diff options
author | 2023-02-21 18:24:12 -0800 | |
---|---|---|
committer | 2023-02-21 18:24:12 -0800 | |
commit | 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch) | |
tree | cc5c2d0a898769fd59549594fedb3ee6f84e59a0 /fs/xfs/xfs_trans_dquot.c | |
download | linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip |
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski:
"Core:
- Add dedicated kmem_cache for typical/small skb->head, avoid having
to access struct page at kfree time, and improve memory use.
- Introduce sysctl to set default RPS configuration for new netdevs.
- Define Netlink protocol specification format which can be used to
describe messages used by each family and auto-generate parsers.
Add tools for generating kernel data structures and uAPI headers.
- Expose all net/core sysctls inside netns.
- Remove 4s sleep in netpoll if carrier is instantly detected on
boot.
- Add configurable limit of MDB entries per port, and port-vlan.
- Continue populating drop reasons throughout the stack.
- Retire a handful of legacy Qdiscs and classifiers.
Protocols:
- Support IPv4 big TCP (TSO frames larger than 64kB).
- Add IP_LOCAL_PORT_RANGE socket option, to control local port range
on socket by socket basis.
- Track and report in procfs number of MPTCP sockets used.
- Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
manager.
- IPv6: don't check net.ipv6.route.max_size and rely on garbage
collection to free memory (similarly to IPv4).
- Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).
- ICMP: add per-rate limit counters.
- Add support for user scanning requests in ieee802154.
- Remove static WEP support.
- Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
reporting.
- WiFi 7 EHT channel puncturing support (client & AP).
BPF:
- Add a rbtree data structure following the "next-gen data structure"
precedent set by recently added linked list, that is, by using
kfunc + kptr instead of adding a new BPF map type.
- Expose XDP hints via kfuncs with initial support for RX hash and
timestamp metadata.
- Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
better support decap on GRE tunnel devices not operating in collect
metadata.
- Improve x86 JIT's codegen for PROBE_MEM runtime error checks.
- Remove the need for trace_printk_lock for bpf_trace_printk and
bpf_trace_vprintk helpers.
- Extend libbpf's bpf_tracing.h support for tracing arguments of
kprobes/uprobes and syscall as a special case.
- Significantly reduce the search time for module symbols by
livepatch and BPF.
- Enable cpumasks to be used as kptrs, which is useful for tracing
programs tracking which tasks end up running on which CPUs in
different time intervals.
- Add support for BPF trampoline on s390x and riscv64.
- Add capability to export the XDP features supported by the NIC.
- Add __bpf_kfunc tag for marking kernel functions as kfuncs.
- Add cgroup.memory=nobpf kernel parameter option to disable BPF
memory accounting for container environments.
Netfilter:
- Remove the CLUSTERIP target. It has been marked as obsolete for
years, and we still have WARN splats wrt races of the out-of-band
/proc interface installed by this target.
- Add 'destroy' commands to nf_tables. They are identical to the
existing 'delete' commands, but do not return an error if the
referenced object (set, chain, rule...) did not exist.
Driver API:
- Improve cpumask_local_spread() locality to help NICs set the right
IRQ affinity on AMD platforms.
- Separate C22 and C45 MDIO bus transactions more clearly.
- Introduce new DCB table to control DSCP rewrite on egress.
- Support configuration of Physical Layer Collision Avoidance (PLCA)
Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
shared medium Ethernet.
- Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
preemption of low priority frames by high priority frames.
- Add support for controlling MACSec offload using netlink SET.
- Rework devlink instance refcounts to allow registration and
de-registration under the instance lock. Split the code into
multiple files, drop some of the unnecessarily granular locks and
factor out common parts of netlink operation handling.
- Add TX frame aggregation parameters (for USB drivers).
- Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
messages with notifications for debug.
- Allow offloading of UDP NEW connections via act_ct.
- Add support for per action HW stats in TC.
- Support hardware miss to TC action (continue processing in SW from
a specific point in the action chain).
- Warn if old Wireless Extension user space interface is used with
modern cfg80211/mac80211 drivers. Do not support Wireless
Extensions for Wi-Fi 7 devices at all. Everyone should switch to
using nl80211 interface instead.
- Improve the CAN bit timing configuration. Use extack to return
error messages directly to user space, update the SJW handling,
including the definition of a new default value that will benefit
CAN-FD controllers, by increasing their oscillator tolerance.
New hardware / drivers:
- Ethernet:
- nVidia BlueField-3 support (control traffic driver)
- Ethernet support for imx93 SoCs
- Motorcomm yt8531 gigabit Ethernet PHY
- onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
- Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
- Amlogic gxl MDIO mux
- WiFi:
- RealTek RTL8188EU (rtl8xxxu)
- Qualcomm Wi-Fi 7 devices (ath12k)
- CAN:
- Renesas R-Car V4H
Drivers:
- Bluetooth:
- Set Per Platform Antenna Gain (PPAG) for Intel controllers.
- Ethernet NICs:
- Intel (1G, igc):
- support TSN / Qbv / packet scheduling features of i226 model
- Intel (100G, ice):
- use GNSS subsystem instead of TTY
- multi-buffer XDP support
- extend support for GPIO pins to E823 devices
- nVidia/Mellanox:
- update the shared buffer configuration on PFC commands
- implement PTP adjphase function for HW offset control
- TC support for Geneve and GRE with VF tunnel offload
- more efficient crypto key management method
- multi-port eswitch support
- Netronome/Corigine:
- add DCB IEEE support
- support IPsec offloading for NFP3800
- Freescale/NXP (enetc):
- support XDP_REDIRECT for XDP non-linear buffers
- improve reconfig, avoid link flap and waiting for idle
- support MAC Merge layer
- Other NICs:
- sfc/ef100: add basic devlink support for ef100
- ionic: rx_push mode operation (writing descriptors via MMIO)
- bnxt: use the auxiliary bus abstraction for RDMA
- r8169: disable ASPM and reset bus in case of tx timeout
- cpsw: support QSGMII mode for J721e CPSW9G
- cpts: support pulse-per-second output
- ngbe: add an mdio bus driver
- usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
- r8152: handle devices with FW with NCM support
- amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
- virtio-net: support multi buffer XDP
- virtio/vsock: replace virtio_vsock_pkt with sk_buff
- tsnep: XDP support
- Ethernet high-speed switches:
- nVidia/Mellanox (mlxsw):
- add support for latency TLV (in FW control messages)
- Microchip (sparx5):
- separate explicit and implicit traffic forwarding rules, make
the implicit rules always active
- add support for egress DSCP rewrite
- IS0 VCAP support (Ingress Classification)
- IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
etc.)
- ES2 VCAP support (Egress Access Control)
- support for Per-Stream Filtering and Policing (802.1Q,
8.6.5.1)
- Ethernet embedded switches:
- Marvell (mv88e6xxx):
- add MAB (port auth) offload support
- enable PTP receive for mv88e6390
- NXP (ocelot):
- support MAC Merge layer
- support for the the vsc7512 internal copper phys
- Microchip:
- lan9303: convert to PHYLINK
- lan966x: support TC flower filter statistics
- lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
- lan937x: support Credit Based Shaper configuration
- ksz9477: support Energy Efficient Ethernet
- other:
- qca8k: convert to regmap read/write API, use bulk operations
- rswitch: Improve TX timestamp accuracy
- Intel WiFi (iwlwifi):
- EHT (Wi-Fi 7) rate reporting
- STEP equalizer support: transfer some STEP (connection to radio
on platforms with integrated wifi) related parameters from the
BIOS to the firmware.
- Qualcomm 802.11ax WiFi (ath11k):
- IPQ5018 support
- Fine Timing Measurement (FTM) responder role support
- channel 177 support
- MediaTek WiFi (mt76):
- per-PHY LED support
- mt7996: EHT (Wi-Fi 7) support
- Wireless Ethernet Dispatch (WED) reset support
- switch to using page pool allocator
- RealTek WiFi (rtw89):
- support new version of Bluetooth co-existance
- Mobile:
- rmnet: support TX aggregation"
* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
page_pool: add a comment explaining the fragment counter usage
net: ethtool: fix __ethtool_dev_mm_supported() implementation
ethtool: pse-pd: Fix double word in comments
xsk: add linux/vmalloc.h to xsk.c
sefltests: netdevsim: wait for devlink instance after netns removal
selftest: fib_tests: Always cleanup before exit
net/mlx5e: Align IPsec ASO result memory to be as required by hardware
net/mlx5e: TC, Set CT miss to the specific ct action instance
net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
net/mlx5: Refactor tc miss handling to a single function
net/mlx5: Kconfig: Make tc offload depend on tc skb extension
net/sched: flower: Support hardware miss to tc action
net/sched: flower: Move filter handle initialization earlier
net/sched: cls_api: Support hardware miss to tc action
net/sched: Rename user cookie and act cookie
sfc: fix builds without CONFIG_RTC_LIB
sfc: clean up some inconsistent indentings
net/mlx4_en: Introduce flexible array to silence overflow warning
net: lan966x: Fix possible deadlock inside PTP
net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
...
Diffstat (limited to 'fs/xfs/xfs_trans_dquot.c')
-rw-r--r-- | fs/xfs/xfs_trans_dquot.c | 859 |
1 files changed, 859 insertions, 0 deletions
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c new file mode 100644 index 000000000..aa00cf67a --- /dev/null +++ b/fs/xfs/xfs_trans_dquot.c @@ -0,0 +1,859 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000-2002 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#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_inode.h" +#include "xfs_trans.h" +#include "xfs_trans_priv.h" +#include "xfs_quota.h" +#include "xfs_qm.h" +#include "xfs_trace.h" +#include "xfs_error.h" + +STATIC void xfs_trans_alloc_dqinfo(xfs_trans_t *); + +/* + * Add the locked dquot to the transaction. + * The dquot must be locked, and it cannot be associated with any + * transaction. + */ +void +xfs_trans_dqjoin( + struct xfs_trans *tp, + struct xfs_dquot *dqp) +{ + ASSERT(XFS_DQ_IS_LOCKED(dqp)); + ASSERT(dqp->q_logitem.qli_dquot == dqp); + + /* + * Get a log_item_desc to point at the new item. + */ + xfs_trans_add_item(tp, &dqp->q_logitem.qli_item); +} + +/* + * This is called to mark the dquot as needing + * to be logged when the transaction is committed. The dquot must + * already be associated with the given transaction. + * Note that it marks the entire transaction as dirty. In the ordinary + * case, this gets called via xfs_trans_commit, after the transaction + * is already dirty. However, there's nothing stop this from getting + * called directly, as done by xfs_qm_scall_setqlim. Hence, the TRANS_DIRTY + * flag. + */ +void +xfs_trans_log_dquot( + struct xfs_trans *tp, + struct xfs_dquot *dqp) +{ + ASSERT(XFS_DQ_IS_LOCKED(dqp)); + + /* Upgrade the dquot to bigtime format if possible. */ + if (dqp->q_id != 0 && + xfs_has_bigtime(tp->t_mountp) && + !(dqp->q_type & XFS_DQTYPE_BIGTIME)) + dqp->q_type |= XFS_DQTYPE_BIGTIME; + + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &dqp->q_logitem.qli_item.li_flags); +} + +/* + * Carry forward whatever is left of the quota blk reservation to + * the spanky new transaction + */ +void +xfs_trans_dup_dqinfo( + struct xfs_trans *otp, + struct xfs_trans *ntp) +{ + struct xfs_dqtrx *oq, *nq; + int i, j; + struct xfs_dqtrx *oqa, *nqa; + uint64_t blk_res_used; + + if (!otp->t_dqinfo) + return; + + xfs_trans_alloc_dqinfo(ntp); + + for (j = 0; j < XFS_QM_TRANS_DQTYPES; j++) { + oqa = otp->t_dqinfo->dqs[j]; + nqa = ntp->t_dqinfo->dqs[j]; + for (i = 0; i < XFS_QM_TRANS_MAXDQS; i++) { + blk_res_used = 0; + + if (oqa[i].qt_dquot == NULL) + break; + oq = &oqa[i]; + nq = &nqa[i]; + + if (oq->qt_blk_res && oq->qt_bcount_delta > 0) + blk_res_used = oq->qt_bcount_delta; + + nq->qt_dquot = oq->qt_dquot; + nq->qt_bcount_delta = nq->qt_icount_delta = 0; + nq->qt_rtbcount_delta = 0; + + /* + * Transfer whatever is left of the reservations. + */ + nq->qt_blk_res = oq->qt_blk_res - blk_res_used; + oq->qt_blk_res = blk_res_used; + + nq->qt_rtblk_res = oq->qt_rtblk_res - + oq->qt_rtblk_res_used; + oq->qt_rtblk_res = oq->qt_rtblk_res_used; + + nq->qt_ino_res = oq->qt_ino_res - oq->qt_ino_res_used; + oq->qt_ino_res = oq->qt_ino_res_used; + + } + } +} + +/* + * Wrap around mod_dquot to account for both user and group quotas. + */ +void +xfs_trans_mod_dquot_byino( + xfs_trans_t *tp, + xfs_inode_t *ip, + uint field, + int64_t delta) +{ + xfs_mount_t *mp = tp->t_mountp; + + if (!XFS_IS_QUOTA_ON(mp) || + xfs_is_quota_inode(&mp->m_sb, ip->i_ino)) + return; + + if (XFS_IS_UQUOTA_ON(mp) && ip->i_udquot) + (void) xfs_trans_mod_dquot(tp, ip->i_udquot, field, delta); + if (XFS_IS_GQUOTA_ON(mp) && ip->i_gdquot) + (void) xfs_trans_mod_dquot(tp, ip->i_gdquot, field, delta); + if (XFS_IS_PQUOTA_ON(mp) && ip->i_pdquot) + (void) xfs_trans_mod_dquot(tp, ip->i_pdquot, field, delta); +} + +STATIC struct xfs_dqtrx * +xfs_trans_get_dqtrx( + struct xfs_trans *tp, + struct xfs_dquot *dqp) +{ + int i; + struct xfs_dqtrx *qa; + + switch (xfs_dquot_type(dqp)) { + case XFS_DQTYPE_USER: + qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_USR]; + break; + case XFS_DQTYPE_GROUP: + qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_GRP]; + break; + case XFS_DQTYPE_PROJ: + qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_PRJ]; + break; + default: + return NULL; + } + + for (i = 0; i < XFS_QM_TRANS_MAXDQS; i++) { + if (qa[i].qt_dquot == NULL || + qa[i].qt_dquot == dqp) + return &qa[i]; + } + + return NULL; +} + +/* + * Make the changes in the transaction structure. + * The moral equivalent to xfs_trans_mod_sb(). + * We don't touch any fields in the dquot, so we don't care + * if it's locked or not (most of the time it won't be). + */ +void +xfs_trans_mod_dquot( + struct xfs_trans *tp, + struct xfs_dquot *dqp, + uint field, + int64_t delta) +{ + struct xfs_dqtrx *qtrx; + + ASSERT(tp); + ASSERT(XFS_IS_QUOTA_ON(tp->t_mountp)); + qtrx = NULL; + + if (!delta) + return; + + if (tp->t_dqinfo == NULL) + xfs_trans_alloc_dqinfo(tp); + /* + * Find either the first free slot or the slot that belongs + * to this dquot. + */ + qtrx = xfs_trans_get_dqtrx(tp, dqp); + ASSERT(qtrx); + if (qtrx->qt_dquot == NULL) + qtrx->qt_dquot = dqp; + + trace_xfs_trans_mod_dquot_before(qtrx); + trace_xfs_trans_mod_dquot(tp, dqp, field, delta); + + switch (field) { + /* regular disk blk reservation */ + case XFS_TRANS_DQ_RES_BLKS: + qtrx->qt_blk_res += delta; + break; + + /* inode reservation */ + case XFS_TRANS_DQ_RES_INOS: + qtrx->qt_ino_res += delta; + break; + + /* disk blocks used. */ + case XFS_TRANS_DQ_BCOUNT: + qtrx->qt_bcount_delta += delta; + break; + + case XFS_TRANS_DQ_DELBCOUNT: + qtrx->qt_delbcnt_delta += delta; + break; + + /* Inode Count */ + case XFS_TRANS_DQ_ICOUNT: + if (qtrx->qt_ino_res && delta > 0) { + qtrx->qt_ino_res_used += delta; + ASSERT(qtrx->qt_ino_res >= qtrx->qt_ino_res_used); + } + qtrx->qt_icount_delta += delta; + break; + + /* rtblk reservation */ + case XFS_TRANS_DQ_RES_RTBLKS: + qtrx->qt_rtblk_res += delta; + break; + + /* rtblk count */ + case XFS_TRANS_DQ_RTBCOUNT: + if (qtrx->qt_rtblk_res && delta > 0) { + qtrx->qt_rtblk_res_used += delta; + ASSERT(qtrx->qt_rtblk_res >= qtrx->qt_rtblk_res_used); + } + qtrx->qt_rtbcount_delta += delta; + break; + + case XFS_TRANS_DQ_DELRTBCOUNT: + qtrx->qt_delrtb_delta += delta; + break; + + default: + ASSERT(0); + } + + trace_xfs_trans_mod_dquot_after(qtrx); +} + + +/* + * Given an array of dqtrx structures, lock all the dquots associated and join + * them to the transaction, provided they have been modified. We know that the + * highest number of dquots of one type - usr, grp and prj - involved in a + * transaction is 3 so we don't need to make this very generic. + */ +STATIC void +xfs_trans_dqlockedjoin( + struct xfs_trans *tp, + struct xfs_dqtrx *q) +{ + ASSERT(q[0].qt_dquot != NULL); + if (q[1].qt_dquot == NULL) { + xfs_dqlock(q[0].qt_dquot); + xfs_trans_dqjoin(tp, q[0].qt_dquot); + } else { + ASSERT(XFS_QM_TRANS_MAXDQS == 2); + xfs_dqlock2(q[0].qt_dquot, q[1].qt_dquot); + xfs_trans_dqjoin(tp, q[0].qt_dquot); + xfs_trans_dqjoin(tp, q[1].qt_dquot); + } +} + +/* Apply dqtrx changes to the quota reservation counters. */ +static inline void +xfs_apply_quota_reservation_deltas( + struct xfs_dquot_res *res, + uint64_t reserved, + int64_t res_used, + int64_t count_delta) +{ + if (reserved != 0) { + /* + * Subtle math here: If reserved > res_used (the normal case), + * we're simply subtracting the unused transaction quota + * reservation from the dquot reservation. + * + * If, however, res_used > reserved, then we have allocated + * more quota blocks than were reserved for the transaction. + * We must add that excess to the dquot reservation since it + * tracks (usage + resv) and by definition we didn't reserve + * that excess. + */ + res->reserved -= abs(reserved - res_used); + } else if (count_delta != 0) { + /* + * These blks were never reserved, either inside a transaction + * or outside one (in a delayed allocation). Also, this isn't + * always a negative number since we sometimes deliberately + * skip quota reservations. + */ + res->reserved += count_delta; + } +} + +/* + * Called by xfs_trans_commit() and similar in spirit to + * xfs_trans_apply_sb_deltas(). + * Go thru all the dquots belonging to this transaction and modify the + * INCORE dquot to reflect the actual usages. + * Unreserve just the reservations done by this transaction. + * dquot is still left locked at exit. + */ +void +xfs_trans_apply_dquot_deltas( + struct xfs_trans *tp) +{ + int i, j; + struct xfs_dquot *dqp; + struct xfs_dqtrx *qtrx, *qa; + int64_t totalbdelta; + int64_t totalrtbdelta; + + if (!tp->t_dqinfo) + return; + + ASSERT(tp->t_dqinfo); + for (j = 0; j < XFS_QM_TRANS_DQTYPES; j++) { + qa = tp->t_dqinfo->dqs[j]; + if (qa[0].qt_dquot == NULL) + continue; + + /* + * Lock all of the dquots and join them to the transaction. + */ + xfs_trans_dqlockedjoin(tp, qa); + + for (i = 0; i < XFS_QM_TRANS_MAXDQS; i++) { + uint64_t blk_res_used; + + qtrx = &qa[i]; + /* + * The array of dquots is filled + * sequentially, not sparsely. + */ + if ((dqp = qtrx->qt_dquot) == NULL) + break; + + ASSERT(XFS_DQ_IS_LOCKED(dqp)); + + /* + * adjust the actual number of blocks used + */ + + /* + * The issue here is - sometimes we don't make a blkquota + * reservation intentionally to be fair to users + * (when the amount is small). On the other hand, + * delayed allocs do make reservations, but that's + * outside of a transaction, so we have no + * idea how much was really reserved. + * So, here we've accumulated delayed allocation blks and + * non-delay blks. The assumption is that the + * delayed ones are always reserved (outside of a + * transaction), and the others may or may not have + * quota reservations. + */ + totalbdelta = qtrx->qt_bcount_delta + + qtrx->qt_delbcnt_delta; + totalrtbdelta = qtrx->qt_rtbcount_delta + + qtrx->qt_delrtb_delta; + + if (totalbdelta != 0 || totalrtbdelta != 0 || + qtrx->qt_icount_delta != 0) { + trace_xfs_trans_apply_dquot_deltas_before(dqp); + trace_xfs_trans_apply_dquot_deltas(qtrx); + } + +#ifdef DEBUG + if (totalbdelta < 0) + ASSERT(dqp->q_blk.count >= -totalbdelta); + + if (totalrtbdelta < 0) + ASSERT(dqp->q_rtb.count >= -totalrtbdelta); + + if (qtrx->qt_icount_delta < 0) + ASSERT(dqp->q_ino.count >= -qtrx->qt_icount_delta); +#endif + if (totalbdelta) + dqp->q_blk.count += totalbdelta; + + if (qtrx->qt_icount_delta) + dqp->q_ino.count += qtrx->qt_icount_delta; + + if (totalrtbdelta) + dqp->q_rtb.count += totalrtbdelta; + + if (totalbdelta != 0 || totalrtbdelta != 0 || + qtrx->qt_icount_delta != 0) + trace_xfs_trans_apply_dquot_deltas_after(dqp); + + /* + * Get any default limits in use. + * Start/reset the timer(s) if needed. + */ + if (dqp->q_id) { + xfs_qm_adjust_dqlimits(dqp); + xfs_qm_adjust_dqtimers(dqp); + } + + dqp->q_flags |= XFS_DQFLAG_DIRTY; + /* + * add this to the list of items to get logged + */ + xfs_trans_log_dquot(tp, dqp); + /* + * Take off what's left of the original reservation. + * In case of delayed allocations, there's no + * reservation that a transaction structure knows of. + */ + blk_res_used = max_t(int64_t, 0, qtrx->qt_bcount_delta); + xfs_apply_quota_reservation_deltas(&dqp->q_blk, + qtrx->qt_blk_res, blk_res_used, + qtrx->qt_bcount_delta); + + /* + * Adjust the RT reservation. + */ + xfs_apply_quota_reservation_deltas(&dqp->q_rtb, + qtrx->qt_rtblk_res, + qtrx->qt_rtblk_res_used, + qtrx->qt_rtbcount_delta); + + /* + * Adjust the inode reservation. + */ + ASSERT(qtrx->qt_ino_res >= qtrx->qt_ino_res_used); + xfs_apply_quota_reservation_deltas(&dqp->q_ino, + qtrx->qt_ino_res, + qtrx->qt_ino_res_used, + qtrx->qt_icount_delta); + + ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count); + ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count); + ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count); + } + } +} + +/* + * Release the reservations, and adjust the dquots accordingly. + * This is called only when the transaction is being aborted. If by + * any chance we have done dquot modifications incore (ie. deltas) already, + * we simply throw those away, since that's the expected behavior + * when a transaction is curtailed without a commit. + */ +void +xfs_trans_unreserve_and_mod_dquots( + struct xfs_trans *tp) +{ + int i, j; + struct xfs_dquot *dqp; + struct xfs_dqtrx *qtrx, *qa; + bool locked; + + if (!tp->t_dqinfo) + return; + + for (j = 0; j < XFS_QM_TRANS_DQTYPES; j++) { + qa = tp->t_dqinfo->dqs[j]; + + for (i = 0; i < XFS_QM_TRANS_MAXDQS; i++) { + qtrx = &qa[i]; + /* + * We assume that the array of dquots is filled + * sequentially, not sparsely. + */ + if ((dqp = qtrx->qt_dquot) == NULL) + break; + /* + * Unreserve the original reservation. We don't care + * about the number of blocks used field, or deltas. + * Also we don't bother to zero the fields. + */ + locked = false; + if (qtrx->qt_blk_res) { + xfs_dqlock(dqp); + locked = true; + dqp->q_blk.reserved -= + (xfs_qcnt_t)qtrx->qt_blk_res; + } + if (qtrx->qt_ino_res) { + if (!locked) { + xfs_dqlock(dqp); + locked = true; + } + dqp->q_ino.reserved -= + (xfs_qcnt_t)qtrx->qt_ino_res; + } + + if (qtrx->qt_rtblk_res) { + if (!locked) { + xfs_dqlock(dqp); + locked = true; + } + dqp->q_rtb.reserved -= + (xfs_qcnt_t)qtrx->qt_rtblk_res; + } + if (locked) + xfs_dqunlock(dqp); + + } + } +} + +STATIC void +xfs_quota_warn( + struct xfs_mount *mp, + struct xfs_dquot *dqp, + int type) +{ + enum quota_type qtype; + + switch (xfs_dquot_type(dqp)) { + case XFS_DQTYPE_PROJ: + qtype = PRJQUOTA; + break; + case XFS_DQTYPE_USER: + qtype = USRQUOTA; + break; + case XFS_DQTYPE_GROUP: + qtype = GRPQUOTA; + break; + default: + return; + } + + quota_send_warning(make_kqid(&init_user_ns, qtype, dqp->q_id), + mp->m_super->s_dev, type); +} + +/* + * Decide if we can make an additional reservation against a quota resource. + * Returns an inode QUOTA_NL_ warning code and whether or not it's fatal. + * + * Note that we assume that the numeric difference between the inode and block + * warning codes will always be 3 since it's userspace ABI now, and will never + * decrease the quota reservation, so the *BELOW messages are irrelevant. + */ +static inline int +xfs_dqresv_check( + struct xfs_dquot_res *res, + struct xfs_quota_limits *qlim, + int64_t delta, + bool *fatal) +{ + xfs_qcnt_t hardlimit = res->hardlimit; + xfs_qcnt_t softlimit = res->softlimit; + xfs_qcnt_t total_count = res->reserved + delta; + + BUILD_BUG_ON(QUOTA_NL_BHARDWARN != QUOTA_NL_IHARDWARN + 3); + BUILD_BUG_ON(QUOTA_NL_BSOFTLONGWARN != QUOTA_NL_ISOFTLONGWARN + 3); + BUILD_BUG_ON(QUOTA_NL_BSOFTWARN != QUOTA_NL_ISOFTWARN + 3); + + *fatal = false; + if (delta <= 0) + return QUOTA_NL_NOWARN; + + if (!hardlimit) + hardlimit = qlim->hard; + if (!softlimit) + softlimit = qlim->soft; + + if (hardlimit && total_count > hardlimit) { + *fatal = true; + return QUOTA_NL_IHARDWARN; + } + + if (softlimit && total_count > softlimit) { + time64_t now = ktime_get_real_seconds(); + + if (res->timer != 0 && now > res->timer) { + *fatal = true; + return QUOTA_NL_ISOFTLONGWARN; + } + + return QUOTA_NL_ISOFTWARN; + } + + return QUOTA_NL_NOWARN; +} + +/* + * This reserves disk blocks and inodes against a dquot. + * Flags indicate if the dquot is to be locked here and also + * if the blk reservation is for RT or regular blocks. + * Sending in XFS_QMOPT_FORCE_RES flag skips the quota check. + */ +STATIC int +xfs_trans_dqresv( + struct xfs_trans *tp, + struct xfs_mount *mp, + struct xfs_dquot *dqp, + int64_t nblks, + long ninos, + uint flags) +{ + struct xfs_quotainfo *q = mp->m_quotainfo; + struct xfs_def_quota *defq; + struct xfs_dquot_res *blkres; + struct xfs_quota_limits *qlim; + + xfs_dqlock(dqp); + + defq = xfs_get_defquota(q, xfs_dquot_type(dqp)); + + if (flags & XFS_TRANS_DQ_RES_BLKS) { + blkres = &dqp->q_blk; + qlim = &defq->blk; + } else { + blkres = &dqp->q_rtb; + qlim = &defq->rtb; + } + + if ((flags & XFS_QMOPT_FORCE_RES) == 0 && dqp->q_id && + xfs_dquot_is_enforced(dqp)) { + int quota_nl; + bool fatal; + + /* + * dquot is locked already. See if we'd go over the hardlimit + * or exceed the timelimit if we'd reserve resources. + */ + quota_nl = xfs_dqresv_check(blkres, qlim, nblks, &fatal); + if (quota_nl != QUOTA_NL_NOWARN) { + /* + * Quota block warning codes are 3 more than the inode + * codes, which we check above. + */ + xfs_quota_warn(mp, dqp, quota_nl + 3); + if (fatal) + goto error_return; + } + + quota_nl = xfs_dqresv_check(&dqp->q_ino, &defq->ino, ninos, + &fatal); + if (quota_nl != QUOTA_NL_NOWARN) { + xfs_quota_warn(mp, dqp, quota_nl); + if (fatal) + goto error_return; + } + } + + /* + * Change the reservation, but not the actual usage. + * Note that q_blk.reserved = q_blk.count + resv + */ + blkres->reserved += (xfs_qcnt_t)nblks; + dqp->q_ino.reserved += (xfs_qcnt_t)ninos; + + /* + * note the reservation amt in the trans struct too, + * so that the transaction knows how much was reserved by + * it against this particular dquot. + * We don't do this when we are reserving for a delayed allocation, + * because we don't have the luxury of a transaction envelope then. + */ + if (tp) { + ASSERT(flags & XFS_QMOPT_RESBLK_MASK); + xfs_trans_mod_dquot(tp, dqp, flags & XFS_QMOPT_RESBLK_MASK, + nblks); + xfs_trans_mod_dquot(tp, dqp, XFS_TRANS_DQ_RES_INOS, ninos); + } + + if (XFS_IS_CORRUPT(mp, dqp->q_blk.reserved < dqp->q_blk.count) || + XFS_IS_CORRUPT(mp, dqp->q_rtb.reserved < dqp->q_rtb.count) || + XFS_IS_CORRUPT(mp, dqp->q_ino.reserved < dqp->q_ino.count)) + goto error_corrupt; + + xfs_dqunlock(dqp); + return 0; + +error_return: + xfs_dqunlock(dqp); + if (xfs_dquot_type(dqp) == XFS_DQTYPE_PROJ) + return -ENOSPC; + return -EDQUOT; +error_corrupt: + xfs_dqunlock(dqp); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return -EFSCORRUPTED; +} + + +/* + * Given dquot(s), make disk block and/or inode reservations against them. + * The fact that this does the reservation against user, group and + * project quotas is important, because this follows a all-or-nothing + * approach. + * + * flags = XFS_QMOPT_FORCE_RES evades limit enforcement. Used by chown. + * XFS_QMOPT_ENOSPC returns ENOSPC not EDQUOT. Used by pquota. + * XFS_TRANS_DQ_RES_BLKS reserves regular disk blocks + * XFS_TRANS_DQ_RES_RTBLKS reserves realtime disk blocks + * dquots are unlocked on return, if they were not locked by caller. + */ +int +xfs_trans_reserve_quota_bydquots( + struct xfs_trans *tp, + struct xfs_mount *mp, + struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, + int64_t nblks, + long ninos, + uint flags) +{ + int error; + + if (!XFS_IS_QUOTA_ON(mp)) + return 0; + + ASSERT(flags & XFS_QMOPT_RESBLK_MASK); + + if (udqp) { + error = xfs_trans_dqresv(tp, mp, udqp, nblks, ninos, flags); + if (error) + return error; + } + + if (gdqp) { + error = xfs_trans_dqresv(tp, mp, gdqp, nblks, ninos, flags); + if (error) + goto unwind_usr; + } + + if (pdqp) { + error = xfs_trans_dqresv(tp, mp, pdqp, nblks, ninos, flags); + if (error) + goto unwind_grp; + } + + /* + * Didn't change anything critical, so, no need to log + */ + return 0; + +unwind_grp: + flags |= XFS_QMOPT_FORCE_RES; + if (gdqp) + xfs_trans_dqresv(tp, mp, gdqp, -nblks, -ninos, flags); +unwind_usr: + flags |= XFS_QMOPT_FORCE_RES; + if (udqp) + xfs_trans_dqresv(tp, mp, udqp, -nblks, -ninos, flags); + return error; +} + + +/* + * Lock the dquot and change the reservation if we can. + * This doesn't change the actual usage, just the reservation. + * The inode sent in is locked. + */ +int +xfs_trans_reserve_quota_nblks( + struct xfs_trans *tp, + struct xfs_inode *ip, + int64_t dblocks, + int64_t rblocks, + bool force) +{ + struct xfs_mount *mp = ip->i_mount; + unsigned int qflags = 0; + int error; + + if (!XFS_IS_QUOTA_ON(mp)) + return 0; + + ASSERT(!xfs_is_quota_inode(&mp->m_sb, ip->i_ino)); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + + if (force) + qflags |= XFS_QMOPT_FORCE_RES; + + /* Reserve data device quota against the inode's dquots. */ + error = xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, dblocks, 0, + XFS_QMOPT_RES_REGBLKS | qflags); + if (error) + return error; + + /* Do the same but for realtime blocks. */ + error = xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, rblocks, 0, + XFS_QMOPT_RES_RTBLKS | qflags); + if (error) { + xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, -dblocks, 0, + XFS_QMOPT_RES_REGBLKS); + return error; + } + + return 0; +} + +/* Change the quota reservations for an inode creation activity. */ +int +xfs_trans_reserve_quota_icreate( + struct xfs_trans *tp, + struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, + int64_t dblocks) +{ + struct xfs_mount *mp = tp->t_mountp; + + if (!XFS_IS_QUOTA_ON(mp)) + return 0; + + return xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp, pdqp, + dblocks, 1, XFS_QMOPT_RES_REGBLKS); +} + +STATIC void +xfs_trans_alloc_dqinfo( + xfs_trans_t *tp) +{ + tp->t_dqinfo = kmem_cache_zalloc(xfs_dqtrx_cache, + GFP_KERNEL | __GFP_NOFAIL); +} + +void +xfs_trans_free_dqinfo( + xfs_trans_t *tp) +{ + if (!tp->t_dqinfo) + return; + kmem_cache_free(xfs_dqtrx_cache, tp->t_dqinfo); + tp->t_dqinfo = NULL; +} |