Revision 13212b54d18d5235fb97fbdcba8ae453fd2a3a51 authored by Zhao Lei on 12 February 2015, 06:18:17 UTC, committed by Chris Mason on 14 February 2015, 16:19:14 UTC
Btrfs will report NO_SPACE when we create and remove files for several times, and we can't write to filesystem until mount it again. Steps to reproduce: 1: Create a single-dev btrfs fs with default option 2: Write a file into it to take up most fs space 3: Delete above file 4: Wait about 100s to let chunk removed 5: goto 2 Script is like following: #!/bin/bash # Recommend 1.2G space, too large disk will make test slow DEV="/dev/sda16" MNT="/mnt/tmp" dev_size="$(lsblk -bn -o SIZE "$DEV")" || exit 2 file_size_m=$((dev_size * 75 / 100 / 1024 / 1024)) echo "Loop write ${file_size_m}M file on $((dev_size / 1024 / 1024))M dev" for ((i = 0; i < 10; i++)); do umount "$MNT" 2>/dev/null; done echo "mkfs $DEV" mkfs.btrfs -f "$DEV" >/dev/null || exit 2 echo "mount $DEV $MNT" mount "$DEV" "$MNT" || exit 2 for ((loop_i = 0; loop_i < 20; loop_i++)); do echo echo "loop $loop_i" echo "dd file..." cmd=(dd if=/dev/zero of="$MNT"/file0 bs=1M count="$file_size_m") "${cmd[@]}" 2>/dev/null || { # NO_SPACE error triggered echo "dd failed: ${cmd[*]}" exit 1 } echo "rm file..." rm -f "$MNT"/file0 || exit 2 for ((i = 0; i < 10; i++)); do df "$MNT" | tail -1 sleep 10 done done Reason: It is triggered by commit: 47ab2a6c689913db23ccae38349714edf8365e0a which is used to remove empty block groups automatically, but the reason is not in that patch. Code before works well because btrfs don't need to create and delete chunks so many times with high complexity. Above bug is caused by many reason, any of them can trigger it. Reason1: When we remove some continuous chunks but leave other chunks after, these disk space should be used by chunk-recreating, but in current code, only first create will successed. Fixed by Forrest Liu <forrestl@synology.com> in: Btrfs: fix find_free_dev_extent() malfunction in case device tree has hole Reason2: contains_pending_extent() return wrong value in calculation. Fixed by Forrest Liu <forrestl@synology.com> in: Btrfs: fix find_free_dev_extent() malfunction in case device tree has hole Reason3: btrfs_check_data_free_space() try to commit transaction and retry allocating chunk when the first allocating failed, but space_info->full is set in first allocating, and prevent second allocating in retry. Fixed in this patch by clear space_info->full in commit transaction. Tested for severial times by above script. Changelog v3->v4: use light weight int instead of atomic_t to record have_remove_bgs in transaction, suggested by: Josef Bacik <jbacik@fb.com> Changelog v2->v3: v2 fixed the bug by adding more commit-transaction, but we only need to reclaim space when we are really have no space for new chunk, noticed by: Filipe David Manana <fdmanana@gmail.com> Actually, our code already have this type of commit-and-retry, we only need to make it working with removed-bgs. v3 fixed the bug with above way. Changelog v1->v2: v1 will introduce a new bug when delete and create chunk in same disk space in same transaction, noticed by: Filipe David Manana <fdmanana@gmail.com> V2 fix this bug by commit transaction after remove block grops. Reported-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com> Suggested-by: Filipe David Manana <fdmanana@gmail.com> Suggested-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
1 parent f55985f
mprotect.c
/*
* mm/mprotect.c
*
* (C) Copyright 1994 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*
* Address space accounting code <alan@lxorguk.ukuu.org.uk>
* (C) Copyright 2002 Red Hat Inc, All Rights Reserved
*/
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/mempolicy.h>
#include <linux/personality.h>
#include <linux/syscalls.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/perf_event.h>
#include <linux/ksm.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
/*
* For a prot_numa update we only hold mmap_sem for read so there is a
* potential race with faulting where a pmd was temporarily none. This
* function checks for a transhuge pmd under the appropriate lock. It
* returns a pte if it was successfully locked or NULL if it raced with
* a transhuge insertion.
*/
static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, int prot_numa, spinlock_t **ptl)
{
pte_t *pte;
spinlock_t *pmdl;
/* !prot_numa is protected by mmap_sem held for write */
if (!prot_numa)
return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
pmdl = pmd_lock(vma->vm_mm, pmd);
if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
spin_unlock(pmdl);
return NULL;
}
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
spin_unlock(pmdl);
return pte;
}
static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
{
struct mm_struct *mm = vma->vm_mm;
pte_t *pte, oldpte;
spinlock_t *ptl;
unsigned long pages = 0;
pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
if (!pte)
return 0;
arch_enter_lazy_mmu_mode();
do {
oldpte = *pte;
if (pte_present(oldpte)) {
pte_t ptent;
bool updated = false;
if (!prot_numa) {
ptent = ptep_modify_prot_start(mm, addr, pte);
if (pte_numa(ptent))
ptent = pte_mknonnuma(ptent);
ptent = pte_modify(ptent, newprot);
/*
* Avoid taking write faults for pages we
* know to be dirty.
*/
if (dirty_accountable && pte_dirty(ptent) &&
(pte_soft_dirty(ptent) ||
!(vma->vm_flags & VM_SOFTDIRTY)))
ptent = pte_mkwrite(ptent);
ptep_modify_prot_commit(mm, addr, pte, ptent);
updated = true;
} else {
struct page *page;
page = vm_normal_page(vma, addr, oldpte);
if (page && !PageKsm(page)) {
if (!pte_numa(oldpte)) {
ptep_set_numa(mm, addr, pte);
updated = true;
}
}
}
if (updated)
pages++;
} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
swp_entry_t entry = pte_to_swp_entry(oldpte);
if (is_write_migration_entry(entry)) {
pte_t newpte;
/*
* A protection check is difficult so
* just be safe and disable write
*/
make_migration_entry_read(&entry);
newpte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(oldpte))
newpte = pte_swp_mksoft_dirty(newpte);
set_pte_at(mm, addr, pte, newpte);
pages++;
}
}
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
return pages;
}
static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
pud_t *pud, unsigned long addr, unsigned long end,
pgprot_t newprot, int dirty_accountable, int prot_numa)
{
pmd_t *pmd;
struct mm_struct *mm = vma->vm_mm;
unsigned long next;
unsigned long pages = 0;
unsigned long nr_huge_updates = 0;
unsigned long mni_start = 0;
pmd = pmd_offset(pud, addr);
do {
unsigned long this_pages;
next = pmd_addr_end(addr, end);
if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd))
continue;
/* invoke the mmu notifier if the pmd is populated */
if (!mni_start) {
mni_start = addr;
mmu_notifier_invalidate_range_start(mm, mni_start, end);
}
if (pmd_trans_huge(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE)
split_huge_page_pmd(vma, addr, pmd);
else {
int nr_ptes = change_huge_pmd(vma, pmd, addr,
newprot, prot_numa);
if (nr_ptes) {
if (nr_ptes == HPAGE_PMD_NR) {
pages += HPAGE_PMD_NR;
nr_huge_updates++;
}
/* huge pmd was handled */
continue;
}
}
/* fall through, the trans huge pmd just split */
}
this_pages = change_pte_range(vma, pmd, addr, next, newprot,
dirty_accountable, prot_numa);
pages += this_pages;
} while (pmd++, addr = next, addr != end);
if (mni_start)
mmu_notifier_invalidate_range_end(mm, mni_start, end);
if (nr_huge_updates)
count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
return pages;
}
static inline unsigned long change_pud_range(struct vm_area_struct *vma,
pgd_t *pgd, unsigned long addr, unsigned long end,
pgprot_t newprot, int dirty_accountable, int prot_numa)
{
pud_t *pud;
unsigned long next;
unsigned long pages = 0;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
pages += change_pmd_range(vma, pud, addr, next, newprot,
dirty_accountable, prot_numa);
} while (pud++, addr = next, addr != end);
return pages;
}
static unsigned long change_protection_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
{
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
unsigned long next;
unsigned long start = addr;
unsigned long pages = 0;
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
set_tlb_flush_pending(mm);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
pages += change_pud_range(vma, pgd, addr, next, newprot,
dirty_accountable, prot_numa);
} while (pgd++, addr = next, addr != end);
/* Only flush the TLB if we actually modified any entries: */
if (pages)
flush_tlb_range(vma, start, end);
clear_tlb_flush_pending(mm);
return pages;
}
unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
{
unsigned long pages;
if (is_vm_hugetlb_page(vma))
pages = hugetlb_change_protection(vma, start, end, newprot);
else
pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
return pages;
}
int
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
unsigned long start, unsigned long end, unsigned long newflags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long oldflags = vma->vm_flags;
long nrpages = (end - start) >> PAGE_SHIFT;
unsigned long charged = 0;
pgoff_t pgoff;
int error;
int dirty_accountable = 0;
if (newflags == oldflags) {
*pprev = vma;
return 0;
}
/*
* If we make a private mapping writable we increase our commit;
* but (without finer accounting) cannot reduce our commit if we
* make it unwritable again. hugetlb mapping were accounted for
* even if read-only so there is no need to account for them here
*/
if (newflags & VM_WRITE) {
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
VM_SHARED|VM_NORESERVE))) {
charged = nrpages;
if (security_vm_enough_memory_mm(mm, charged))
return -ENOMEM;
newflags |= VM_ACCOUNT;
}
}
/*
* First try to merge with previous and/or next vma.
*/
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*pprev = vma_merge(mm, *pprev, start, end, newflags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
if (*pprev) {
vma = *pprev;
goto success;
}
*pprev = vma;
if (start != vma->vm_start) {
error = split_vma(mm, vma, start, 1);
if (error)
goto fail;
}
if (end != vma->vm_end) {
error = split_vma(mm, vma, end, 0);
if (error)
goto fail;
}
success:
/*
* vm_flags and vm_page_prot are protected by the mmap_sem
* held in write mode.
*/
vma->vm_flags = newflags;
dirty_accountable = vma_wants_writenotify(vma);
vma_set_page_prot(vma);
change_protection(vma, start, end, vma->vm_page_prot,
dirty_accountable, 0);
vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
vm_stat_account(mm, newflags, vma->vm_file, nrpages);
perf_event_mmap(vma);
return 0;
fail:
vm_unacct_memory(charged);
return error;
}
SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
unsigned long, prot)
{
unsigned long vm_flags, nstart, end, tmp, reqprot;
struct vm_area_struct *vma, *prev;
int error = -EINVAL;
const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
return -EINVAL;
if (start & ~PAGE_MASK)
return -EINVAL;
if (!len)
return 0;
len = PAGE_ALIGN(len);
end = start + len;
if (end <= start)
return -ENOMEM;
if (!arch_validate_prot(prot))
return -EINVAL;
reqprot = prot;
/*
* Does the application expect PROT_READ to imply PROT_EXEC:
*/
if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
prot |= PROT_EXEC;
vm_flags = calc_vm_prot_bits(prot);
down_write(¤t->mm->mmap_sem);
vma = find_vma(current->mm, start);
error = -ENOMEM;
if (!vma)
goto out;
prev = vma->vm_prev;
if (unlikely(grows & PROT_GROWSDOWN)) {
if (vma->vm_start >= end)
goto out;
start = vma->vm_start;
error = -EINVAL;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto out;
} else {
if (vma->vm_start > start)
goto out;
if (unlikely(grows & PROT_GROWSUP)) {
end = vma->vm_end;
error = -EINVAL;
if (!(vma->vm_flags & VM_GROWSUP))
goto out;
}
}
if (start > vma->vm_start)
prev = vma;
for (nstart = start ; ; ) {
unsigned long newflags;
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
newflags = vm_flags;
newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
/* newflags >> 4 shift VM_MAY% in place of VM_% */
if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
error = -EACCES;
goto out;
}
error = security_file_mprotect(vma, reqprot, prot);
if (error)
goto out;
tmp = vma->vm_end;
if (tmp > end)
tmp = end;
error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
if (error)
goto out;
nstart = tmp;
if (nstart < prev->vm_end)
nstart = prev->vm_end;
if (nstart >= end)
goto out;
vma = prev->vm_next;
if (!vma || vma->vm_start != nstart) {
error = -ENOMEM;
goto out;
}
}
out:
up_write(¤t->mm->mmap_sem);
return error;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...