2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/fs/ext4/sysfs.c

593 lines
16 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/sysfs.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Theodore Ts'o (tytso@mit.edu)
*
*/
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/part_stat.h>
#include "ext4.h"
#include "ext4_jbd2.h"
typedef enum {
attr_noop,
attr_delayed_allocation_blocks,
attr_session_write_kbytes,
attr_lifetime_write_kbytes,
attr_reserved_clusters,
ext4: shrink race window in ext4_should_retry_alloc() When generic/371 is run on kvm-xfstests using 5.10 and 5.11 kernels, it fails at significant rates on the two test scenarios that disable delayed allocation (ext3conv and data_journal) and force actual block allocation for the fallocate and pwrite functions in the test. The failure rate on 5.10 for both ext3conv and data_journal on one test system typically runs about 85%. On 5.11, the failure rate on ext3conv sometimes drops to as low as 1% while the rate on data_journal increases to nearly 100%. The observed failures are largely due to ext4_should_retry_alloc() cutting off block allocation retries when s_mb_free_pending (used to indicate that a transaction in progress will free blocks) is 0. However, free space is usually available when this occurs during runs of generic/371. It appears that a thread attempting to allocate blocks is just missing transaction commits in other threads that increase the free cluster count and reset s_mb_free_pending while the allocating thread isn't running. Explicitly testing for free space availability avoids this race. The current code uses a post-increment operator in the conditional expression that determines whether the retry limit has been exceeded. This means that the conditional expression uses the value of the retry counter before it's increased, resulting in an extra retry cycle. The current code actually retries twice before hitting its retry limit rather than once. Increasing the retry limit to 3 from the current actual maximum retry count of 2 in combination with the change described above reduces the observed failure rate to less that 0.1% on both ext3conv and data_journal with what should be limited impact on users sensitive to the overhead caused by retries. A per filesystem percpu counter exported via sysfs is added to allow users or developers to track the number of times the retry limit is exceeded without resorting to debugging methods. This should provide some insight into worst case retry behavior. Signed-off-by: Eric Whitney <enwlinux@gmail.com> Link: https://lore.kernel.org/r/20210218151132.19678-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-02-18 23:11:32 +08:00
attr_sra_exceeded_retry_limit,
attr_inode_readahead,
attr_trigger_test_error,
attr_first_error_time,
attr_last_error_time,
attr_feature,
attr_pointer_ui,
attr_pointer_ul,
attr_pointer_u64,
attr_pointer_u8,
attr_pointer_string,
attr_pointer_atomic,
attr_journal_task,
} attr_id_t;
typedef enum {
ptr_explicit,
ptr_ext4_sb_info_offset,
ptr_ext4_super_block_offset,
} attr_ptr_t;
static const char proc_dirname[] = "fs/ext4";
static struct proc_dir_entry *ext4_proc_root;
struct ext4_attr {
struct attribute attr;
short attr_id;
short attr_ptr;
unsigned short attr_size;
union {
int offset;
void *explicit_ptr;
} u;
};
static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
{
struct super_block *sb = sbi->s_buddy_cache->i_sb;
return snprintf(buf, PAGE_SIZE, "%lu\n",
(part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
sbi->s_sectors_written_start) >> 1);
}
static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
{
struct super_block *sb = sbi->s_buddy_cache->i_sb;
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1)));
}
static ssize_t inode_readahead_blks_store(struct ext4_sb_info *sbi,
const char *buf, size_t count)
{
unsigned long t;
int ret;
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret)
return ret;
if (t && (!is_power_of_2(t) || t > 0x40000000))
return -EINVAL;
sbi->s_inode_readahead_blks = t;
return count;
}
static ssize_t reserved_clusters_store(struct ext4_sb_info *sbi,
const char *buf, size_t count)
{
unsigned long long val;
ext4_fsblk_t clusters = (ext4_blocks_count(sbi->s_es) >>
sbi->s_cluster_bits);
int ret;
ret = kstrtoull(skip_spaces(buf), 0, &val);
if (ret || val >= clusters)
return -EINVAL;
atomic64_set(&sbi->s_resv_clusters, val);
return count;
}
static ssize_t trigger_test_error(struct ext4_sb_info *sbi,
const char *buf, size_t count)
{
int len = count;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (len && buf[len-1] == '\n')
len--;
if (len)
ext4_error(sbi->s_sb, "%.*s", len, buf);
return count;
}
static ssize_t journal_task_show(struct ext4_sb_info *sbi, char *buf)
{
if (!sbi->s_journal)
return snprintf(buf, PAGE_SIZE, "<none>\n");
return snprintf(buf, PAGE_SIZE, "%d\n",
task_pid_vnr(sbi->s_journal->j_task));
}
#define EXT4_ATTR(_name,_mode,_id) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
.attr_id = attr_##_id, \
}
#define EXT4_ATTR_FUNC(_name,_mode) EXT4_ATTR(_name,_mode,_name)
#define EXT4_ATTR_FEATURE(_name) EXT4_ATTR(_name, 0444, feature)
#define EXT4_ATTR_OFFSET(_name,_mode,_id,_struct,_elname) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
.attr_id = attr_##_id, \
.attr_ptr = ptr_##_struct##_offset, \
.u = { \
.offset = offsetof(struct _struct, _elname),\
}, \
}
#define EXT4_ATTR_STRING(_name,_mode,_size,_struct,_elname) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
.attr_id = attr_pointer_string, \
.attr_size = _size, \
.attr_ptr = ptr_##_struct##_offset, \
.u = { \
.offset = offsetof(struct _struct, _elname),\
}, \
}
#define EXT4_RO_ATTR_ES_UI(_name,_elname) \
EXT4_ATTR_OFFSET(_name, 0444, pointer_ui, ext4_super_block, _elname)
#define EXT4_RO_ATTR_ES_U8(_name,_elname) \
EXT4_ATTR_OFFSET(_name, 0444, pointer_u8, ext4_super_block, _elname)
#define EXT4_RO_ATTR_ES_U64(_name,_elname) \
EXT4_ATTR_OFFSET(_name, 0444, pointer_u64, ext4_super_block, _elname)
#define EXT4_RO_ATTR_ES_STRING(_name,_elname,_size) \
EXT4_ATTR_STRING(_name, 0444, _size, ext4_super_block, _elname)
#define EXT4_RW_ATTR_SBI_UI(_name,_elname) \
EXT4_ATTR_OFFSET(_name, 0644, pointer_ui, ext4_sb_info, _elname)
#define EXT4_RW_ATTR_SBI_UL(_name,_elname) \
EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname)
#define EXT4_RO_ATTR_SBI_ATOMIC(_name,_elname) \
EXT4_ATTR_OFFSET(_name, 0444, pointer_atomic, ext4_sb_info, _elname)
#define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
.attr_id = attr_##_id, \
.attr_ptr = ptr_explicit, \
.u = { \
.explicit_ptr = _ptr, \
}, \
}
#define ATTR_LIST(name) &ext4_attr_##name.attr
EXT4_ATTR_FUNC(delayed_allocation_blocks, 0444);
EXT4_ATTR_FUNC(session_write_kbytes, 0444);
EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444);
EXT4_ATTR_FUNC(reserved_clusters, 0644);
ext4: shrink race window in ext4_should_retry_alloc() When generic/371 is run on kvm-xfstests using 5.10 and 5.11 kernels, it fails at significant rates on the two test scenarios that disable delayed allocation (ext3conv and data_journal) and force actual block allocation for the fallocate and pwrite functions in the test. The failure rate on 5.10 for both ext3conv and data_journal on one test system typically runs about 85%. On 5.11, the failure rate on ext3conv sometimes drops to as low as 1% while the rate on data_journal increases to nearly 100%. The observed failures are largely due to ext4_should_retry_alloc() cutting off block allocation retries when s_mb_free_pending (used to indicate that a transaction in progress will free blocks) is 0. However, free space is usually available when this occurs during runs of generic/371. It appears that a thread attempting to allocate blocks is just missing transaction commits in other threads that increase the free cluster count and reset s_mb_free_pending while the allocating thread isn't running. Explicitly testing for free space availability avoids this race. The current code uses a post-increment operator in the conditional expression that determines whether the retry limit has been exceeded. This means that the conditional expression uses the value of the retry counter before it's increased, resulting in an extra retry cycle. The current code actually retries twice before hitting its retry limit rather than once. Increasing the retry limit to 3 from the current actual maximum retry count of 2 in combination with the change described above reduces the observed failure rate to less that 0.1% on both ext3conv and data_journal with what should be limited impact on users sensitive to the overhead caused by retries. A per filesystem percpu counter exported via sysfs is added to allow users or developers to track the number of times the retry limit is exceeded without resorting to debugging methods. This should provide some insight into worst case retry behavior. Signed-off-by: Eric Whitney <enwlinux@gmail.com> Link: https://lore.kernel.org/r/20210218151132.19678-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-02-18 23:11:32 +08:00
EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444);
EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead,
ext4_sb_info, s_inode_readahead_blks);
EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats);
EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan);
EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc);
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups);
EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error);
EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
EXT4_RW_ATTR_SBI_UI(err_ratelimit_burst, s_err_ratelimit_state.burst);
EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval);
EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
#ifdef CONFIG_EXT4_DEBUG
EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail);
#endif
EXT4_RO_ATTR_SBI_ATOMIC(warning_count, s_warning_count);
EXT4_RO_ATTR_SBI_ATOMIC(msg_count, s_msg_count);
EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode);
EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode);
EXT4_RO_ATTR_ES_UI(first_error_ino, s_first_error_ino);
EXT4_RO_ATTR_ES_UI(last_error_ino, s_last_error_ino);
EXT4_RO_ATTR_ES_U64(first_error_block, s_first_error_block);
EXT4_RO_ATTR_ES_U64(last_error_block, s_last_error_block);
EXT4_RO_ATTR_ES_UI(first_error_line, s_first_error_line);
EXT4_RO_ATTR_ES_UI(last_error_line, s_last_error_line);
EXT4_RO_ATTR_ES_STRING(first_error_func, s_first_error_func, 32);
EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32);
EXT4_ATTR(first_error_time, 0444, first_error_time);
EXT4_ATTR(last_error_time, 0444, last_error_time);
EXT4_ATTR(journal_task, 0444, journal_task);
EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch);
EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit);
static unsigned int old_bump_val = 128;
EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
static struct attribute *ext4_attrs[] = {
ATTR_LIST(delayed_allocation_blocks),
ATTR_LIST(session_write_kbytes),
ATTR_LIST(lifetime_write_kbytes),
ATTR_LIST(reserved_clusters),
ext4: shrink race window in ext4_should_retry_alloc() When generic/371 is run on kvm-xfstests using 5.10 and 5.11 kernels, it fails at significant rates on the two test scenarios that disable delayed allocation (ext3conv and data_journal) and force actual block allocation for the fallocate and pwrite functions in the test. The failure rate on 5.10 for both ext3conv and data_journal on one test system typically runs about 85%. On 5.11, the failure rate on ext3conv sometimes drops to as low as 1% while the rate on data_journal increases to nearly 100%. The observed failures are largely due to ext4_should_retry_alloc() cutting off block allocation retries when s_mb_free_pending (used to indicate that a transaction in progress will free blocks) is 0. However, free space is usually available when this occurs during runs of generic/371. It appears that a thread attempting to allocate blocks is just missing transaction commits in other threads that increase the free cluster count and reset s_mb_free_pending while the allocating thread isn't running. Explicitly testing for free space availability avoids this race. The current code uses a post-increment operator in the conditional expression that determines whether the retry limit has been exceeded. This means that the conditional expression uses the value of the retry counter before it's increased, resulting in an extra retry cycle. The current code actually retries twice before hitting its retry limit rather than once. Increasing the retry limit to 3 from the current actual maximum retry count of 2 in combination with the change described above reduces the observed failure rate to less that 0.1% on both ext3conv and data_journal with what should be limited impact on users sensitive to the overhead caused by retries. A per filesystem percpu counter exported via sysfs is added to allow users or developers to track the number of times the retry limit is exceeded without resorting to debugging methods. This should provide some insight into worst case retry behavior. Signed-off-by: Eric Whitney <enwlinux@gmail.com> Link: https://lore.kernel.org/r/20210218151132.19678-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-02-18 23:11:32 +08:00
ATTR_LIST(sra_exceeded_retry_limit),
ATTR_LIST(inode_readahead_blks),
ATTR_LIST(inode_goal),
ATTR_LIST(mb_stats),
ATTR_LIST(mb_max_to_scan),
ATTR_LIST(mb_min_to_scan),
ATTR_LIST(mb_order2_req),
ATTR_LIST(mb_stream_req),
ATTR_LIST(mb_group_prealloc),
ATTR_LIST(mb_max_inode_prealloc),
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
ATTR_LIST(mb_max_linear_groups),
ATTR_LIST(max_writeback_mb_bump),
ATTR_LIST(extent_max_zeroout_kb),
ATTR_LIST(trigger_fs_error),
ATTR_LIST(err_ratelimit_interval_ms),
ATTR_LIST(err_ratelimit_burst),
ATTR_LIST(warning_ratelimit_interval_ms),
ATTR_LIST(warning_ratelimit_burst),
ATTR_LIST(msg_ratelimit_interval_ms),
ATTR_LIST(msg_ratelimit_burst),
ATTR_LIST(errors_count),
ATTR_LIST(warning_count),
ATTR_LIST(msg_count),
ATTR_LIST(first_error_ino),
ATTR_LIST(last_error_ino),
ATTR_LIST(first_error_block),
ATTR_LIST(last_error_block),
ATTR_LIST(first_error_line),
ATTR_LIST(last_error_line),
ATTR_LIST(first_error_func),
ATTR_LIST(last_error_func),
ATTR_LIST(first_error_errcode),
ATTR_LIST(last_error_errcode),
ATTR_LIST(first_error_time),
ATTR_LIST(last_error_time),
ATTR_LIST(journal_task),
#ifdef CONFIG_EXT4_DEBUG
ATTR_LIST(simulate_fail),
#endif
ATTR_LIST(mb_prefetch),
ATTR_LIST(mb_prefetch_limit),
NULL,
};
ATTRIBUTE_GROUPS(ext4);
/* Features this copy of ext4 supports */
EXT4_ATTR_FEATURE(lazy_itable_init);
EXT4_ATTR_FEATURE(batched_discard);
EXT4_ATTR_FEATURE(meta_bg_resize);
#ifdef CONFIG_FS_ENCRYPTION
EXT4_ATTR_FEATURE(encryption);
fscrypt: support test_dummy_encryption=v2 v1 encryption policies are deprecated in favor of v2, and some new features (e.g. encryption+casefolding) are only being added for v2. Therefore, the "test_dummy_encryption" mount option (which is used for encryption I/O testing with xfstests) needs to support v2 policies. To do this, extend its syntax to be "test_dummy_encryption=v1" or "test_dummy_encryption=v2". The existing "test_dummy_encryption" (no argument) also continues to be accepted, to specify the default setting -- currently v1, but the next patch changes it to v2. To cleanly support both v1 and v2 while also making it easy to support specifying other encryption settings in the future (say, accepting "$contents_mode:$filenames_mode:v2"), make ext4 and f2fs maintain a pointer to the dummy fscrypt_context rather than using mount flags. To avoid concurrency issues, don't allow test_dummy_encryption to be set or changed during a remount. (The former restriction is new, but xfstests doesn't run into it, so no one should notice.) Tested with 'gce-xfstests -c {ext4,f2fs}/encrypt -g auto'. On ext4, there are two regressions, both of which are test bugs: ext4/023 and ext4/028 fail because they set an xattr and expect it to be stored inline, but the increase in size of the fscrypt_context from 24 to 40 bytes causes this xattr to be spilled into an external block. Link: https://lore.kernel.org/r/20200512233251.118314-4-ebiggers@kernel.org Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2020-05-13 07:32:50 +08:00
EXT4_ATTR_FEATURE(test_dummy_encryption_v2);
#endif
#ifdef CONFIG_UNICODE
EXT4_ATTR_FEATURE(casefold);
#endif
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
#ifdef CONFIG_FS_VERITY
EXT4_ATTR_FEATURE(verity);
#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
EXT4_ATTR_FEATURE(fast_commit);
EXT4_ATTR_FEATURE(encrypted_casefold);
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
ATTR_LIST(batched_discard),
ATTR_LIST(meta_bg_resize),
#ifdef CONFIG_FS_ENCRYPTION
ATTR_LIST(encryption),
fscrypt: support test_dummy_encryption=v2 v1 encryption policies are deprecated in favor of v2, and some new features (e.g. encryption+casefolding) are only being added for v2. Therefore, the "test_dummy_encryption" mount option (which is used for encryption I/O testing with xfstests) needs to support v2 policies. To do this, extend its syntax to be "test_dummy_encryption=v1" or "test_dummy_encryption=v2". The existing "test_dummy_encryption" (no argument) also continues to be accepted, to specify the default setting -- currently v1, but the next patch changes it to v2. To cleanly support both v1 and v2 while also making it easy to support specifying other encryption settings in the future (say, accepting "$contents_mode:$filenames_mode:v2"), make ext4 and f2fs maintain a pointer to the dummy fscrypt_context rather than using mount flags. To avoid concurrency issues, don't allow test_dummy_encryption to be set or changed during a remount. (The former restriction is new, but xfstests doesn't run into it, so no one should notice.) Tested with 'gce-xfstests -c {ext4,f2fs}/encrypt -g auto'. On ext4, there are two regressions, both of which are test bugs: ext4/023 and ext4/028 fail because they set an xattr and expect it to be stored inline, but the increase in size of the fscrypt_context from 24 to 40 bytes causes this xattr to be spilled into an external block. Link: https://lore.kernel.org/r/20200512233251.118314-4-ebiggers@kernel.org Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2020-05-13 07:32:50 +08:00
ATTR_LIST(test_dummy_encryption_v2),
#endif
#ifdef CONFIG_UNICODE
ATTR_LIST(casefold),
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
#endif
#ifdef CONFIG_FS_VERITY
ATTR_LIST(verity),
#endif
ATTR_LIST(metadata_csum_seed),
ATTR_LIST(fast_commit),
ATTR_LIST(encrypted_casefold),
NULL,
};
ATTRIBUTE_GROUPS(ext4_feat);
static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
{
switch (a->attr_ptr) {
case ptr_explicit:
return a->u.explicit_ptr;
case ptr_ext4_sb_info_offset:
return (void *) (((char *) sbi) + a->u.offset);
case ptr_ext4_super_block_offset:
return (void *) (((char *) sbi->s_es) + a->u.offset);
}
return NULL;
}
static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi)
{
return snprintf(buf, PAGE_SIZE, "%lld\n",
((time64_t)hi << 32) + le32_to_cpu(lo));
}
#define print_tstamp(buf, es, tstamp) \
__print_tstamp(buf, (es)->tstamp, (es)->tstamp ## _hi)
static ssize_t ext4_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
s_kobj);
struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
void *ptr = calc_ptr(a, sbi);
switch (a->attr_id) {
case attr_delayed_allocation_blocks:
return snprintf(buf, PAGE_SIZE, "%llu\n",
(s64) EXT4_C2B(sbi,
percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
case attr_session_write_kbytes:
return session_write_kbytes_show(sbi, buf);
case attr_lifetime_write_kbytes:
return lifetime_write_kbytes_show(sbi, buf);
case attr_reserved_clusters:
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)
atomic64_read(&sbi->s_resv_clusters));
ext4: shrink race window in ext4_should_retry_alloc() When generic/371 is run on kvm-xfstests using 5.10 and 5.11 kernels, it fails at significant rates on the two test scenarios that disable delayed allocation (ext3conv and data_journal) and force actual block allocation for the fallocate and pwrite functions in the test. The failure rate on 5.10 for both ext3conv and data_journal on one test system typically runs about 85%. On 5.11, the failure rate on ext3conv sometimes drops to as low as 1% while the rate on data_journal increases to nearly 100%. The observed failures are largely due to ext4_should_retry_alloc() cutting off block allocation retries when s_mb_free_pending (used to indicate that a transaction in progress will free blocks) is 0. However, free space is usually available when this occurs during runs of generic/371. It appears that a thread attempting to allocate blocks is just missing transaction commits in other threads that increase the free cluster count and reset s_mb_free_pending while the allocating thread isn't running. Explicitly testing for free space availability avoids this race. The current code uses a post-increment operator in the conditional expression that determines whether the retry limit has been exceeded. This means that the conditional expression uses the value of the retry counter before it's increased, resulting in an extra retry cycle. The current code actually retries twice before hitting its retry limit rather than once. Increasing the retry limit to 3 from the current actual maximum retry count of 2 in combination with the change described above reduces the observed failure rate to less that 0.1% on both ext3conv and data_journal with what should be limited impact on users sensitive to the overhead caused by retries. A per filesystem percpu counter exported via sysfs is added to allow users or developers to track the number of times the retry limit is exceeded without resorting to debugging methods. This should provide some insight into worst case retry behavior. Signed-off-by: Eric Whitney <enwlinux@gmail.com> Link: https://lore.kernel.org/r/20210218151132.19678-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-02-18 23:11:32 +08:00
case attr_sra_exceeded_retry_limit:
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)
percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit));
case attr_inode_readahead:
case attr_pointer_ui:
if (!ptr)
return 0;
if (a->attr_ptr == ptr_ext4_super_block_offset)
return snprintf(buf, PAGE_SIZE, "%u\n",
le32_to_cpup(ptr));
else
return snprintf(buf, PAGE_SIZE, "%u\n",
*((unsigned int *) ptr));
case attr_pointer_ul:
if (!ptr)
return 0;
return snprintf(buf, PAGE_SIZE, "%lu\n",
*((unsigned long *) ptr));
case attr_pointer_u8:
if (!ptr)
return 0;
return snprintf(buf, PAGE_SIZE, "%u\n",
*((unsigned char *) ptr));
case attr_pointer_u64:
if (!ptr)
return 0;
if (a->attr_ptr == ptr_ext4_super_block_offset)
return snprintf(buf, PAGE_SIZE, "%llu\n",
le64_to_cpup(ptr));
else
return snprintf(buf, PAGE_SIZE, "%llu\n",
*((unsigned long long *) ptr));
case attr_pointer_string:
if (!ptr)
return 0;
return snprintf(buf, PAGE_SIZE, "%.*s\n", a->attr_size,
(char *) ptr);
case attr_pointer_atomic:
if (!ptr)
return 0;
return snprintf(buf, PAGE_SIZE, "%d\n",
atomic_read((atomic_t *) ptr));
case attr_feature:
return snprintf(buf, PAGE_SIZE, "supported\n");
case attr_first_error_time:
return print_tstamp(buf, sbi->s_es, s_first_error_time);
case attr_last_error_time:
return print_tstamp(buf, sbi->s_es, s_last_error_time);
case attr_journal_task:
return journal_task_show(sbi, buf);
}
return 0;
}
static ssize_t ext4_attr_store(struct kobject *kobj,
struct attribute *attr,
const char *buf, size_t len)
{
struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
s_kobj);
struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
void *ptr = calc_ptr(a, sbi);
unsigned long t;
int ret;
switch (a->attr_id) {
case attr_reserved_clusters:
return reserved_clusters_store(sbi, buf, len);
case attr_pointer_ui:
if (!ptr)
return 0;
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret)
return ret;
if (a->attr_ptr == ptr_ext4_super_block_offset)
*((__le32 *) ptr) = cpu_to_le32(t);
else
*((unsigned int *) ptr) = t;
return len;
case attr_pointer_ul:
if (!ptr)
return 0;
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret)
return ret;
*((unsigned long *) ptr) = t;
return len;
case attr_inode_readahead:
return inode_readahead_blks_store(sbi, buf, len);
case attr_trigger_test_error:
return trigger_test_error(sbi, buf, len);
}
return 0;
}
static void ext4_sb_release(struct kobject *kobj)
{
struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
s_kobj);
complete(&sbi->s_kobj_unregister);
}
static const struct sysfs_ops ext4_attr_ops = {
.show = ext4_attr_show,
.store = ext4_attr_store,
};
static struct kobj_type ext4_sb_ktype = {
.default_groups = ext4_groups,
.sysfs_ops = &ext4_attr_ops,
.release = ext4_sb_release,
};
static struct kobj_type ext4_feat_ktype = {
.default_groups = ext4_feat_groups,
.sysfs_ops = &ext4_attr_ops,
.release = (void (*)(struct kobject *))kfree,
};
static struct kobject *ext4_root;
static struct kobject *ext4_feat;
int ext4_register_sysfs(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
int err;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &ext4_sb_ktype, ext4_root,
"%s", sb->s_id);
if (err) {
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
return err;
}
if (ext4_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
if (sbi->s_proc) {
proc_create_single_data("options", S_IRUGO, sbi->s_proc,
ext4_seq_options_show, sb);
proc_create_single_data("es_shrinker_info", S_IRUGO,
sbi->s_proc, ext4_seq_es_shrinker_info_show,
sb);
proc_create_single_data("fc_info", 0444, sbi->s_proc,
ext4_fc_info_show, sb);
proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc,
&ext4_mb_seq_groups_ops, sb);
proc_create_single_data("mb_stats", 0444, sbi->s_proc,
ext4_seq_mb_stats_show, sb);
proc_create_seq_data("mb_structs_summary", 0444, sbi->s_proc,
&ext4_mb_seq_structs_summary_ops, sb);
}
return 0;
}
void ext4_unregister_sysfs(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (sbi->s_proc)
remove_proc_subtree(sb->s_id, ext4_proc_root);
kobject_del(&sbi->s_kobj);
}
int __init ext4_init_sysfs(void)
{
int ret;
ext4_root = kobject_create_and_add("ext4", fs_kobj);
if (!ext4_root)
return -ENOMEM;
ext4_feat = kzalloc(sizeof(*ext4_feat), GFP_KERNEL);
if (!ext4_feat) {
ret = -ENOMEM;
goto root_err;
}
ret = kobject_init_and_add(ext4_feat, &ext4_feat_ktype,
ext4_root, "features");
if (ret)
goto feat_err;
ext4_proc_root = proc_mkdir(proc_dirname, NULL);
return ret;
feat_err:
kobject_put(ext4_feat);
ext4_feat = NULL;
root_err:
kobject_put(ext4_root);
ext4_root = NULL;
return ret;
}
void ext4_exit_sysfs(void)
{
kobject_put(ext4_feat);
ext4_feat = NULL;
kobject_put(ext4_root);
ext4_root = NULL;
remove_proc_entry(proc_dirname, NULL);
ext4_proc_root = NULL;
}