From: Mike Rapoport <rppt@linux.ibm.com>
To: Peter Xu <peterx@redhat.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
David Hildenbrand <david@redhat.com>,
Hugh Dickins <hughd@google.com>, Maya Gokhale <gokhale2@llnl.gov>,
Jerome Glisse <jglisse@redhat.com>,
Pavel Emelyanov <xemul@virtuozzo.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Martin Cracauer <cracauer@cons.org>, Shaohua Li <shli@fb.com>,
Marty McFadden <mcfadden8@llnl.gov>,
Andrea Arcangeli <aarcange@redhat.com>,
Mike Kravetz <mike.kravetz@oracle.com>,
Denis Plotnikov <dplotnikov@virtuozzo.com>,
Mike Rapoport <rppt@linux.vnet.ibm.com>,
Mel Gorman <mgorman@suse.de>,
"Kirill A . Shutemov" <kirill@shutemov.name>,
"Dr . David Alan Gilbert" <dgilbert@redhat.com>
Subject: Re: [PATCH v2 08/26] userfaultfd: wp: add WP pagetable tracking to x86
Date: Mon, 25 Feb 2019 17:48:41 +0200 [thread overview]
Message-ID: <20190225154841.GC24917@rapoport-lnx> (raw)
In-Reply-To: <20190212025632.28946-9-peterx@redhat.com>
On Tue, Feb 12, 2019 at 10:56:14AM +0800, Peter Xu wrote:
> From: Andrea Arcangeli <aarcange@redhat.com>
>
> Accurate userfaultfd WP tracking is possible by tracking exactly which
> virtual memory ranges were writeprotected by userland. We can't relay
> only on the RW bit of the mapped pagetable because that information is
> destroyed by fork() or KSM or swap. If we were to relay on that, we'd
> need to stay on the safe side and generate false positive wp faults
> for every swapped out page.
>
> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
> Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
> ---
> arch/x86/Kconfig | 1 +
> arch/x86/include/asm/pgtable.h | 52 ++++++++++++++++++++++++++++
> arch/x86/include/asm/pgtable_64.h | 8 ++++-
> arch/x86/include/asm/pgtable_types.h | 9 +++++
> include/asm-generic/pgtable.h | 1 +
> include/asm-generic/pgtable_uffd.h | 51 +++++++++++++++++++++++++++
> init/Kconfig | 5 +++
> 7 files changed, 126 insertions(+), 1 deletion(-)
> create mode 100644 include/asm-generic/pgtable_uffd.h
>
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index 68261430fe6e..cb43bc008675 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -209,6 +209,7 @@ config X86
> select USER_STACKTRACE_SUPPORT
> select VIRT_TO_BUS
> select X86_FEATURE_NAMES if PROC_FS
> + select HAVE_ARCH_USERFAULTFD_WP if USERFAULTFD
>
> config INSTRUCTION_DECODER
> def_bool y
> diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
> index 2779ace16d23..6863236e8484 100644
> --- a/arch/x86/include/asm/pgtable.h
> +++ b/arch/x86/include/asm/pgtable.h
> @@ -23,6 +23,7 @@
>
> #ifndef __ASSEMBLY__
> #include <asm/x86_init.h>
> +#include <asm-generic/pgtable_uffd.h>
>
> extern pgd_t early_top_pgt[PTRS_PER_PGD];
> int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
> @@ -293,6 +294,23 @@ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
> return native_make_pte(v & ~clear);
> }
>
> +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
> +static inline int pte_uffd_wp(pte_t pte)
> +{
> + return pte_flags(pte) & _PAGE_UFFD_WP;
> +}
> +
> +static inline pte_t pte_mkuffd_wp(pte_t pte)
> +{
> + return pte_set_flags(pte, _PAGE_UFFD_WP);
> +}
> +
> +static inline pte_t pte_clear_uffd_wp(pte_t pte)
> +{
> + return pte_clear_flags(pte, _PAGE_UFFD_WP);
> +}
> +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
> +
> static inline pte_t pte_mkclean(pte_t pte)
> {
> return pte_clear_flags(pte, _PAGE_DIRTY);
> @@ -372,6 +390,23 @@ static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
> return native_make_pmd(v & ~clear);
> }
>
> +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
> +static inline int pmd_uffd_wp(pmd_t pmd)
> +{
> + return pmd_flags(pmd) & _PAGE_UFFD_WP;
> +}
> +
> +static inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
> +{
> + return pmd_set_flags(pmd, _PAGE_UFFD_WP);
> +}
> +
> +static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
> +{
> + return pmd_clear_flags(pmd, _PAGE_UFFD_WP);
> +}
> +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
> +
> static inline pmd_t pmd_mkold(pmd_t pmd)
> {
> return pmd_clear_flags(pmd, _PAGE_ACCESSED);
> @@ -1351,6 +1386,23 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
> #endif
> #endif
>
> +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
> +static inline pte_t pte_swp_mkuffd_wp(pte_t pte)
> +{
> + return pte_set_flags(pte, _PAGE_SWP_UFFD_WP);
> +}
> +
> +static inline int pte_swp_uffd_wp(pte_t pte)
> +{
> + return pte_flags(pte) & _PAGE_SWP_UFFD_WP;
> +}
> +
> +static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
> +{
> + return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP);
> +}
> +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
> +
> #define PKRU_AD_BIT 0x1
> #define PKRU_WD_BIT 0x2
> #define PKRU_BITS_PER_PKEY 2
> diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
> index 9c85b54bf03c..e0c5d29b8685 100644
> --- a/arch/x86/include/asm/pgtable_64.h
> +++ b/arch/x86/include/asm/pgtable_64.h
> @@ -189,7 +189,7 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
> *
> * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number
> * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
> - * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|X|SD|0| <- swp entry
> + * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|F|SD|0| <- swp entry
> *
> * G (8) is aliased and used as a PROT_NONE indicator for
> * !present ptes. We need to start storing swap entries above
> @@ -197,9 +197,15 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
> * erratum where they can be incorrectly set by hardware on
> * non-present PTEs.
> *
> + * SD Bits 1-4 are not used in non-present format and available for
> + * special use described below:
> + *
> * SD (1) in swp entry is used to store soft dirty bit, which helps us
> * remember soft dirty over page migration
> *
> + * F (2) in swp entry is used to record when a pagetable is
> + * writeprotected by userfaultfd WP support.
> + *
> * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
> * but also L and G.
> *
> diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
> index d6ff0bbdb394..8cebcff91e57 100644
> --- a/arch/x86/include/asm/pgtable_types.h
> +++ b/arch/x86/include/asm/pgtable_types.h
> @@ -32,6 +32,7 @@
>
> #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1
> #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1
> +#define _PAGE_BIT_UFFD_WP _PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
> #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */
> #define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4
>
> @@ -100,6 +101,14 @@
> #define _PAGE_SWP_SOFT_DIRTY (_AT(pteval_t, 0))
> #endif
>
> +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
> +#define _PAGE_UFFD_WP (_AT(pteval_t, 1) << _PAGE_BIT_UFFD_WP)
> +#define _PAGE_SWP_UFFD_WP _PAGE_USER
> +#else
> +#define _PAGE_UFFD_WP (_AT(pteval_t, 0))
> +#define _PAGE_SWP_UFFD_WP (_AT(pteval_t, 0))
> +#endif
> +
> #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
> #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX)
> #define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP)
> diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
> index 05e61e6c843f..f49afe951711 100644
> --- a/include/asm-generic/pgtable.h
> +++ b/include/asm-generic/pgtable.h
> @@ -10,6 +10,7 @@
> #include <linux/mm_types.h>
> #include <linux/bug.h>
> #include <linux/errno.h>
> +#include <asm-generic/pgtable_uffd.h>
>
> #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
> defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
> diff --git a/include/asm-generic/pgtable_uffd.h b/include/asm-generic/pgtable_uffd.h
> new file mode 100644
> index 000000000000..643d1bf559c2
> --- /dev/null
> +++ b/include/asm-generic/pgtable_uffd.h
> @@ -0,0 +1,51 @@
> +#ifndef _ASM_GENERIC_PGTABLE_UFFD_H
> +#define _ASM_GENERIC_PGTABLE_UFFD_H
> +
> +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
> +static __always_inline int pte_uffd_wp(pte_t pte)
> +{
> + return 0;
> +}
> +
> +static __always_inline int pmd_uffd_wp(pmd_t pmd)
> +{
> + return 0;
> +}
> +
> +static __always_inline pte_t pte_mkuffd_wp(pte_t pte)
> +{
> + return pte;
> +}
> +
> +static __always_inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
> +{
> + return pmd;
> +}
> +
> +static __always_inline pte_t pte_clear_uffd_wp(pte_t pte)
> +{
> + return pte;
> +}
> +
> +static __always_inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
> +{
> + return pmd;
> +}
> +
> +static __always_inline pte_t pte_swp_mkuffd_wp(pte_t pte)
> +{
> + return pte;
> +}
> +
> +static __always_inline int pte_swp_uffd_wp(pte_t pte)
> +{
> + return 0;
> +}
> +
> +static __always_inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
> +{
> + return pte;
> +}
> +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
> +
> +#endif /* _ASM_GENERIC_PGTABLE_UFFD_H */
> diff --git a/init/Kconfig b/init/Kconfig
> index c9386a365eea..892d61ddf2eb 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1424,6 +1424,11 @@ config ADVISE_SYSCALLS
> applications use these syscalls, you can disable this option to save
> space.
>
> +config HAVE_ARCH_USERFAULTFD_WP
> + bool
> + help
> + Arch has userfaultfd write protection support
> +
> config MEMBARRIER
> bool "Enable membarrier() system call" if EXPERT
> default y
> --
> 2.17.1
>
--
Sincerely yours,
Mike.
next prev parent reply other threads:[~2019-02-25 15:48 UTC|newest]
Thread overview: 113+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-12 2:56 [PATCH v2 00/26] userfaultfd: write protection support Peter Xu
2019-02-12 2:56 ` [PATCH v2 01/26] mm: gup: rename "nonblocking" to "locked" where proper Peter Xu
2019-02-21 15:17 ` Jerome Glisse
2019-02-22 3:42 ` Peter Xu
2019-02-12 2:56 ` [PATCH v2 02/26] mm: userfault: return VM_FAULT_RETRY on signals Peter Xu
2019-02-21 15:29 ` Jerome Glisse
2019-02-22 3:51 ` Peter Xu
2019-02-12 2:56 ` [PATCH v2 03/26] userfaultfd: don't retake mmap_sem to emulate NOPAGE Peter Xu
2019-02-21 15:34 ` Jerome Glisse
2019-02-12 2:56 ` [PATCH v2 04/26] mm: allow VM_FAULT_RETRY for multiple times Peter Xu
2019-02-13 3:34 ` Peter Xu
2019-02-20 11:48 ` Peter Xu
2019-02-21 8:56 ` [PATCH v2.1 " Peter Xu
2019-02-21 15:53 ` Jerome Glisse
2019-02-22 4:25 ` Peter Xu
2019-02-22 15:11 ` Jerome Glisse
2019-02-25 6:19 ` Peter Xu
2019-02-12 2:56 ` [PATCH v2 05/26] mm: gup: " Peter Xu
2019-02-21 16:06 ` Jerome Glisse
2019-02-22 4:41 ` Peter Xu
2019-02-22 15:13 ` Jerome Glisse
2019-02-12 2:56 ` [PATCH v2 06/26] userfaultfd: wp: add helper for writeprotect check Peter Xu
2019-02-21 16:07 ` Jerome Glisse
2019-02-25 15:41 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 07/26] userfaultfd: wp: hook userfault handler to write protection fault Peter Xu
2019-02-21 16:25 ` Jerome Glisse
2019-02-25 15:43 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 08/26] userfaultfd: wp: add WP pagetable tracking to x86 Peter Xu
2019-02-21 17:20 ` Jerome Glisse
2019-02-25 15:48 ` Mike Rapoport [this message]
2019-02-12 2:56 ` [PATCH v2 09/26] userfaultfd: wp: userfaultfd_pte/huge_pmd_wp() helpers Peter Xu
2019-02-21 17:21 ` Jerome Glisse
2019-02-25 17:12 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 10/26] userfaultfd: wp: add UFFDIO_COPY_MODE_WP Peter Xu
2019-02-21 17:29 ` Jerome Glisse
2019-02-22 7:11 ` Peter Xu
2019-02-22 15:15 ` Jerome Glisse
2019-02-25 6:45 ` Peter Xu
2019-02-25 15:58 ` Mike Rapoport
2019-02-26 5:09 ` Peter Xu
2019-02-26 8:28 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 11/26] mm: merge parameters for change_protection() Peter Xu
2019-02-21 17:32 ` Jerome Glisse
2019-02-12 2:56 ` [PATCH v2 12/26] userfaultfd: wp: apply _PAGE_UFFD_WP bit Peter Xu
2019-02-21 17:44 ` Jerome Glisse
2019-02-22 7:31 ` Peter Xu
2019-02-22 15:17 ` Jerome Glisse
2019-02-25 18:00 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 13/26] mm: export wp_page_copy() Peter Xu
2019-02-21 17:44 ` Jerome Glisse
2019-02-12 2:56 ` [PATCH v2 14/26] userfaultfd: wp: handle COW properly for uffd-wp Peter Xu
2019-02-21 18:04 ` Jerome Glisse
2019-02-22 8:46 ` Peter Xu
2019-02-22 15:35 ` Jerome Glisse
2019-02-25 7:13 ` Peter Xu
2019-02-25 15:32 ` Jerome Glisse
2019-02-12 2:56 ` [PATCH v2 15/26] userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork Peter Xu
2019-02-21 18:06 ` Jerome Glisse
2019-02-22 9:09 ` Peter Xu
2019-02-22 15:36 ` Jerome Glisse
2019-02-25 18:19 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 16/26] userfaultfd: wp: add pmd_swp_*uffd_wp() helpers Peter Xu
2019-02-21 18:07 ` Jerome Glisse
2019-02-25 18:20 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 17/26] userfaultfd: wp: support swap and page migration Peter Xu
2019-02-21 18:16 ` Jerome Glisse
2019-02-25 7:48 ` Peter Xu
2019-02-25 18:28 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 18/26] khugepaged: skip collapse if uffd-wp detected Peter Xu
2019-02-21 18:17 ` Jerome Glisse
2019-02-25 18:50 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 19/26] userfaultfd: introduce helper vma_find_uffd Peter Xu
2019-02-21 18:19 ` Jerome Glisse
2019-02-25 20:48 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 20/26] userfaultfd: wp: support write protection for userfault vma range Peter Xu
2019-02-21 18:23 ` Jerome Glisse
2019-02-25 8:16 ` Peter Xu
2019-02-25 20:52 ` Mike Rapoport
2019-02-26 6:06 ` Peter Xu
2019-02-26 6:43 ` Mike Rapoport
2019-02-26 7:20 ` Peter Xu
2019-02-26 7:46 ` Mike Rapoport
2019-02-26 7:54 ` Peter Xu
2019-02-12 2:56 ` [PATCH v2 21/26] userfaultfd: wp: add the writeprotect API to userfaultfd ioctl Peter Xu
2019-02-21 18:28 ` Jerome Glisse
2019-02-25 8:31 ` Peter Xu
2019-02-25 21:03 ` Mike Rapoport
2019-02-26 6:30 ` Peter Xu
2019-02-12 2:56 ` [PATCH v2 22/26] userfaultfd: wp: enabled write protection in userfaultfd API Peter Xu
2019-02-21 18:29 ` Jerome Glisse
2019-02-25 8:34 ` Peter Xu
2019-02-12 2:56 ` [PATCH v2 23/26] userfaultfd: wp: don't wake up when doing write protect Peter Xu
2019-02-21 18:36 ` Jerome Glisse
2019-02-25 8:58 ` Peter Xu
2019-02-25 21:15 ` Mike Rapoport
2019-02-25 21:09 ` Mike Rapoport
2019-02-26 6:24 ` Peter Xu
2019-02-26 7:29 ` Mike Rapoport
2019-02-26 7:41 ` Peter Xu
2019-02-26 8:00 ` Mike Rapoport
2019-02-28 2:47 ` Peter Xu
2019-02-26 8:00 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 24/26] userfaultfd: wp: UFFDIO_REGISTER_MODE_WP documentation update Peter Xu
2019-02-21 18:38 ` Jerome Glisse
2019-02-25 21:19 ` Mike Rapoport
2019-02-26 6:53 ` Peter Xu
2019-02-26 7:04 ` Mike Rapoport
2019-02-26 7:42 ` Peter Xu
2019-02-12 2:56 ` [PATCH v2 25/26] userfaultfd: selftests: refactor statistics Peter Xu
2019-02-26 6:50 ` Mike Rapoport
2019-02-12 2:56 ` [PATCH v2 26/26] userfaultfd: selftests: add write-protect test Peter Xu
2019-02-26 6:58 ` Mike Rapoport
2019-02-26 7:52 ` Peter Xu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190225154841.GC24917@rapoport-lnx \
--to=rppt@linux.ibm.com \
--cc=aarcange@redhat.com \
--cc=cracauer@cons.org \
--cc=david@redhat.com \
--cc=dgilbert@redhat.com \
--cc=dplotnikov@virtuozzo.com \
--cc=gokhale2@llnl.gov \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jglisse@redhat.com \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mcfadden8@llnl.gov \
--cc=mgorman@suse.de \
--cc=mike.kravetz@oracle.com \
--cc=peterx@redhat.com \
--cc=rppt@linux.vnet.ibm.com \
--cc=shli@fb.com \
--cc=xemul@virtuozzo.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).