On Fri, May 24, 2019 at 01:50:45PM -0400, Daniel Jordan wrote:
[snip]
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 0e8834ac32b7..72c1034d2ec7 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1564,6 +1564,25 @@ long get_user_pages_unlocked(unsigned long start,
> unsigned long nr_pages,
> int get_user_pages_fast(unsigned long start, int nr_pages,
> unsigned int gup_flags, struct page **pages);
>
> +int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
> + struct task_struct *task, bool bypass_rlim);
> +
> +static inline int account_locked_vm(struct mm_struct *mm, unsigned long
> pages,
> + bool inc)
> +{
> + int ret;
> +
> + if (pages == 0 || !mm)
> + return 0;
> +
> + down_write(&mm->mmap_sem);
> + ret = __account_locked_vm(mm, pages, inc, current,
> + capable(CAP_IPC_LOCK));
> + up_write(&mm->mmap_sem);
> +
> + return ret;
> +}
> +
> /* Container for pinned pfns / pages */
> struct frame_vector {
> unsigned int nr_allocated; /* Number of frames we have space for */
> diff --git a/mm/util.c b/mm/util.c
> index e2e4f8c3fa12..bd3bdf16a084 100644
> --- a/mm/util.c
> +++ b/mm/util.c
> @@ -6,6 +6,7 @@
> #include <linux/err.h>
> #include <linux/sched.h>
> #include <linux/sched/mm.h>
> +#include <linux/sched/signal.h>
> #include <linux/sched/task_stack.h>
> #include <linux/security.h>
> #include <linux/swap.h>
> @@ -346,6 +347,51 @@ int __weak get_user_pages_fast(unsigned long start,
> }
> EXPORT_SYMBOL_GPL(get_user_pages_fast);
>
> +/**
> + * __account_locked_vm - account locked pages to an mm's locked_vm
> + * @mm: mm to account against, may be NULL
This kernel doc is wrong. You dereference mm straight away...
> + * @pages: number of pages to account
> + * @inc: %true if @pages should be considered positive, %false if not
> + * @task: task used to check RLIMIT_MEMLOCK
> + * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped
> + *
> + * Assumes @task and @mm are valid (i.e. at least one reference on each), and
> + * that mmap_sem is held as writer.
> + *
> + * Return:
> + * * 0 on success
> + * * 0 if @mm is NULL (can happen for example if the task is exiting)
> + * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
> + */
> +int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
> + struct task_struct *task, bool bypass_rlim)
> +{
> + unsigned long locked_vm, limit;
> + int ret = 0;
> +
> + locked_vm = mm->locked_vm;
here...
Perhaps the comment was meant to document account_locked_vm()? Or should the
parameter checks be moved here?
Ira
> + if (inc) {
> + if (!bypass_rlim) {
> + limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
> + if (locked_vm + pages > limit)
> + ret = -ENOMEM;
> + }
> + if (!ret)
> + mm->locked_vm = locked_vm + pages;
> + } else {
> + WARN_ON_ONCE(pages > locked_vm);
> + mm->locked_vm = locked_vm - pages;
> + }
> +
> + pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid,
> + (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT,
> + locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK),
> + ret ? " - exceeded" : "");
> +
> + return ret;
> +}
> +EXPORT_SYMBOL_GPL(__account_locked_vm);
>
> +
> unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
> unsigned long len, unsigned long prot,
> unsigned long flag, unsigned long pgoff)
>
> base-commit: a188339ca5a396acc588e5851ed7e19f66b0ebd9
> --
> 2.21.0
>
