mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-14 15:54:15 +08:00
2916ecc0f9
Introduce a new migration mode that allow to offload the copy to a device DMA engine. This changes the workflow of migration and not all address_space migratepage callback can support this. This is intended to be use by migrate_vma() which itself is use for thing like HMM (see include/linux/hmm.h). No additional per-filesystem migratepage testing is needed. I disables MIGRATE_SYNC_NO_COPY in all problematic migratepage() callback and i added comment in those to explain why (part of this patch). The commit message is unclear it should say that any callback that wish to support this new mode need to be aware of the difference in the migration flow from other mode. Some of these callbacks do extra locking while copying (aio, zsmalloc, balloon, ...) and for DMA to be effective you want to copy multiple pages in one DMA operations. But in the problematic case you can not easily hold the extra lock accross multiple call to this callback. Usual flow is: For each page { 1 - lock page 2 - call migratepage() callback 3 - (extra locking in some migratepage() callback) 4 - migrate page state (freeze refcount, update page cache, buffer head, ...) 5 - copy page 6 - (unlock any extra lock of migratepage() callback) 7 - return from migratepage() callback 8 - unlock page } The new mode MIGRATE_SYNC_NO_COPY: 1 - lock multiple pages For each page { 2 - call migratepage() callback 3 - abort in all problematic migratepage() callback 4 - migrate page state (freeze refcount, update page cache, buffer head, ...) } // finished all calls to migratepage() callback 5 - DMA copy multiple pages 6 - unlock all the pages To support MIGRATE_SYNC_NO_COPY in the problematic case we would need a new callback migratepages() (for instance) that deals with multiple pages in one transaction. Because the problematic cases are not important for current usage I did not wanted to complexify this patchset even more for no good reason. Link: http://lkml.kernel.org/r/20170817000548.32038-14-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
164 lines
4.9 KiB
C
164 lines
4.9 KiB
C
/*
|
|
* mm/balloon_compaction.c
|
|
*
|
|
* Common interface for making balloon pages movable by compaction.
|
|
*
|
|
* Copyright (C) 2012, Red Hat, Inc. Rafael Aquini <aquini@redhat.com>
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/export.h>
|
|
#include <linux/balloon_compaction.h>
|
|
|
|
/*
|
|
* balloon_page_enqueue - allocates a new page and inserts it into the balloon
|
|
* page list.
|
|
* @b_dev_info: balloon device descriptor where we will insert a new page to
|
|
*
|
|
* Driver must call it to properly allocate a new enlisted balloon page
|
|
* before definitively removing it from the guest system.
|
|
* This function returns the page address for the recently enqueued page or
|
|
* NULL in the case we fail to allocate a new page this turn.
|
|
*/
|
|
struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
|
|
{
|
|
unsigned long flags;
|
|
struct page *page = alloc_page(balloon_mapping_gfp_mask() |
|
|
__GFP_NOMEMALLOC | __GFP_NORETRY);
|
|
if (!page)
|
|
return NULL;
|
|
|
|
/*
|
|
* Block others from accessing the 'page' when we get around to
|
|
* establishing additional references. We should be the only one
|
|
* holding a reference to the 'page' at this point.
|
|
*/
|
|
BUG_ON(!trylock_page(page));
|
|
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
|
|
balloon_page_insert(b_dev_info, page);
|
|
__count_vm_event(BALLOON_INFLATE);
|
|
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
|
|
unlock_page(page);
|
|
return page;
|
|
}
|
|
EXPORT_SYMBOL_GPL(balloon_page_enqueue);
|
|
|
|
/*
|
|
* balloon_page_dequeue - removes a page from balloon's page list and returns
|
|
* the its address to allow the driver release the page.
|
|
* @b_dev_info: balloon device decriptor where we will grab a page from.
|
|
*
|
|
* Driver must call it to properly de-allocate a previous enlisted balloon page
|
|
* before definetively releasing it back to the guest system.
|
|
* This function returns the page address for the recently dequeued page or
|
|
* NULL in the case we find balloon's page list temporarily empty due to
|
|
* compaction isolated pages.
|
|
*/
|
|
struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
|
|
{
|
|
struct page *page, *tmp;
|
|
unsigned long flags;
|
|
bool dequeued_page;
|
|
|
|
dequeued_page = false;
|
|
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
|
|
list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
|
|
/*
|
|
* Block others from accessing the 'page' while we get around
|
|
* establishing additional references and preparing the 'page'
|
|
* to be released by the balloon driver.
|
|
*/
|
|
if (trylock_page(page)) {
|
|
#ifdef CONFIG_BALLOON_COMPACTION
|
|
if (PageIsolated(page)) {
|
|
/* raced with isolation */
|
|
unlock_page(page);
|
|
continue;
|
|
}
|
|
#endif
|
|
balloon_page_delete(page);
|
|
__count_vm_event(BALLOON_DEFLATE);
|
|
unlock_page(page);
|
|
dequeued_page = true;
|
|
break;
|
|
}
|
|
}
|
|
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
|
|
|
|
if (!dequeued_page) {
|
|
/*
|
|
* If we are unable to dequeue a balloon page because the page
|
|
* list is empty and there is no isolated pages, then something
|
|
* went out of track and some balloon pages are lost.
|
|
* BUG() here, otherwise the balloon driver may get stuck into
|
|
* an infinite loop while attempting to release all its pages.
|
|
*/
|
|
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
|
|
if (unlikely(list_empty(&b_dev_info->pages) &&
|
|
!b_dev_info->isolated_pages))
|
|
BUG();
|
|
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
|
|
page = NULL;
|
|
}
|
|
return page;
|
|
}
|
|
EXPORT_SYMBOL_GPL(balloon_page_dequeue);
|
|
|
|
#ifdef CONFIG_BALLOON_COMPACTION
|
|
|
|
bool balloon_page_isolate(struct page *page, isolate_mode_t mode)
|
|
|
|
{
|
|
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
|
|
list_del(&page->lru);
|
|
b_dev_info->isolated_pages++;
|
|
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
|
|
|
|
return true;
|
|
}
|
|
|
|
void balloon_page_putback(struct page *page)
|
|
{
|
|
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
|
|
list_add(&page->lru, &b_dev_info->pages);
|
|
b_dev_info->isolated_pages--;
|
|
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
|
|
}
|
|
|
|
|
|
/* move_to_new_page() counterpart for a ballooned page */
|
|
int balloon_page_migrate(struct address_space *mapping,
|
|
struct page *newpage, struct page *page,
|
|
enum migrate_mode mode)
|
|
{
|
|
struct balloon_dev_info *balloon = balloon_page_device(page);
|
|
|
|
/*
|
|
* We can not easily support the no copy case here so ignore it as it
|
|
* is unlikely to be use with ballon pages. See include/linux/hmm.h for
|
|
* user of the MIGRATE_SYNC_NO_COPY mode.
|
|
*/
|
|
if (mode == MIGRATE_SYNC_NO_COPY)
|
|
return -EINVAL;
|
|
|
|
VM_BUG_ON_PAGE(!PageLocked(page), page);
|
|
VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
|
|
|
|
return balloon->migratepage(balloon, newpage, page, mode);
|
|
}
|
|
|
|
const struct address_space_operations balloon_aops = {
|
|
.migratepage = balloon_page_migrate,
|
|
.isolate_page = balloon_page_isolate,
|
|
.putback_page = balloon_page_putback,
|
|
};
|
|
EXPORT_SYMBOL_GPL(balloon_aops);
|
|
|
|
#endif /* CONFIG_BALLOON_COMPACTION */
|