mirror of
https://github.com/torvalds/linux.git
synced 2024-12-24 11:51:27 +00:00
752ade68cb
There are many code paths opencoding kvmalloc. Let's use the helper instead. The main difference to kvmalloc is that those users are usually not considering all the aspects of the memory allocator. E.g. allocation requests <= 32kB (with 4kB pages) are basically never failing and invoke OOM killer to satisfy the allocation. This sounds too disruptive for something that has a reasonable fallback - the vmalloc. On the other hand those requests might fallback to vmalloc even when the memory allocator would succeed after several more reclaim/compaction attempts previously. There is no guarantee something like that happens though. This patch converts many of those places to kv[mz]alloc* helpers because they are more conservative. Link: http://lkml.kernel.org/r/20170306103327.2766-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> # Xen bits Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Andreas Dilger <andreas.dilger@intel.com> # Lustre Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> # KVM/s390 Acked-by: Dan Williams <dan.j.williams@intel.com> # nvdim Acked-by: David Sterba <dsterba@suse.com> # btrfs Acked-by: Ilya Dryomov <idryomov@gmail.com> # Ceph Acked-by: Tariq Toukan <tariqt@mellanox.com> # mlx4 Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx5 Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Tony Luck <tony.luck@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Santosh Raspatur <santosh@chelsio.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Yishai Hadas <yishaih@mellanox.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: "Yan, Zheng" <zyan@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
225 lines
6.0 KiB
C
225 lines
6.0 KiB
C
#include <linux/kernel.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/err.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/sched.h>
|
|
|
|
/**
|
|
* get_vaddr_frames() - map virtual addresses to pfns
|
|
* @start: starting user address
|
|
* @nr_frames: number of pages / pfns from start to map
|
|
* @gup_flags: flags modifying lookup behaviour
|
|
* @vec: structure which receives pages / pfns of the addresses mapped.
|
|
* It should have space for at least nr_frames entries.
|
|
*
|
|
* This function maps virtual addresses from @start and fills @vec structure
|
|
* with page frame numbers or page pointers to corresponding pages (choice
|
|
* depends on the type of the vma underlying the virtual address). If @start
|
|
* belongs to a normal vma, the function grabs reference to each of the pages
|
|
* to pin them in memory. If @start belongs to VM_IO | VM_PFNMAP vma, we don't
|
|
* touch page structures and the caller must make sure pfns aren't reused for
|
|
* anything else while he is using them.
|
|
*
|
|
* The function returns number of pages mapped which may be less than
|
|
* @nr_frames. In particular we stop mapping if there are more vmas of
|
|
* different type underlying the specified range of virtual addresses.
|
|
* When the function isn't able to map a single page, it returns error.
|
|
*
|
|
* This function takes care of grabbing mmap_sem as necessary.
|
|
*/
|
|
int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
|
|
unsigned int gup_flags, struct frame_vector *vec)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct *vma;
|
|
int ret = 0;
|
|
int err;
|
|
int locked;
|
|
|
|
if (nr_frames == 0)
|
|
return 0;
|
|
|
|
if (WARN_ON_ONCE(nr_frames > vec->nr_allocated))
|
|
nr_frames = vec->nr_allocated;
|
|
|
|
down_read(&mm->mmap_sem);
|
|
locked = 1;
|
|
vma = find_vma_intersection(mm, start, start + 1);
|
|
if (!vma) {
|
|
ret = -EFAULT;
|
|
goto out;
|
|
}
|
|
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
|
|
vec->got_ref = true;
|
|
vec->is_pfns = false;
|
|
ret = get_user_pages_locked(start, nr_frames,
|
|
gup_flags, (struct page **)(vec->ptrs), &locked);
|
|
goto out;
|
|
}
|
|
|
|
vec->got_ref = false;
|
|
vec->is_pfns = true;
|
|
do {
|
|
unsigned long *nums = frame_vector_pfns(vec);
|
|
|
|
while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) {
|
|
err = follow_pfn(vma, start, &nums[ret]);
|
|
if (err) {
|
|
if (ret == 0)
|
|
ret = err;
|
|
goto out;
|
|
}
|
|
start += PAGE_SIZE;
|
|
ret++;
|
|
}
|
|
/*
|
|
* We stop if we have enough pages or if VMA doesn't completely
|
|
* cover the tail page.
|
|
*/
|
|
if (ret >= nr_frames || start < vma->vm_end)
|
|
break;
|
|
vma = find_vma_intersection(mm, start, start + 1);
|
|
} while (vma && vma->vm_flags & (VM_IO | VM_PFNMAP));
|
|
out:
|
|
if (locked)
|
|
up_read(&mm->mmap_sem);
|
|
if (!ret)
|
|
ret = -EFAULT;
|
|
if (ret > 0)
|
|
vec->nr_frames = ret;
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(get_vaddr_frames);
|
|
|
|
/**
|
|
* put_vaddr_frames() - drop references to pages if get_vaddr_frames() acquired
|
|
* them
|
|
* @vec: frame vector to put
|
|
*
|
|
* Drop references to pages if get_vaddr_frames() acquired them. We also
|
|
* invalidate the frame vector so that it is prepared for the next call into
|
|
* get_vaddr_frames().
|
|
*/
|
|
void put_vaddr_frames(struct frame_vector *vec)
|
|
{
|
|
int i;
|
|
struct page **pages;
|
|
|
|
if (!vec->got_ref)
|
|
goto out;
|
|
pages = frame_vector_pages(vec);
|
|
/*
|
|
* frame_vector_pages() might needed to do a conversion when
|
|
* get_vaddr_frames() got pages but vec was later converted to pfns.
|
|
* But it shouldn't really fail to convert pfns back...
|
|
*/
|
|
if (WARN_ON(IS_ERR(pages)))
|
|
goto out;
|
|
for (i = 0; i < vec->nr_frames; i++)
|
|
put_page(pages[i]);
|
|
vec->got_ref = false;
|
|
out:
|
|
vec->nr_frames = 0;
|
|
}
|
|
EXPORT_SYMBOL(put_vaddr_frames);
|
|
|
|
/**
|
|
* frame_vector_to_pages - convert frame vector to contain page pointers
|
|
* @vec: frame vector to convert
|
|
*
|
|
* Convert @vec to contain array of page pointers. If the conversion is
|
|
* successful, return 0. Otherwise return an error. Note that we do not grab
|
|
* page references for the page structures.
|
|
*/
|
|
int frame_vector_to_pages(struct frame_vector *vec)
|
|
{
|
|
int i;
|
|
unsigned long *nums;
|
|
struct page **pages;
|
|
|
|
if (!vec->is_pfns)
|
|
return 0;
|
|
nums = frame_vector_pfns(vec);
|
|
for (i = 0; i < vec->nr_frames; i++)
|
|
if (!pfn_valid(nums[i]))
|
|
return -EINVAL;
|
|
pages = (struct page **)nums;
|
|
for (i = 0; i < vec->nr_frames; i++)
|
|
pages[i] = pfn_to_page(nums[i]);
|
|
vec->is_pfns = false;
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(frame_vector_to_pages);
|
|
|
|
/**
|
|
* frame_vector_to_pfns - convert frame vector to contain pfns
|
|
* @vec: frame vector to convert
|
|
*
|
|
* Convert @vec to contain array of pfns.
|
|
*/
|
|
void frame_vector_to_pfns(struct frame_vector *vec)
|
|
{
|
|
int i;
|
|
unsigned long *nums;
|
|
struct page **pages;
|
|
|
|
if (vec->is_pfns)
|
|
return;
|
|
pages = (struct page **)(vec->ptrs);
|
|
nums = (unsigned long *)pages;
|
|
for (i = 0; i < vec->nr_frames; i++)
|
|
nums[i] = page_to_pfn(pages[i]);
|
|
vec->is_pfns = true;
|
|
}
|
|
EXPORT_SYMBOL(frame_vector_to_pfns);
|
|
|
|
/**
|
|
* frame_vector_create() - allocate & initialize structure for pinned pfns
|
|
* @nr_frames: number of pfns slots we should reserve
|
|
*
|
|
* Allocate and initialize struct pinned_pfns to be able to hold @nr_pfns
|
|
* pfns.
|
|
*/
|
|
struct frame_vector *frame_vector_create(unsigned int nr_frames)
|
|
{
|
|
struct frame_vector *vec;
|
|
int size = sizeof(struct frame_vector) + sizeof(void *) * nr_frames;
|
|
|
|
if (WARN_ON_ONCE(nr_frames == 0))
|
|
return NULL;
|
|
/*
|
|
* This is absurdly high. It's here just to avoid strange effects when
|
|
* arithmetics overflows.
|
|
*/
|
|
if (WARN_ON_ONCE(nr_frames > INT_MAX / sizeof(void *) / 2))
|
|
return NULL;
|
|
/*
|
|
* Avoid higher order allocations, use vmalloc instead. It should
|
|
* be rare anyway.
|
|
*/
|
|
vec = kvmalloc(size, GFP_KERNEL);
|
|
if (!vec)
|
|
return NULL;
|
|
vec->nr_allocated = nr_frames;
|
|
vec->nr_frames = 0;
|
|
return vec;
|
|
}
|
|
EXPORT_SYMBOL(frame_vector_create);
|
|
|
|
/**
|
|
* frame_vector_destroy() - free memory allocated to carry frame vector
|
|
* @vec: Frame vector to free
|
|
*
|
|
* Free structure allocated by frame_vector_create() to carry frames.
|
|
*/
|
|
void frame_vector_destroy(struct frame_vector *vec)
|
|
{
|
|
/* Make sure put_vaddr_frames() got called properly... */
|
|
VM_BUG_ON(vec->nr_frames > 0);
|
|
kvfree(vec);
|
|
}
|
|
EXPORT_SYMBOL(frame_vector_destroy);
|