aboutsummaryrefslogtreecommitdiff
path: root/fs/ocfs2/alloc.h
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /fs/ocfs2/alloc.h
downloadlinux-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/ocfs2/alloc.h')
-rw-r--r--fs/ocfs2/alloc.h310
1 files changed, 310 insertions, 0 deletions
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
new file mode 100644
index 000000000..4af7abaa6
--- /dev/null
+++ b/fs/ocfs2/alloc.h
@@ -0,0 +1,310 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * alloc.h
+ *
+ * Function prototypes
+ *
+ * Copyright (C) 2002, 2004 Oracle. All rights reserved.
+ */
+
+#ifndef OCFS2_ALLOC_H
+#define OCFS2_ALLOC_H
+
+
+/*
+ * For xattr tree leaf, we limit the leaf byte size to be 64K.
+ */
+#define OCFS2_MAX_XATTR_TREE_LEAF_SIZE 65536
+
+/*
+ * ocfs2_extent_tree and ocfs2_extent_tree_operations are used to abstract
+ * the b-tree operations in ocfs2. Now all the b-tree operations are not
+ * limited to ocfs2_dinode only. Any data which need to allocate clusters
+ * to store can use b-tree. And it only needs to implement its ocfs2_extent_tree
+ * and operation.
+ *
+ * ocfs2_extent_tree becomes the first-class object for extent tree
+ * manipulation. Callers of the alloc.c code need to fill it via one of
+ * the ocfs2_init_*_extent_tree() operations below.
+ *
+ * ocfs2_extent_tree contains info for the root of the b-tree, it must have a
+ * root ocfs2_extent_list and a root_bh so that they can be used in the b-tree
+ * functions. It needs the ocfs2_caching_info structure associated with
+ * I/O on the tree. With metadata ecc, we now call different journal_access
+ * functions for each type of metadata, so it must have the
+ * root_journal_access function.
+ * ocfs2_extent_tree_operations abstract the normal operations we do for
+ * the root of extent b-tree.
+ */
+struct ocfs2_extent_tree_operations;
+struct ocfs2_extent_tree {
+ const struct ocfs2_extent_tree_operations *et_ops;
+ struct buffer_head *et_root_bh;
+ struct ocfs2_extent_list *et_root_el;
+ struct ocfs2_caching_info *et_ci;
+ ocfs2_journal_access_func et_root_journal_access;
+ void *et_object;
+ unsigned int et_max_leaf_clusters;
+ struct ocfs2_cached_dealloc_ctxt *et_dealloc;
+};
+
+/*
+ * ocfs2_init_*_extent_tree() will fill an ocfs2_extent_tree from the
+ * specified object buffer.
+ */
+void ocfs2_init_dinode_extent_tree(struct ocfs2_extent_tree *et,
+ struct ocfs2_caching_info *ci,
+ struct buffer_head *bh);
+void ocfs2_init_xattr_tree_extent_tree(struct ocfs2_extent_tree *et,
+ struct ocfs2_caching_info *ci,
+ struct buffer_head *bh);
+struct ocfs2_xattr_value_buf;
+void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et,
+ struct ocfs2_caching_info *ci,
+ struct ocfs2_xattr_value_buf *vb);
+void ocfs2_init_dx_root_extent_tree(struct ocfs2_extent_tree *et,
+ struct ocfs2_caching_info *ci,
+ struct buffer_head *bh);
+void ocfs2_init_refcount_extent_tree(struct ocfs2_extent_tree *et,
+ struct ocfs2_caching_info *ci,
+ struct buffer_head *bh);
+
+/*
+ * Read an extent block into *bh. If *bh is NULL, a bh will be
+ * allocated. This is a cached read. The extent block will be validated
+ * with ocfs2_validate_extent_block().
+ */
+int ocfs2_read_extent_block(struct ocfs2_caching_info *ci, u64 eb_blkno,
+ struct buffer_head **bh);
+
+struct ocfs2_alloc_context;
+int ocfs2_insert_extent(handle_t *handle,
+ struct ocfs2_extent_tree *et,
+ u32 cpos,
+ u64 start_blk,
+ u32 new_clusters,
+ u8 flags,
+ struct ocfs2_alloc_context *meta_ac);
+
+enum ocfs2_alloc_restarted {
+ RESTART_NONE = 0,
+ RESTART_TRANS,
+ RESTART_META
+};
+int ocfs2_add_clusters_in_btree(handle_t *handle,
+ struct ocfs2_extent_tree *et,
+ u32 *logical_offset,
+ u32 clusters_to_add,
+ int mark_unwritten,
+ struct ocfs2_alloc_context *data_ac,
+ struct ocfs2_alloc_context *meta_ac,
+ enum ocfs2_alloc_restarted *reason_ret);
+struct ocfs2_cached_dealloc_ctxt;
+struct ocfs2_path;
+int ocfs2_split_extent(handle_t *handle,
+ struct ocfs2_extent_tree *et,
+ struct ocfs2_path *path,
+ int split_index,
+ struct ocfs2_extent_rec *split_rec,
+ struct ocfs2_alloc_context *meta_ac,
+ struct ocfs2_cached_dealloc_ctxt *dealloc);
+int ocfs2_mark_extent_written(struct inode *inode,
+ struct ocfs2_extent_tree *et,
+ handle_t *handle, u32 cpos, u32 len, u32 phys,
+ struct ocfs2_alloc_context *meta_ac,
+ struct ocfs2_cached_dealloc_ctxt *dealloc);
+int ocfs2_change_extent_flag(handle_t *handle,
+ struct ocfs2_extent_tree *et,
+ u32 cpos, u32 len, u32 phys,
+ struct ocfs2_alloc_context *meta_ac,
+ struct ocfs2_cached_dealloc_ctxt *dealloc,
+ int new_flags, int clear_flags);
+int ocfs2_remove_extent(handle_t *handle, struct ocfs2_extent_tree *et,
+ u32 cpos, u32 len,
+ struct ocfs2_alloc_context *meta_ac,
+ struct ocfs2_cached_dealloc_ctxt *dealloc);
+int ocfs2_remove_btree_range(struct inode *inode,
+ struct ocfs2_extent_tree *et,
+ u32 cpos, u32 phys_cpos, u32 len, int flags,
+ struct ocfs2_cached_dealloc_ctxt *dealloc,
+ u64 refcount_loc, bool refcount_tree_locked);
+
+int ocfs2_num_free_extents(struct ocfs2_extent_tree *et);
+
+/*
+ * how many new metadata chunks would an allocation need at maximum?
+ *
+ * Please note that the caller must make sure that root_el is the root
+ * of extent tree. So for an inode, it should be &fe->id2.i_list. Otherwise
+ * the result may be wrong.
+ */
+static inline int ocfs2_extend_meta_needed(struct ocfs2_extent_list *root_el)
+{
+ /*
+ * Rather than do all the work of determining how much we need
+ * (involves a ton of reads and locks), just ask for the
+ * maximal limit. That's a tree depth shift. So, one block for
+ * level of the tree (current l_tree_depth), one block for the
+ * new tree_depth==0 extent_block, and one block at the new
+ * top-of-the tree.
+ */
+ return le16_to_cpu(root_el->l_tree_depth) + 2;
+}
+
+void ocfs2_dinode_new_extent_list(struct inode *inode, struct ocfs2_dinode *di);
+void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di);
+int ocfs2_convert_inline_data_to_extents(struct inode *inode,
+ struct buffer_head *di_bh);
+
+int ocfs2_truncate_log_init(struct ocfs2_super *osb);
+void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb);
+void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
+ int cancel);
+int ocfs2_flush_truncate_log(struct ocfs2_super *osb);
+int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb,
+ int slot_num,
+ struct ocfs2_dinode **tl_copy);
+int ocfs2_complete_truncate_log_recovery(struct ocfs2_super *osb,
+ struct ocfs2_dinode *tl_copy);
+int ocfs2_truncate_log_needs_flush(struct ocfs2_super *osb);
+int ocfs2_truncate_log_append(struct ocfs2_super *osb,
+ handle_t *handle,
+ u64 start_blk,
+ unsigned int num_clusters);
+int __ocfs2_flush_truncate_log(struct ocfs2_super *osb);
+int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
+ unsigned int needed);
+
+/*
+ * Process local structure which describes the block unlinks done
+ * during an operation. This is populated via
+ * ocfs2_cache_block_dealloc().
+ *
+ * ocfs2_run_deallocs() should be called after the potentially
+ * de-allocating routines. No journal handles should be open, and most
+ * locks should have been dropped.
+ */
+struct ocfs2_cached_dealloc_ctxt {
+ struct ocfs2_per_slot_free_list *c_first_suballocator;
+ struct ocfs2_cached_block_free *c_global_allocator;
+};
+static inline void ocfs2_init_dealloc_ctxt(struct ocfs2_cached_dealloc_ctxt *c)
+{
+ c->c_first_suballocator = NULL;
+ c->c_global_allocator = NULL;
+}
+int ocfs2_cache_cluster_dealloc(struct ocfs2_cached_dealloc_ctxt *ctxt,
+ u64 blkno, unsigned int bit);
+int ocfs2_cache_block_dealloc(struct ocfs2_cached_dealloc_ctxt *ctxt,
+ int type, int slot, u64 suballoc, u64 blkno,
+ unsigned int bit);
+static inline int ocfs2_dealloc_has_cluster(struct ocfs2_cached_dealloc_ctxt *c)
+{
+ return c->c_global_allocator != NULL;
+}
+int ocfs2_run_deallocs(struct ocfs2_super *osb,
+ struct ocfs2_cached_dealloc_ctxt *ctxt);
+
+struct ocfs2_truncate_context {
+ struct ocfs2_cached_dealloc_ctxt tc_dealloc;
+ int tc_ext_alloc_locked; /* is it cluster locked? */
+ /* these get destroyed once it's passed to ocfs2_commit_truncate. */
+ struct buffer_head *tc_last_eb_bh;
+};
+
+int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
+ u64 range_start, u64 range_end);
+int ocfs2_commit_truncate(struct ocfs2_super *osb,
+ struct inode *inode,
+ struct buffer_head *di_bh);
+int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
+ unsigned int start, unsigned int end, int trunc);
+
+int ocfs2_find_leaf(struct ocfs2_caching_info *ci,
+ struct ocfs2_extent_list *root_el, u32 cpos,
+ struct buffer_head **leaf_bh);
+int ocfs2_search_extent_list(struct ocfs2_extent_list *el, u32 v_cluster);
+
+int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range);
+/*
+ * Helper function to look at the # of clusters in an extent record.
+ */
+static inline unsigned int ocfs2_rec_clusters(struct ocfs2_extent_list *el,
+ struct ocfs2_extent_rec *rec)
+{
+ /*
+ * Cluster count in extent records is slightly different
+ * between interior nodes and leaf nodes. This is to support
+ * unwritten extents which need a flags field in leaf node
+ * records, thus shrinking the available space for a clusters
+ * field.
+ */
+ if (el->l_tree_depth)
+ return le32_to_cpu(rec->e_int_clusters);
+ else
+ return le16_to_cpu(rec->e_leaf_clusters);
+}
+
+/*
+ * This is only valid for leaf nodes, which are the only ones that can
+ * have empty extents anyway.
+ */
+static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec)
+{
+ return !rec->e_leaf_clusters;
+}
+
+int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end,
+ struct page **pages, int *num);
+void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
+ unsigned int from, unsigned int to,
+ struct page *page, int zero, u64 *phys);
+/*
+ * Structures which describe a path through a btree, and functions to
+ * manipulate them.
+ *
+ * The idea here is to be as generic as possible with the tree
+ * manipulation code.
+ */
+struct ocfs2_path_item {
+ struct buffer_head *bh;
+ struct ocfs2_extent_list *el;
+};
+
+#define OCFS2_MAX_PATH_DEPTH 5
+
+struct ocfs2_path {
+ int p_tree_depth;
+ ocfs2_journal_access_func p_root_access;
+ struct ocfs2_path_item p_node[OCFS2_MAX_PATH_DEPTH];
+};
+
+#define path_root_bh(_path) ((_path)->p_node[0].bh)
+#define path_root_el(_path) ((_path)->p_node[0].el)
+#define path_root_access(_path)((_path)->p_root_access)
+#define path_leaf_bh(_path) ((_path)->p_node[(_path)->p_tree_depth].bh)
+#define path_leaf_el(_path) ((_path)->p_node[(_path)->p_tree_depth].el)
+#define path_num_items(_path) ((_path)->p_tree_depth + 1)
+
+void ocfs2_reinit_path(struct ocfs2_path *path, int keep_root);
+void ocfs2_free_path(struct ocfs2_path *path);
+int ocfs2_find_path(struct ocfs2_caching_info *ci,
+ struct ocfs2_path *path,
+ u32 cpos);
+struct ocfs2_path *ocfs2_new_path_from_path(struct ocfs2_path *path);
+struct ocfs2_path *ocfs2_new_path_from_et(struct ocfs2_extent_tree *et);
+int ocfs2_path_bh_journal_access(handle_t *handle,
+ struct ocfs2_caching_info *ci,
+ struct ocfs2_path *path,
+ int idx);
+int ocfs2_journal_access_path(struct ocfs2_caching_info *ci,
+ handle_t *handle,
+ struct ocfs2_path *path);
+int ocfs2_find_cpos_for_right_leaf(struct super_block *sb,
+ struct ocfs2_path *path, u32 *cpos);
+int ocfs2_find_cpos_for_left_leaf(struct super_block *sb,
+ struct ocfs2_path *path, u32 *cpos);
+int ocfs2_find_subtree_root(struct ocfs2_extent_tree *et,
+ struct ocfs2_path *left,
+ struct ocfs2_path *right);
+#endif /* OCFS2_ALLOC_H */