From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- drivers/block/drbd/drbd_proc.c | 323 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 323 insertions(+) create mode 100644 drivers/block/drbd/drbd_proc.c (limited to 'drivers/block/drbd/drbd_proc.c') diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c new file mode 100644 index 000000000..1d0feafce --- /dev/null +++ b/drivers/block/drbd/drbd_proc.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + drbd_proc.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 1999-2008, Philipp Reisner . + Copyright (C) 2002-2008, Lars Ellenberg . + + + */ + +#include + +#include +#include +#include +#include +#include +#include +#include "drbd_int.h" + +struct proc_dir_entry *drbd_proc; + +static void seq_printf_with_thousands_grouping(struct seq_file *seq, long v) +{ + /* v is in kB/sec. We don't expect TiByte/sec yet. */ + if (unlikely(v >= 1000000)) { + /* cool: > GiByte/s */ + seq_printf(seq, "%ld,", v / 1000000); + v %= 1000000; + seq_printf(seq, "%03ld,%03ld", v/1000, v % 1000); + } else if (likely(v >= 1000)) + seq_printf(seq, "%ld,%03ld", v/1000, v % 1000); + else + seq_printf(seq, "%ld", v); +} + +static void drbd_get_syncer_progress(struct drbd_device *device, + union drbd_dev_state state, unsigned long *rs_total, + unsigned long *bits_left, unsigned int *per_mil_done) +{ + /* this is to break it at compile time when we change that, in case we + * want to support more than (1<<32) bits on a 32bit arch. */ + typecheck(unsigned long, device->rs_total); + *rs_total = device->rs_total; + + /* note: both rs_total and rs_left are in bits, i.e. in + * units of BM_BLOCK_SIZE. + * for the percentage, we don't care. */ + + if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T) + *bits_left = device->ov_left; + else + *bits_left = drbd_bm_total_weight(device) - device->rs_failed; + /* >> 10 to prevent overflow, + * +1 to prevent division by zero */ + if (*bits_left > *rs_total) { + /* D'oh. Maybe a logic bug somewhere. More likely just a race + * between state change and reset of rs_total. + */ + *bits_left = *rs_total; + *per_mil_done = *rs_total ? 0 : 1000; + } else { + /* Make sure the division happens in long context. + * We allow up to one petabyte storage right now, + * at a granularity of 4k per bit that is 2**38 bits. + * After shift right and multiplication by 1000, + * this should still fit easily into a 32bit long, + * so we don't need a 64bit division on 32bit arch. + * Note: currently we don't support such large bitmaps on 32bit + * arch anyways, but no harm done to be prepared for it here. + */ + unsigned int shift = *rs_total > UINT_MAX ? 16 : 10; + unsigned long left = *bits_left >> shift; + unsigned long total = 1UL + (*rs_total >> shift); + unsigned long tmp = 1000UL - left * 1000UL/total; + *per_mil_done = tmp; + } +} + + +/*lge + * progress bars shamelessly adapted from driver/md/md.c + * output looks like + * [=====>..............] 33.5% (23456/123456) + * finish: 2:20:20 speed: 6,345 (6,456) K/sec + */ +static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *seq, + union drbd_dev_state state) +{ + unsigned long db, dt, dbdt, rt, rs_total, rs_left; + unsigned int res; + int i, x, y; + int stalled = 0; + + drbd_get_syncer_progress(device, state, &rs_total, &rs_left, &res); + + x = res/50; + y = 20-x; + seq_puts(seq, "\t["); + for (i = 1; i < x; i++) + seq_putc(seq, '='); + seq_putc(seq, '>'); + for (i = 0; i < y; i++) + seq_putc(seq, '.'); + seq_puts(seq, "] "); + + if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T) + seq_puts(seq, "verified:"); + else + seq_puts(seq, "sync'ed:"); + seq_printf(seq, "%3u.%u%% ", res / 10, res % 10); + + /* if more than a few GB, display in MB */ + if (rs_total > (4UL << (30 - BM_BLOCK_SHIFT))) + seq_printf(seq, "(%lu/%lu)M", + (unsigned long) Bit2KB(rs_left >> 10), + (unsigned long) Bit2KB(rs_total >> 10)); + else + seq_printf(seq, "(%lu/%lu)K", + (unsigned long) Bit2KB(rs_left), + (unsigned long) Bit2KB(rs_total)); + + seq_puts(seq, "\n\t"); + + /* see drivers/md/md.c + * We do not want to overflow, so the order of operands and + * the * 100 / 100 trick are important. We do a +1 to be + * safe against division by zero. We only estimate anyway. + * + * dt: time from mark until now + * db: blocks written from mark until now + * rt: remaining time + */ + /* Rolling marks. last_mark+1 may just now be modified. last_mark+2 is + * at least (DRBD_SYNC_MARKS-2)*DRBD_SYNC_MARK_STEP old, and has at + * least DRBD_SYNC_MARK_STEP time before it will be modified. */ + /* ------------------------ ~18s average ------------------------ */ + i = (device->rs_last_mark + 2) % DRBD_SYNC_MARKS; + dt = (jiffies - device->rs_mark_time[i]) / HZ; + if (dt > 180) + stalled = 1; + + if (!dt) + dt++; + db = device->rs_mark_left[i] - rs_left; + rt = (dt * (rs_left / (db/100+1)))/100; /* seconds */ + + seq_printf(seq, "finish: %lu:%02lu:%02lu", + rt / 3600, (rt % 3600) / 60, rt % 60); + + dbdt = Bit2KB(db/dt); + seq_puts(seq, " speed: "); + seq_printf_with_thousands_grouping(seq, dbdt); + seq_puts(seq, " ("); + /* ------------------------- ~3s average ------------------------ */ + if (drbd_proc_details >= 1) { + /* this is what drbd_rs_should_slow_down() uses */ + i = (device->rs_last_mark + DRBD_SYNC_MARKS-1) % DRBD_SYNC_MARKS; + dt = (jiffies - device->rs_mark_time[i]) / HZ; + if (!dt) + dt++; + db = device->rs_mark_left[i] - rs_left; + dbdt = Bit2KB(db/dt); + seq_printf_with_thousands_grouping(seq, dbdt); + seq_puts(seq, " -- "); + } + + /* --------------------- long term average ---------------------- */ + /* mean speed since syncer started + * we do account for PausedSync periods */ + dt = (jiffies - device->rs_start - device->rs_paused) / HZ; + if (dt == 0) + dt = 1; + db = rs_total - rs_left; + dbdt = Bit2KB(db/dt); + seq_printf_with_thousands_grouping(seq, dbdt); + seq_putc(seq, ')'); + + if (state.conn == C_SYNC_TARGET || + state.conn == C_VERIFY_S) { + seq_puts(seq, " want: "); + seq_printf_with_thousands_grouping(seq, device->c_sync_rate); + } + seq_printf(seq, " K/sec%s\n", stalled ? " (stalled)" : ""); + + if (drbd_proc_details >= 1) { + /* 64 bit: + * we convert to sectors in the display below. */ + unsigned long bm_bits = drbd_bm_bits(device); + unsigned long bit_pos; + unsigned long long stop_sector = 0; + if (state.conn == C_VERIFY_S || + state.conn == C_VERIFY_T) { + bit_pos = bm_bits - device->ov_left; + if (verify_can_do_stop_sector(device)) + stop_sector = device->ov_stop_sector; + } else + bit_pos = device->bm_resync_fo; + /* Total sectors may be slightly off for oddly + * sized devices. So what. */ + seq_printf(seq, + "\t%3d%% sector pos: %llu/%llu", + (int)(bit_pos / (bm_bits/100+1)), + (unsigned long long)bit_pos * BM_SECT_PER_BIT, + (unsigned long long)bm_bits * BM_SECT_PER_BIT); + if (stop_sector != 0 && stop_sector != ULLONG_MAX) + seq_printf(seq, " stop sector: %llu", stop_sector); + seq_putc(seq, '\n'); + } +} + +int drbd_seq_show(struct seq_file *seq, void *v) +{ + int i, prev_i = -1; + const char *sn; + struct drbd_device *device; + struct net_conf *nc; + union drbd_dev_state state; + char wp; + + static char write_ordering_chars[] = { + [WO_NONE] = 'n', + [WO_DRAIN_IO] = 'd', + [WO_BDEV_FLUSH] = 'f', + }; + + seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n", + GENL_MAGIC_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX, drbd_buildtag()); + + /* + cs .. connection state + ro .. node role (local/remote) + ds .. disk state (local/remote) + protocol + various flags + ns .. network send + nr .. network receive + dw .. disk write + dr .. disk read + al .. activity log write count + bm .. bitmap update write count + pe .. pending (waiting for ack or data reply) + ua .. unack'd (still need to send ack or data reply) + ap .. application requests accepted, but not yet completed + ep .. number of epochs currently "on the fly", P_BARRIER_ACK pending + wo .. write ordering mode currently in use + oos .. known out-of-sync kB + */ + + rcu_read_lock(); + idr_for_each_entry(&drbd_devices, device, i) { + if (prev_i != i - 1) + seq_putc(seq, '\n'); + prev_i = i; + + state = device->state; + sn = drbd_conn_str(state.conn); + + if (state.conn == C_STANDALONE && + state.disk == D_DISKLESS && + state.role == R_SECONDARY) { + seq_printf(seq, "%2d: cs:Unconfigured\n", i); + } else { + /* reset device->congestion_reason */ + + nc = rcu_dereference(first_peer_device(device)->connection->net_conf); + wp = nc ? nc->wire_protocol - DRBD_PROT_A + 'A' : ' '; + seq_printf(seq, + "%2d: cs:%s ro:%s/%s ds:%s/%s %c %c%c%c%c%c%c\n" + " ns:%u nr:%u dw:%u dr:%u al:%u bm:%u " + "lo:%d pe:%d ua:%d ap:%d ep:%d wo:%c", + i, sn, + drbd_role_str(state.role), + drbd_role_str(state.peer), + drbd_disk_str(state.disk), + drbd_disk_str(state.pdsk), + wp, + drbd_suspended(device) ? 's' : 'r', + state.aftr_isp ? 'a' : '-', + state.peer_isp ? 'p' : '-', + state.user_isp ? 'u' : '-', + device->congestion_reason ?: '-', + test_bit(AL_SUSPENDED, &device->flags) ? 's' : '-', + device->send_cnt/2, + device->recv_cnt/2, + device->writ_cnt/2, + device->read_cnt/2, + device->al_writ_cnt, + device->bm_writ_cnt, + atomic_read(&device->local_cnt), + atomic_read(&device->ap_pending_cnt) + + atomic_read(&device->rs_pending_cnt), + atomic_read(&device->unacked_cnt), + atomic_read(&device->ap_bio_cnt), + first_peer_device(device)->connection->epochs, + write_ordering_chars[device->resource->write_ordering] + ); + seq_printf(seq, " oos:%llu\n", + Bit2KB((unsigned long long) + drbd_bm_total_weight(device))); + } + if (state.conn == C_SYNC_SOURCE || + state.conn == C_SYNC_TARGET || + state.conn == C_VERIFY_S || + state.conn == C_VERIFY_T) + drbd_syncer_progress(device, seq, state); + + if (drbd_proc_details >= 1 && get_ldev_if_state(device, D_FAILED)) { + lc_seq_printf_stats(seq, device->resync); + lc_seq_printf_stats(seq, device->act_log); + put_ldev(device); + } + + if (drbd_proc_details >= 2) + seq_printf(seq, "\tblocked on activity log: %d\n", atomic_read(&device->ap_actlog_cnt)); + } + rcu_read_unlock(); + + return 0; +} -- cgit v1.2.3