The patch titled
Subject: shmem: make shmem_inode_info::lock irq-safe
has been added to the -mm tree. Its filename is
shmem-make-shmem_inode_info-lock-irq-safe.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/shmem-make-shmem_inode_info-lock-irq-safe.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/shmem-make-shmem_inode_info-lock-irq-safe.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Subject: shmem: make shmem_inode_info::lock irq-safe
We are going to need to call shmem_charge() under tree_lock to get
accoutning right on collapse of small tmpfs pages into a huge one.
The problem is that tree_lock is irq-safe and lockdep is not happy, that
we take irq-unsafe lock under irq-safe[1].
Let's convert the lock to irq-safe.
[1] https://gist.github.com/kiryl/80c0149e03ed35dfaf26628b8e03cdbc
Link: http://lkml.kernel.org/r/1465297246-98985-29-git-send-email-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Jerome Marchand <jmarchan@xxxxxxxxxx>
Cc: Yang Shi <yang.shi@xxxxxxxxxx>
Cc: Sasha Levin <sasha.levin@xxxxxxxxxx>
Cc: Andres Lagar-Cavilla <andreslc@xxxxxxxxxx>
Cc: Ning Qu <quning@xxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
ipc/shm.c | 4 ++--
mm/shmem.c | 50 ++++++++++++++++++++++++++------------------------
2 files changed, 28 insertions(+), 26 deletions(-)
diff -puN ipc/shm.c~shmem-make-shmem_inode_info-lock-irq-safe ipc/shm.c
--- a/ipc/shm.c~shmem-make-shmem_inode_info-lock-irq-safe
+++ a/ipc/shm.c
@@ -766,10 +766,10 @@ static void shm_add_rss_swap(struct shmi
} else {
#ifdef CONFIG_SHMEM
struct shmem_inode_info *info = SHMEM_I(inode);
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
*rss_add += inode->i_mapping->nrpages;
*swp_add += info->swapped;
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
#else
*rss_add += inode->i_mapping->nrpages;
#endif
diff -puN mm/shmem.c~shmem-make-shmem_inode_info-lock-irq-safe mm/shmem.c
--- a/mm/shmem.c~shmem-make-shmem_inode_info-lock-irq-safe
+++ a/mm/shmem.c
@@ -258,14 +258,15 @@ bool shmem_charge(struct inode *inode, l
{
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+ unsigned long flags;
if (shmem_acct_block(info->flags, pages))
return false;
- spin_lock(&info->lock);
+ spin_lock_irqsave(&info->lock, flags);
info->alloced += pages;
inode->i_blocks += pages * BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irqrestore(&info->lock, flags);
inode->i_mapping->nrpages += pages;
if (!sbinfo->max_blocks)
@@ -273,10 +274,10 @@ bool shmem_charge(struct inode *inode, l
if (percpu_counter_compare(&sbinfo->used_blocks,
sbinfo->max_blocks - pages) > 0) {
inode->i_mapping->nrpages -= pages;
- spin_lock(&info->lock);
+ spin_lock_irqsave(&info->lock, flags);
info->alloced -= pages;
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irqrestore(&info->lock, flags);
return false;
}
@@ -288,12 +289,13 @@ void shmem_uncharge(struct inode *inode,
{
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+ unsigned long flags;
- spin_lock(&info->lock);
+ spin_lock_irqsave(&info->lock, flags);
info->alloced -= pages;
inode->i_blocks -= pages * BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irqrestore(&info->lock, flags);
if (sbinfo->max_blocks)
percpu_counter_sub(&sbinfo->used_blocks, pages);
@@ -818,10 +820,10 @@ static void shmem_undo_range(struct inod
index++;
}
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
info->swapped -= nr_swaps_freed;
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
}
void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
@@ -838,9 +840,9 @@ static int shmem_getattr(struct vfsmount
struct shmem_inode_info *info = SHMEM_I(inode);
if (info->alloced - info->swapped != inode->i_mapping->nrpages) {
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
}
generic_fillattr(inode, stat);
return 0;
@@ -984,9 +986,9 @@ static int shmem_unuse_inode(struct shme
delete_from_swap_cache(*pagep);
set_page_dirty(*pagep);
if (!error) {
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
info->swapped--;
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
swap_free(swap);
}
}
@@ -1134,10 +1136,10 @@ static int shmem_writepage(struct page *
list_add_tail(&info->swaplist, &shmem_swaplist);
if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
info->swapped++;
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
swap_shmem_alloc(swap);
shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
@@ -1523,10 +1525,10 @@ repeat:
mem_cgroup_commit_charge(page, memcg, true, false);
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
info->swapped--;
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
if (sgp == SGP_WRITE)
mark_page_accessed(page);
@@ -1603,11 +1605,11 @@ alloc_nohuge: page = shmem_alloc_and_ac
PageTransHuge(page));
lru_cache_add_anon(page);
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
info->alloced += 1 << compound_order(page);
inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page);
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
alloced = true;
/*
@@ -1639,9 +1641,9 @@ clear:
if (alloced) {
ClearPageDirty(page);
delete_from_page_cache(page);
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
}
error = -EINVAL;
goto unlock;
@@ -1673,9 +1675,9 @@ unlock:
}
if (error == -ENOSPC && !once++) {
info = SHMEM_I(inode);
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
goto repeat;
}
if (error == -EEXIST) /* from above or from radix_tree_insert */
@@ -1874,7 +1876,7 @@ int shmem_lock(struct file *file, int lo
struct shmem_inode_info *info = SHMEM_I(inode);
int retval = -ENOMEM;
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
if (lock && !(info->flags & VM_LOCKED)) {
if (!user_shm_lock(inode->i_size, user))
goto out_nomem;
@@ -1889,7 +1891,7 @@ int shmem_lock(struct file *file, int lo
retval = 0;
out_nomem:
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
return retval;
}
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-2.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-3.patch
mm-thp-make-swapin-readahead-under-down_read-of-mmap_sem-fix.patch
thp-mlock-update-unevictable-lrutxt.patch
mm-do-not-pass-mm_struct-into-handle_mm_fault.patch
mm-introduce-fault_env.patch
mm-postpone-page-table-allocation-until-we-have-page-to-map.patch
rmap-support-file-thp.patch
mm-introduce-do_set_pmd.patch
thp-vmstats-add-counters-for-huge-file-pages.patch
thp-support-file-pages-in-zap_huge_pmd.patch
thp-handle-file-pages-in-split_huge_pmd.patch
thp-handle-file-cow-faults.patch
thp-skip-file-huge-pmd-on-copy_huge_pmd.patch
thp-prepare-change_huge_pmd-for-file-thp.patch
thp-run-vma_adjust_trans_huge-outside-i_mmap_rwsem.patch
thp-file-pages-support-for-split_huge_page.patch
thp-mlock-do-not-mlock-pte-mapped-file-huge-pages.patch
vmscan-split-file-huge-pages-before-paging-them-out.patch
page-flags-relax-policy-for-pg_mappedtodisk-and-pg_reclaim.patch
radix-tree-implement-radix_tree_maybe_preload_order.patch
filemap-prepare-find-and-delete-operations-for-huge-pages.patch
truncate-handle-file-thp.patch
mm-rmap-account-shmem-thp-pages.patch
shmem-prepare-huge=-mount-option-and-sysfs-knob.patch
shmem-add-huge-pages-support.patch
shmem-thp-respect-madv_nohugepage-for-file-mappings.patch
thp-extract-khugepaged-from-mm-huge_memoryc.patch
khugepaged-move-up_readmmap_sem-out-of-khugepaged_alloc_page.patch
shmem-make-shmem_inode_info-lock-irq-safe.patch
khugepaged-add-support-of-collapse-for-tmpfs-shmem-pages.patch
thp-introduce-config_transparent_huge_pagecache.patch
shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
thp-update-documentation-vm-transhugefilesystems-proctxt.patch
a.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
