Hi, Daniel,
Daniel Jordan <daniel.m.jordan@xxxxxxxxxx> writes:
> On Wed, Oct 10, 2018 at 03:19:03PM +0800, Huang Ying wrote:
>> And for all, Any comment is welcome!
>>
>> This patchset is based on the 2018-10-3 head of mmotm/master.
>
> There seems to be some infrequent memory corruption with THPs that have been
> swapped out: page contents differ after swapin.
Thanks a lot for testing this! I know there were big effort behind this
and it definitely will improve the quality of the patchset greatly!
> Reproducer at the bottom. Part of some tests I'm writing, had to separate it a
> little hack-ily. Basically it writes the word offset _at_ each word offset in
> a memory blob, tries to push it to swap, and verifies the offset is the same
> after swapin.
>
> I ran with THP enabled=always. THP swapin_enabled could be always or never, it
> happened with both. Every time swapping occurred, a single THP-sized chunk in
> the middle of the blob had different offsets. Example:
>
> ** > word corruption gap
> ** corruption detected 14929920 bytes in (got 15179776, expected 14929920) **
> ** corruption detected 14929928 bytes in (got 15179784, expected 14929928) **
> ** corruption detected 14929936 bytes in (got 15179792, expected 14929936) **
> ...pattern continues...
> ** corruption detected 17027048 bytes in (got 15179752, expected 17027048) **
> ** corruption detected 17027056 bytes in (got 15179760, expected 17027056) **
> ** corruption detected 17027064 bytes in (got 15179768, expected 17027064) **
15179776 < 15179xxx <= 17027064
15179776 % 4096 = 0
And 15179776 = 15179768 + 8
So I guess we have some alignment bug. Could you try the patches
attached? It deal with some alignment issue.
> 100.0% of memory was swapped out at mincore time
> 0.00305% of pages were corrupted (first corrupt word 14929920, last corrupt word 17027064)
>
> The problem goes away with THP enabled=never, and I don't see it on 2018-10-3
> mmotm/master with THP enabled=always.
>
> The server had an NVMe swap device and ~760G memory over two nodes, and the
> program was always run like this: swap-verify -s $((64 * 2**30))
>
> The kernels had one extra patch, Alexander Duyck's
> "dma-direct: Fix return value of dma_direct_supported", which was required to
> get them to build.
>
Thanks again!
Best Regards,
Huang, Ying
---------------------------------->8-----------------------------
>From e1c3e4f565deeb8245bdc4ee53a1f1e4188b6d4a Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@xxxxxxxxx>
Date: Wed, 24 Oct 2018 11:24:15 +0800
Subject: [PATCH] Fix alignment bug
---
include/linux/huge_mm.h | 6 ++----
mm/huge_memory.c | 9 ++++-----
mm/swap_state.c | 2 +-
3 files changed, 7 insertions(+), 10 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 96baae08f47c..e7b3527bc493 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -379,8 +379,7 @@ struct page_vma_mapped_walk;
#ifdef CONFIG_THP_SWAP
extern void __split_huge_swap_pmd(struct vm_area_struct *vma,
- unsigned long haddr,
- pmd_t *pmd);
+ unsigned long addr, pmd_t *pmd);
extern int split_huge_swap_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, pmd_t orig_pmd);
extern int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd);
@@ -411,8 +410,7 @@ static inline bool transparent_hugepage_swapin_enabled(
}
#else /* CONFIG_THP_SWAP */
static inline void __split_huge_swap_pmd(struct vm_area_struct *vma,
- unsigned long haddr,
- pmd_t *pmd)
+ unsigned long addr, pmd_t *pmd)
{
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ed64266b63dc..b2af3bff7624 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1731,10 +1731,11 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
#ifdef CONFIG_THP_SWAP
/* Convert a PMD swap mapping to a set of PTE swap mappings */
void __split_huge_swap_pmd(struct vm_area_struct *vma,
- unsigned long haddr,
+ unsigned long addr,
pmd_t *pmd)
{
struct mm_struct *mm = vma->vm_mm;
+ unsigned long haddr = addr & HPAGE_PMD_MASK;
pgtable_t pgtable;
pmd_t _pmd;
swp_entry_t entry;
@@ -1772,7 +1773,7 @@ int split_huge_swap_pmd(struct vm_area_struct *vma, pmd_t *pmd,
ptl = pmd_lock(mm, pmd);
if (pmd_same(*pmd, orig_pmd))
- __split_huge_swap_pmd(vma, address & HPAGE_PMD_MASK, pmd);
+ __split_huge_swap_pmd(vma, address, pmd);
else
ret = -ENOENT;
spin_unlock(ptl);
@@ -2013,9 +2014,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
* swap mapping and operate on the PTEs
*/
if (next - addr != HPAGE_PMD_SIZE) {
- unsigned long haddr = addr & HPAGE_PMD_MASK;
-
- __split_huge_swap_pmd(vma, haddr, pmd);
+ __split_huge_swap_pmd(vma, addr, pmd);
goto out;
}
free_swap_and_cache(entry, HPAGE_PMD_NR);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 784ad6388da0..fd143ef82351 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -451,7 +451,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
/* May fail (-ENOMEM) if XArray node allocation failed. */
__SetPageLocked(new_page);
__SetPageSwapBacked(new_page);
- err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL);
+ err = add_to_swap_cache(new_page, hentry, gfp_mask & GFP_KERNEL);
if (likely(!err)) {
/* Initiate read into locked page */
SetPageWorkingset(new_page);
--
2.18.1
