would also require retaking the rwsem and revalidating the whole vma status. It seems simpler to wait the targeted wakeup so that if false wakeups materialize we still wait for our specific wakeup event, unless of course there are signals or the uffd was released. Debug code collecting the stack trace of the wakeup showed this: $ ./userfaultfd 100 99999 nr_pages: 25600, nr_pages_per_cpu: 800 bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2 bounces: 99997, mode: rnd ver poll, Bus error (core dumped) save_stack_trace+0x2b/0x50 try_to_wake_up+0x2a6/0x580 wake_up_q+0x32/0x70 rwsem_wake+0xe0/0x120 call_rwsem_wake+0x1b/0x30 up_write+0x3b/0x40 vm_mmap_pgoff+0x9c/0xc0 SyS_mmap_pgoff+0x1a9/0x240 SyS_mmap+0x22/0x30 entry_SYSCALL_64_fastpath+0x1f/0xbd 0xffffffffffffffff FAULT_FLAG_ALLOW_RETRY missing 70 CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xb8/0x112 handle_userfault+0x572/0x650 handle_mm_fault+0x12cb/0x1520 __do_page_fault+0x175/0x500 trace_do_page_fault+0x61/0x270 do_async_page_fault+0x19/0x90 async_page_fault+0x25/0x30 This always happens when the main userfault selftest thread is running clone() while glibc runs either mprotect or mmap (both taking mmap_sem down_write()) to allocate the thread stack of the background threads, while locking/userfault threads already run at full throttle and are susceptible to false wakeups that may cause handle_userfault() to return before than expected (which results in graceful SIGBUS at the next attempt). This was reproduced only with >=32 CPUs because the loop to start the thread where clone() is too quick with fewer CPUs, while with 32 CPUs there's already significant activity on ~32 locking and userfault threads when the last background threads are started with clone(). This >=32 CPUs SMP race condition is likely reproducible only with the selftest because of the much heavier userfault load it generates if compared to real apps. We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a patch floating around that provides it also hidden this problem but in reality only is successfully at hiding the problem. False wakeups could still happen again the second time handle_userfault() is invoked, even if it's a so rare race condition that getting false wakeups twice in a row is impossible to reproduce. This full fix is needed for correctness, the only alternative would be to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP support can stick to a strict "one more" VM_FAULT_RETRY logic (no need of returning it infinite times to avoid the SIGBUS). Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Michael Rapoport <RAPOPORT@il.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-25 07:17:59 +08:00
WRITE_ONCE(uwq->waken, true);
/*
* The Program-Order guarantees provided by the scheduler
* ensure uwq->waken is visible before the task is woken.
userfaultfd: fix SIGBUS resulting from false rwsem wakeups With >=32 CPUs the userfaultfd selftest triggered a graceful but unexpected SIGBUS because VM_FAULT_RETRY was returned by handle_userfault() despite the UFFDIO_COPY wasn't completed. This seems caused by rwsem waking the thread blocked in handle_userfault() and we can't run up_read() before the wait_event sequence is complete. Keeping the wait_even sequence identical to the first one, would require running userfaultfd_must_wait() again to know if the loop should be repeated, and it would also require retaking the rwsem and revalidating the whole vma status. It seems simpler to wait the targeted wakeup so that if false wakeups materialize we still wait for our specific wakeup event, unless of course there are signals or the uffd was released. Debug code collecting the stack trace of the wakeup showed this: $ ./userfaultfd 100 99999 nr_pages: 25600, nr_pages_per_cpu: 800 bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2 bounces: 99997, mode: rnd ver poll, Bus error (core dumped) save_stack_trace+0x2b/0x50 try_to_wake_up+0x2a6/0x580 wake_up_q+0x32/0x70 rwsem_wake+0xe0/0x120 call_rwsem_wake+0x1b/0x30 up_write+0x3b/0x40 vm_mmap_pgoff+0x9c/0xc0 SyS_mmap_pgoff+0x1a9/0x240 SyS_mmap+0x22/0x30 entry_SYSCALL_64_fastpath+0x1f/0xbd 0xffffffffffffffff FAULT_FLAG_ALLOW_RETRY missing 70 CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xb8/0x112 handle_userfault+0x572/0x650 handle_mm_fault+0x12cb/0x1520 __do_page_fault+0x175/0x500 trace_do_page_fault+0x61/0x270 do_async_page_fault+0x19/0x90 async_page_fault+0x25/0x30 This always happens when the main userfault selftest thread is running clone() while glibc runs either mprotect or mmap (both taking mmap_sem down_write()) to allocate the thread stack of the background threads, while locking/userfault threads already run at full throttle and are susceptible to false wakeups that may cause handle_userfault() to return before than expected (which results in graceful SIGBUS at the next attempt). This was reproduced only with >=32 CPUs because the loop to start the thread where clone() is too quick with fewer CPUs, while with 32 CPUs there's already significant activity on ~32 locking and userfault threads when the last background threads are started with clone(). This >=32 CPUs SMP race condition is likely reproducible only with the selftest because of the much heavier userfault load it generates if compared to real apps. We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a patch floating around that provides it also hidden this problem but in reality only is successfully at hiding the problem. False wakeups could still happen again the second time handle_userfault() is invoked, even if it's a so rare race condition that getting false wakeups twice in a row is impossible to reproduce. This full fix is needed for correctness, the only alternative would be to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP support can stick to a strict "one more" VM_FAULT_RETRY logic (no need of returning it infinite times to avoid the SIGBUS). Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Michael Rapoport <RAPOPORT@il.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-25 07:17:59 +08:00
*/
ret = wake_up_state(wq->private, mode);
if (ret) {
/*
* Wake only once, autoremove behavior.
*
* After the effect of list_del_init is visible to the other
* CPUs, the waitqueue may disappear from under us, see the
* !list_empty_careful() in handle_userfault().
*
* try_to_wake_up() has an implicit smp_mb(), and the
* wq->private is read before calling the extern function
* "wake_up_state" (which in turns calls try_to_wake_up).
*/
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
list_del_init(&wq->entry);
}
out:
return ret;
}
/**
* userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
* context.
* @ctx: [in] Pointer to the userfaultfd context.
*/
static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
{
if (!atomic_inc_not_zero(&ctx->refcount))
BUG();
}
/**
* userfaultfd_ctx_put - Releases a reference to the internal userfaultfd
* context.
* @ctx: [in] Pointer to userfaultfd context.
*
* The userfaultfd context reference must have been previously acquired either
* with userfaultfd_ctx_get() or userfaultfd_ctx_fdget().
*/
static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
{
if (atomic_dec_and_test(&ctx->refcount)) {
VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh));
VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->fault_wqh));
VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->event_wqh));
VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
mmdrop(ctx->mm);
kmem_cache_free(userfaultfd_ctx_cachep, ctx);
}
}
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
static inline void msg_init(struct uffd_msg *msg)
{
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
BUILD_BUG_ON(sizeof(struct uffd_msg) != 32);
/*
* Must use memset to zero out the paddings or kernel data is
* leaked to userland.
*/
memset(msg, 0, sizeof(struct uffd_msg));
}
static inline struct uffd_msg userfault_msg(unsigned long address,
unsigned int flags,
unsigned long reason,
unsigned int features)
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
{
struct uffd_msg msg;
msg_init(&msg);
msg.event = UFFD_EVENT_PAGEFAULT;
msg.arg.pagefault.address = address;
if (flags & FAULT_FLAG_WRITE)
/*
* If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
* uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE
* was not set in a UFFD_EVENT_PAGEFAULT, it means it
* was a read fault, otherwise if set it means it's
* a write fault.
*/
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
if (reason & VM_UFFD_WP)
/*
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
* If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
* uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was
* not set in a UFFD_EVENT_PAGEFAULT, it means it was
* a missing fault, otherwise if set it means it's a
* write protect fault.
*/
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
if (features & UFFD_FEATURE_THREAD_ID)
msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
return msg;
}
#ifdef CONFIG_HUGETLB_PAGE
/*
* Same functionality as userfaultfd_must_wait below with modifications for
* hugepmd ranges.
*/
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
mm/hugetlb: add size parameter to huge_pte_offset() A poisoned or migrated hugepage is stored as a swap entry in the page tables. On architectures that support hugepages consisting of contiguous page table entries (such as on arm64) this leads to ambiguity in determining the page table entry to return in huge_pte_offset() when a poisoned entry is encountered. Let's remove the ambiguity by adding a size parameter to convey additional information about the requested address. Also fixup the definition/usage of huge_pte_offset() throughout the tree. Link: http://lkml.kernel.org/r/20170522133604.11392-4-punit.agrawal@arm.com Signed-off-by: Punit Agrawal <punit.agrawal@arm.com> Acked-by: Steve Capper <steve.capper@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: James Hogan <james.hogan@imgtec.com> (odd fixer:METAG ARCHITECTURE) Cc: Ralf Baechle <ralf@linux-mips.org> (supporter:MIPS) Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Rich Felker <dalias@libc.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-07 06:39:42 +08:00
struct vm_area_struct *vma,
unsigned long address,
unsigned long flags,
unsigned long reason)
{
struct mm_struct *mm = ctx->mm;
pte_t *pte;
bool ret = true;
VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
mm/hugetlb: add size parameter to huge_pte_offset() A poisoned or migrated hugepage is stored as a swap entry in the page tables. On architectures that support hugepages consisting of contiguous page table entries (such as on arm64) this leads to ambiguity in determining the page table entry to return in huge_pte_offset() when a poisoned entry is encountered. Let's remove the ambiguity by adding a size parameter to convey additional information about the requested address. Also fixup the definition/usage of huge_pte_offset() throughout the tree. Link: http://lkml.kernel.org/r/20170522133604.11392-4-punit.agrawal@arm.com Signed-off-by: Punit Agrawal <punit.agrawal@arm.com> Acked-by: Steve Capper <steve.capper@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: James Hogan <james.hogan@imgtec.com> (odd fixer:METAG ARCHITECTURE) Cc: Ralf Baechle <ralf@linux-mips.org> (supporter:MIPS) Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Rich Felker <dalias@libc.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-07 06:39:42 +08:00
pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
if (!pte)
goto out;
ret = false;
/*
* Lockless access: we're in a wait_event so it's ok if it
* changes under us.
*/
if (huge_pte_none(*pte))
ret = true;
if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP))
ret = true;
out:
return ret;
}
#else
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
mm/hugetlb: add size parameter to huge_pte_offset() A poisoned or migrated hugepage is stored as a swap entry in the page tables. On architectures that support hugepages consisting of contiguous page table entries (such as on arm64) this leads to ambiguity in determining the page table entry to return in huge_pte_offset() when a poisoned entry is encountered. Let's remove the ambiguity by adding a size parameter to convey additional information about the requested address. Also fixup the definition/usage of huge_pte_offset() throughout the tree. Link: http://lkml.kernel.org/r/20170522133604.11392-4-punit.agrawal@arm.com Signed-off-by: Punit Agrawal <punit.agrawal@arm.com> Acked-by: Steve Capper <steve.capper@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: James Hogan <james.hogan@imgtec.com> (odd fixer:METAG ARCHITECTURE) Cc: Ralf Baechle <ralf@linux-mips.org> (supporter:MIPS) Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Rich Felker <dalias@libc.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-07 06:39:42 +08:00
struct vm_area_struct *vma,
unsigned long address,
unsigned long flags,
unsigned long reason)
{
return false; /* should never get here */
}
#endif /* CONFIG_HUGETLB_PAGE */
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and userfaultfd_read if they are run on different threads simultaneously. Until now qemu solved the race in userland: the race was explicitly and intentionally left for userland to solve. However we can also solve it in kernel. Requiring all users to solve this race if they use two threads (one for the background transfer and one for the userfault reads) isn't very attractive from an API prospective, furthermore this allows to remove a whole bunch of mutex and bitmap code from qemu, making it faster. The cost of __get_user_pages_fast should be insignificant considering it scales perfectly and the pagetables are already hot in the CPU cache, compared to the overhead in userland to maintain those structures. Applying this patch is backwards compatible with respect to the userfaultfd userland API, however reverting this change wouldn't be backwards compatible anymore. Without this patch qemu in the background transfer thread, has to read the old state, and do UFFDIO_WAKE if old_state is missing but it become REQUESTED by the time it tries to set it to RECEIVED (signaling the other side received an userfault). vcpu background_thr userfault_thr ----- ----- ----- vcpu0 handle_mm_fault() postcopy_place_page read old_state -> MISSING UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending) vcpu0 fault at 0x7fb76a139000 enters handle_userfault poll() is kicked poll() -> POLLIN read() -> 0x7fb76a139000 postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED /* check that no userfault raced with UFFDIO_COPY */ if (old_state == MISSING && tmp_state == REQUESTED) UFFDIO_WAKE from background thread And a second case where a UFFDIO_WAKE would be needed is in the userfault thread: vcpu background_thr userfault_thr ----- ----- ----- vcpu0 handle_mm_fault() postcopy_place_page read old_state -> MISSING UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending) tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED vcpu0 fault at 0x7fb76a139000 enters handle_userfault poll() is kicked poll() -> POLLIN read() -> 0x7fb76a139000 if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED) UFFDIO_WAKE from userfault thread This patch removes the need of both UFFDIO_WAKE and of the associated per-page tristate as well. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:51 +08:00
/*
* Verify the pagetables are still not ok after having reigstered into
* the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
* userfault that has already been resolved, if userfaultfd_read and
* UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different
* threads.
*/
static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
unsigned long address,
unsigned long flags,
unsigned long reason)
{
struct mm_struct *mm = ctx->mm;
pgd_t *pgd;
p4d_t *p4d;
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and userfaultfd_read if they are run on different threads simultaneously. Until now qemu solved the race in userland: the race was explicitly and intentionally left for userland to solve. However we can also solve it in kernel. Requiring all users to solve this race if they use two threads (one for the background transfer and one for the userfault reads) isn't very attractive from an API prospective, furthermore this allows to remove a whole bunch of mutex and bitmap code from qemu, making it faster. The cost of __get_user_pages_fast should be insignificant considering it scales perfectly and the pagetables are already hot in the CPU cache, compared to the overhead in userland to maintain those structures. Applying this patch is backwards compatible with respect to the userfaultfd userland API, however reverting this change wouldn't be backwards compatible anymore. Without this patch qemu in the background transfer thread, has to read the old state, and do UFFDIO_WAKE if old_state is missing but it become REQUESTED by the time it tries to set it to RECEIVED (signaling the other side received an userfault). vcpu background_thr userfault_thr ----- ----- ----- vcpu0 handle_mm_fault() postcopy_place_page read old_state -> MISSING UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending) vcpu0 fault at 0x7fb76a139000 enters handle_userfault poll() is kicked poll() -> POLLIN read() -> 0x7fb76a139000 postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED /* check that no userfault raced with UFFDIO_COPY */ if (old_state == MISSING && tmp_state == REQUESTED) UFFDIO_WAKE from background thread And a second case where a UFFDIO_WAKE would be needed is in the userfault thread: vcpu background_thr userfault_thr ----- ----- ----- vcpu0 handle_mm_fault() postcopy_place_page read old_state -> MISSING UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending) tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED vcpu0 fault at 0x7fb76a139000 enters handle_userfault poll() is kicked poll() -> POLLIN read() -> 0x7fb76a139000 if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED) UFFDIO_WAKE from userfault thread This patch removes the need of both UFFDIO_WAKE and of the associated per-page tristate as well. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:51 +08:00
pud_t *pud;
pmd_t *pmd, _pmd;
pte_t *pte;
bool ret = true;
VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
goto out;
p4d = p4d_offset(pgd, address);
if (!p4d_present(*p4d))
goto out;
pud = pud_offset(p4d, address);
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and userfaultfd_read if they are run on different threads simultaneously. Until now qemu solved the race in userland: the race was explicitly and intentionally left for userland to solve. However we can also solve it in kernel. Requiring all users to solve this race if they use two threads (one for the background transfer and one for the userfault reads) isn't very attractive from an API prospective, furthermore this allows to remove a whole bunch of mutex and bitmap code from qemu, making it faster. The cost of __get_user_pages_fast should be insignificant considering it scales perfectly and the pagetables are already hot in the CPU cache, compared to the overhead in userland to maintain those structures. Applying this patch is backwards compatible with respect to the userfaultfd userland API, however reverting this change wouldn't be backwards compatible anymore. Without this patch qemu in the background transfer thread, has to read the old state, and do UFFDIO_WAKE if old_state is missing but it become REQUESTED by the time it tries to set it to RECEIVED (signaling the other side received an userfault). vcpu background_thr userfault_thr ----- ----- ----- vcpu0 handle_mm_fault() postcopy_place_page read old_state -> MISSING UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending) vcpu0 fault at 0x7fb76a139000 enters handle_userfault poll() is kicked poll() -> POLLIN read() -> 0x7fb76a139000 postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED /* check that no userfault raced with UFFDIO_COPY */ if (old_state == MISSING && tmp_state == REQUESTED) UFFDIO_WAKE from background thread And a second case where a UFFDIO_WAKE would be needed is in the userfault thread: vcpu background_thr userfault_thr ----- ----- ----- vcpu0 handle_mm_fault() postcopy_place_page read old_state -> MISSING UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending) tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED vcpu0 fault at 0x7fb76a139000 enters handle_userfault poll() is kicked poll() -> POLLIN read() -> 0x7fb76a139000 if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED) UFFDIO_WAKE from userfault thread This patch removes the need of both UFFDIO_WAKE and of the associated per-page tristate as well. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:51 +08:00
if (!pud_present(*pud))
goto out;
pmd = pmd_offset(pud, address);
/*
* READ_ONCE must function as a barrier with narrower scope
* and it must be equivalent to:
* _pmd = *pmd; barrier();
*
* This is to deal with the instability (as in
* pmd_trans_unstable) of the pmd.
*/
_pmd = READ_ONCE(*pmd);
if (!pmd_present(_pmd))
goto out;
ret = false;
if (pmd_trans_huge(_pmd))
goto out;
/*
* the pmd is stable (as in !pmd_trans_unstable) so we can re-read it
* and use the standard pte_offset_map() instead of parsing _pmd.
*/
pte = pte_offset_map(pmd, address);
/*
* Lockless access: we're in a wait_event so it's ok if it
* changes under us.
*/
if (pte_none(*pte))
ret = true;
pte_unmap(pte);
out:
return ret;
}
/*
* The locking rules involved in returning VM_FAULT_RETRY depending on
* FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
* FAULT_FLAG_KILLABLE are not straightforward. The "Caution"
* recommendation in __lock_page_or_retry is not an understatement.
*
* If FAULT_FLAG_ALLOW_RETRY is set, the mmap_sem must be released
* before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is
* not set.
*
* If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not
* set, VM_FAULT_RETRY can still be returned if and only if there are
* fatal_signal_pending()s, and the mmap_sem must be released before
* returning it.
*/
int handle_userfault(struct vm_fault *vmf, unsigned long reason)
{
struct mm_struct *mm = vmf->vma->vm_mm;
struct userfaultfd_ctx *ctx;
struct userfaultfd_wait_queue uwq;
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
int ret;
bool must_wait, return_to_userland;
userfaultfd: fix SIGBUS resulting from false rwsem wakeups With >=32 CPUs the userfaultfd selftest triggered a graceful but unexpected SIGBUS because VM_FAULT_RETRY was returned by handle_userfault() despite the UFFDIO_COPY wasn't completed. This seems caused by rwsem waking the thread blocked in handle_userfault() and we can't run up_read() before the wait_event sequence is complete. Keeping the wait_even sequence identical to the first one, would require running userfaultfd_must_wait() again to know if the loop should be repeated, and it would also require retaking the rwsem and revalidating the whole vma status. It seems simpler to wait the targeted wakeup so that if false wakeups materialize we still wait for our specific wakeup event, unless of course there are signals or the uffd was released. Debug code collecting the stack trace of the wakeup showed this: $ ./userfaultfd 100 99999 nr_pages: 25600, nr_pages_per_cpu: 800 bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2 bounces: 99997, mode: rnd ver poll, Bus error (core dumped) save_stack_trace+0x2b/0x50 try_to_wake_up+0x2a6/0x580 wake_up_q+0x32/0x70 rwsem_wake+0xe0/0x120 call_rwsem_wake+0x1b/0x30 up_write+0x3b/0x40 vm_mmap_pgoff+0x9c/0xc0 SyS_mmap_pgoff+0x1a9/0x240 SyS_mmap+0x22/0x30 entry_SYSCALL_64_fastpath+0x1f/0xbd 0xffffffffffffffff FAULT_FLAG_ALLOW_RETRY missing 70 CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xb8/0x112 handle_userfault+0x572/0x650 handle_mm_fault+0x12cb/0x1520 __do_page_fault+0x175/0x500 trace_do_page_fault+0x61/0x270 do_async_page_fault+0x19/0x90 async_page_fault+0x25/0x30 This always happens when the main userfault selftest thread is running clone() while glibc runs either mprotect or mmap (both taking mmap_sem down_write()) to allocate the thread stack of the background threads, while locking/userfault threads already run at full throttle and are susceptible to false wakeups that may cause handle_userfault() to return before than expected (which results in graceful SIGBUS at the next attempt). This was reproduced only with >=32 CPUs because the loop to start the thread where clone() is too quick with fewer CPUs, while with 32 CPUs there's already significant activity on ~32 locking and userfault threads when the last background threads are started with clone(). This >=32 CPUs SMP race condition is likely reproducible only with the selftest because of the much heavier userfault load it generates if compared to real apps. We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a patch floating around that provides it also hidden this problem but in reality only is successfully at hiding the problem. False wakeups could still happen again the second time handle_userfault() is invoked, even if it's a so rare race condition that getting false wakeups twice in a row is impossible to reproduce. This full fix is needed for correctness, the only alternative would be to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP support can stick to a strict "one more" VM_FAULT_RETRY logic (no need of returning it infinite times to avoid the SIGBUS). Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Michael Rapoport <RAPOPORT@il.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-25 07:17:59 +08:00
long blocking_state;
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
ret = VM_FAULT_SIGBUS;
/*
* We don't do userfault handling for the final child pid update.
*
* We also don't do userfault handling during
* coredumping. hugetlbfs has the special
* follow_hugetlb_page() to skip missing pages in the
* FOLL_DUMP case, anon memory also checks for FOLL_DUMP with
* the no_page_table() helper in follow_page_mask(), but the
* shmem_vm_ops->fault method is invoked even during
* coredumping without mmap_sem and it ends up here.
*/
if (current->flags & (PF_EXITING|PF_DUMPCORE))
goto out;
/*
* Coredumping runs without mmap_sem so we can only check that
* the mmap_sem is held, if PF_DUMPCORE was not set.
*/
WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));
ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
if (!ctx)
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
goto out;
BUG_ON(ctx->mm != mm);
VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));
mm: userfaultfd: add feature to request for a signal delivery In some cases, userfaultfd mechanism should just deliver a SIGBUS signal to the faulting process, instead of the page-fault event. Dealing with page-fault event using a monitor thread can be an overhead in these cases. For example applications like the database could use the signaling mechanism for robustness purpose. Database uses hugetlbfs for performance reason. Files on hugetlbfs filesystem are created and huge pages allocated using fallocate() API. Pages are deallocated/freed using fallocate() hole punching support. These files are mmapped and accessed by many processes as shared memory. The database keeps track of which offsets in the hugetlbfs file have pages allocated. Any access to mapped address over holes in the file, which can occur due to bugs in the application, is considered invalid and expect the process to simply receive a SIGBUS. However, currently when a hole in the file is accessed via the mapped address, kernel/mm attempts to automatically allocate a page at page fault time, resulting in implicitly filling the hole in the file. This may not be the desired behavior for applications like the database that want to explicitly manage page allocations of hugetlbfs files. Using userfaultfd mechanism with this support to get a signal, database application can prevent pages from being allocated implicitly when processes access mapped address over holes in the file. This patch adds UFFD_FEATURE_SIGBUS feature to userfaultfd mechnism to request for a SIGBUS signal. See following for previous discussion about the database requirement leading to this proposal as suggested by Andrea. http://www.spinics.net/lists/linux-mm/msg129224.html Link: http://lkml.kernel.org/r/1501552446-748335-2-git-send-email-prakash.sangappa@oracle.com Signed-off-by: Prakash Sangappa <prakash.sangappa@oracle.com> Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 07:23:39 +08:00
if (ctx->features & UFFD_FEATURE_SIGBUS)
goto out;
/*
* If it's already released don't get it. This avoids to loop
* in __get_user_pages if userfaultfd_release waits on the
* caller of handle_userfault to release the mmap_sem.
*/
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 05:07:29 +08:00
if (unlikely(READ_ONCE(ctx->released))) {
/*
* Don't return VM_FAULT_SIGBUS in this case, so a non
* cooperative manager can close the uffd after the
* last UFFDIO_COPY, without risking to trigger an
* involuntary SIGBUS if the process was starting the
* userfaultfd while the userfaultfd was still armed
* (but after the last UFFDIO_COPY). If the uffd
* wasn't already closed when the userfault reached
* this point, that would normally be solved by
* userfaultfd_must_wait returning 'false'.
*
* If we were to return VM_FAULT_SIGBUS here, the non
* cooperative manager would be instead forced to
* always call UFFDIO_UNREGISTER before it can safely
* close the uffd.
*/
ret = VM_FAULT_NOPAGE;
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
goto out;
}
/*
* Check that we can return VM_FAULT_RETRY.
*
* NOTE: it should become possible to return VM_FAULT_RETRY
* even if FAULT_FLAG_TRIED is set without leading to gup()
* -EBUSY failures, if the userfaultfd is to be extended for
* VM_UFFD_WP tracking and we intend to arm the userfault
* without first stopping userland access to the memory. For
* VM_UFFD_MISSING userfaults this is enough for now.
*/
if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) {
/*
* Validate the invariant that nowait must allow retry
* to be sure not to return SIGBUS erroneously on
* nowait invocations.
*/
BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
#ifdef CONFIG_DEBUG_VM
if (printk_ratelimit()) {
printk(KERN_WARNING
"FAULT_FLAG_ALLOW_RETRY missing %x\n",
vmf->flags);
dump_stack();
}
#endif
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
goto out;
}
/*
* Handle nowait, not much to do other than tell it to retry
* and wait.
*/
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
ret = VM_FAULT_RETRY;
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
goto out;
/* take the reference before dropping the mmap_sem */
userfaultfd_ctx_get(ctx);
init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
uwq.wq.private = current;
uwq.msg = userfault_msg(vmf->address, vmf->flags, reason,
ctx->features);
uwq.ctx = ctx;
userfaultfd: fix SIGBUS resulting from false rwsem wakeups With >=32 CPUs the userfaultfd selftest triggered a graceful but unexpected SIGBUS because VM_FAULT_RETRY was returned by handle_userfault() despite the UFFDIO_COPY wasn't completed. This seems caused by rwsem waking the thread blocked in handle_userfault() and we can't run up_read() before the wait_event sequence is complete. Keeping the wait_even sequence identical to the first one, would require running userfaultfd_must_wait() again to know if the loop should be repeated, and it would also require retaking the rwsem and revalidating the whole vma status. It seems simpler to wait the targeted wakeup so that if false wakeups materialize we still wait for our specific wakeup event, unless of course there are signals or the uffd was released. Debug code collecting the stack trace of the wakeup showed this: $ ./userfaultfd 100 99999 nr_pages: 25600, nr_pages_per_cpu: 800 bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2 bounces: 99997, mode: rnd ver poll, Bus error (core dumped) save_stack_trace+0x2b/0x50 try_to_wake_up+0x2a6/0x580 wake_up_q+0x32/0x70 rwsem_wake+0xe0/0x120 call_rwsem_wake+0x1b/0x30 up_write+0x3b/0x40 vm_mmap_pgoff+0x9c/0xc0 SyS_mmap_pgoff+0x1a9/0x240 SyS_mmap+0x22/0x30 entry_SYSCALL_64_fastpath+0x1f/0xbd 0xffffffffffffffff FAULT_FLAG_ALLOW_RETRY missing 70 CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xb8/0x112 handle_userfault+0x572/0x650 handle_mm_fault+0x12cb/0x1520 __do_page_fault+0x175/0x500 trace_do_page_fault+0x61/0x270 do_async_page_fault+0x19/0x90 async_page_fault+0x25/0x30 This always happens when the main userfault selftest thread is running clone() while glibc runs either mprotect or mmap (both taking mmap_sem down_write()) to allocate the thread stack of the background threads, while locking/userfault threads already run at full throttle and are susceptible to false wakeups that may cause handle_userfault() to return before than expected (which results in graceful SIGBUS at the next attempt). This was reproduced only with >=32 CPUs because the loop to start the thread where clone() is too quick with fewer CPUs, while with 32 CPUs there's already significant activity on ~32 locking and userfault threads when the last background threads are started with clone(). This >=32 CPUs SMP race condition is likely reproducible only with the selftest because of the much heavier userfault load it generates if compared to real apps. We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a patch floating around that provides it also hidden this problem but in reality only is successfully at hiding the problem. False wakeups could still happen again the second time handle_userfault() is invoked, even if it's a so rare race condition that getting false wakeups twice in a row is impossible to reproduce. This full fix is needed for correctness, the only alternative would be to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP support can stick to a strict "one more" VM_FAULT_RETRY logic (no need of returning it infinite times to avoid the SIGBUS). Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Michael Rapoport <RAPOPORT@il.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-25 07:17:59 +08:00
uwq.waken = false;
return_to_userland =
(vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
userfaultfd: fix SIGBUS resulting from false rwsem wakeups With >=32 CPUs the userfaultfd selftest triggered a graceful but unexpected SIGBUS because VM_FAULT_RETRY was returned by handle_userfault() despite the UFFDIO_COPY wasn't completed. This seems caused by rwsem waking the thread blocked in handle_userfault() and we can't run up_read() before the wait_event sequence is complete. Keeping the wait_even sequence identical to the first one, would require running userfaultfd_must_wait() again to know if the loop should be repeated, and it would also require retaking the rwsem and revalidating the whole vma status. It seems simpler to wait the targeted wakeup so that if false wakeups materialize we still wait for our specific wakeup event, unless of course there are signals or the uffd was released. Debug code collecting the stack trace of the wakeup showed this: $ ./userfaultfd 100 99999 nr_pages: 25600, nr_pages_per_cpu: 800 bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2 bounces: 99997, mode: rnd ver poll, Bus error (core dumped) save_stack_trace+0x2b/0x50 try_to_wake_up+0x2a6/0x580 wake_up_q+0x32/0x70 rwsem_wake+0xe0/0x120 call_rwsem_wake+0x1b/0x30 up_write+0x3b/0x40 vm_mmap_pgoff+0x9c/0xc0 SyS_mmap_pgoff+0x1a9/0x240 SyS_mmap+0x22/0x30 entry_SYSCALL_64_fastpath+0x1f/0xbd 0xffffffffffffffff FAULT_FLAG_ALLOW_RETRY missing 70 CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xb8/0x112 handle_userfault+0x572/0x650 handle_mm_fault+0x12cb/0x1520 __do_page_fault+0x175/0x500 trace_do_page_fault+0x61/0x270 do_async_page_fault+0x19/0x90 async_page_fault+0x25/0x30 This always happens when the main userfault selftest thread is running clone() while glibc runs either mprotect or mmap (both taking mmap_sem down_write()) to allocate the thread stack of the background threads, while locking/userfault threads already run at full throttle and are susceptible to false wakeups that may cause handle_userfault() to return before than expected (which results in graceful SIGBUS at the next attempt). This was reproduced only with >=32 CPUs because the loop to start the thread where clone() is too quick with fewer CPUs, while with 32 CPUs there's already significant activity on ~32 locking and userfault threads when the last background threads are started with clone(). This >=32 CPUs SMP race condition is likely reproducible only with the selftest because of the much heavier userfault load it generates if compared to real apps. We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a patch floating around that provides it also hidden this problem but in reality only is successfully at hiding the problem. False wakeups could still happen again the second time handle_userfault() is invoked, even if it's a so rare race condition that getting false wakeups twice in a row is impossible to reproduce. This full fix is needed for correctness, the only alternative would be to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP support can stick to a strict "one more" VM_FAULT_RETRY logic (no need of returning it infinite times to avoid the SIGBUS). Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Michael Rapoport <RAPOPORT@il.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-25 07:17:59 +08:00
blocking_state = return_to_userland ? TASK_INTERRUPTIBLE :
TASK_KILLABLE;
spin_lock(&ctx->fault_pending_wqh.lock);
/*
* After the __add_wait_queue the uwq is visible to userland
* through poll/read().
*/
__add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq);
/*
* The smp_mb() after __set_current_state prevents the reads
* following the spin_unlock to happen before the list_add in
* __add_wait_queue.
*/
userfaultfd: fix SIGBUS resulting from false rwsem wakeups With >=32 CPUs the userfaultfd selftest triggered a graceful but unexpected SIGBUS because VM_FAULT_RETRY was returned by handle_userfault() despite the UFFDIO_COPY wasn't completed. This seems caused by rwsem waking the thread blocked in handle_userfault() and we can't run up_read() before the wait_event sequence is complete. Keeping the wait_even sequence identical to the first one, would require running userfaultfd_must_wait() again to know if the loop should be repeated, and it would also require retaking the rwsem and revalidating the whole vma status. It seems simpler to wait the targeted wakeup so that if false wakeups materialize we still wait for our specific wakeup event, unless of course there are signals or the uffd was released. Debug code collecting the stack trace of the wakeup showed this: $ ./userfaultfd 100 99999 nr_pages: 25600, nr_pages_per_cpu: 800 bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2 bounces: 99997, mode: rnd ver poll, Bus error (core dumped) save_stack_trace+0x2b/0x50 try_to_wake_up+0x2a6/0x580 wake_up_q+0x32/0x70 rwsem_wake+0xe0/0x120 call_rwsem_wake+0x1b/0x30 up_write+0x3b/0x40 vm_mmap_pgoff+0x9c/0xc0 SyS_mmap_pgoff+0x1a9/0x240 SyS_mmap+0x22/0x30 entry_SYSCALL_64_fastpath+0x1f/0xbd 0xffffffffffffffff FAULT_FLAG_ALLOW_RETRY missing 70 CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xb8/0x112 handle_userfault+0x572/0x650 handle_mm_fault+0x12cb/0x1520 __do_page_fault+0x175/0x500 trace_do_page_fault+0x61/0x270 do_async_page_fault+0x19/0x90 async_page_fault+0x25/0x30 This always happens when the main userfault selftest thread is running clone() while glibc runs either mprotect or mmap (both taking mmap_sem down_write()) to allocate the thread stack of the background threads, while locking/userfault threads already run at full throttle and are susceptible to false wakeups that may cause handle_userfault() to return before than expected (which results in graceful SIGBUS at the next attempt). This was reproduced only with >=32 CPUs because the loop to start the thread where clone() is too quick with fewer CPUs, while with 32 CPUs there's already significant activity on ~32 locking and userfault threads when the last background threads are started with clone(). This >=32 CPUs SMP race condition is likely reproducible only with the selftest because of the much heavier userfault load it generates if compared to real apps. We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a patch floating around that provides it also hidden this problem but in reality only is successfully at hiding the problem. False wakeups could still happen again the second time handle_userfault() is invoked, even if it's a so rare race condition that getting false wakeups twice in a row is impossible to reproduce. This full fix is needed for correctness, the only alternative would be to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP support can stick to a strict "one more" VM_FAULT_RETRY logic (no need of returning it infinite times to avoid the SIGBUS). Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Michael Rapoport <RAPOPORT@il.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-25 07:17:59 +08:00
set_current_state(blocking_state);
spin_unlock(&ctx->fault_pending_wqh.lock);
if (!is_vm_hugetlb_page(vmf->vma))
must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
reason);
else
mm/hugetlb: add size parameter to huge_pte_offset() A poisoned or migrated hugepage is stored as a swap entry in the page tables. On architectures that support hugepages consisting of contiguous page table entries (such as on arm64) this leads to ambiguity in determining the page table entry to return in huge_pte_offset() when a poisoned entry is encountered. Let's remove the ambiguity by adding a size parameter to convey additional information about the requested address. Also fixup the definition/usage of huge_pte_offset() throughout the tree. Link: http://lkml.kernel.org/r/20170522133604.11392-4-punit.agrawal@arm.com Signed-off-by: Punit Agrawal <punit.agrawal@arm.com> Acked-by: Steve Capper <steve.capper@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: James Hogan <james.hogan@imgtec.com> (odd fixer:METAG ARCHITECTURE) Cc: Ralf Baechle <ralf@linux-mips.org> (supporter:MIPS) Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Rich Felker <dalias@libc.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-07 06:39:42 +08:00
must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma,
vmf->address,
vmf->flags, reason);
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and userfaultfd_read if they are run on different threads simultaneously. Until now qemu solved the race in userland: the race was explicitly and intentionally left for userland to solve. However we can also solve it in kernel. Requiring all users to solve this race if they use two threads (one for the background transfer and one for the userfault reads) isn't very attractive from an API prospective, furthermore this allows to remove a whole bunch of mutex and bitmap code from qemu, making it faster. The cost of __get_user_pages_fast should be insignificant considering it scales perfectly and the pagetables are already hot in the CPU cache, compared to the overhead in userland to maintain those structures. Applying this patch is backwards compatible with respect to the userfaultfd userland API, however reverting this change wouldn't be backwards compatible anymore. Without this patch qemu in the background transfer thread, has to read the old state, and do UFFDIO_WAKE if old_state is missing but it become REQUESTED by the time it tries to set it to RECEIVED (signaling the other side received an userfault). vcpu background_thr userfault_thr ----- ----- ----- vcpu0 handle_mm_fault() postcopy_place_page read old_state -> MISSING UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending) vcpu0 fault at 0x7fb76a139000 enters handle_userfault poll() is kicked poll() -> POLLIN read() -> 0x7fb76a139000 postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED /* check that no userfault raced with UFFDIO_COPY */ if (old_state == MISSING && tmp_state == REQUESTED) UFFDIO_WAKE from background thread And a second case where a UFFDIO_WAKE would be needed is in the userfault thread: vcpu background_thr userfault_thr ----- ----- ----- vcpu0 handle_mm_fault() postcopy_place_page read old_state -> MISSING UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending) tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED vcpu0 fault at 0x7fb76a139000 enters handle_userfault poll() is kicked poll() -> POLLIN read() -> 0x7fb76a139000 if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED) UFFDIO_WAKE from userfault thread This patch removes the need of both UFFDIO_WAKE and of the associated per-page tristate as well. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:51 +08:00
up_read(&mm->mmap_sem);
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 05:07:29 +08:00
if (likely(must_wait && !READ_ONCE(ctx->released) &&
(return_to_userland ? !signal_pending(current) :
!fatal_signal_pending(current)))) {
wake_up_poll(&ctx->fd_wqh, POLLIN);
schedule();
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
ret |= VM_FAULT_MAJOR;
userfaultfd: fix SIGBUS resulting from false rwsem wakeups With >=32 CPUs the userfaultfd selftest triggered a graceful but unexpected SIGBUS because VM_FAULT_RETRY was returned by handle_userfault() despite the UFFDIO_COPY wasn't completed. This seems caused by rwsem waking the thread blocked in handle_userfault() and we can't run up_read() before the wait_event sequence is complete. Keeping the wait_even sequence identical to the first one, would require running userfaultfd_must_wait() again to know if the loop should be repeated, and it would also require retaking the rwsem and revalidating the whole vma status. It seems simpler to wait the targeted wakeup so that if false wakeups materialize we still wait for our specific wakeup event, unless of course there are signals or the uffd was released. Debug code collecting the stack trace of the wakeup showed this: $ ./userfaultfd 100 99999 nr_pages: 25600, nr_pages_per_cpu: 800 bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2 bounces: 99997, mode: rnd ver poll, Bus error (core dumped) save_stack_trace+0x2b/0x50 try_to_wake_up+0x2a6/0x580 wake_up_q+0x32/0x70 rwsem_wake+0xe0/0x120 call_rwsem_wake+0x1b/0x30 up_write+0x3b/0x40 vm_mmap_pgoff+0x9c/0xc0 SyS_mmap_pgoff+0x1a9/0x240 SyS_mmap+0x22/0x30 entry_SYSCALL_64_fastpath+0x1f/0xbd 0xffffffffffffffff FAULT_FLAG_ALLOW_RETRY missing 70 CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xb8/0x112 handle_userfault+0x572/0x650 handle_mm_fault+0x12cb/0x1520 __do_page_fault+0x175/0x500 trace_do_page_fault+0x61/0x270 do_async_page_fault+0x19/0x90 async_page_fault+0x25/0x30 This always happens when the main userfault selftest thread is running clone() while glibc runs either mprotect or mmap (both taking mmap_sem down_write()) to allocate the thread stack of the background threads, while locking/userfault threads already run at full throttle and are susceptible to false wakeups that may cause handle_userfault() to return before than expected (which results in graceful SIGBUS at the next attempt). This was reproduced only with >=32 CPUs because the loop to start the thread where clone() is too quick with fewer CPUs, while with 32 CPUs there's already significant activity on ~32 locking and userfault threads when the last background threads are started with clone(). This >=32 CPUs SMP race condition is likely reproducible only with the selftest because of the much heavier userfault load it generates if compared to real apps. We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a patch floating around that provides it also hidden this problem but in reality only is successfully at hiding the problem. False wakeups could still happen again the second time handle_userfault() is invoked, even if it's a so rare race condition that getting false wakeups twice in a row is impossible to reproduce. This full fix is needed for correctness, the only alternative would be to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP support can stick to a strict "one more" VM_FAULT_RETRY logic (no need of returning it infinite times to avoid the SIGBUS). Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Michael Rapoport <RAPOPORT@il.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-25 07:17:59 +08:00
/*
* False wakeups can orginate even from rwsem before
* up_read() however userfaults will wait either for a
* targeted wakeup on the specific uwq waitqueue from
* wake_userfault() or for signals or for uffd
* release.
*/
while (!READ_ONCE(uwq.waken)) {
/*
* This needs the full smp_store_mb()
* guarantee as the state write must be
* visible to other CPUs before reading
* uwq.waken from other CPUs.
*/
set_current_state(blocking_state);
if (READ_ONCE(uwq.waken) ||
READ_ONCE(ctx->released) ||
(return_to_userland ? signal_pending(current) :
fatal_signal_pending(current)))
break;
schedule();
}
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
}
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
__set_current_state(TASK_RUNNING);
if (return_to_userland) {
if (signal_pending(current) &&
!fatal_signal_pending(current)) {
/*
* If we got a SIGSTOP or SIGCONT and this is
* a normal userland page fault, just let
* userland return so the signal will be
* handled and gdb debugging works. The page
* fault code immediately after we return from
* this function is going to release the
* mmap_sem and it's not depending on it
* (unlike gup would if we were not to return
* VM_FAULT_RETRY).
*
* If a fatal signal is pending we still take
* the streamlined VM_FAULT_RETRY failure path
* and there's no need to retake the mmap_sem
* in such case.
*/
down_read(&mm->mmap_sem);
ret = VM_FAULT_NOPAGE;
}
}
/*
* Here we race with the list_del; list_add in
* userfaultfd_ctx_read(), however because we don't ever run
* list_del_init() to refile across the two lists, the prev
* and next pointers will never point to self. list_add also
* would never let any of the two pointers to point to
* self. So list_empty_careful won't risk to see both pointers
* pointing to self at any time during the list refile. The
* only case where list_del_init() is called is the full
* removal in the wake function and there we don't re-list_add
* and it's fine not to block on the spinlock. The uwq on this
* kernel stack can be released after the list_del_init.
*/
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
if (!list_empty_careful(&uwq.wq.entry)) {
spin_lock(&ctx->fault_pending_wqh.lock);
/*
* No need of list_del_init(), the uwq on the stack
* will be freed shortly anyway.
*/
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
list_del(&uwq.wq.entry);
spin_unlock(&ctx->fault_pending_wqh.lock);
}
/*
* ctx may go away after this if the userfault pseudo fd is
* already released.
*/
userfaultfd_ctx_put(ctx);
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
out:
return ret;
}
static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
struct userfaultfd_wait_queue *ewq)
{
if (WARN_ON_ONCE(current->flags & PF_EXITING))
goto out;
ewq->ctx = ctx;
init_waitqueue_entry(&ewq->wq, current);
spin_lock(&ctx->event_wqh.lock);
/*
* After the __add_wait_queue the uwq is visible to userland
* through poll/read().
*/
__add_wait_queue(&ctx->event_wqh, &ewq->wq);
for (;;) {
set_current_state(TASK_KILLABLE);
if (ewq->msg.event == 0)
break;
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 05:07:29 +08:00
if (READ_ONCE(ctx->released) ||
fatal_signal_pending(current)) {
userfaultfd: non-cooperative: fix fork use after free When reading the event from the uffd, we put it on a temporary fork_event list to detect if we can still access it after releasing and retaking the event_wqh.lock. If fork aborts and removes the event from the fork_event all is fine as long as we're still in the userfault read context and fork_event head is still alive. We've to put the event allocated in the fork kernel stack, back from fork_event list-head to the event_wqh head, before returning from userfaultfd_ctx_read, because the fork_event head lifetime is limited to the userfaultfd_ctx_read stack lifetime. Forgetting to move the event back to its event_wqh place then results in __remove_wait_queue(&ctx->event_wqh, &ewq->wq); in userfaultfd_event_wait_completion to remove it from a head that has been already freed from the reader stack. This could only happen if resolve_userfault_fork failed (for example if there are no file descriptors available to allocate the fork uffd). If it succeeded it was put back correctly. Furthermore, after find_userfault_evt receives a fork event, the forked userfault context in fork_nctx and uwq->msg.arg.reserved.reserved1 can be released by the fork thread as soon as the event_wqh.lock is released. Taking a reference on the fork_nctx before dropping the lock prevents an use after free in resolve_userfault_fork(). If the fork side aborted and it already released everything, we still try to succeed resolve_userfault_fork(), if possible. Fixes: 893e26e61d04eac9 ("userfaultfd: non-cooperative: Add fork() event") Link: http://lkml.kernel.org/r/20170920180413.26713-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Mark Rutland <mark.rutland@arm.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-04 07:15:38 +08:00
/*
* &ewq->wq may be queued in fork_event, but
* __remove_wait_queue ignores the head
* parameter. It would be a problem if it
* didn't.
*/
__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
if (ewq->msg.event == UFFD_EVENT_FORK) {
struct userfaultfd_ctx *new;
new = (struct userfaultfd_ctx *)
(unsigned long)
ewq->msg.arg.reserved.reserved1;
userfaultfd_ctx_put(new);
}
break;
}
spin_unlock(&ctx->event_wqh.lock);
wake_up_poll(&ctx->fd_wqh, POLLIN);
schedule();
spin_lock(&ctx->event_wqh.lock);
}
__set_current_state(TASK_RUNNING);
spin_unlock(&ctx->event_wqh.lock);
/*
* ctx may go away after this if the userfault pseudo fd is
* already released.
*/
out:
userfaultfd_ctx_put(ctx);
}
static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
struct userfaultfd_wait_queue *ewq)
{
ewq->msg.event = 0;
wake_up_locked(&ctx->event_wqh);
__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
}
2017-02-23 07:42:27 +08:00
int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
{
struct userfaultfd_ctx *ctx = NULL, *octx;
struct userfaultfd_fork_ctx *fctx;
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
return 0;
}
list_for_each_entry(fctx, fcs, list)
if (fctx->orig == octx) {
ctx = fctx->new;
break;
}
if (!ctx) {
fctx = kmalloc(sizeof(*fctx), GFP_KERNEL);
if (!fctx)
return -ENOMEM;
ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
if (!ctx) {
kfree(fctx);
return -ENOMEM;
}
atomic_set(&ctx->refcount, 1);
ctx->flags = octx->flags;
ctx->state = UFFD_STATE_RUNNING;
ctx->features = octx->features;
ctx->released = false;
ctx->mm = vma->vm_mm;
mmgrab(ctx->mm);
2017-02-23 07:42:27 +08:00
userfaultfd_ctx_get(octx);
fctx->orig = octx;
fctx->new = ctx;
list_add_tail(&fctx->list, fcs);
}
vma->vm_userfaultfd_ctx.ctx = ctx;
return 0;
}
static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
2017-02-23 07:42:27 +08:00
{
struct userfaultfd_ctx *ctx = fctx->orig;
struct userfaultfd_wait_queue ewq;
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_FORK;
ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
userfaultfd_event_wait_completion(ctx, &ewq);
2017-02-23 07:42:27 +08:00
}
void dup_userfaultfd_complete(struct list_head *fcs)
{
struct userfaultfd_fork_ctx *fctx, *n;
list_for_each_entry_safe(fctx, n, fcs, list) {
dup_fctx(fctx);
2017-02-23 07:42:27 +08:00
list_del(&fctx->list);
kfree(fctx);
}
}
void mremap_userfaultfd_prep(struct vm_area_struct *vma,
struct vm_userfaultfd_ctx *vm_ctx)
{
struct userfaultfd_ctx *ctx;
ctx = vma->vm_userfaultfd_ctx.ctx;
if (ctx && (ctx->features & UFFD_FEATURE_EVENT_REMAP)) {
vm_ctx->ctx = ctx;
userfaultfd_ctx_get(ctx);
}
}
void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
unsigned long from, unsigned long to,
unsigned long len)
{
struct userfaultfd_ctx *ctx = vm_ctx->ctx;
struct userfaultfd_wait_queue ewq;
if (!ctx)
return;
if (to & ~PAGE_MASK) {
userfaultfd_ctx_put(ctx);
return;
}
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_REMAP;
ewq.msg.arg.remap.from = from;
ewq.msg.arg.remap.to = to;
ewq.msg.arg.remap.len = len;
userfaultfd_event_wait_completion(ctx, &ewq);
}
bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
struct userfaultfd_ctx *ctx;
struct userfaultfd_wait_queue ewq;
ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
return true;
userfaultfd_ctx_get(ctx);
up_read(&mm->mmap_sem);
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_REMOVE;
ewq.msg.arg.remove.start = start;
ewq.msg.arg.remove.end = end;
userfaultfd_event_wait_completion(ctx, &ewq);
return false;
}
static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
unsigned long start, unsigned long end)
{
struct userfaultfd_unmap_ctx *unmap_ctx;
list_for_each_entry(unmap_ctx, unmaps, list)
if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
unmap_ctx->end == end)
return true;
return false;
}
int userfaultfd_unmap_prep(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct list_head *unmaps)
{
for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
struct userfaultfd_unmap_ctx *unmap_ctx;
struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
has_unmap_ctx(ctx, unmaps, start, end))
continue;
unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
if (!unmap_ctx)
return -ENOMEM;
userfaultfd_ctx_get(ctx);
unmap_ctx->ctx = ctx;
unmap_ctx->start = start;
unmap_ctx->end = end;
list_add_tail(&unmap_ctx->list, unmaps);
}
return 0;
}
void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
{
struct userfaultfd_unmap_ctx *ctx, *n;
struct userfaultfd_wait_queue ewq;
list_for_each_entry_safe(ctx, n, uf, list) {
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_UNMAP;
ewq.msg.arg.remove.start = ctx->start;
ewq.msg.arg.remove.end = ctx->end;
userfaultfd_event_wait_completion(ctx->ctx, &ewq);
list_del(&ctx->list);
kfree(ctx);
}
}
static int userfaultfd_release(struct inode *inode, struct file *file)
{
struct userfaultfd_ctx *ctx = file->private_data;
struct mm_struct *mm = ctx->mm;
struct vm_area_struct *vma, *prev;
/* len == 0 means wake all */
struct userfaultfd_wake_range range = { .len = 0, };
unsigned long new_flags;
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 05:07:29 +08:00
WRITE_ONCE(ctx->released, true);
if (!mmget_not_zero(mm))
goto wakeup;
/*
* Flush page faults out of all CPUs. NOTE: all page faults
* must be retried without returning VM_FAULT_SIGBUS if
* userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx
* changes while handle_userfault released the mmap_sem. So
* it's critical that released is set to true (above), before
* taking the mmap_sem for writing.
*/
down_write(&mm->mmap_sem);
prev = NULL;
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cond_resched();
BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
!!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
if (vma->vm_userfaultfd_ctx.ctx != ctx) {
prev = vma;
continue;
}
new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
new_flags, vma->anon_vma,
vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
NULL_VM_UFFD_CTX);
if (prev)
vma = prev;
else
prev = vma;
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
up_write(&mm->mmap_sem);
mmput(mm);
wakeup:
/*
* After no new page faults can wait on this fault_*wqh, flush
* the last page faults that may have been already waiting on
* the fault_*wqh.
*/
spin_lock(&ctx->fault_pending_wqh.lock);
__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range);
spin_unlock(&ctx->fault_pending_wqh.lock);
/* Flush pending events that may still wait on event_wqh */
wake_up_all(&ctx->event_wqh);
wake_up_poll(&ctx->fd_wqh, POLLHUP);
userfaultfd_ctx_put(ctx);
return 0;
}
/* fault_pending_wqh.lock must be hold by the caller */
static inline struct userfaultfd_wait_queue *find_userfault_in(
wait_queue_head_t *wqh)
{
wait_queue_entry_t *wq;
struct userfaultfd_wait_queue *uwq;
VM_BUG_ON(!spin_is_locked(&wqh->lock));
uwq = NULL;
if (!waitqueue_active(wqh))
goto out;
/* walk in reverse to provide FIFO behavior to read userfaults */
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
wq = list_last_entry(&wqh->head, typeof(*wq), entry);
uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
out:
return uwq;
}
static inline struct userfaultfd_wait_queue *find_userfault(
struct userfaultfd_ctx *ctx)
{
return find_userfault_in(&ctx->fault_pending_wqh);
}
static inline struct userfaultfd_wait_queue *find_userfault_evt(
struct userfaultfd_ctx *ctx)
{
return find_userfault_in(&ctx->event_wqh);
}
static unsigned int userfaultfd_poll(struct file *file, poll_table *wait)
{
struct userfaultfd_ctx *ctx = file->private_data;
unsigned int ret;
poll_wait(file, &ctx->fd_wqh, wait);
switch (ctx->state) {
case UFFD_STATE_WAIT_API:
return POLLERR;
case UFFD_STATE_RUNNING:
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
/*
* poll() never guarantees that read won't block.
* userfaults can be waken before they're read().
*/
if (unlikely(!(file->f_flags & O_NONBLOCK)))
return POLLERR;
/*
* lockless access to see if there are pending faults
* __pollwait last action is the add_wait_queue but
* the spin_unlock would allow the waitqueue_active to
* pass above the actual list_add inside
* add_wait_queue critical section. So use a full
* memory barrier to serialize the list_add write of
* add_wait_queue() with the waitqueue_active read
* below.
*/
ret = 0;
smp_mb();
if (waitqueue_active(&ctx->fault_pending_wqh))
ret = POLLIN;
else if (waitqueue_active(&ctx->event_wqh))
ret = POLLIN;
return ret;
default:
WARN_ON_ONCE(1);
return POLLERR;
}
}
2017-02-23 07:42:27 +08:00
static const struct file_operations userfaultfd_fops;
static int resolve_userfault_fork(struct userfaultfd_ctx *ctx,
struct userfaultfd_ctx *new,
struct uffd_msg *msg)
{
int fd;
struct file *file;
unsigned int flags = new->flags & UFFD_SHARED_FCNTL_FLAGS;
fd = get_unused_fd_flags(flags);
if (fd < 0)
return fd;
file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, new,
O_RDWR | flags);
if (IS_ERR(file)) {
put_unused_fd(fd);
return PTR_ERR(file);
}
fd_install(fd, file);
msg->arg.reserved.reserved1 = 0;
msg->arg.fork.ufd = fd;
return 0;
}
static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
struct uffd_msg *msg)
{
ssize_t ret;
DECLARE_WAITQUEUE(wait, current);
struct userfaultfd_wait_queue *uwq;
2017-02-23 07:42:27 +08:00
/*
* Handling fork event requires sleeping operations, so
* we drop the event_wqh lock, then do these ops, then
* lock it back and wake up the waiter. While the lock is
* dropped the ewq may go away so we keep track of it
* carefully.
*/
LIST_HEAD(fork_event);
struct userfaultfd_ctx *fork_nctx = NULL;
/* always take the fd_wqh lock before the fault_pending_wqh lock */
spin_lock(&ctx->fd_wqh.lock);
__add_wait_queue(&ctx->fd_wqh, &wait);
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
spin_lock(&ctx->fault_pending_wqh.lock);
uwq = find_userfault(ctx);
if (uwq) {
/*
* Use a seqcount to repeat the lockless check
* in wake_userfault() to avoid missing
* wakeups because during the refile both
* waitqueue could become empty if this is the
* only userfault.
*/
write_seqcount_begin(&ctx->refile_seq);
/*
* The fault_pending_wqh.lock prevents the uwq
* to disappear from under us.
*
* Refile this userfault from
* fault_pending_wqh to fault_wqh, it's not
* pending anymore after we read it.
*
* Use list_del() by hand (as
* userfaultfd_wake_function also uses
* list_del_init() by hand) to be sure nobody
* changes __remove_wait_queue() to use
* list_del_init() in turn breaking the
* !list_empty_careful() check in
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
* handle_userfault(). The uwq->wq.head list
* must never be empty at any time during the
* refile, or the waitqueue could disappear
* from under us. The "wait_queue_head_t"
* parameter of __remove_wait_queue() is unused
* anyway.
*/
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
list_del(&uwq->wq.entry);
__add_wait_queue(&ctx->fault_wqh, &uwq->wq);
write_seqcount_end(&ctx->refile_seq);
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
/* careful to always initialize msg if ret == 0 */
*msg = uwq->msg;
spin_unlock(&ctx->fault_pending_wqh.lock);
ret = 0;
break;
}
spin_unlock(&ctx->fault_pending_wqh.lock);
spin_lock(&ctx->event_wqh.lock);
uwq = find_userfault_evt(ctx);
if (uwq) {
*msg = uwq->msg;
2017-02-23 07:42:27 +08:00
if (uwq->msg.event == UFFD_EVENT_FORK) {
fork_nctx = (struct userfaultfd_ctx *)
(unsigned long)
uwq->msg.arg.reserved.reserved1;
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
list_move(&uwq->wq.entry, &fork_event);
userfaultfd: non-cooperative: fix fork use after free When reading the event from the uffd, we put it on a temporary fork_event list to detect if we can still access it after releasing and retaking the event_wqh.lock. If fork aborts and removes the event from the fork_event all is fine as long as we're still in the userfault read context and fork_event head is still alive. We've to put the event allocated in the fork kernel stack, back from fork_event list-head to the event_wqh head, before returning from userfaultfd_ctx_read, because the fork_event head lifetime is limited to the userfaultfd_ctx_read stack lifetime. Forgetting to move the event back to its event_wqh place then results in __remove_wait_queue(&ctx->event_wqh, &ewq->wq); in userfaultfd_event_wait_completion to remove it from a head that has been already freed from the reader stack. This could only happen if resolve_userfault_fork failed (for example if there are no file descriptors available to allocate the fork uffd). If it succeeded it was put back correctly. Furthermore, after find_userfault_evt receives a fork event, the forked userfault context in fork_nctx and uwq->msg.arg.reserved.reserved1 can be released by the fork thread as soon as the event_wqh.lock is released. Taking a reference on the fork_nctx before dropping the lock prevents an use after free in resolve_userfault_fork(). If the fork side aborted and it already released everything, we still try to succeed resolve_userfault_fork(), if possible. Fixes: 893e26e61d04eac9 ("userfaultfd: non-cooperative: Add fork() event") Link: http://lkml.kernel.org/r/20170920180413.26713-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Mark Rutland <mark.rutland@arm.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-04 07:15:38 +08:00
/*
* fork_nctx can be freed as soon as
* we drop the lock, unless we take a
* reference on it.
*/
userfaultfd_ctx_get(fork_nctx);
2017-02-23 07:42:27 +08:00
spin_unlock(&ctx->event_wqh.lock);
ret = 0;
break;
}
userfaultfd_event_complete(ctx, uwq);
spin_unlock(&ctx->event_wqh.lock);
ret = 0;
break;
}
spin_unlock(&ctx->event_wqh.lock);
if (signal_pending(current)) {
ret = -ERESTARTSYS;
break;
}
if (no_wait) {
ret = -EAGAIN;
break;
}
spin_unlock(&ctx->fd_wqh.lock);
schedule();
spin_lock(&ctx->fd_wqh.lock);
}
__remove_wait_queue(&ctx->fd_wqh, &wait);
__set_current_state(TASK_RUNNING);
spin_unlock(&ctx->fd_wqh.lock);
2017-02-23 07:42:27 +08:00
if (!ret && msg->event == UFFD_EVENT_FORK) {
ret = resolve_userfault_fork(ctx, fork_nctx, msg);
userfaultfd: non-cooperative: fix fork use after free When reading the event from the uffd, we put it on a temporary fork_event list to detect if we can still access it after releasing and retaking the event_wqh.lock. If fork aborts and removes the event from the fork_event all is fine as long as we're still in the userfault read context and fork_event head is still alive. We've to put the event allocated in the fork kernel stack, back from fork_event list-head to the event_wqh head, before returning from userfaultfd_ctx_read, because the fork_event head lifetime is limited to the userfaultfd_ctx_read stack lifetime. Forgetting to move the event back to its event_wqh place then results in __remove_wait_queue(&ctx->event_wqh, &ewq->wq); in userfaultfd_event_wait_completion to remove it from a head that has been already freed from the reader stack. This could only happen if resolve_userfault_fork failed (for example if there are no file descriptors available to allocate the fork uffd). If it succeeded it was put back correctly. Furthermore, after find_userfault_evt receives a fork event, the forked userfault context in fork_nctx and uwq->msg.arg.reserved.reserved1 can be released by the fork thread as soon as the event_wqh.lock is released. Taking a reference on the fork_nctx before dropping the lock prevents an use after free in resolve_userfault_fork(). If the fork side aborted and it already released everything, we still try to succeed resolve_userfault_fork(), if possible. Fixes: 893e26e61d04eac9 ("userfaultfd: non-cooperative: Add fork() event") Link: http://lkml.kernel.org/r/20170920180413.26713-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Mark Rutland <mark.rutland@arm.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-04 07:15:38 +08:00
spin_lock(&ctx->event_wqh.lock);
if (!list_empty(&fork_event)) {
/*
* The fork thread didn't abort, so we can
* drop the temporary refcount.
*/
userfaultfd_ctx_put(fork_nctx);
uwq = list_first_entry(&fork_event,
typeof(*uwq),
wq.entry);
/*
* If fork_event list wasn't empty and in turn
* the event wasn't already released by fork
* (the event is allocated on fork kernel
* stack), put the event back to its place in
* the event_wq. fork_event head will be freed
* as soon as we return so the event cannot
* stay queued there no matter the current
* "ret" value.
*/
list_del(&uwq->wq.entry);
__add_wait_queue(&ctx->event_wqh, &uwq->wq);
2017-02-23 07:42:27 +08:00
userfaultfd: non-cooperative: fix fork use after free When reading the event from the uffd, we put it on a temporary fork_event list to detect if we can still access it after releasing and retaking the event_wqh.lock. If fork aborts and removes the event from the fork_event all is fine as long as we're still in the userfault read context and fork_event head is still alive. We've to put the event allocated in the fork kernel stack, back from fork_event list-head to the event_wqh head, before returning from userfaultfd_ctx_read, because the fork_event head lifetime is limited to the userfaultfd_ctx_read stack lifetime. Forgetting to move the event back to its event_wqh place then results in __remove_wait_queue(&ctx->event_wqh, &ewq->wq); in userfaultfd_event_wait_completion to remove it from a head that has been already freed from the reader stack. This could only happen if resolve_userfault_fork failed (for example if there are no file descriptors available to allocate the fork uffd). If it succeeded it was put back correctly. Furthermore, after find_userfault_evt receives a fork event, the forked userfault context in fork_nctx and uwq->msg.arg.reserved.reserved1 can be released by the fork thread as soon as the event_wqh.lock is released. Taking a reference on the fork_nctx before dropping the lock prevents an use after free in resolve_userfault_fork(). If the fork side aborted and it already released everything, we still try to succeed resolve_userfault_fork(), if possible. Fixes: 893e26e61d04eac9 ("userfaultfd: non-cooperative: Add fork() event") Link: http://lkml.kernel.org/r/20170920180413.26713-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Mark Rutland <mark.rutland@arm.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-04 07:15:38 +08:00
/*
* Leave the event in the waitqueue and report
* error to userland if we failed to resolve
* the userfault fork.
*/
if (likely(!ret))
2017-02-23 07:42:27 +08:00
userfaultfd_event_complete(ctx, uwq);
userfaultfd: non-cooperative: fix fork use after free When reading the event from the uffd, we put it on a temporary fork_event list to detect if we can still access it after releasing and retaking the event_wqh.lock. If fork aborts and removes the event from the fork_event all is fine as long as we're still in the userfault read context and fork_event head is still alive. We've to put the event allocated in the fork kernel stack, back from fork_event list-head to the event_wqh head, before returning from userfaultfd_ctx_read, because the fork_event head lifetime is limited to the userfaultfd_ctx_read stack lifetime. Forgetting to move the event back to its event_wqh place then results in __remove_wait_queue(&ctx->event_wqh, &ewq->wq); in userfaultfd_event_wait_completion to remove it from a head that has been already freed from the reader stack. This could only happen if resolve_userfault_fork failed (for example if there are no file descriptors available to allocate the fork uffd). If it succeeded it was put back correctly. Furthermore, after find_userfault_evt receives a fork event, the forked userfault context in fork_nctx and uwq->msg.arg.reserved.reserved1 can be released by the fork thread as soon as the event_wqh.lock is released. Taking a reference on the fork_nctx before dropping the lock prevents an use after free in resolve_userfault_fork(). If the fork side aborted and it already released everything, we still try to succeed resolve_userfault_fork(), if possible. Fixes: 893e26e61d04eac9 ("userfaultfd: non-cooperative: Add fork() event") Link: http://lkml.kernel.org/r/20170920180413.26713-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Mark Rutland <mark.rutland@arm.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-04 07:15:38 +08:00
} else {
/*
* Here the fork thread aborted and the
* refcount from the fork thread on fork_nctx
* has already been released. We still hold
* the reference we took before releasing the
* lock above. If resolve_userfault_fork
* failed we've to drop it because the
* fork_nctx has to be freed in such case. If
* it succeeded we'll hold it because the new
* uffd references it.
*/
if (ret)
userfaultfd_ctx_put(fork_nctx);
2017-02-23 07:42:27 +08:00
}
userfaultfd: non-cooperative: fix fork use after free When reading the event from the uffd, we put it on a temporary fork_event list to detect if we can still access it after releasing and retaking the event_wqh.lock. If fork aborts and removes the event from the fork_event all is fine as long as we're still in the userfault read context and fork_event head is still alive. We've to put the event allocated in the fork kernel stack, back from fork_event list-head to the event_wqh head, before returning from userfaultfd_ctx_read, because the fork_event head lifetime is limited to the userfaultfd_ctx_read stack lifetime. Forgetting to move the event back to its event_wqh place then results in __remove_wait_queue(&ctx->event_wqh, &ewq->wq); in userfaultfd_event_wait_completion to remove it from a head that has been already freed from the reader stack. This could only happen if resolve_userfault_fork failed (for example if there are no file descriptors available to allocate the fork uffd). If it succeeded it was put back correctly. Furthermore, after find_userfault_evt receives a fork event, the forked userfault context in fork_nctx and uwq->msg.arg.reserved.reserved1 can be released by the fork thread as soon as the event_wqh.lock is released. Taking a reference on the fork_nctx before dropping the lock prevents an use after free in resolve_userfault_fork(). If the fork side aborted and it already released everything, we still try to succeed resolve_userfault_fork(), if possible. Fixes: 893e26e61d04eac9 ("userfaultfd: non-cooperative: Add fork() event") Link: http://lkml.kernel.org/r/20170920180413.26713-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Mark Rutland <mark.rutland@arm.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-04 07:15:38 +08:00
spin_unlock(&ctx->event_wqh.lock);
2017-02-23 07:42:27 +08:00
}
return ret;
}
static ssize_t userfaultfd_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
struct userfaultfd_ctx *ctx = file->private_data;
ssize_t _ret, ret = 0;
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
struct uffd_msg msg;
int no_wait = file->f_flags & O_NONBLOCK;
if (ctx->state == UFFD_STATE_WAIT_API)
return -EINVAL;
for (;;) {
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
if (count < sizeof(msg))
return ret ? ret : -EINVAL;
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
_ret = userfaultfd_ctx_read(ctx, no_wait, &msg);
if (_ret < 0)
return ret ? ret : _ret;
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg)))
return ret ? ret : -EFAULT;
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
ret += sizeof(msg);
buf += sizeof(msg);
count -= sizeof(msg);
/*
* Allow to read more than one fault at time but only
* block if waiting for the very first one.
*/
no_wait = O_NONBLOCK;
}
}
static void __wake_userfault(struct userfaultfd_ctx *ctx,
struct userfaultfd_wake_range *range)
{
spin_lock(&ctx->fault_pending_wqh.lock);
/* wake all in the range and autoremove */
if (waitqueue_active(&ctx->fault_pending_wqh))
__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
range);
if (waitqueue_active(&ctx->fault_wqh))
__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range);
spin_unlock(&ctx->fault_pending_wqh.lock);
}
static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
struct userfaultfd_wake_range *range)
{
unsigned seq;
bool need_wakeup;
/*
* To be sure waitqueue_active() is not reordered by the CPU
* before the pagetable update, use an explicit SMP memory
* barrier here. PT lock release or up_read(mmap_sem) still
* have release semantics that can allow the
* waitqueue_active() to be reordered before the pte update.
*/
smp_mb();
/*
* Use waitqueue_active because it's very frequent to
* change the address space atomically even if there are no
* userfaults yet. So we take the spinlock only when we're
* sure we've userfaults to wake.
*/
do {
seq = read_seqcount_begin(&ctx->refile_seq);
need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
waitqueue_active(&ctx->fault_wqh);
cond_resched();
} while (read_seqcount_retry(&ctx->refile_seq, seq));
if (need_wakeup)
__wake_userfault(ctx, range);
}
static __always_inline int validate_range(struct mm_struct *mm,
__u64 start, __u64 len)
{
__u64 task_size = mm->task_size;
if (start & ~PAGE_MASK)
return -EINVAL;
if (len & ~PAGE_MASK)
return -EINVAL;
if (!len)
return -EINVAL;
if (start < mmap_min_addr)
return -EINVAL;
if (start >= task_size)
return -EINVAL;
if (len > task_size - start)
return -EINVAL;
return 0;
}
static inline bool vma_can_userfault(struct vm_area_struct *vma)
{
return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
vma_is_shmem(vma);
}
static int userfaultfd_register(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
struct mm_struct *mm = ctx->mm;
struct vm_area_struct *vma, *prev, *cur;
int ret;
struct uffdio_register uffdio_register;
struct uffdio_register __user *user_uffdio_register;
unsigned long vm_flags, new_flags;
bool found;
bool basic_ioctls;
unsigned long start, end, vma_end;
user_uffdio_register = (struct uffdio_register __user *) arg;
ret = -EFAULT;
if (copy_from_user(&uffdio_register, user_uffdio_register,
sizeof(uffdio_register)-sizeof(__u64)))
goto out;
ret = -EINVAL;
if (!uffdio_register.mode)
goto out;
if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING|
UFFDIO_REGISTER_MODE_WP))
goto out;
vm_flags = 0;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
vm_flags |= VM_UFFD_MISSING;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
vm_flags |= VM_UFFD_WP;
/*
* FIXME: remove the below error constraint by
* implementing the wprotect tracking mode.
*/
ret = -EINVAL;
goto out;
}
ret = validate_range(mm, uffdio_register.range.start,
uffdio_register.range.len);
if (ret)
goto out;
start = uffdio_register.range.start;
end = start + uffdio_register.range.len;
ret = -ENOMEM;
if (!mmget_not_zero(mm))
goto out;
down_write(&mm->mmap_sem);
vma = find_vma_prev(mm, start, &prev);
if (!vma)
goto out_unlock;
/* check that there's at least one vma in the range */
ret = -EINVAL;
if (vma->vm_start >= end)
goto out_unlock;
/*
* If the first vma contains huge pages, make sure start address
* is aligned to huge page size.
*/
if (is_vm_hugetlb_page(vma)) {
unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
if (start & (vma_hpagesize - 1))
goto out_unlock;
}
/*
* Search for not compatible vmas.
*/
found = false;
basic_ioctls = false;
for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
cond_resched();
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
!!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
/* check not compatible vmas */
ret = -EINVAL;
if (!vma_can_userfault(cur))
goto out_unlock;
/*
* If this vma contains ending address, and huge pages
* check alignment.
*/
if (is_vm_hugetlb_page(cur) && end <= cur->vm_end &&
end > cur->vm_start) {
unsigned long vma_hpagesize = vma_kernel_pagesize(cur);
ret = -EINVAL;
if (end & (vma_hpagesize - 1))
goto out_unlock;
}
/*
* Check that this vma isn't already owned by a
* different userfaultfd. We can't allow more than one
* userfaultfd to own a single vma simultaneously or we
* wouldn't know which one to deliver the userfaults to.
*/
ret = -EBUSY;
if (cur->vm_userfaultfd_ctx.ctx &&
cur->vm_userfaultfd_ctx.ctx != ctx)
goto out_unlock;
/*
* Note vmas containing huge pages
*/
if (is_vm_hugetlb_page(cur))
basic_ioctls = true;
found = true;
}
BUG_ON(!found);
if (vma->vm_start < start)
prev = vma;
ret = 0;
do {
cond_resched();
BUG_ON(!vma_can_userfault(vma));
BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
vma->vm_userfaultfd_ctx.ctx != ctx);
/*
* Nothing to do: this vma is already registered into this
* userfaultfd and with the right tracking mode too.
*/
if (vma->vm_userfaultfd_ctx.ctx == ctx &&
(vma->vm_flags & vm_flags) == vm_flags)
goto skip;
if (vma->vm_start > start)
start = vma->vm_start;
vma_end = min(end, vma->vm_end);
new_flags = (vma->vm_flags & ~vm_flags) | vm_flags;
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
((struct vm_userfaultfd_ctx){ ctx }));
if (prev) {
vma = prev;
goto next;
}
if (vma->vm_start < start) {
ret = split_vma(mm, vma, start, 1);
if (ret)
break;
}
if (vma->vm_end > end) {
ret = split_vma(mm, vma, end, 0);
if (ret)
break;
}
next:
/*
* In the vma_merge() successful mprotect-like case 8:
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx.ctx = ctx;
skip:
prev = vma;
start = vma->vm_end;
vma = vma->vm_next;
} while (vma && vma->vm_start < end);
out_unlock:
up_write(&mm->mmap_sem);
mmput(mm);
if (!ret) {
/*
* Now that we scanned all vmas we can already tell
* userland which ioctls methods are guaranteed to
* succeed on this range.
*/
if (put_user(basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
UFFD_API_RANGE_IOCTLS,
&user_uffdio_register->ioctls))
ret = -EFAULT;
}
out:
return ret;
}
static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
struct mm_struct *mm = ctx->mm;
struct vm_area_struct *vma, *prev, *cur;
int ret;
struct uffdio_range uffdio_unregister;
unsigned long new_flags;
bool found;
unsigned long start, end, vma_end;
const void __user *buf = (void __user *)arg;
ret = -EFAULT;
if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
goto out;
ret = validate_range(mm, uffdio_unregister.start,
uffdio_unregister.len);
if (ret)
goto out;
start = uffdio_unregister.start;
end = start + uffdio_unregister.len;
ret = -ENOMEM;
if (!mmget_not_zero(mm))
goto out;
down_write(&mm->mmap_sem);
vma = find_vma_prev(mm, start, &prev);
if (!vma)
goto out_unlock;
/* check that there's at least one vma in the range */
ret = -EINVAL;
if (vma->vm_start >= end)
goto out_unlock;
/*
* If the first vma contains huge pages, make sure start address
* is aligned to huge page size.
*/
if (is_vm_hugetlb_page(vma)) {
unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
if (start & (vma_hpagesize - 1))
goto out_unlock;
}
/*
* Search for not compatible vmas.
*/
found = false;
ret = -EINVAL;
for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
cond_resched();
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
!!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
/*
* Check not compatible vmas, not strictly required
* here as not compatible vmas cannot have an
* userfaultfd_ctx registered on them, but this
* provides for more strict behavior to notice
* unregistration errors.
*/
if (!vma_can_userfault(cur))
goto out_unlock;
found = true;
}
BUG_ON(!found);
if (vma->vm_start < start)
prev = vma;
ret = 0;
do {
cond_resched();
BUG_ON(!vma_can_userfault(vma));
/*
* Nothing to do: this vma is already registered into this
* userfaultfd and with the right tracking mode too.
*/
if (!vma->vm_userfaultfd_ctx.ctx)
goto skip;
if (vma->vm_start > start)
start = vma->vm_start;
vma_end = min(end, vma->vm_end);
if (userfaultfd_missing(vma)) {
/*
* Wake any concurrent pending userfault while
* we unregister, so they will not hang
* permanently and it avoids userland to call
* UFFDIO_WAKE explicitly.
*/
struct userfaultfd_wake_range range;
range.start = start;
range.len = vma_end - start;
wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
}
new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
NULL_VM_UFFD_CTX);
if (prev) {
vma = prev;
goto next;
}
if (vma->vm_start < start) {
ret = split_vma(mm, vma, start, 1);
if (ret)
break;
}
if (vma->vm_end > end) {
ret = split_vma(mm, vma, end, 0);
if (ret)
break;
}
next:
/*
* In the vma_merge() successful mprotect-like case 8:
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
skip:
prev = vma;
start = vma->vm_end;
vma = vma->vm_next;
} while (vma && vma->vm_start < end);
out_unlock:
up_write(&mm->mmap_sem);
mmput(mm);
out:
return ret;
}
/*
userfaultfd: wake pending userfaults This is an optimization but it's a userland visible one and it affects the API. The downside of this optimization is that if you call poll() and you get POLLIN, read(ufd) may still return -EAGAIN. The blocked userfault may be waken by a different thread, before read(ufd) comes around. This in short means that poll() isn't really usable if the userfaultfd is opened in blocking mode. userfaults won't wait in "pending" state to be read anymore and any UFFDIO_WAKE or similar operations that has the objective of waking userfaults after their resolution, will wake all blocked userfaults for the resolved range, including those that haven't been read() by userland yet. The behavior of poll() becomes not standard, but this obviates the need of "spurious" UFFDIO_WAKE and it lets the userland threads to restart immediately without requiring an UFFDIO_WAKE. This is even more significant in case of repeated faults on the same address from multiple threads. This optimization is justified by the measurement that the number of spurious UFFDIO_WAKE accounts for 5% and 10% of the total userfaults for heavy workloads, so it's worth optimizing those away. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:41 +08:00
* userfaultfd_wake may be used in combination with the
* UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches.
*/
static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
int ret;
struct uffdio_range uffdio_wake;
struct userfaultfd_wake_range range;
const void __user *buf = (void __user *)arg;
ret = -EFAULT;
if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
goto out;
ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
if (ret)
goto out;
range.start = uffdio_wake.start;
range.len = uffdio_wake.len;
/*
* len == 0 means wake all and we don't want to wake all here,
* so check it again to be sure.
*/
VM_BUG_ON(!range.len);
wake_userfault(ctx, &range);
ret = 0;
out:
return ret;
}
static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
__s64 ret;
struct uffdio_copy uffdio_copy;
struct uffdio_copy __user *user_uffdio_copy;
struct userfaultfd_wake_range range;
user_uffdio_copy = (struct uffdio_copy __user *) arg;
ret = -EFAULT;
if (copy_from_user(&uffdio_copy, user_uffdio_copy,
/* don't copy "copy" last field */
sizeof(uffdio_copy)-sizeof(__s64)))
goto out;
ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
if (ret)
goto out;
/*
* double check for wraparound just in case. copy_from_user()
* will later check uffdio_copy.src + uffdio_copy.len to fit
* in the userland range.
*/
ret = -EINVAL;
if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
goto out;
if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
goto out;
if (mmget_not_zero(ctx->mm)) {
ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
uffdio_copy.len);
mmput(ctx->mm);
} else {
return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
return -EFAULT;
if (ret < 0)
goto out;
BUG_ON(!ret);
/* len == 0 would wake all */
range.len = ret;
if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
range.start = uffdio_copy.dst;
wake_userfault(ctx, &range);
}
ret = range.len == uffdio_copy.len ? 0 : -EAGAIN;
out:
return ret;
}
static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
__s64 ret;
struct uffdio_zeropage uffdio_zeropage;
struct uffdio_zeropage __user *user_uffdio_zeropage;
struct userfaultfd_wake_range range;
user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
ret = -EFAULT;
if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
/* don't copy "zeropage" last field */
sizeof(uffdio_zeropage)-sizeof(__s64)))
goto out;
ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
uffdio_zeropage.range.len);
if (ret)
goto out;
ret = -EINVAL;
if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
goto out;
if (mmget_not_zero(ctx->mm)) {
ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
uffdio_zeropage.range.len);
mmput(ctx->mm);
} else {
return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
return -EFAULT;
if (ret < 0)
goto out;
/* len == 0 would wake all */
BUG_ON(!ret);
range.len = ret;
if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
range.start = uffdio_zeropage.range.start;
wake_userfault(ctx, &range);
}
ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN;
out:
return ret;
}
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
/*
* For the current set of features the bits just coincide
*/
return (unsigned int)user_features;
}
/*
* userland asks for a certain API version and we return which bits
* and ioctl commands are implemented in this kernel for such API
* version or -EINVAL if unknown.
*/
static int userfaultfd_api(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
struct uffdio_api uffdio_api;
void __user *buf = (void __user *)arg;
int ret;
__u64 features;
ret = -EINVAL;
if (ctx->state != UFFD_STATE_WAIT_API)
goto out;
ret = -EFAULT;
userfaultfd: change the read API to return a uffd_msg I had requests to return the full address (not the page aligned one) to userland. It's not entirely clear how the page offset could be relevant because userfaults aren't like SIGBUS that can sigjump to a different place and it actually skip resolving the fault depending on a page offset. There's currently no real way to skip the fault especially because after a UFFDIO_COPY|ZEROPAGE, the fault is optimized to be retried within the kernel without having to return to userland first (not even self modifying code replacing the .text that touched the faulting address would prevent the fault to be repeated). Userland cannot skip repeating the fault even more so if the fault was triggered by a KVM secondary page fault or any get_user_pages or any copy-user inside some syscall which will return to kernel code. The second time FAULT_FLAG_RETRY_NOWAIT won't be set leading to a SIGBUS being raised because the userfault can't wait if it cannot release the mmap_map first (and FAULT_FLAG_RETRY_NOWAIT is required for that). Still returning userland a proper structure during the read() on the uffd, can allow to use the current UFFD_API for the future non-cooperative extensions too and it looks cleaner as well. Once we get additional fields there's no point to return the fault address page aligned anymore to reuse the bits below PAGE_SHIFT. The only downside is that the read() syscall will read 32bytes instead of 8bytes but that's not going to be measurable overhead. The total number of new events that can be extended or of new future bits for already shipped events, is limited to 64 by the features field of the uffdio_api structure. If more will be needed a bump of UFFD_API will be required. [akpm@linux-foundation.org: use __packed] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com> Cc: zhang.zhanghailiang@huawei.com Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Feiner <pfeiner@google.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:46:37 +08:00
if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
goto out;
features = uffdio_api.features;
if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) {
memset(&uffdio_api, 0, sizeof(uffdio_api));
if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
goto out;
ret = -EINVAL;
goto out;
}
/* report all available features and ioctls to userland */
uffdio_api.features = UFFD_API_FEATURES;
uffdio_api.ioctls = UFFD_API_IOCTLS;
ret = -EFAULT;
if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
goto out;
ctx->state = UFFD_STATE_RUNNING;
/* only enable the requested features for this uffd context */
ctx->features = uffd_ctx_features(features);
ret = 0;
out:
return ret;
}
static long userfaultfd_ioctl(struct file *file, unsigned cmd,
unsigned long arg)
{
int ret = -EINVAL;
struct userfaultfd_ctx *ctx = file->private_data;
if (cmd != UFFDIO_API && ctx->state == UFFD_STATE_WAIT_API)
return -EINVAL;
switch(cmd) {
case UFFDIO_API:
ret = userfaultfd_api(ctx, arg);
break;
case UFFDIO_REGISTER:
ret = userfaultfd_register(ctx, arg);
break;
case UFFDIO_UNREGISTER:
ret = userfaultfd_unregister(ctx, arg);
break;
case UFFDIO_WAKE:
ret = userfaultfd_wake(ctx, arg);
break;
case UFFDIO_COPY:
ret = userfaultfd_copy(ctx, arg);
break;
case UFFDIO_ZEROPAGE:
ret = userfaultfd_zeropage(ctx, arg);
break;
}
return ret;
}
#ifdef CONFIG_PROC_FS
static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
{
struct userfaultfd_ctx *ctx = f->private_data;
wait_queue_entry_t *wq;
struct userfaultfd_wait_queue *uwq;
unsigned long pending = 0, total = 0;
spin_lock(&ctx->fault_pending_wqh.lock);
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) {
uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
pending++;
total++;
}
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 18:06:46 +08:00
list_for_each_entry(wq, &ctx->fault_wqh.head, entry) {
uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
total++;
}
spin_unlock(&ctx->fault_pending_wqh.lock);
/*
* If more protocols will be added, there will be all shown
* separated by a space. Like this:
* protocols: aa:... bb:...
*/
seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
pending, total, UFFD_API, ctx->features,
UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
}
#endif
static const struct file_operations userfaultfd_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = userfaultfd_show_fdinfo,
#endif
.release = userfaultfd_release,
.poll = userfaultfd_poll,
.read = userfaultfd_read,
.unlocked_ioctl = userfaultfd_ioctl,
.compat_ioctl = userfaultfd_ioctl,
.llseek = noop_llseek,
};
static void init_once_userfaultfd_ctx(void *mem)
{
struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem;
init_waitqueue_head(&ctx->fault_pending_wqh);
init_waitqueue_head(&ctx->fault_wqh);
init_waitqueue_head(&ctx->event_wqh);
init_waitqueue_head(&ctx->fd_wqh);
seqcount_init(&ctx->refile_seq);
}
/**
* userfaultfd_file_create - Creates a userfaultfd file pointer.
* @flags: Flags for the userfaultfd file.
*
* This function creates a userfaultfd file pointer, w/out installing
* it into the fd table. This is useful when the userfaultfd file is
* used during the initialization of data structures that require
* extra setup after the userfaultfd creation. So the userfaultfd
* creation is split into the file pointer creation phase, and the
* file descriptor installation phase. In this way races with
* userspace closing the newly installed file descriptor can be
* avoided. Returns a userfaultfd file pointer, or a proper error
* pointer.
*/
static struct file *userfaultfd_file_create(int flags)
{
struct file *file;
struct userfaultfd_ctx *ctx;
BUG_ON(!current->mm);
/* Check the UFFD_* constants for consistency. */
BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
file = ERR_PTR(-EINVAL);
if (flags & ~UFFD_SHARED_FCNTL_FLAGS)
goto out;
file = ERR_PTR(-ENOMEM);
ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
if (!ctx)
goto out;
atomic_set(&ctx->refcount, 1);
ctx->flags = flags;
ctx->features = 0;
ctx->state = UFFD_STATE_WAIT_API;
ctx->released = false;
ctx->mm = current->mm;
/* prevent the mm struct to be freed */
mmgrab(ctx->mm);
file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
if (IS_ERR(file)) {
mmdrop(ctx->mm);
kmem_cache_free(userfaultfd_ctx_cachep, ctx);
}
out:
return file;
}
SYSCALL_DEFINE1(userfaultfd, int, flags)
{
int fd, error;
struct file *file;
error = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS);
if (error < 0)
return error;
fd = error;
file = userfaultfd_file_create(flags);
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto err_put_unused_fd;
}
fd_install(fd, file);
return fd;
err_put_unused_fd:
put_unused_fd(fd);
return error;
}
static int __init userfaultfd_init(void)
{
userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
sizeof(struct userfaultfd_ctx),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
init_once_userfaultfd_ctx);
return 0;
}
__initcall(userfaultfd_init);