955abe0a1b
Patch series "mm/vdpa: correct misuse of non-direct-reclaim __GFP_NOFAIL
and improve related doc and warn", v4.
__GFP_NOFAIL carries the semantics of never failing, so its callers do not
check the return value:
%__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
cannot handle allocation failures. The allocation could block
indefinitely but will never return with failure. Testing for
failure is pointless.
However, __GFP_NOFAIL can sometimes fail if it exceeds size limits or is
used with GFP_ATOMIC/GFP_NOWAIT in a non-sleepable context. This patchset
handles illegal using __GFP_NOFAIL together with GFP_ATOMIC lacking
__GFP_DIRECT_RECLAIM(without this, we can't do anything to reclaim memory
to satisfy the nofail requirement) and improve related document and
warnings.
The proper size limits for __GFP_NOFAIL will be handled separately after
more discussions.
This patch (of 3):
mm doesn't support non-blockable __GFP_NOFAIL allocation. Because
persisting in providing __GFP_NOFAIL services for non-block users who
cannot perform direct memory reclaim may only result in an endless busy
loop.
Therefore, in such cases, the current mm-core may directly return a NULL
pointer:
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct alloc_context *ac)
{
...
if (gfp_mask & __GFP_NOFAIL) {
/*
* All existing users of the __GFP_NOFAIL are blockable, so warn
* of any new users that actually require GFP_NOWAIT
*/
if (WARN_ON_ONCE_GFP(!can_direct_reclaim, gfp_mask))
goto fail;
...
}
...
fail:
warn_alloc(gfp_mask, ac->nodemask,
"page allocation failure: order:%u", order);
got_pg:
return page;
}
Unfortuantely, vpda does that nofail allocation under non-sleepable lock.
A possible way to fix that is to move the pages allocation out of the lock
into the caller, but having to allocate a huge number of pages and
auxiliary page array seems to be problematic as well per Tetsuon: " You
should implement proper error handling instead of using __GFP_NOFAIL if
count can become large."
So I chose another way, which does not release kernel bounce pages when
user tries to register userspace bounce pages. Then we can avoid
allocating in paths where failure is not expected.(e.g in the release).
We pay this for more memory usage as we don't release kernel bounce pages
but further optimizations could be done on top.
[v-songbaohua@oppo.com: Refine the changelog]
Link: https://lkml.kernel.org/r/20240830202823.21478-1-21cnbao@gmail.com
Link: https://lkml.kernel.org/r/20240830202823.21478-2-21cnbao@gmail.com
Fixes: 6c77ed2288 ("vduse: Support using userspace pages as bounce buffer")
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Reviewed-by: Xie Yongji <xieyongji@bytedance.com>
Tested-by: Xie Yongji <xieyongji@bytedance.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hailong.Liu <hailong.liu@oppo.com>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yafang Shao <laoar.shao@gmail.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "Eugenio Pérez" <eperezma@redhat.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
90 lines
2.5 KiB
C
90 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* MMU-based software IOTLB.
|
|
*
|
|
* Copyright (C) 2020-2021 Bytedance Inc. and/or its affiliates. All rights reserved.
|
|
*
|
|
* Author: Xie Yongji <xieyongji@bytedance.com>
|
|
*
|
|
*/
|
|
|
|
#ifndef _VDUSE_IOVA_DOMAIN_H
|
|
#define _VDUSE_IOVA_DOMAIN_H
|
|
|
|
#include <linux/iova.h>
|
|
#include <linux/dma-mapping.h>
|
|
#include <linux/vhost_iotlb.h>
|
|
|
|
#define IOVA_START_PFN 1
|
|
|
|
#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
|
|
|
|
struct vduse_bounce_map {
|
|
struct page *bounce_page;
|
|
struct page *user_bounce_page;
|
|
u64 orig_phys;
|
|
};
|
|
|
|
struct vduse_iova_domain {
|
|
struct iova_domain stream_iovad;
|
|
struct iova_domain consistent_iovad;
|
|
struct vduse_bounce_map *bounce_maps;
|
|
size_t bounce_size;
|
|
unsigned long iova_limit;
|
|
int bounce_map;
|
|
struct vhost_iotlb *iotlb;
|
|
spinlock_t iotlb_lock;
|
|
struct file *file;
|
|
bool user_bounce_pages;
|
|
rwlock_t bounce_lock;
|
|
};
|
|
|
|
int vduse_domain_set_map(struct vduse_iova_domain *domain,
|
|
struct vhost_iotlb *iotlb);
|
|
|
|
void vduse_domain_clear_map(struct vduse_iova_domain *domain,
|
|
struct vhost_iotlb *iotlb);
|
|
|
|
void vduse_domain_sync_single_for_device(struct vduse_iova_domain *domain,
|
|
dma_addr_t dma_addr, size_t size,
|
|
enum dma_data_direction dir);
|
|
|
|
void vduse_domain_sync_single_for_cpu(struct vduse_iova_domain *domain,
|
|
dma_addr_t dma_addr, size_t size,
|
|
enum dma_data_direction dir);
|
|
|
|
dma_addr_t vduse_domain_map_page(struct vduse_iova_domain *domain,
|
|
struct page *page, unsigned long offset,
|
|
size_t size, enum dma_data_direction dir,
|
|
unsigned long attrs);
|
|
|
|
void vduse_domain_unmap_page(struct vduse_iova_domain *domain,
|
|
dma_addr_t dma_addr, size_t size,
|
|
enum dma_data_direction dir, unsigned long attrs);
|
|
|
|
void *vduse_domain_alloc_coherent(struct vduse_iova_domain *domain,
|
|
size_t size, dma_addr_t *dma_addr,
|
|
gfp_t flag, unsigned long attrs);
|
|
|
|
void vduse_domain_free_coherent(struct vduse_iova_domain *domain, size_t size,
|
|
void *vaddr, dma_addr_t dma_addr,
|
|
unsigned long attrs);
|
|
|
|
void vduse_domain_reset_bounce_map(struct vduse_iova_domain *domain);
|
|
|
|
int vduse_domain_add_user_bounce_pages(struct vduse_iova_domain *domain,
|
|
struct page **pages, int count);
|
|
|
|
void vduse_domain_remove_user_bounce_pages(struct vduse_iova_domain *domain);
|
|
|
|
void vduse_domain_destroy(struct vduse_iova_domain *domain);
|
|
|
|
struct vduse_iova_domain *vduse_domain_create(unsigned long iova_limit,
|
|
size_t bounce_size);
|
|
|
|
int vduse_domain_init(void);
|
|
|
|
void vduse_domain_exit(void);
|
|
|
|
#endif /* _VDUSE_IOVA_DOMAIN_H */
|