From 0726b01e70455f9900ab524117c7b520d197dc8c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Sat, 17 Oct 2020 16:14:50 -0700 Subject: [PATCH] mm/madvise: pass mm to do_madvise Patch series "introduce memory hinting API for external process", v9. Now, we have MADV_PAGEOUT and MADV_COLD as madvise hinting API. With that, application could give hints to kernel what memory range are preferred to be reclaimed. However, in some platform(e.g., Android), the information required to make the hinting decision is not known to the app. Instead, it is known to a centralized userspace daemon(e.g., ActivityManagerService), and that daemon must be able to initiate reclaim on its own without any app involvement. To solve the concern, this patch introduces new syscall - process_madvise(2). Bascially, it's same with madvise(2) syscall but it has some differences. 1. It needs pidfd of target process to provide the hint 2. It supports only MADV_{COLD|PAGEOUT|MERGEABLE|UNMEREABLE} at this moment. Other hints in madvise will be opened when there are explicit requests from community to prevent unexpected bugs we couldn't support. 3. Only privileged processes can do something for other process's address space. For more detail of the new API, please see "mm: introduce external memory hinting API" description in this patchset. This patch (of 3): In upcoming patches, do_madvise will be called from external process context so we shouldn't asssume "current" is always hinted process's task_struct. Furthermore, we must not access mm_struct via task->mm, but obtain it via access_mm() once (in the following patch) and only use that pointer [1], so pass it to do_madvise() as well. Note the vma->vm_mm pointers are safe, so we can use them further down the call stack. And let's pass current->mm as arguments of do_madvise so it shouldn't change existing behavior but prepare next patch to make review easy. [vbabka@suse.cz: changelog tweak] [minchan@kernel.org: use current->mm for io_uring] Link: http://lkml.kernel.org/r/20200423145215.72666-1-minchan@kernel.org [akpm@linux-foundation.org: fix it for upstream changes] [akpm@linux-foundation.org: whoops] [rdunlap@infradead.org: add missing includes] Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Reviewed-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Acked-by: David Rientjes Cc: Jens Axboe Cc: Jann Horn Cc: Tim Murray Cc: Daniel Colascione Cc: Sandeep Patil Cc: Sonny Rao Cc: Brian Geffon Cc: Michal Hocko Cc: Johannes Weiner Cc: Shakeel Butt Cc: John Dias Cc: Joel Fernandes Cc: Alexander Duyck Cc: SeongJae Park Cc: Christian Brauner Cc: Kirill Tkhai Cc: Oleksandr Natalenko Cc: SeongJae Park Cc: Christian Brauner Cc: Florian Weimer Cc: Link: https://lkml.kernel.org/r/20200901000633.1920247-1-minchan@kernel.org Link: http://lkml.kernel.org/r/20200622192900.22757-1-minchan@kernel.org Link: http://lkml.kernel.org/r/20200302193630.68771-2-minchan@kernel.org Link: http://lkml.kernel.org/r/20200622192900.22757-2-minchan@kernel.org Link: https://lkml.kernel.org/r/20200901000633.1920247-2-minchan@kernel.org Signed-off-by: Linus Torvalds --- fs/io_uring.c | 2 +- include/linux/mm.h | 2 +- mm/madvise.c | 32 ++++++++++++++++++-------------- 3 files changed, 20 insertions(+), 16 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 2e1dc354cd08..b58169240c77 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3989,7 +3989,7 @@ static int io_madvise(struct io_kiocb *req, bool force_nonblock) if (force_nonblock) return -EAGAIN; - ret = do_madvise(ma->addr, ma->len, ma->advice); + ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); if (ret < 0) req_set_fail_links(req); io_req_complete(req, ret); diff --git a/include/linux/mm.h b/include/linux/mm.h index 61a2633fcc7f..ef360fe70aaf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2579,7 +2579,7 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); -extern int do_madvise(unsigned long start, size_t len_in, int behavior); +extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, diff --git a/mm/madvise.c b/mm/madvise.c index fd1f448b4e1d..d550ef045288 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -258,6 +258,7 @@ static long madvise_willneed(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { + struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; loff_t offset; @@ -294,10 +295,10 @@ static long madvise_willneed(struct vm_area_struct *vma, get_file(file); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); - mmap_read_lock(current->mm); + mmap_read_lock(mm); return 0; } @@ -766,6 +767,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, unsigned long start, unsigned long end, int behavior) { + struct mm_struct *mm = vma->vm_mm; + *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; @@ -773,8 +776,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, if (!userfaultfd_remove(vma, start, end)) { *prev = NULL; /* mmap_lock has been dropped, prev is stale */ - mmap_read_lock(current->mm); - vma = find_vma(current->mm, start); + mmap_read_lock(mm); + vma = find_vma(mm, start); if (!vma) return -ENOMEM; if (start < vma->vm_start) { @@ -828,6 +831,7 @@ static long madvise_remove(struct vm_area_struct *vma, loff_t offset; int error; struct file *f; + struct mm_struct *mm = vma->vm_mm; *prev = NULL; /* tell sys_madvise we drop mmap_lock */ @@ -855,13 +859,13 @@ static long madvise_remove(struct vm_area_struct *vma, get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_lock was not released by userfaultfd_remove() */ - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); - mmap_read_lock(current->mm); + mmap_read_lock(mm); return error; } @@ -1045,7 +1049,7 @@ madvise_behavior_valid(int behavior) * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. */ -int do_madvise(unsigned long start, size_t len_in, int behavior) +int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { unsigned long end, tmp; struct vm_area_struct *vma, *prev; @@ -1083,10 +1087,10 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) write = madvise_need_mmap_write(behavior); if (write) { - if (mmap_write_lock_killable(current->mm)) + if (mmap_write_lock_killable(mm)) return -EINTR; } else { - mmap_read_lock(current->mm); + mmap_read_lock(mm); } /* @@ -1094,7 +1098,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) * ranges, just ignore them, but return -ENOMEM at the end. * - different from the way of handling in mlock etc. */ - vma = find_vma_prev(current->mm, start, &prev); + vma = find_vma_prev(mm, start, &prev); if (vma && start > vma->vm_start) prev = vma; @@ -1131,19 +1135,19 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) if (prev) vma = prev->vm_next; else /* madvise_remove dropped mmap_lock */ - vma = find_vma(current->mm, start); + vma = find_vma(mm, start); } out: blk_finish_plug(&plug); if (write) - mmap_write_unlock(current->mm); + mmap_write_unlock(mm); else - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { - return do_madvise(start, len_in, behavior); + return do_madvise(current->mm, start, len_in, behavior); }