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
process_vm_access.c
/*
* linux/mm/process_vm_access.c
*
* Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#ifdef CONFIG_COMPAT
#include <linux/compat.h>
#endif
/**
* process_vm_rw_pages - read/write pages from task specified
* @pages: array of pointers to pages we want to copy
* @start_offset: offset in page to start copying from/to
* @len: number of bytes to copy
* @iter: where to copy to/from locally
* @vm_write: 0 means copy from, 1 means copy to
* Returns 0 on success, error code otherwise
*/
static int process_vm_rw_pages(struct page **pages,
unsigned offset,
size_t len,
struct iov_iter *iter,
int vm_write)
{
/* Do the copy for each page */
while (len && iov_iter_count(iter)) {
struct page *page = *pages++;
size_t copy = PAGE_SIZE - offset;
size_t copied;
if (copy > len)
copy = len;
if (vm_write) {
copied = copy_page_from_iter(page, offset, copy, iter);
set_page_dirty_lock(page);
} else {
copied = copy_page_to_iter(page, offset, copy, iter);
}
len -= copied;
if (copied < copy && iov_iter_count(iter))
return -EFAULT;
offset = 0;
}
return 0;
}
/* Maximum number of pages kmalloc'd to hold struct page's during copy */
#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2)
/**
* process_vm_rw_single_vec - read/write pages from task specified
* @addr: start memory address of target process
* @len: size of area to copy to/from
* @iter: where to copy to/from locally
* @process_pages: struct pages area that can store at least
* nr_pages_to_copy struct page pointers
* @mm: mm for task
* @task: task to read/write from
* @vm_write: 0 means copy from, 1 means copy to
* Returns 0 on success or on failure error code
*/
static int process_vm_rw_single_vec(unsigned long addr,
unsigned long len,
struct iov_iter *iter,
struct page **process_pages,
struct mm_struct *mm,
struct task_struct *task,
int vm_write)
{
unsigned long pa = addr & PAGE_MASK;
unsigned long start_offset = addr - pa;
unsigned long nr_pages;
ssize_t rc = 0;
unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
/ sizeof(struct pages *);
/* Work out address and page range required */
if (len == 0)
return 0;
nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
while (!rc && nr_pages && iov_iter_count(iter)) {
int pages = min(nr_pages, max_pages_per_loop);
size_t bytes;
/* Get the pages we're interested in */
down_read(&mm->mmap_sem);
pages = get_user_pages(task, mm, pa, pages,
vm_write, 0, process_pages, NULL);
up_read(&mm->mmap_sem);
if (pages <= 0)
return -EFAULT;
bytes = pages * PAGE_SIZE - start_offset;
if (bytes > len)
bytes = len;
rc = process_vm_rw_pages(process_pages,
start_offset, bytes, iter,
vm_write);
len -= bytes;
start_offset = 0;
nr_pages -= pages;
pa += pages * PAGE_SIZE;
while (pages)
put_page(process_pages[--pages]);
}
return rc;
}
/* Maximum number of entries for process pages array
which lives on stack */
#define PVM_MAX_PP_ARRAY_COUNT 16
/**
* process_vm_rw_core - core of reading/writing pages from task specified
* @pid: PID of process to read/write from/to
* @iter: where to copy to/from locally
* @rvec: iovec array specifying where to copy to/from in the other process
* @riovcnt: size of rvec array
* @flags: currently unused
* @vm_write: 0 if reading from other process, 1 if writing to other process
* Returns the number of bytes read/written or error code. May
* return less bytes than expected if an error occurs during the copying
* process.
*/
static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
const struct iovec *rvec,
unsigned long riovcnt,
unsigned long flags, int vm_write)
{
struct task_struct *task;
struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT];
struct page **process_pages = pp_stack;
struct mm_struct *mm;
unsigned long i;
ssize_t rc = 0;
unsigned long nr_pages = 0;
unsigned long nr_pages_iov;
ssize_t iov_len;
size_t total_len = iov_iter_count(iter);
/*
* Work out how many pages of struct pages we're going to need
* when eventually calling get_user_pages
*/
for (i = 0; i < riovcnt; i++) {
iov_len = rvec[i].iov_len;
if (iov_len > 0) {
nr_pages_iov = ((unsigned long)rvec[i].iov_base
+ iov_len)
/ PAGE_SIZE - (unsigned long)rvec[i].iov_base
/ PAGE_SIZE + 1;
nr_pages = max(nr_pages, nr_pages_iov);
}
}
if (nr_pages == 0)
return 0;
if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) {
/* For reliability don't try to kmalloc more than
2 pages worth */
process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES,
sizeof(struct pages *)*nr_pages),
GFP_KERNEL);
if (!process_pages)
return -ENOMEM;
}
/* Get process information */
rcu_read_lock();
task = find_task_by_vpid(pid);
if (task)
get_task_struct(task);
rcu_read_unlock();
if (!task) {
rc = -ESRCH;
goto free_proc_pages;
}
mm = mm_access(task, PTRACE_MODE_ATTACH);
if (!mm || IS_ERR(mm)) {
rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
/*
* Explicitly map EACCES to EPERM as EPERM is a more a
* appropriate error code for process_vw_readv/writev
*/
if (rc == -EACCES)
rc = -EPERM;
goto put_task_struct;
}
for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++)
rc = process_vm_rw_single_vec(
(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
iter, process_pages, mm, task, vm_write);
/* copied = space before - space after */
total_len -= iov_iter_count(iter);
/* If we have managed to copy any data at all then
we return the number of bytes copied. Otherwise
we return the error code */
if (total_len)
rc = total_len;
mmput(mm);
put_task_struct:
put_task_struct(task);
free_proc_pages:
if (process_pages != pp_stack)
kfree(process_pages);
return rc;
}
/**
* process_vm_rw - check iovecs before calling core routine
* @pid: PID of process to read/write from/to
* @lvec: iovec array specifying where to copy to/from locally
* @liovcnt: size of lvec array
* @rvec: iovec array specifying where to copy to/from in the other process
* @riovcnt: size of rvec array
* @flags: currently unused
* @vm_write: 0 if reading from other process, 1 if writing to other process
* Returns the number of bytes read/written or error code. May
* return less bytes than expected if an error occurs during the copying
* process.
*/
static ssize_t process_vm_rw(pid_t pid,
const struct iovec __user *lvec,
unsigned long liovcnt,
const struct iovec __user *rvec,
unsigned long riovcnt,
unsigned long flags, int vm_write)
{
struct iovec iovstack_l[UIO_FASTIOV];
struct iovec iovstack_r[UIO_FASTIOV];
struct iovec *iov_l = iovstack_l;
struct iovec *iov_r = iovstack_r;
struct iov_iter iter;
ssize_t rc;
if (flags != 0)
return -EINVAL;
/* Check iovecs */
if (vm_write)
rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV,
iovstack_l, &iov_l);
else
rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV,
iovstack_l, &iov_l);
if (rc <= 0)
goto free_iovecs;
iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
iovstack_r, &iov_r);
if (rc <= 0)
goto free_iovecs;
rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
free_iovecs:
if (iov_r != iovstack_r)
kfree(iov_r);
if (iov_l != iovstack_l)
kfree(iov_l);
return rc;
}
SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec,
unsigned long, liovcnt, const struct iovec __user *, rvec,
unsigned long, riovcnt, unsigned long, flags)
{
return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0);
}
SYSCALL_DEFINE6(process_vm_writev, pid_t, pid,
const struct iovec __user *, lvec,
unsigned long, liovcnt, const struct iovec __user *, rvec,
unsigned long, riovcnt, unsigned long, flags)
{
return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1);
}
#ifdef CONFIG_COMPAT
static ssize_t
compat_process_vm_rw(compat_pid_t pid,
const struct compat_iovec __user *lvec,
unsigned long liovcnt,
const struct compat_iovec __user *rvec,
unsigned long riovcnt,
unsigned long flags, int vm_write)
{
struct iovec iovstack_l[UIO_FASTIOV];
struct iovec iovstack_r[UIO_FASTIOV];
struct iovec *iov_l = iovstack_l;
struct iovec *iov_r = iovstack_r;
struct iov_iter iter;
ssize_t rc = -EFAULT;
if (flags != 0)
return -EINVAL;
if (vm_write)
rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt,
UIO_FASTIOV, iovstack_l,
&iov_l);
else
rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt,
UIO_FASTIOV, iovstack_l,
&iov_l);
if (rc <= 0)
goto free_iovecs;
iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
UIO_FASTIOV, iovstack_r,
&iov_r);
if (rc <= 0)
goto free_iovecs;
rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
free_iovecs:
if (iov_r != iovstack_r)
kfree(iov_r);
if (iov_l != iovstack_l)
kfree(iov_l);
return rc;
}
COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid,
const struct compat_iovec __user *, lvec,
compat_ulong_t, liovcnt,
const struct compat_iovec __user *, rvec,
compat_ulong_t, riovcnt,
compat_ulong_t, flags)
{
return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
riovcnt, flags, 0);
}
COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid,
const struct compat_iovec __user *, lvec,
compat_ulong_t, liovcnt,
const struct compat_iovec __user *, rvec,
compat_ulong_t, riovcnt,
compat_ulong_t, flags)
{
return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
riovcnt, flags, 1);
}
#endif
Computing file changes ...
