OpenCloudOS-Kernel/include/uapi/linux/userfaultfd.h

168 lines
4.3 KiB
C
Raw Normal View History

/*
* include/linux/userfaultfd.h
*
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
* Copyright (C) 2015 Red Hat, Inc.
*
*/
#ifndef _LINUX_USERFAULTFD_H
#define _LINUX_USERFAULTFD_H
#include <linux/types.h>
#define UFFD_API ((__u64)0xAA)
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
/*
* After implementing the respective features it will become:
* #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \
* UFFD_FEATURE_EVENT_FORK)
*/
#define UFFD_API_FEATURES (0)
#define UFFD_API_IOCTLS \
((__u64)1 << _UFFDIO_REGISTER | \
(__u64)1 << _UFFDIO_UNREGISTER | \
(__u64)1 << _UFFDIO_API)
#define UFFD_API_RANGE_IOCTLS \
((__u64)1 << _UFFDIO_WAKE | \
(__u64)1 << _UFFDIO_COPY | \
(__u64)1 << _UFFDIO_ZEROPAGE)
/*
* Valid ioctl command number range with this API is from 0x00 to
* 0x3F. UFFDIO_API is the fixed number, everything else can be
* changed by implementing a different UFFD_API. If sticking to the
* same UFFD_API more ioctl can be added and userland will be aware of
* which ioctl the running kernel implements through the ioctl command
* bitmask written by the UFFDIO_API.
*/
#define _UFFDIO_REGISTER (0x00)
#define _UFFDIO_UNREGISTER (0x01)
#define _UFFDIO_WAKE (0x02)
#define _UFFDIO_COPY (0x03)
#define _UFFDIO_ZEROPAGE (0x04)
#define _UFFDIO_API (0x3F)
/* userfaultfd ioctl ids */
#define UFFDIO 0xAA
#define UFFDIO_API _IOWR(UFFDIO, _UFFDIO_API, \
struct uffdio_api)
#define UFFDIO_REGISTER _IOWR(UFFDIO, _UFFDIO_REGISTER, \
struct uffdio_register)
#define UFFDIO_UNREGISTER _IOR(UFFDIO, _UFFDIO_UNREGISTER, \
struct uffdio_range)
#define UFFDIO_WAKE _IOR(UFFDIO, _UFFDIO_WAKE, \
struct uffdio_range)
#define UFFDIO_COPY _IOWR(UFFDIO, _UFFDIO_COPY, \
struct uffdio_copy)
#define UFFDIO_ZEROPAGE _IOWR(UFFDIO, _UFFDIO_ZEROPAGE, \
struct uffdio_zeropage)
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
/* read() structure */
struct uffd_msg {
__u8 event;
__u8 reserved1;
__u16 reserved2;
__u32 reserved3;
union {
struct {
__u64 flags;
__u64 address;
} pagefault;
struct {
/* unused reserved fields */
__u64 reserved1;
__u64 reserved2;
__u64 reserved3;
} reserved;
} arg;
} __packed;
/*
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
* Start at 0x12 and not at 0 to be more strict against bugs.
*/
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
#define UFFD_EVENT_PAGEFAULT 0x12
#if 0 /* not available yet */
#define UFFD_EVENT_FORK 0x13
#endif
/* flags for UFFD_EVENT_PAGEFAULT */
#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */
#define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */
struct uffdio_api {
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
/* userland asks for an API number and the features to enable */
__u64 api;
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
/*
* Kernel answers below with the all available features for
* the API, this notifies userland of which events and/or
* which flags for each event are enabled in the current
* kernel.
*
* Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE
* are to be considered implicitly always enabled in all kernels as
* long as the uffdio_api.api requested matches UFFD_API.
*/
#if 0 /* not available yet */
#define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0)
#define UFFD_FEATURE_EVENT_FORK (1<<1)
#endif
__u64 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
__u64 ioctls;
};
struct uffdio_range {
__u64 start;
__u64 len;
};
struct uffdio_register {
struct uffdio_range range;
#define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0)
#define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1)
__u64 mode;
/*
* kernel answers which ioctl commands are available for the
* range, keep at the end as the last 8 bytes aren't read.
*/
__u64 ioctls;
};
struct uffdio_copy {
__u64 dst;
__u64 src;
__u64 len;
/*
* There will be a wrprotection flag later that allows to map
* pages wrprotected on the fly. And such a flag will be
* available if the wrprotection ioctl are implemented for the
* range according to the uffdio_register.ioctls.
*/
#define UFFDIO_COPY_MODE_DONTWAKE ((__u64)1<<0)
__u64 mode;
/*
* "copy" is written by the ioctl and must be at the end: the
* copy_from_user will not read the last 8 bytes.
*/
__s64 copy;
};
struct uffdio_zeropage {
struct uffdio_range range;
#define UFFDIO_ZEROPAGE_MODE_DONTWAKE ((__u64)1<<0)
__u64 mode;
/*
* "zeropage" is written by the ioctl and must be at the end:
* the copy_from_user will not read the last 8 bytes.
*/
__s64 zeropage;
};
#endif /* _LINUX_USERFAULTFD_H */