diff options
author | Andrea Arcangeli <aarcange@redhat.com> | 2015-09-04 15:46:37 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-09-04 16:54:41 -0700 |
commit | a9b85f9415fd9e529d03299e5335433f614ec1fb (patch) | |
tree | a4ba811f5c13dd5db253da3a6296771203b59c78 /include/uapi/linux | |
parent | 3f602d2724b1f7d2d27ddcd7963a040a5890fd16 (diff) | |
download | linux-stable-a9b85f9415fd9e529d03299e5335433f614ec1fb.tar.gz linux-stable-a9b85f9415fd9e529d03299e5335433f614ec1fb.tar.bz2 linux-stable-a9b85f9415fd9e529d03299e5335433f614ec1fb.zip |
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>
Diffstat (limited to 'include/uapi/linux')
-rw-r--r-- | include/uapi/linux/userfaultfd.h | 70 |
1 files changed, 55 insertions, 15 deletions
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 330206016249..a5f8825381ef 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -11,9 +11,15 @@ #include <linux/types.h> +#include <linux/compiler.h> + #define UFFD_API ((__u64)0xAA) -/* FIXME: add "|UFFD_FEATURE_WP" to UFFD_API_FEATURES after implementing it */ -#define UFFD_API_FEATURES (UFFD_FEATURE_WRITE_BIT) +/* + * 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 | \ @@ -45,26 +51,60 @@ #define UFFDIO_WAKE _IOR(UFFDIO, _UFFDIO_WAKE, \ struct uffdio_range) -/* - * Valid bits below PAGE_SHIFT in the userfault address read through - * the read() syscall. - */ -#define UFFD_BIT_WRITE (1<<0) /* this was a write fault, MISSING or WP */ -#define UFFD_BIT_WP (1<<1) /* handle_userfault() reason VM_UFFD_WP */ -#define UFFD_BITS 2 /* two above bits used for UFFD_BIT_* mask */ +/* 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; /* - * Features reported in uffdio_api.features field + * Start at 0x12 and not at 0 to be more strict against bugs. */ -#define UFFD_FEATURE_WRITE_BIT (1<<0) /* Corresponds to UFFD_BIT_WRITE */ -#define UFFD_FEATURE_WP_BIT (1<<1) /* Corresponds to UFFD_BIT_WP */ +#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 { - /* userland asks for an API number */ + /* userland asks for an API number and the features to enable */ __u64 api; - - /* kernel answers below with the available features for the API */ + /* + * 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; + __u64 ioctls; }; |