1
0
Files
kernel-49/fs/xfs/libxfs/xfs_trans_resv.c
Greg Kroah-Hartman 3063bf541a Merge 4.9.136 into android-4.9
Also revert commit b91d532928df ("ipv6: set rt6i_protocol properly in
the route when it is installed") as it breaks the test systems.

Changes in 4.9.136
	xfrm: Validate address prefix lengths in the xfrm selector.
	xfrm6: call kfree_skb when skb is toobig
	mac80211: Always report TX status
	cfg80211: reg: Init wiphy_idx in regulatory_hint_core()
	mac80211: fix pending queue hang due to TX_DROP
	cfg80211: Address some corner cases in scan result channel updating
	mac80211: TDLS: fix skb queue/priority assignment
	ARM: 8799/1: mm: fix pci_ioremap_io() offset check
	xfrm: validate template mode
	ARM: dts: BCM63xx: Fix incorrect interrupt specifiers
	net: macb: Clean 64b dma addresses if they are not detected
	soc: fsl: qbman: qman: avoid allocating from non existing gen_pool
	soc: fsl: qe: Fix copy/paste bug in ucc_get_tdm_sync_shift()
	nl80211: Fix possible Spectre-v1 for NL80211_TXRATE_HT
	mac80211_hwsim: do not omit multicast announce of first added radio
	Bluetooth: SMP: fix crash in unpairing
	pxa168fb: prepare the clock
	qed: Avoid implicit enum conversion in qed_roce_mode_to_flavor
	qed: Avoid constant logical operation warning in qed_vf_pf_acquire
	asix: Check for supported Wake-on-LAN modes
	ax88179_178a: Check for supported Wake-on-LAN modes
	lan78xx: Check for supported Wake-on-LAN modes
	sr9800: Check for supported Wake-on-LAN modes
	r8152: Check for supported Wake-on-LAN Modes
	smsc75xx: Check for Wake-on-LAN modes
	smsc95xx: Check for Wake-on-LAN modes
	perf/ring_buffer: Prevent concurent ring buffer access
	perf/x86/intel/uncore: Fix PCI BDF address of M3UPI on SKX
	net: fec: fix rare tx timeout
	declance: Fix continuation with the adapter identification message
	net: cxgb3_main: fix a missing-check bug
	perf symbols: Fix memory corruption because of zero length symbols
	mm/memory_hotplug.c: fix overflow in test_pages_in_a_zone()
	MIPS: microMIPS: Fix decoding of swsp16 instruction
	MIPS: Handle non word sized instructions when examining frame
	scsi: aacraid: Fix typo in blink status
	f2fs: fix multiple f2fs_add_link() having same name for inline dentry
	igb: Remove superfluous reset to PHY and page 0 selection
	ACPI: sysfs: Make ACPI GPE mask kernel parameter cover all GPEs
	PCI: Disable MSI for HiSilicon Hip06/Hip07 only in Root Port mode
	i2c: bcm2835: Avoid possible NULL ptr dereference
	efi/fb: Correct PCI_STD_RESOURCE_END usage
	ipv6: set rt6i_protocol properly in the route when it is installed
	platform/x86: acer-wmi: setup accelerometer when ACPI device was found
	IB/ipoib: Do not warn if IPoIB debugfs doesn't exist
	IB/core: Fix the validations of a multicast LID in attach or detach operations
	orangefs: off by ones in xattr size checks
	rxe: Fix a sleep-in-atomic bug in post_one_send
	nvme-pci: fix CMB sysfs file removal in reset path
	net: phy: marvell: Limit 88m1101 autoneg errata to 88E1145 as well.
	net/mlx5: Fix command completion after timeout access invalid structure
	tipc: Fix tipc_sk_reinit handling of -EAGAIN
	tipc: fix a race condition of releasing subscriber object
	bnxt_en: Don't use rtnl lock to protect link change logic in workqueue.
	ath10k: fix NAPI enable/disable symmetry for AHB interface
	ARM: dts: bcm283x: Reserve first page for firmware
	btrfs: fiemap: Cache and merge fiemap extent before submit it to user
	ata: sata_rcar: Handle return value of clk_prepare_enable
	reset: hi6220: Set module license so that it can be loaded
	ASoC: Intel: Skylake: Fix to parse consecutive string tkns in manifest
	arch/sparc: increase CONFIG_NODES_SHIFT on SPARC64 to 5
	mac80211: fix TX aggregation start/stop callback race
	libata: fix error checking in in ata_parse_force_one()
	net: ethernet: stmmac: Fix altr_tse_pcs SGMII Initialization
	qlcnic: Fix tunnel offload for 82xx adapters
	x86/cpu/cyrix: Add alternative Device ID of Geode GX1 SoC
	ARM: 8677/1: boot/compressed: fix decompressor header layout for v7-M
	gpu: ipu-v3: Fix CSI selection for VDIC
	elevator: fix truncation of icq_cache_name
	net: stmmac: ensure jumbo_frm error return is correctly checked for -ve value
	Btrfs: clear EXTENT_DEFRAG bits in finish_ordered_io
	ufs: we need to sync inode before freeing it
	net/mlx5e: Fix fixpoint divide exception in mlx5e_am_stats_compare
	ip6_tunnel: Correct tos value in collect_md mode
	net/mlx5: Fix driver load error flow when firmware is stuck
	perf evsel: Fix probing of precise_ip level for default cycles event
	perf probe: Fix probe definition for inlined functions
	net/mlx5: Fix health work queue spin lock to IRQ safe
	usb: renesas_usbhs: gadget: fix spin_lock_init() for &uep->lock
	usb: renesas_usbhs: gadget: fix unused-but-set-variable warning
	usb: dwc3: omap: remove IRQ_NOAUTOEN used with shared irq
	clk: samsung: Fix m2m scaler clock on Exynos542x
	ptr_ring: fix up after recent ptr_ring changes
	staging: wilc1000: Fix problem with wrong vif index
	rds: ib: Fix missing call to rds_ib_dev_put in rds_ib_setup_qp
	iio: adc: Revert "axp288: Drop bogus AXP288_ADC_TS_PIN_CTRL register modifications"
	qed: Warn PTT usage by wrong hw-function
	ocfs2: fix deadlock caused by recursive locking in xattr
	net: cdc_ncm: GetNtbFormat endian fix
	sctp: use right member as the param of list_for_each_entry
	ALSA: hda - No loopback on ALC299 codec
	ath10k: convert warning about non-existent OTP board id to debug message
	ipv6: fix cleanup ordering for ip6_mr failure
	IB/ipoib: Fix lockdep issue found on ipoib_ib_dev_heavy_flush
	IB/rxe: put the pool on allocation failure
	nbd: only set MSG_MORE when we have more to send
	mm/frame_vector.c: release a semaphore in 'get_vaddr_frames()'
	IB/mlx5: Avoid passing an invalid QP type to firmware
	scsi: qla2xxx: Avoid double completion of abort command
	drm: bochs: Don't remove uninitialized fbdev framebuffer
	i40e: avoid NVM acquire deadlock during NVM update
	Revert "IB/ipoib: Update broadcast object if PKey value was changed in index 0"
	Btrfs: incremental send, fix invalid memory access
	drm/msm: Fix possible null dereference on failure of get_pages()
	module: fix DEBUG_SET_MODULE_RONX typo
	iio: pressure: zpa2326: Remove always-true check which confuses gcc
	l2tp: remove configurable payload offset
	macsec: fix memory leaks when skb_to_sgvec fails
	perf/core: Fix locking for children siblings group read
	cifs: Use ULL suffix for 64-bit constant
	futex: futex_wake_op, do not fail on invalid op
	ALSA: hda - Fix incorrect usage of IS_REACHABLE()
	test_bpf: Fix testing with CONFIG_BPF_JIT_ALWAYS_ON=y on other arches
	xen-netfront: Update features after registering netdev
	sparc64: Fix regression in pmdp_invalidate().
	xen-netfront: Fix mismatched rtnl_unlock
	enic: do not overwrite error code
	bonding: ratelimit failed speed/duplex update warning
	nvmet: fix space padding in serial number
	iio: buffer: fix the function signature to match implementation
	x86/paravirt: Fix some warning messages
	IB/mlx4: Fix an error handling path in 'mlx4_ib_rereg_user_mr()'
	libertas: call into generic suspend code before turning off power
	xhci: Fix USB3 NULL pointer dereference at logical disconnect.
	perf tests: Fix indexing when invoking subtests
	ARM: dts: imx53-qsb: disable 1.2GHz OPP
	rxrpc: Don't check RXRPC_CALL_TX_LAST after calling rxrpc_rotate_tx_window()
	rxrpc: Only take the rwind and mtu values from latest ACK
	net: ena: fix NULL dereference due to untimely napi initialization
	fs/fat/fatent.c: add cond_resched() to fat_count_free_clusters()
	mtd: spi-nor: Add support for is25wp series chips
	Revert "netfilter: ipv6: nf_defrag: drop skb dst before queueing"
	perf tools: Disable parallelism for 'make clean'
	bridge: do not add port to router list when receives query with source 0.0.0.0
	net: bridge: remove ipv6 zero address check in mcast queries
	ipv6: mcast: fix a use-after-free in inet6_mc_check
	ipv6/ndisc: Preserve IPv6 control buffer if protocol error handlers are called
	llc: set SOCK_RCU_FREE in llc_sap_add_socket()
	net/ipv6: Fix index counter for unicast addresses in in6_dump_addrs
	net: sched: gred: pass the right attribute to gred_change_table_def()
	net: socket: fix a missing-check bug
	net: stmmac: Fix stmmac_mdio_reset() when building stmmac as modules
	net: udp: fix handling of CHECKSUM_COMPLETE packets
	r8169: fix NAPI handling under high load
	sctp: fix race on sctp_id2asoc
	vhost: Fix Spectre V1 vulnerability
	ethtool: fix a privilege escalation bug
	bonding: fix length of actor system
	net: drop skb on failure in ip_check_defrag()
	net: fix pskb_trim_rcsum_slow() with odd trim offset
	rtnetlink: Disallow FDB configuration for non-Ethernet device
	ip6_tunnel: Fix encapsulation layout
	Revert "x86/mm: Expand static page table for fixmap space"
	crypto: shash - Fix a sleep-in-atomic bug in shash_setkey_unaligned
	ahci: don't ignore result code of ahci_reset_controller()
	gpio: mxs: Get rid of external API call
	xfs: truncate transaction does not modify the inobt
	cachefiles: fix the race between cachefiles_bury_object() and rmdir(2)
	ptp: fix Spectre v1 vulnerability
	drm/edid: Add 6 bpc quirk for BOE panel in HP Pavilion 15-n233sl
	RDMA/ucma: Fix Spectre v1 vulnerability
	IB/ucm: Fix Spectre v1 vulnerability
	cdc-acm: correct counting of UART states in serial state notification
	usb: gadget: storage: Fix Spectre v1 vulnerability
	USB: fix the usbfs flag sanitization for control transfers
	Input: elan_i2c - add ACPI ID for Lenovo IdeaPad 330-15IGM
	sched/fair: Fix throttle_list starvation with low CFS quota
	x86/percpu: Fix this_cpu_read()
	x86/time: Correct the attribute on jiffies' definition
	net: fs_enet: do not call phy_stop() in interrupts
	posix-timers: Sanitize overrun handling
	Linux 4.9.136

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2019-02-11 22:51:32 +03:00

909 lines
29 KiB
C

/*
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
* Copyright (C) 2010 Red Hat, Inc.
* All Rights Reserved.
*
* 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.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_bmap_btree.h"
#include "xfs_ialloc.h"
#include "xfs_quota.h"
#include "xfs_trans.h"
#include "xfs_qm.h"
#include "xfs_trans_space.h"
#include "xfs_trace.h"
/*
* A buffer has a format structure overhead in the log in addition
* to the data, so we need to take this into account when reserving
* space in a transaction for a buffer. Round the space required up
* to a multiple of 128 bytes so that we don't change the historical
* reservation that has been used for this overhead.
*/
STATIC uint
xfs_buf_log_overhead(void)
{
return round_up(sizeof(struct xlog_op_header) +
sizeof(struct xfs_buf_log_format), 128);
}
/*
* Calculate out transaction log reservation per item in bytes.
*
* The nbufs argument is used to indicate the number of items that
* will be changed in a transaction. size is used to tell how many
* bytes should be reserved per item.
*/
STATIC uint
xfs_calc_buf_res(
uint nbufs,
uint size)
{
return nbufs * (size + xfs_buf_log_overhead());
}
/*
* Per-extent log reservation for the btree changes involved in freeing or
* allocating an extent. In classic XFS there were two trees that will be
* modified (bnobt + cntbt). With rmap enabled, there are three trees
* (rmapbt). With reflink, there are four trees (refcountbt). The number of
* blocks reserved is based on the formula:
*
* num trees * ((2 blocks/level * max depth) - 1)
*
* Keep in mind that max depth is calculated separately for each type of tree.
*/
uint
xfs_allocfree_log_count(
struct xfs_mount *mp,
uint num_ops)
{
uint blocks;
blocks = num_ops * 2 * (2 * mp->m_ag_maxlevels - 1);
if (xfs_sb_version_hasrmapbt(&mp->m_sb))
blocks += num_ops * (2 * mp->m_rmap_maxlevels - 1);
if (xfs_sb_version_hasreflink(&mp->m_sb))
blocks += num_ops * (2 * mp->m_refc_maxlevels - 1);
return blocks;
}
/*
* Logging inodes is really tricksy. They are logged in memory format,
* which means that what we write into the log doesn't directly translate into
* the amount of space they use on disk.
*
* Case in point - btree format forks in memory format use more space than the
* on-disk format. In memory, the buffer contains a normal btree block header so
* the btree code can treat it as though it is just another generic buffer.
* However, when we write it to the inode fork, we don't write all of this
* header as it isn't needed. e.g. the root is only ever in the inode, so
* there's no need for sibling pointers which would waste 16 bytes of space.
*
* Hence when we have an inode with a maximally sized btree format fork, then
* amount of information we actually log is greater than the size of the inode
* on disk. Hence we need an inode reservation function that calculates all this
* correctly. So, we log:
*
* - 4 log op headers for object
* - for the ilf, the inode core and 2 forks
* - inode log format object
* - the inode core
* - two inode forks containing bmap btree root blocks.
* - the btree data contained by both forks will fit into the inode size,
* hence when combined with the inode core above, we have a total of the
* actual inode size.
* - the BMBT headers need to be accounted separately, as they are
* additional to the records and pointers that fit inside the inode
* forks.
*/
STATIC uint
xfs_calc_inode_res(
struct xfs_mount *mp,
uint ninodes)
{
return ninodes *
(4 * sizeof(struct xlog_op_header) +
sizeof(struct xfs_inode_log_format) +
mp->m_sb.sb_inodesize +
2 * XFS_BMBT_BLOCK_LEN(mp));
}
/*
* The free inode btree is a conditional feature and the log reservation
* requirements differ slightly from that of the traditional inode allocation
* btree. The finobt tracks records for inode chunks with at least one free
* inode. A record can be removed from the tree for an inode allocation
* or free and thus the finobt reservation is unconditional across:
*
* - inode allocation
* - inode free
* - inode chunk allocation
*
* The 'modify' param indicates to include the record modification scenario. The
* 'alloc' param indicates to include the reservation for free space btree
* modifications on behalf of finobt modifications. This is required only for
* transactions that do not already account for free space btree modifications.
*
* the free inode btree: max depth * block size
* the allocation btrees: 2 trees * (max depth - 1) * block size
* the free inode btree entry: block size
*/
STATIC uint
xfs_calc_finobt_res(
struct xfs_mount *mp,
int alloc,
int modify)
{
uint res;
if (!xfs_sb_version_hasfinobt(&mp->m_sb))
return 0;
res = xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1));
if (alloc)
res += xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
if (modify)
res += (uint)XFS_FSB_TO_B(mp, 1);
return res;
}
/*
* Various log reservation values.
*
* These are based on the size of the file system block because that is what
* most transactions manipulate. Each adds in an additional 128 bytes per
* item logged to try to account for the overhead of the transaction mechanism.
*
* Note: Most of the reservations underestimate the number of allocation
* groups into which they could free extents in the xfs_defer_finish() call.
* This is because the number in the worst case is quite high and quite
* unusual. In order to fix this we need to change xfs_defer_finish() to free
* extents in only a single AG at a time. This will require changes to the
* EFI code as well, however, so that the EFI for the extents not freed is
* logged again in each transaction. See SGI PV #261917.
*
* Reservation functions here avoid a huge stack in xfs_trans_init due to
* register overflow from temporaries in the calculations.
*/
/*
* In a write transaction we can allocate a maximum of 2
* extents. This gives:
* the inode getting the new extents: inode size
* the inode's bmap btree: max depth * block size
* the agfs of the ags from which the extents are allocated: 2 * sector
* the superblock free block counter: sector size
* the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
* And the bmap_finish transaction can free bmap blocks in a join:
* the agfs of the ags containing the blocks: 2 * sector size
* the agfls of the ags containing the blocks: 2 * sector size
* the super block free block counter: sector size
* the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_write_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2),
XFS_FSB_TO_B(mp, 1))));
}
/*
* In truncating a file we free up to two extents at once. We can modify:
* the inode being truncated: inode size
* the inode's bmap btree: (max depth + 1) * block size
* And the bmap_finish transaction can free the blocks and bmap blocks:
* the agf for each of the ags: 4 * sector size
* the agfl for each of the ags: 4 * sector size
* the super block to reflect the freed blocks: sector size
* worst case split in allocation btrees per extent assuming 4 extents:
* 4 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_itruncate_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1,
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4),
XFS_FSB_TO_B(mp, 1))));
}
/*
* In renaming a files we can modify:
* the four inodes involved: 4 * inode size
* the two directory btrees: 2 * (max depth + v2) * dir block size
* the two directory bmap btrees: 2 * max depth * block size
* And the bmap_finish transaction can free dir and bmap blocks (two sets
* of bmap blocks) giving:
* the agf for the ags in which the blocks live: 3 * sector size
* the agfl for the ags in which the blocks live: 3 * sector size
* the superblock for the free block count: sector size
* the allocation btrees: 3 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_rename_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX((xfs_calc_inode_res(mp, 4) +
xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 3),
XFS_FSB_TO_B(mp, 1))));
}
/*
* For removing an inode from unlinked list at first, we can modify:
* the agi hash list and counters: sector size
* the on disk inode before ours in the agi hash list: inode cluster size
*/
STATIC uint
xfs_calc_iunlink_remove_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
max_t(uint, XFS_FSB_TO_B(mp, 1), mp->m_inode_cluster_size);
}
/*
* For creating a link to an inode:
* the parent directory inode: inode size
* the linked inode: inode size
* the directory btree could split: (max depth + v2) * dir block size
* the directory bmap btree could join or split: (max depth + v2) * blocksize
* And the bmap_finish transaction can free some bmap blocks giving:
* the agf for the ag in which the blocks live: sector size
* the agfl for the ag in which the blocks live: sector size
* the superblock for the free block count: sector size
* the allocation btrees: 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_link_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_iunlink_remove_reservation(mp) +
MAX((xfs_calc_inode_res(mp, 2) +
xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1))));
}
/*
* For adding an inode to unlinked list we can modify:
* the agi hash list: sector size
* the unlinked inode: inode size
*/
STATIC uint
xfs_calc_iunlink_add_reservation(xfs_mount_t *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_inode_res(mp, 1);
}
/*
* For removing a directory entry we can modify:
* the parent directory inode: inode size
* the removed inode: inode size
* the directory btree could join: (max depth + v2) * dir block size
* the directory bmap btree could join or split: (max depth + v2) * blocksize
* And the bmap_finish transaction can free the dir and bmap blocks giving:
* the agf for the ag in which the blocks live: 2 * sector size
* the agfl for the ag in which the blocks live: 2 * sector size
* the superblock for the free block count: sector size
* the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_remove_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_iunlink_add_reservation(mp) +
MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2),
XFS_FSB_TO_B(mp, 1))));
}
/*
* For create, break it in to the two cases that the transaction
* covers. We start with the modify case - allocation done by modification
* of the state of existing inodes - and the allocation case.
*/
/*
* For create we can modify:
* the parent directory inode: inode size
* the new inode: inode size
* the inode btree entry: block size
* the superblock for the nlink flag: sector size
* the directory btree: (max depth + v2) * dir block size
* the directory inode's bmap btree: (max depth + v2) * block size
* the finobt (record modification and allocation btrees)
*/
STATIC uint
xfs_calc_create_resv_modify(
struct xfs_mount *mp)
{
return xfs_calc_inode_res(mp, 2) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
(uint)XFS_FSB_TO_B(mp, 1) +
xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)) +
xfs_calc_finobt_res(mp, 1, 1);
}
/*
* For create we can allocate some inodes giving:
* the agi and agf of the ag getting the new inodes: 2 * sectorsize
* the superblock for the nlink flag: sector size
* the inode blocks allocated: mp->m_ialloc_blks * blocksize
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
*/
STATIC uint
xfs_calc_create_resv_alloc(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
mp->m_sb.sb_sectsize +
xfs_calc_buf_res(mp->m_ialloc_blks, XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
STATIC uint
__xfs_calc_create_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX(xfs_calc_create_resv_alloc(mp),
xfs_calc_create_resv_modify(mp));
}
/*
* For icreate we can allocate some inodes giving:
* the agi and agf of the ag getting the new inodes: 2 * sectorsize
* the superblock for the nlink flag: sector size
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
* the finobt (record insertion)
*/
STATIC uint
xfs_calc_icreate_resv_alloc(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
mp->m_sb.sb_sectsize +
xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_finobt_res(mp, 0, 0);
}
STATIC uint
xfs_calc_icreate_reservation(xfs_mount_t *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX(xfs_calc_icreate_resv_alloc(mp),
xfs_calc_create_resv_modify(mp));
}
STATIC uint
xfs_calc_create_reservation(
struct xfs_mount *mp)
{
if (xfs_sb_version_hascrc(&mp->m_sb))
return xfs_calc_icreate_reservation(mp);
return __xfs_calc_create_reservation(mp);
}
STATIC uint
xfs_calc_create_tmpfile_reservation(
struct xfs_mount *mp)
{
uint res = XFS_DQUOT_LOGRES(mp);
if (xfs_sb_version_hascrc(&mp->m_sb))
res += xfs_calc_icreate_resv_alloc(mp);
else
res += xfs_calc_create_resv_alloc(mp);
return res + xfs_calc_iunlink_add_reservation(mp);
}
/*
* Making a new directory is the same as creating a new file.
*/
STATIC uint
xfs_calc_mkdir_reservation(
struct xfs_mount *mp)
{
return xfs_calc_create_reservation(mp);
}
/*
* Making a new symplink is the same as creating a new file, but
* with the added blocks for remote symlink data which can be up to 1kB in
* length (MAXPATHLEN).
*/
STATIC uint
xfs_calc_symlink_reservation(
struct xfs_mount *mp)
{
return xfs_calc_create_reservation(mp) +
xfs_calc_buf_res(1, MAXPATHLEN);
}
/*
* In freeing an inode we can modify:
* the inode being freed: inode size
* the super block free inode counter: sector size
* the agi hash list and counters: sector size
* the inode btree entry: block size
* the on disk inode before ours in the agi hash list: inode cluster size
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
* the finobt (record insertion, removal or modification)
*/
STATIC uint
xfs_calc_ifree_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
xfs_calc_iunlink_remove_reservation(mp) +
xfs_calc_buf_res(1, 0) +
xfs_calc_buf_res(2 + mp->m_ialloc_blks +
mp->m_in_maxlevels, 0) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_finobt_res(mp, 0, 1);
}
/*
* When only changing the inode we log the inode and possibly the superblock
* We also add a bit of slop for the transaction stuff.
*/
STATIC uint
xfs_calc_ichange_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
}
/*
* Growing the data section of the filesystem.
* superblock
* agi and agf
* allocation btrees
*/
STATIC uint
xfs_calc_growdata_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
/*
* Growing the rt section of the filesystem.
* In the first set of transactions (ALLOC) we allocate space to the
* bitmap or summary files.
* superblock: sector size
* agf of the ag from which the extent is allocated: sector size
* bmap btree for bitmap/summary inode: max depth * blocksize
* bitmap/summary inode: inode size
* allocation btrees for 1 block alloc: 2 * (2 * maxdepth - 1) * blocksize
*/
STATIC uint
xfs_calc_growrtalloc_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
/*
* Growing the rt section of the filesystem.
* In the second set of transactions (ZERO) we zero the new metadata blocks.
* one bitmap/summary block: blocksize
*/
STATIC uint
xfs_calc_growrtzero_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_blocksize);
}
/*
* Growing the rt section of the filesystem.
* In the third set of transactions (FREE) we update metadata without
* allocating any new blocks.
* superblock: sector size
* bitmap inode: inode size
* summary inode: inode size
* one bitmap block: blocksize
* summary blocks: new summary size
*/
STATIC uint
xfs_calc_growrtfree_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_inode_res(mp, 2) +
xfs_calc_buf_res(1, mp->m_sb.sb_blocksize) +
xfs_calc_buf_res(1, mp->m_rsumsize);
}
/*
* Logging the inode modification timestamp on a synchronous write.
* inode
*/
STATIC uint
xfs_calc_swrite_reservation(
struct xfs_mount *mp)
{
return xfs_calc_inode_res(mp, 1);
}
/*
* Logging the inode mode bits when writing a setuid/setgid file
* inode
*/
STATIC uint
xfs_calc_writeid_reservation(
struct xfs_mount *mp)
{
return xfs_calc_inode_res(mp, 1);
}
/*
* Converting the inode from non-attributed to attributed.
* the inode being converted: inode size
* agf block and superblock (for block allocation)
* the new block (directory sized)
* bmap blocks for the new directory block
* allocation btrees
*/
STATIC uint
xfs_calc_addafork_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(1, mp->m_dir_geo->blksize) +
xfs_calc_buf_res(XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1,
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
/*
* Removing the attribute fork of a file
* the inode being truncated: inode size
* the inode's bmap btree: max depth * block size
* And the bmap_finish transaction can free the blocks and bmap blocks:
* the agf for each of the ags: 4 * sector size
* the agfl for each of the ags: 4 * sector size
* the super block to reflect the freed blocks: sector size
* worst case split in allocation btrees per extent assuming 4 extents:
* 4 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_attrinval_reservation(
struct xfs_mount *mp)
{
return MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4),
XFS_FSB_TO_B(mp, 1))));
}
/*
* Setting an attribute at mount time.
* the inode getting the attribute
* the superblock for allocations
* the agfs extents are allocated from
* the attribute btree * max depth
* the inode allocation btree
* Since attribute transaction space is dependent on the size of the attribute,
* the calculation is done partially at mount time and partially at runtime(see
* below).
*/
STATIC uint
xfs_calc_attrsetm_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1));
}
/*
* Setting an attribute at runtime, transaction space unit per block.
* the superblock for allocations: sector size
* the inode bmap btree could join or split: max depth * block size
* Since the runtime attribute transaction space is dependent on the total
* blocks needed for the 1st bmap, here we calculate out the space unit for
* one block so that the caller could figure out the total space according
* to the attibute extent length in blocks by:
* ext * M_RES(mp)->tr_attrsetrt.tr_logres
*/
STATIC uint
xfs_calc_attrsetrt_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
XFS_FSB_TO_B(mp, 1));
}
/*
* Removing an attribute.
* the inode: inode size
* the attribute btree could join: max depth * block size
* the inode bmap btree could join or split: max depth * block size
* And the bmap_finish transaction can free the attr blocks freed giving:
* the agf for the ag in which the blocks live: 2 * sector size
* the agfl for the ag in which the blocks live: 2 * sector size
* the superblock for the free block count: sector size
* the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_attrrm_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH,
XFS_FSB_TO_B(mp, 1)) +
(uint)XFS_FSB_TO_B(mp,
XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK)) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), 0)),
(xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2),
XFS_FSB_TO_B(mp, 1))));
}
/*
* Clearing a bad agino number in an agi hash bucket.
*/
STATIC uint
xfs_calc_clear_agi_bucket_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
}
/*
* Adjusting quota limits.
* the xfs_disk_dquot_t: sizeof(struct xfs_disk_dquot)
*/
STATIC uint
xfs_calc_qm_setqlim_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, sizeof(struct xfs_disk_dquot));
}
/*
* Allocating quota on disk if needed.
* the write transaction log space for quota file extent allocation
* the unit of quota allocation: one system block size
*/
STATIC uint
xfs_calc_qm_dqalloc_reservation(
struct xfs_mount *mp)
{
return xfs_calc_write_reservation(mp) +
xfs_calc_buf_res(1,
XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) - 1);
}
/*
* Turning off quotas.
* the xfs_qoff_logitem_t: sizeof(struct xfs_qoff_logitem) * 2
* the superblock for the quota flags: sector size
*/
STATIC uint
xfs_calc_qm_quotaoff_reservation(
struct xfs_mount *mp)
{
return sizeof(struct xfs_qoff_logitem) * 2 +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
}
/*
* End of turning off quotas.
* the xfs_qoff_logitem_t: sizeof(struct xfs_qoff_logitem) * 2
*/
STATIC uint
xfs_calc_qm_quotaoff_end_reservation(
struct xfs_mount *mp)
{
return sizeof(struct xfs_qoff_logitem) * 2;
}
/*
* Syncing the incore super block changes to disk.
* the super block to reflect the changes: sector size
*/
STATIC uint
xfs_calc_sb_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
}
void
xfs_trans_resv_calc(
struct xfs_mount *mp,
struct xfs_trans_resv *resp)
{
/*
* The following transactions are logged in physical format and
* require a permanent reservation on space.
*/
resp->tr_write.tr_logres = xfs_calc_write_reservation(mp);
if (xfs_sb_version_hasreflink(&mp->m_sb))
resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT_REFLINK;
else
resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT;
resp->tr_write.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_itruncate.tr_logres = xfs_calc_itruncate_reservation(mp);
if (xfs_sb_version_hasreflink(&mp->m_sb))
resp->tr_itruncate.tr_logcount =
XFS_ITRUNCATE_LOG_COUNT_REFLINK;
else
resp->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT;
resp->tr_itruncate.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_rename.tr_logres = xfs_calc_rename_reservation(mp);
resp->tr_rename.tr_logcount = XFS_RENAME_LOG_COUNT;
resp->tr_rename.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_link.tr_logres = xfs_calc_link_reservation(mp);
resp->tr_link.tr_logcount = XFS_LINK_LOG_COUNT;
resp->tr_link.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_remove.tr_logres = xfs_calc_remove_reservation(mp);
resp->tr_remove.tr_logcount = XFS_REMOVE_LOG_COUNT;
resp->tr_remove.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_symlink.tr_logres = xfs_calc_symlink_reservation(mp);
resp->tr_symlink.tr_logcount = XFS_SYMLINK_LOG_COUNT;
resp->tr_symlink.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_create.tr_logres = xfs_calc_create_reservation(mp);
resp->tr_create.tr_logcount = XFS_CREATE_LOG_COUNT;
resp->tr_create.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_create_tmpfile.tr_logres =
xfs_calc_create_tmpfile_reservation(mp);
resp->tr_create_tmpfile.tr_logcount = XFS_CREATE_TMPFILE_LOG_COUNT;
resp->tr_create_tmpfile.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_mkdir.tr_logres = xfs_calc_mkdir_reservation(mp);
resp->tr_mkdir.tr_logcount = XFS_MKDIR_LOG_COUNT;
resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_ifree.tr_logres = xfs_calc_ifree_reservation(mp);
resp->tr_ifree.tr_logcount = XFS_INACTIVE_LOG_COUNT;
resp->tr_ifree.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_addafork.tr_logres = xfs_calc_addafork_reservation(mp);
resp->tr_addafork.tr_logcount = XFS_ADDAFORK_LOG_COUNT;
resp->tr_addafork.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_attrinval.tr_logres = xfs_calc_attrinval_reservation(mp);
resp->tr_attrinval.tr_logcount = XFS_ATTRINVAL_LOG_COUNT;
resp->tr_attrinval.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_attrsetm.tr_logres = xfs_calc_attrsetm_reservation(mp);
resp->tr_attrsetm.tr_logcount = XFS_ATTRSET_LOG_COUNT;
resp->tr_attrsetm.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_attrrm.tr_logres = xfs_calc_attrrm_reservation(mp);
resp->tr_attrrm.tr_logcount = XFS_ATTRRM_LOG_COUNT;
resp->tr_attrrm.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_growrtalloc.tr_logres = xfs_calc_growrtalloc_reservation(mp);
resp->tr_growrtalloc.tr_logcount = XFS_DEFAULT_PERM_LOG_COUNT;
resp->tr_growrtalloc.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_qm_dqalloc.tr_logres = xfs_calc_qm_dqalloc_reservation(mp);
if (xfs_sb_version_hasreflink(&mp->m_sb))
resp->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT_REFLINK;
else
resp->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT;
resp->tr_qm_dqalloc.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
/*
* The following transactions are logged in logical format with
* a default log count.
*/
resp->tr_qm_setqlim.tr_logres = xfs_calc_qm_setqlim_reservation(mp);
resp->tr_qm_setqlim.tr_logcount = XFS_DEFAULT_LOG_COUNT;
resp->tr_qm_quotaoff.tr_logres = xfs_calc_qm_quotaoff_reservation(mp);
resp->tr_qm_quotaoff.tr_logcount = XFS_DEFAULT_LOG_COUNT;
resp->tr_qm_equotaoff.tr_logres =
xfs_calc_qm_quotaoff_end_reservation(mp);
resp->tr_qm_equotaoff.tr_logcount = XFS_DEFAULT_LOG_COUNT;
resp->tr_sb.tr_logres = xfs_calc_sb_reservation(mp);
resp->tr_sb.tr_logcount = XFS_DEFAULT_LOG_COUNT;
/* The following transaction are logged in logical format */
resp->tr_ichange.tr_logres = xfs_calc_ichange_reservation(mp);
resp->tr_growdata.tr_logres = xfs_calc_growdata_reservation(mp);
resp->tr_fsyncts.tr_logres = xfs_calc_swrite_reservation(mp);
resp->tr_writeid.tr_logres = xfs_calc_writeid_reservation(mp);
resp->tr_attrsetrt.tr_logres = xfs_calc_attrsetrt_reservation(mp);
resp->tr_clearagi.tr_logres = xfs_calc_clear_agi_bucket_reservation(mp);
resp->tr_growrtzero.tr_logres = xfs_calc_growrtzero_reservation(mp);
resp->tr_growrtfree.tr_logres = xfs_calc_growrtfree_reservation(mp);
}