On Sun, Mar 17, 2019 at 7:36 PM <ira.weiny@xxxxxxxxx> wrote:
>
> From: Ira Weiny <ira.weiny@xxxxxxxxx>
>
> Rather than have a separate get_user_pages_longterm() call,
> introduce FOLL_LONGTERM and change the longterm callers to use
> it.
>
> This patch does not change any functionality.
>
> FOLL_LONGTERM can only be supported with get_user_pages() as it
> requires vmas to determine if DAX is in use.
>
> CC: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
> CC: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> CC: Michal Hocko <mhocko@xxxxxxxxxx>
> Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx>
[..]
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 2d483dbdffc0..6831077d126c 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
[..]
> @@ -2609,6 +2596,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
> #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
> #define FOLL_COW 0x4000 /* internal GUP flag */
> #define FOLL_ANON 0x8000 /* don't do file mappings */
> +#define FOLL_LONGTERM 0x10000 /* mapping is intended for a long term pin */
Let's change this comment to say something like /* mapping lifetime is
indefinite / at the discretion of userspace */, since "longterm is not
well defined.
I think it should also include a /* FIXME: */ to say something about
the havoc a long term pin might wreak on fs and mm code paths.
> static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
> {
> diff --git a/mm/gup.c b/mm/gup.c
> index f84e22685aaa..8cb4cff067bc 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -1112,26 +1112,7 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
> }
> EXPORT_SYMBOL(get_user_pages_remote);
>
> -/*
> - * This is the same as get_user_pages_remote(), just with a
> - * less-flexible calling convention where we assume that the task
> - * and mm being operated on are the current task's and don't allow
> - * passing of a locked parameter. We also obviously don't pass
> - * FOLL_REMOTE in here.
> - */
> -long get_user_pages(unsigned long start, unsigned long nr_pages,
> - unsigned int gup_flags, struct page **pages,
> - struct vm_area_struct **vmas)
> -{
> - return __get_user_pages_locked(current, current->mm, start, nr_pages,
> - pages, vmas, NULL,
> - gup_flags | FOLL_TOUCH);
> -}
> -EXPORT_SYMBOL(get_user_pages);
> -
> #if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
> -
> -#ifdef CONFIG_FS_DAX
> static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
> {
> long i;
> @@ -1150,12 +1131,6 @@ static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
> }
> return false;
> }
> -#else
> -static inline bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
> -{
> - return false;
> -}
> -#endif
>
> #ifdef CONFIG_CMA
> static struct page *new_non_cma_page(struct page *page, unsigned long private)
> @@ -1209,10 +1184,13 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
> return __alloc_pages_node(nid, gfp_mask, 0);
> }
>
> -static long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
> - unsigned int gup_flags,
> +static long check_and_migrate_cma_pages(struct task_struct *tsk,
> + struct mm_struct *mm,
> + unsigned long start,
> + unsigned long nr_pages,
> struct page **pages,
> - struct vm_area_struct **vmas)
> + struct vm_area_struct **vmas,
> + unsigned int gup_flags)
> {
> long i;
> bool drain_allow = true;
> @@ -1268,10 +1246,14 @@ static long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
> putback_movable_pages(&cma_page_list);
> }
> /*
> - * We did migrate all the pages, Try to get the page references again
> - * migrating any new CMA pages which we failed to isolate earlier.
> + * We did migrate all the pages, Try to get the page references
> + * again migrating any new CMA pages which we failed to isolate
> + * earlier.
> */
> - nr_pages = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
> + nr_pages = __get_user_pages_locked(tsk, mm, start, nr_pages,
> + pages, vmas, NULL,
> + gup_flags);
> +
Why did this need to change to __get_user_pages_locked?
> if ((nr_pages > 0) && migrate_allow) {
> drain_allow = true;
> goto check_again;
> @@ -1281,66 +1263,115 @@ static long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
> return nr_pages;
> }
> #else
> -static inline long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
> - unsigned int gup_flags,
> - struct page **pages,
> - struct vm_area_struct **vmas)
> +static long check_and_migrate_cma_pages(struct task_struct *tsk,
> + struct mm_struct *mm,
> + unsigned long start,
> + unsigned long nr_pages,
> + struct page **pages,
> + struct vm_area_struct **vmas,
> + unsigned int gup_flags)
> {
> return nr_pages;
> }
> #endif
>
> /*
> - * This is the same as get_user_pages() in that it assumes we are
> - * operating on the current task's mm, but it goes further to validate
> - * that the vmas associated with the address range are suitable for
> - * longterm elevated page reference counts. For example, filesystem-dax
> - * mappings are subject to the lifetime enforced by the filesystem and
> - * we need guarantees that longterm users like RDMA and V4L2 only
> - * establish mappings that have a kernel enforced revocation mechanism.
> + * __gup_longterm_locked() is a wrapper for __get_uer_pages_locked which
s/uer/user/
> + * allows us to process the FOLL_LONGTERM flag if present.
> + *
> + * FOLL_LONGTERM Checks for either DAX VMAs or PPC CMA regions and either fails
> + * the pin or attempts to migrate the page as appropriate.
> + *
> + * In the filesystem-dax case mappings are subject to the lifetime enforced by
> + * the filesystem and we need guarantees that longterm users like RDMA and V4L2
> + * only establish mappings that have a kernel enforced revocation mechanism.
> + *
> + * In the CMA case pages can't be pinned in a CMA region as this would
> + * unnecessarily fragment that region. So CMA attempts to migrate the page
> + * before pinning.
> *
> * "longterm" == userspace controlled elevated page count lifetime.
> * Contrast this to iov_iter_get_pages() usages which are transient.
Ah, here's the longterm documentation, but if I was a developer
considering whether to use FOLL_LONGTERM or not I would expect to find
the documentation at the flag definition site.
I think it has become more clear since get_user_pages_longterm() was
initially merged that we need to warn people not to use it, or at
least seriously reconsider whether they want an interface to support
indefinite pins.
> */
> -long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
> - unsigned int gup_flags, struct page **pages,
> - struct vm_area_struct **vmas_arg)
> +static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
...why the __always_inline?
