aboutsummaryrefslogtreecommitdiff
path: root/drivers/block/null_blk/null_blk.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 /drivers/block/null_blk/null_blk.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 '')
-rw-r--r--drivers/block/null_blk/null_blk.h187
1 files changed, 187 insertions, 0 deletions
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
new file mode 100644
index 000000000..eb5972c50
--- /dev/null
+++ b/drivers/block/null_blk/null_blk.h
@@ -0,0 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BLK_NULL_BLK_H
+#define __BLK_NULL_BLK_H
+
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/blk-mq.h>
+#include <linux/hrtimer.h>
+#include <linux/configfs.h>
+#include <linux/badblocks.h>
+#include <linux/fault-inject.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+
+struct nullb_cmd {
+ union {
+ struct request *rq;
+ struct bio *bio;
+ };
+ unsigned int tag;
+ blk_status_t error;
+ bool fake_timeout;
+ struct nullb_queue *nq;
+ struct hrtimer timer;
+};
+
+struct nullb_queue {
+ unsigned long *tag_map;
+ wait_queue_head_t wait;
+ unsigned int queue_depth;
+ struct nullb_device *dev;
+ unsigned int requeue_selection;
+
+ struct list_head poll_list;
+ spinlock_t poll_lock;
+
+ struct nullb_cmd *cmds;
+};
+
+struct nullb_zone {
+ /*
+ * Zone lock to prevent concurrent modification of a zone write
+ * pointer position and condition: with memory backing, a write
+ * command execution may sleep on memory allocation. For this case,
+ * use mutex as the zone lock. Otherwise, use the spinlock for
+ * locking the zone.
+ */
+ union {
+ spinlock_t spinlock;
+ struct mutex mutex;
+ };
+ enum blk_zone_type type;
+ enum blk_zone_cond cond;
+ sector_t start;
+ sector_t wp;
+ unsigned int len;
+ unsigned int capacity;
+};
+
+/* Queue modes */
+enum {
+ NULL_Q_BIO = 0,
+ NULL_Q_RQ = 1,
+ NULL_Q_MQ = 2,
+};
+
+struct nullb_device {
+ struct nullb *nullb;
+ struct config_item item;
+ struct radix_tree_root data; /* data stored in the disk */
+ struct radix_tree_root cache; /* disk cache data */
+ unsigned long flags; /* device flags */
+ unsigned int curr_cache;
+ struct badblocks badblocks;
+
+ unsigned int nr_zones;
+ unsigned int nr_zones_imp_open;
+ unsigned int nr_zones_exp_open;
+ unsigned int nr_zones_closed;
+ unsigned int imp_close_zone_no;
+ struct nullb_zone *zones;
+ sector_t zone_size_sects;
+ bool need_zone_res_mgmt;
+ spinlock_t zone_res_lock;
+
+ unsigned long size; /* device size in MB */
+ unsigned long completion_nsec; /* time in ns to complete a request */
+ unsigned long cache_size; /* disk cache size in MB */
+ unsigned long zone_size; /* zone size in MB if device is zoned */
+ unsigned long zone_capacity; /* zone capacity in MB if device is zoned */
+ unsigned int zone_nr_conv; /* number of conventional zones */
+ unsigned int zone_max_open; /* max number of open zones */
+ unsigned int zone_max_active; /* max number of active zones */
+ unsigned int submit_queues; /* number of submission queues */
+ unsigned int prev_submit_queues; /* number of submission queues before change */
+ unsigned int poll_queues; /* number of IOPOLL submission queues */
+ unsigned int prev_poll_queues; /* number of IOPOLL submission queues before change */
+ unsigned int home_node; /* home node for the device */
+ unsigned int queue_mode; /* block interface */
+ unsigned int blocksize; /* block size */
+ unsigned int max_sectors; /* Max sectors per command */
+ unsigned int irqmode; /* IRQ completion handler */
+ unsigned int hw_queue_depth; /* queue depth */
+ unsigned int index; /* index of the disk, only valid with a disk */
+ unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
+ bool blocking; /* blocking blk-mq device */
+ bool use_per_node_hctx; /* use per-node allocation for hardware context */
+ bool power; /* power on/off the device */
+ bool memory_backed; /* if data is stored in memory */
+ bool discard; /* if support discard */
+ bool zoned; /* if device is zoned */
+ bool virt_boundary; /* virtual boundary on/off for the device */
+ bool no_sched; /* no IO scheduler for the device */
+ bool shared_tag_bitmap; /* use hostwide shared tags */
+};
+
+struct nullb {
+ struct nullb_device *dev;
+ struct list_head list;
+ unsigned int index;
+ struct request_queue *q;
+ struct gendisk *disk;
+ struct blk_mq_tag_set *tag_set;
+ struct blk_mq_tag_set __tag_set;
+ unsigned int queue_depth;
+ atomic_long_t cur_bytes;
+ struct hrtimer bw_timer;
+ unsigned long cache_flush_pos;
+ spinlock_t lock;
+
+ struct nullb_queue *queues;
+ unsigned int nr_queues;
+ char disk_name[DISK_NAME_LEN];
+};
+
+blk_status_t null_handle_discard(struct nullb_device *dev, sector_t sector,
+ sector_t nr_sectors);
+blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
+ sector_t sector, unsigned int nr_sectors);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q);
+int null_register_zoned_dev(struct nullb *nullb);
+void null_free_zoned_dev(struct nullb_device *dev);
+int null_report_zones(struct gendisk *disk, sector_t sector,
+ unsigned int nr_zones, report_zones_cb cb, void *data);
+blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_op op,
+ sector_t sector, sector_t nr_sectors);
+size_t null_zone_valid_read_len(struct nullb *nullb,
+ sector_t sector, unsigned int len);
+ssize_t zone_cond_store(struct nullb_device *dev, const char *page,
+ size_t count, enum blk_zone_cond cond);
+#else
+static inline int null_init_zoned_dev(struct nullb_device *dev,
+ struct request_queue *q)
+{
+ pr_err("CONFIG_BLK_DEV_ZONED not enabled\n");
+ return -EINVAL;
+}
+static inline int null_register_zoned_dev(struct nullb *nullb)
+{
+ return -ENODEV;
+}
+static inline void null_free_zoned_dev(struct nullb_device *dev) {}
+static inline blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd,
+ enum req_op op, sector_t sector, sector_t nr_sectors)
+{
+ return BLK_STS_NOTSUPP;
+}
+static inline size_t null_zone_valid_read_len(struct nullb *nullb,
+ sector_t sector,
+ unsigned int len)
+{
+ return len;
+}
+static inline ssize_t zone_cond_store(struct nullb_device *dev,
+ const char *page, size_t count,
+ enum blk_zone_cond cond)
+{
+ return -EOPNOTSUPP;
+}
+#define null_report_zones NULL
+#endif /* CONFIG_BLK_DEV_ZONED */
+#endif /* __NULL_BLK_H */