linux_dsm_epyc7002/mm/balloon_compaction.c

164 lines
4.9 KiB
C
Raw Normal View History

/*
* 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;
virtio_balloon: fix race between migration and ballooning In balloon_page_dequeue, pages_lock should cover the loop (ie, list_for_each_entry_safe). Otherwise, the cursor page could be isolated by compaction and then list_del by isolation could poison the page->lru.{prev,next} so the loop finally could access wrong address like this. This patch fixes the bug. general protection fault: 0000 [#1] SMP Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 2 PID: 82 Comm: vballoon Not tainted 4.4.0-rc5-mm1-access_bit+ #1906 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff8800a7ff0000 ti: ffff8800a7fec000 task.ti: ffff8800a7fec000 RIP: 0010:[<ffffffff8115e754>] [<ffffffff8115e754>] balloon_page_dequeue+0x54/0x130 RSP: 0018:ffff8800a7fefdc0 EFLAGS: 00010246 RAX: ffff88013fff9a70 RBX: ffffea000056fe00 RCX: 0000000000002b7d RDX: ffff88013fff9a70 RSI: ffffea000056fe00 RDI: ffff88013fff9a68 RBP: ffff8800a7fefde8 R08: ffffea000056fda0 R09: 0000000000000000 R10: ffff8800a7fefd90 R11: 0000000000000001 R12: dead0000000000e0 R13: ffffea000056fe20 R14: ffff880138809070 R15: ffff880138809060 FS: 0000000000000000(0000) GS:ffff88013fc40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007f229c10e000 CR3: 00000000b8b53000 CR4: 00000000000006a0 Stack: 0000000000000100 ffff880138809088 ffff880138809000 ffff880138809060 0000000000000046 ffff8800a7fefe28 ffffffff812c86d3 ffff880138809020 ffff880138809000 fffffffffff91900 0000000000000100 ffff880138809060 Call Trace: [<ffffffff812c86d3>] leak_balloon+0x93/0x1a0 [<ffffffff812c8bc7>] balloon+0x217/0x2a0 [<ffffffff8143739e>] ? __schedule+0x31e/0x8b0 [<ffffffff81078160>] ? abort_exclusive_wait+0xb0/0xb0 [<ffffffff812c89b0>] ? update_balloon_stats+0xf0/0xf0 [<ffffffff8105b6e9>] kthread+0xc9/0xe0 [<ffffffff8105b620>] ? kthread_park+0x60/0x60 [<ffffffff8143b4af>] ret_from_fork+0x3f/0x70 [<ffffffff8105b620>] ? kthread_park+0x60/0x60 Code: 8d 60 e0 0f 84 af 00 00 00 48 8b 43 20 a8 01 75 3b 48 89 d8 f0 0f ba 28 00 72 10 48 8b 03 f6 c4 08 75 2f 48 89 df e8 8c 83 f9 ff <49> 8b 44 24 20 4d 8d 6c 24 20 48 83 e8 20 4d 39 f5 74 7a 4c 89 RIP [<ffffffff8115e754>] balloon_page_dequeue+0x54/0x130 RSP <ffff8800a7fefdc0> ---[ end trace 43cf28060d708d5f ]--- Kernel panic - not syncing: Fatal exception Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: disabled Cc: <stable@vger.kernel.org> Signed-off-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Rafael Aquini <aquini@redhat.com>
2015-12-28 06:35:13 +07:00
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)) {
mm/balloon_compaction: redesign ballooned pages management Sasha Levin reported KASAN splash inside isolate_migratepages_range(). Problem is in the function __is_movable_balloon_page() which tests AS_BALLOON_MAP in page->mapping->flags. This function has no protection against anonymous pages. As result it tried to check address space flags inside struct anon_vma. Further investigation shows more problems in current implementation: * Special branch in __unmap_and_move() never works: balloon_page_movable() checks page flags and page_count. In __unmap_and_move() page is locked, reference counter is elevated, thus balloon_page_movable() always fails. As a result execution goes to the normal migration path. virtballoon_migratepage() returns MIGRATEPAGE_BALLOON_SUCCESS instead of MIGRATEPAGE_SUCCESS, move_to_new_page() thinks this is an error code and assigns newpage->mapping to NULL. Newly migrated page lose connectivity with balloon an all ability for further migration. * lru_lock erroneously required in isolate_migratepages_range() for isolation ballooned page. This function releases lru_lock periodically, this makes migration mostly impossible for some pages. * balloon_page_dequeue have a tight race with balloon_page_isolate: balloon_page_isolate could be executed in parallel with dequeue between picking page from list and locking page_lock. Race is rare because they use trylock_page() for locking. This patch fixes all of them. Instead of fake mapping with special flag this patch uses special state of page->_mapcount: PAGE_BALLOON_MAPCOUNT_VALUE = -256. Buddy allocator uses PAGE_BUDDY_MAPCOUNT_VALUE = -128 for similar purpose. Storing mark directly in struct page makes everything safer and easier. PagePrivate is used to mark pages present in page list (i.e. not isolated, like PageLRU for normal pages). It replaces special rules for reference counter and makes balloon migration similar to migration of normal pages. This flag is protected by page_lock together with link to the balloon device. Signed-off-by: Konstantin Khlebnikov <k.khlebnikov@samsung.com> Reported-by: Sasha Levin <sasha.levin@oracle.com> Link: http://lkml.kernel.org/p/53E6CEAA.9020105@oracle.com Cc: Rafael Aquini <aquini@redhat.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: <stable@vger.kernel.org> [3.8+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-10 05:29:27 +07:00
/* raced with isolation */
unlock_page(page);
continue;
}
#endif
balloon_page_delete(page);
__count_vm_event(BALLOON_DEFLATE);
unlock_page(page);
dequeued_page = true;
break;
}
}
virtio_balloon: fix race between migration and ballooning In balloon_page_dequeue, pages_lock should cover the loop (ie, list_for_each_entry_safe). Otherwise, the cursor page could be isolated by compaction and then list_del by isolation could poison the page->lru.{prev,next} so the loop finally could access wrong address like this. This patch fixes the bug. general protection fault: 0000 [#1] SMP Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 2 PID: 82 Comm: vballoon Not tainted 4.4.0-rc5-mm1-access_bit+ #1906 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff8800a7ff0000 ti: ffff8800a7fec000 task.ti: ffff8800a7fec000 RIP: 0010:[<ffffffff8115e754>] [<ffffffff8115e754>] balloon_page_dequeue+0x54/0x130 RSP: 0018:ffff8800a7fefdc0 EFLAGS: 00010246 RAX: ffff88013fff9a70 RBX: ffffea000056fe00 RCX: 0000000000002b7d RDX: ffff88013fff9a70 RSI: ffffea000056fe00 RDI: ffff88013fff9a68 RBP: ffff8800a7fefde8 R08: ffffea000056fda0 R09: 0000000000000000 R10: ffff8800a7fefd90 R11: 0000000000000001 R12: dead0000000000e0 R13: ffffea000056fe20 R14: ffff880138809070 R15: ffff880138809060 FS: 0000000000000000(0000) GS:ffff88013fc40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007f229c10e000 CR3: 00000000b8b53000 CR4: 00000000000006a0 Stack: 0000000000000100 ffff880138809088 ffff880138809000 ffff880138809060 0000000000000046 ffff8800a7fefe28 ffffffff812c86d3 ffff880138809020 ffff880138809000 fffffffffff91900 0000000000000100 ffff880138809060 Call Trace: [<ffffffff812c86d3>] leak_balloon+0x93/0x1a0 [<ffffffff812c8bc7>] balloon+0x217/0x2a0 [<ffffffff8143739e>] ? __schedule+0x31e/0x8b0 [<ffffffff81078160>] ? abort_exclusive_wait+0xb0/0xb0 [<ffffffff812c89b0>] ? update_balloon_stats+0xf0/0xf0 [<ffffffff8105b6e9>] kthread+0xc9/0xe0 [<ffffffff8105b620>] ? kthread_park+0x60/0x60 [<ffffffff8143b4af>] ret_from_fork+0x3f/0x70 [<ffffffff8105b620>] ? kthread_park+0x60/0x60 Code: 8d 60 e0 0f 84 af 00 00 00 48 8b 43 20 a8 01 75 3b 48 89 d8 f0 0f ba 28 00 72 10 48 8b 03 f6 c4 08 75 2f 48 89 df e8 8c 83 f9 ff <49> 8b 44 24 20 4d 8d 6c 24 20 48 83 e8 20 4d 39 f5 74 7a 4c 89 RIP [<ffffffff8115e754>] balloon_page_dequeue+0x54/0x130 RSP <ffff8800a7fefdc0> ---[ end trace 43cf28060d708d5f ]--- Kernel panic - not syncing: Fatal exception Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: disabled Cc: <stable@vger.kernel.org> Signed-off-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Rafael Aquini <aquini@redhat.com>
2015-12-28 06:35:13 +07:00
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;
mm/balloon_compaction: redesign ballooned pages management Sasha Levin reported KASAN splash inside isolate_migratepages_range(). Problem is in the function __is_movable_balloon_page() which tests AS_BALLOON_MAP in page->mapping->flags. This function has no protection against anonymous pages. As result it tried to check address space flags inside struct anon_vma. Further investigation shows more problems in current implementation: * Special branch in __unmap_and_move() never works: balloon_page_movable() checks page flags and page_count. In __unmap_and_move() page is locked, reference counter is elevated, thus balloon_page_movable() always fails. As a result execution goes to the normal migration path. virtballoon_migratepage() returns MIGRATEPAGE_BALLOON_SUCCESS instead of MIGRATEPAGE_SUCCESS, move_to_new_page() thinks this is an error code and assigns newpage->mapping to NULL. Newly migrated page lose connectivity with balloon an all ability for further migration. * lru_lock erroneously required in isolate_migratepages_range() for isolation ballooned page. This function releases lru_lock periodically, this makes migration mostly impossible for some pages. * balloon_page_dequeue have a tight race with balloon_page_isolate: balloon_page_isolate could be executed in parallel with dequeue between picking page from list and locking page_lock. Race is rare because they use trylock_page() for locking. This patch fixes all of them. Instead of fake mapping with special flag this patch uses special state of page->_mapcount: PAGE_BALLOON_MAPCOUNT_VALUE = -256. Buddy allocator uses PAGE_BUDDY_MAPCOUNT_VALUE = -128 for similar purpose. Storing mark directly in struct page makes everything safer and easier. PagePrivate is used to mark pages present in page list (i.e. not isolated, like PageLRU for normal pages). It replaces special rules for reference counter and makes balloon migration similar to migration of normal pages. This flag is protected by page_lock together with link to the balloon device. Signed-off-by: Konstantin Khlebnikov <k.khlebnikov@samsung.com> Reported-by: Sasha Levin <sasha.levin@oracle.com> Link: http://lkml.kernel.org/p/53E6CEAA.9020105@oracle.com Cc: Rafael Aquini <aquini@redhat.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: <stable@vger.kernel.org> [3.8+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-10 05:29:27 +07:00
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;
mm/balloon_compaction: redesign ballooned pages management Sasha Levin reported KASAN splash inside isolate_migratepages_range(). Problem is in the function __is_movable_balloon_page() which tests AS_BALLOON_MAP in page->mapping->flags. This function has no protection against anonymous pages. As result it tried to check address space flags inside struct anon_vma. Further investigation shows more problems in current implementation: * Special branch in __unmap_and_move() never works: balloon_page_movable() checks page flags and page_count. In __unmap_and_move() page is locked, reference counter is elevated, thus balloon_page_movable() always fails. As a result execution goes to the normal migration path. virtballoon_migratepage() returns MIGRATEPAGE_BALLOON_SUCCESS instead of MIGRATEPAGE_SUCCESS, move_to_new_page() thinks this is an error code and assigns newpage->mapping to NULL. Newly migrated page lose connectivity with balloon an all ability for further migration. * lru_lock erroneously required in isolate_migratepages_range() for isolation ballooned page. This function releases lru_lock periodically, this makes migration mostly impossible for some pages. * balloon_page_dequeue have a tight race with balloon_page_isolate: balloon_page_isolate could be executed in parallel with dequeue between picking page from list and locking page_lock. Race is rare because they use trylock_page() for locking. This patch fixes all of them. Instead of fake mapping with special flag this patch uses special state of page->_mapcount: PAGE_BALLOON_MAPCOUNT_VALUE = -256. Buddy allocator uses PAGE_BUDDY_MAPCOUNT_VALUE = -128 for similar purpose. Storing mark directly in struct page makes everything safer and easier. PagePrivate is used to mark pages present in page list (i.e. not isolated, like PageLRU for normal pages). It replaces special rules for reference counter and makes balloon migration similar to migration of normal pages. This flag is protected by page_lock together with link to the balloon device. Signed-off-by: Konstantin Khlebnikov <k.khlebnikov@samsung.com> Reported-by: Sasha Levin <sasha.levin@oracle.com> Link: http://lkml.kernel.org/p/53E6CEAA.9020105@oracle.com Cc: Rafael Aquini <aquini@redhat.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: <stable@vger.kernel.org> [3.8+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-10 05:29:27 +07:00
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);
mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY 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>
2017-09-09 06:12:06 +07:00
/*
* 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 */