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(). ... --- lib/debugobjects.c | 1414 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1414 insertions(+) create mode 100644 lib/debugobjects.c (limited to 'lib/debugobjects.c') diff --git a/lib/debugobjects.c b/lib/debugobjects.c new file mode 100644 index 000000000..df86e649d --- /dev/null +++ b/lib/debugobjects.c @@ -0,0 +1,1414 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic infrastructure for lifetime debugging of objects. + * + * Copyright (C) 2008, Thomas Gleixner + */ + +#define pr_fmt(fmt) "ODEBUG: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ODEBUG_HASH_BITS 14 +#define ODEBUG_HASH_SIZE (1 << ODEBUG_HASH_BITS) + +#define ODEBUG_POOL_SIZE 1024 +#define ODEBUG_POOL_MIN_LEVEL 256 +#define ODEBUG_POOL_PERCPU_SIZE 64 +#define ODEBUG_BATCH_SIZE 16 + +#define ODEBUG_CHUNK_SHIFT PAGE_SHIFT +#define ODEBUG_CHUNK_SIZE (1 << ODEBUG_CHUNK_SHIFT) +#define ODEBUG_CHUNK_MASK (~(ODEBUG_CHUNK_SIZE - 1)) + +/* + * We limit the freeing of debug objects via workqueue at a maximum + * frequency of 10Hz and about 1024 objects for each freeing operation. + * So it is freeing at most 10k debug objects per second. + */ +#define ODEBUG_FREE_WORK_MAX 1024 +#define ODEBUG_FREE_WORK_DELAY DIV_ROUND_UP(HZ, 10) + +struct debug_bucket { + struct hlist_head list; + raw_spinlock_t lock; +}; + +/* + * Debug object percpu free list + * Access is protected by disabling irq + */ +struct debug_percpu_free { + struct hlist_head free_objs; + int obj_free; +}; + +static DEFINE_PER_CPU(struct debug_percpu_free, percpu_obj_pool); + +static struct debug_bucket obj_hash[ODEBUG_HASH_SIZE]; + +static struct debug_obj obj_static_pool[ODEBUG_POOL_SIZE] __initdata; + +static DEFINE_RAW_SPINLOCK(pool_lock); + +static HLIST_HEAD(obj_pool); +static HLIST_HEAD(obj_to_free); + +/* + * Because of the presence of percpu free pools, obj_pool_free will + * under-count those in the percpu free pools. Similarly, obj_pool_used + * will over-count those in the percpu free pools. Adjustments will be + * made at debug_stats_show(). Both obj_pool_min_free and obj_pool_max_used + * can be off. + */ +static int obj_pool_min_free = ODEBUG_POOL_SIZE; +static int obj_pool_free = ODEBUG_POOL_SIZE; +static int obj_pool_used; +static int obj_pool_max_used; +static bool obj_freeing; +/* The number of objs on the global free list */ +static int obj_nr_tofree; + +static int debug_objects_maxchain __read_mostly; +static int __maybe_unused debug_objects_maxchecked __read_mostly; +static int debug_objects_fixups __read_mostly; +static int debug_objects_warnings __read_mostly; +static int debug_objects_enabled __read_mostly + = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; +static int debug_objects_pool_size __read_mostly + = ODEBUG_POOL_SIZE; +static int debug_objects_pool_min_level __read_mostly + = ODEBUG_POOL_MIN_LEVEL; +static const struct debug_obj_descr *descr_test __read_mostly; +static struct kmem_cache *obj_cache __read_mostly; + +/* + * Track numbers of kmem_cache_alloc()/free() calls done. + */ +static int debug_objects_allocated; +static int debug_objects_freed; + +static void free_obj_work(struct work_struct *work); +static DECLARE_DELAYED_WORK(debug_obj_work, free_obj_work); + +static int __init enable_object_debug(char *str) +{ + debug_objects_enabled = 1; + return 0; +} + +static int __init disable_object_debug(char *str) +{ + debug_objects_enabled = 0; + return 0; +} + +early_param("debug_objects", enable_object_debug); +early_param("no_debug_objects", disable_object_debug); + +static const char *obj_states[ODEBUG_STATE_MAX] = { + [ODEBUG_STATE_NONE] = "none", + [ODEBUG_STATE_INIT] = "initialized", + [ODEBUG_STATE_INACTIVE] = "inactive", + [ODEBUG_STATE_ACTIVE] = "active", + [ODEBUG_STATE_DESTROYED] = "destroyed", + [ODEBUG_STATE_NOTAVAILABLE] = "not available", +}; + +static void fill_pool(void) +{ + gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; + struct debug_obj *obj; + unsigned long flags; + + if (likely(READ_ONCE(obj_pool_free) >= debug_objects_pool_min_level)) + return; + + /* + * Reuse objs from the global free list; they will be reinitialized + * when allocating. + * + * Both obj_nr_tofree and obj_pool_free are checked locklessly; the + * READ_ONCE()s pair with the WRITE_ONCE()s in pool_lock critical + * sections. + */ + while (READ_ONCE(obj_nr_tofree) && (READ_ONCE(obj_pool_free) < obj_pool_min_free)) { + raw_spin_lock_irqsave(&pool_lock, flags); + /* + * Recheck with the lock held as the worker thread might have + * won the race and freed the global free list already. + */ + while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) { + obj = hlist_entry(obj_to_free.first, typeof(*obj), node); + hlist_del(&obj->node); + WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1); + hlist_add_head(&obj->node, &obj_pool); + WRITE_ONCE(obj_pool_free, obj_pool_free + 1); + } + raw_spin_unlock_irqrestore(&pool_lock, flags); + } + + if (unlikely(!obj_cache)) + return; + + while (READ_ONCE(obj_pool_free) < debug_objects_pool_min_level) { + struct debug_obj *new[ODEBUG_BATCH_SIZE]; + int cnt; + + for (cnt = 0; cnt < ODEBUG_BATCH_SIZE; cnt++) { + new[cnt] = kmem_cache_zalloc(obj_cache, gfp); + if (!new[cnt]) + break; + } + if (!cnt) + return; + + raw_spin_lock_irqsave(&pool_lock, flags); + while (cnt) { + hlist_add_head(&new[--cnt]->node, &obj_pool); + debug_objects_allocated++; + WRITE_ONCE(obj_pool_free, obj_pool_free + 1); + } + raw_spin_unlock_irqrestore(&pool_lock, flags); + } +} + +/* + * Lookup an object in the hash bucket. + */ +static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b) +{ + struct debug_obj *obj; + int cnt = 0; + + hlist_for_each_entry(obj, &b->list, node) { + cnt++; + if (obj->object == addr) + return obj; + } + if (cnt > debug_objects_maxchain) + debug_objects_maxchain = cnt; + + return NULL; +} + +/* + * Allocate a new object from the hlist + */ +static struct debug_obj *__alloc_object(struct hlist_head *list) +{ + struct debug_obj *obj = NULL; + + if (list->first) { + obj = hlist_entry(list->first, typeof(*obj), node); + hlist_del(&obj->node); + } + + return obj; +} + +/* + * Allocate a new object. If the pool is empty, switch off the debugger. + * Must be called with interrupts disabled. + */ +static struct debug_obj * +alloc_object(void *addr, struct debug_bucket *b, const struct debug_obj_descr *descr) +{ + struct debug_percpu_free *percpu_pool = this_cpu_ptr(&percpu_obj_pool); + struct debug_obj *obj; + + if (likely(obj_cache)) { + obj = __alloc_object(&percpu_pool->free_objs); + if (obj) { + percpu_pool->obj_free--; + goto init_obj; + } + } + + raw_spin_lock(&pool_lock); + obj = __alloc_object(&obj_pool); + if (obj) { + obj_pool_used++; + WRITE_ONCE(obj_pool_free, obj_pool_free - 1); + + /* + * Looking ahead, allocate one batch of debug objects and + * put them into the percpu free pool. + */ + if (likely(obj_cache)) { + int i; + + for (i = 0; i < ODEBUG_BATCH_SIZE; i++) { + struct debug_obj *obj2; + + obj2 = __alloc_object(&obj_pool); + if (!obj2) + break; + hlist_add_head(&obj2->node, + &percpu_pool->free_objs); + percpu_pool->obj_free++; + obj_pool_used++; + WRITE_ONCE(obj_pool_free, obj_pool_free - 1); + } + } + + if (obj_pool_used > obj_pool_max_used) + obj_pool_max_used = obj_pool_used; + + if (obj_pool_free < obj_pool_min_free) + obj_pool_min_free = obj_pool_free; + } + raw_spin_unlock(&pool_lock); + +init_obj: + if (obj) { + obj->object = addr; + obj->descr = descr; + obj->state = ODEBUG_STATE_NONE; + obj->astate = 0; + hlist_add_head(&obj->node, &b->list); + } + return obj; +} + +/* + * workqueue function to free objects. + * + * To reduce contention on the global pool_lock, the actual freeing of + * debug objects will be delayed if the pool_lock is busy. + */ +static void free_obj_work(struct work_struct *work) +{ + struct hlist_node *tmp; + struct debug_obj *obj; + unsigned long flags; + HLIST_HEAD(tofree); + + WRITE_ONCE(obj_freeing, false); + if (!raw_spin_trylock_irqsave(&pool_lock, flags)) + return; + + if (obj_pool_free >= debug_objects_pool_size) + goto free_objs; + + /* + * The objs on the pool list might be allocated before the work is + * run, so recheck if pool list it full or not, if not fill pool + * list from the global free list. As it is likely that a workload + * may be gearing up to use more and more objects, don't free any + * of them until the next round. + */ + while (obj_nr_tofree && obj_pool_free < debug_objects_pool_size) { + obj = hlist_entry(obj_to_free.first, typeof(*obj), node); + hlist_del(&obj->node); + hlist_add_head(&obj->node, &obj_pool); + WRITE_ONCE(obj_pool_free, obj_pool_free + 1); + WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1); + } + raw_spin_unlock_irqrestore(&pool_lock, flags); + return; + +free_objs: + /* + * Pool list is already full and there are still objs on the free + * list. Move remaining free objs to a temporary list to free the + * memory outside the pool_lock held region. + */ + if (obj_nr_tofree) { + hlist_move_list(&obj_to_free, &tofree); + debug_objects_freed += obj_nr_tofree; + WRITE_ONCE(obj_nr_tofree, 0); + } + raw_spin_unlock_irqrestore(&pool_lock, flags); + + hlist_for_each_entry_safe(obj, tmp, &tofree, node) { + hlist_del(&obj->node); + kmem_cache_free(obj_cache, obj); + } +} + +static void __free_object(struct debug_obj *obj) +{ + struct debug_obj *objs[ODEBUG_BATCH_SIZE]; + struct debug_percpu_free *percpu_pool; + int lookahead_count = 0; + unsigned long flags; + bool work; + + local_irq_save(flags); + if (!obj_cache) + goto free_to_obj_pool; + + /* + * Try to free it into the percpu pool first. + */ + percpu_pool = this_cpu_ptr(&percpu_obj_pool); + if (percpu_pool->obj_free < ODEBUG_POOL_PERCPU_SIZE) { + hlist_add_head(&obj->node, &percpu_pool->free_objs); + percpu_pool->obj_free++; + local_irq_restore(flags); + return; + } + + /* + * As the percpu pool is full, look ahead and pull out a batch + * of objects from the percpu pool and free them as well. + */ + for (; lookahead_count < ODEBUG_BATCH_SIZE; lookahead_count++) { + objs[lookahead_count] = __alloc_object(&percpu_pool->free_objs); + if (!objs[lookahead_count]) + break; + percpu_pool->obj_free--; + } + +free_to_obj_pool: + raw_spin_lock(&pool_lock); + work = (obj_pool_free > debug_objects_pool_size) && obj_cache && + (obj_nr_tofree < ODEBUG_FREE_WORK_MAX); + obj_pool_used--; + + if (work) { + WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + 1); + hlist_add_head(&obj->node, &obj_to_free); + if (lookahead_count) { + WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + lookahead_count); + obj_pool_used -= lookahead_count; + while (lookahead_count) { + hlist_add_head(&objs[--lookahead_count]->node, + &obj_to_free); + } + } + + if ((obj_pool_free > debug_objects_pool_size) && + (obj_nr_tofree < ODEBUG_FREE_WORK_MAX)) { + int i; + + /* + * Free one more batch of objects from obj_pool. + */ + for (i = 0; i < ODEBUG_BATCH_SIZE; i++) { + obj = __alloc_object(&obj_pool); + hlist_add_head(&obj->node, &obj_to_free); + WRITE_ONCE(obj_pool_free, obj_pool_free - 1); + WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + 1); + } + } + } else { + WRITE_ONCE(obj_pool_free, obj_pool_free + 1); + hlist_add_head(&obj->node, &obj_pool); + if (lookahead_count) { + WRITE_ONCE(obj_pool_free, obj_pool_free + lookahead_count); + obj_pool_used -= lookahead_count; + while (lookahead_count) { + hlist_add_head(&objs[--lookahead_count]->node, + &obj_pool); + } + } + } + raw_spin_unlock(&pool_lock); + local_irq_restore(flags); +} + +/* + * Put the object back into the pool and schedule work to free objects + * if necessary. + */ +static void free_object(struct debug_obj *obj) +{ + __free_object(obj); + if (!READ_ONCE(obj_freeing) && READ_ONCE(obj_nr_tofree)) { + WRITE_ONCE(obj_freeing, true); + schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY); + } +} + +#ifdef CONFIG_HOTPLUG_CPU +static int object_cpu_offline(unsigned int cpu) +{ + struct debug_percpu_free *percpu_pool; + struct hlist_node *tmp; + struct debug_obj *obj; + unsigned long flags; + + /* Remote access is safe as the CPU is dead already */ + percpu_pool = per_cpu_ptr(&percpu_obj_pool, cpu); + hlist_for_each_entry_safe(obj, tmp, &percpu_pool->free_objs, node) { + hlist_del(&obj->node); + kmem_cache_free(obj_cache, obj); + } + + raw_spin_lock_irqsave(&pool_lock, flags); + obj_pool_used -= percpu_pool->obj_free; + debug_objects_freed += percpu_pool->obj_free; + raw_spin_unlock_irqrestore(&pool_lock, flags); + + percpu_pool->obj_free = 0; + + return 0; +} +#endif + +/* + * We run out of memory. That means we probably have tons of objects + * allocated. + */ +static void debug_objects_oom(void) +{ + struct debug_bucket *db = obj_hash; + struct hlist_node *tmp; + HLIST_HEAD(freelist); + struct debug_obj *obj; + unsigned long flags; + int i; + + pr_warn("Out of memory. ODEBUG disabled\n"); + + for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { + raw_spin_lock_irqsave(&db->lock, flags); + hlist_move_list(&db->list, &freelist); + raw_spin_unlock_irqrestore(&db->lock, flags); + + /* Now free them */ + hlist_for_each_entry_safe(obj, tmp, &freelist, node) { + hlist_del(&obj->node); + free_object(obj); + } + } +} + +/* + * We use the pfn of the address for the hash. That way we can check + * for freed objects simply by checking the affected bucket. + */ +static struct debug_bucket *get_bucket(unsigned long addr) +{ + unsigned long hash; + + hash = hash_long((addr >> ODEBUG_CHUNK_SHIFT), ODEBUG_HASH_BITS); + return &obj_hash[hash]; +} + +static void debug_print_object(struct debug_obj *obj, char *msg) +{ + const struct debug_obj_descr *descr = obj->descr; + static int limit; + + if (limit < 5 && descr != descr_test) { + void *hint = descr->debug_hint ? + descr->debug_hint(obj->object) : NULL; + limit++; + WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) " + "object: %p object type: %s hint: %pS\n", + msg, obj_states[obj->state], obj->astate, + obj->object, descr->name, hint); + } + debug_objects_warnings++; +} + +/* + * Try to repair the damage, so we have a better chance to get useful + * debug output. + */ +static bool +debug_object_fixup(bool (*fixup)(void *addr, enum debug_obj_state state), + void * addr, enum debug_obj_state state) +{ + if (fixup && fixup(addr, state)) { + debug_objects_fixups++; + return true; + } + return false; +} + +static void debug_object_is_on_stack(void *addr, int onstack) +{ + int is_on_stack; + static int limit; + + if (limit > 4) + return; + + is_on_stack = object_is_on_stack(addr); + if (is_on_stack == onstack) + return; + + limit++; + if (is_on_stack) + pr_warn("object %p is on stack %p, but NOT annotated.\n", addr, + task_stack_page(current)); + else + pr_warn("object %p is NOT on stack %p, but annotated.\n", addr, + task_stack_page(current)); + + WARN_ON(1); +} + +static void +__debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack) +{ + enum debug_obj_state state; + bool check_stack = false; + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + + /* + * On RT enabled kernels the pool refill must happen in preemptible + * context: + */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) + fill_pool(); + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (!obj) { + obj = alloc_object(addr, db, descr); + if (!obj) { + debug_objects_enabled = 0; + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_objects_oom(); + return; + } + check_stack = true; + } + + switch (obj->state) { + case ODEBUG_STATE_NONE: + case ODEBUG_STATE_INIT: + case ODEBUG_STATE_INACTIVE: + obj->state = ODEBUG_STATE_INIT; + break; + + case ODEBUG_STATE_ACTIVE: + state = obj->state; + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "init"); + debug_object_fixup(descr->fixup_init, addr, state); + return; + + case ODEBUG_STATE_DESTROYED: + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "init"); + return; + default: + break; + } + + raw_spin_unlock_irqrestore(&db->lock, flags); + if (check_stack) + debug_object_is_on_stack(addr, onstack); +} + +/** + * debug_object_init - debug checks when an object is initialized + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + */ +void debug_object_init(void *addr, const struct debug_obj_descr *descr) +{ + if (!debug_objects_enabled) + return; + + __debug_object_init(addr, descr, 0); +} +EXPORT_SYMBOL_GPL(debug_object_init); + +/** + * debug_object_init_on_stack - debug checks when an object on stack is + * initialized + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + */ +void debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr) +{ + if (!debug_objects_enabled) + return; + + __debug_object_init(addr, descr, 1); +} +EXPORT_SYMBOL_GPL(debug_object_init_on_stack); + +/** + * debug_object_activate - debug checks when an object is activated + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + * Returns 0 for success, -EINVAL for check failed. + */ +int debug_object_activate(void *addr, const struct debug_obj_descr *descr) +{ + enum debug_obj_state state; + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + int ret; + struct debug_obj o = { .object = addr, + .state = ODEBUG_STATE_NOTAVAILABLE, + .descr = descr }; + + if (!debug_objects_enabled) + return 0; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (obj) { + bool print_object = false; + + switch (obj->state) { + case ODEBUG_STATE_INIT: + case ODEBUG_STATE_INACTIVE: + obj->state = ODEBUG_STATE_ACTIVE; + ret = 0; + break; + + case ODEBUG_STATE_ACTIVE: + state = obj->state; + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "activate"); + ret = debug_object_fixup(descr->fixup_activate, addr, state); + return ret ? 0 : -EINVAL; + + case ODEBUG_STATE_DESTROYED: + print_object = true; + ret = -EINVAL; + break; + default: + ret = 0; + break; + } + raw_spin_unlock_irqrestore(&db->lock, flags); + if (print_object) + debug_print_object(obj, "activate"); + return ret; + } + + raw_spin_unlock_irqrestore(&db->lock, flags); + + /* + * We are here when a static object is activated. We + * let the type specific code confirm whether this is + * true or not. if true, we just make sure that the + * static object is tracked in the object tracker. If + * not, this must be a bug, so we try to fix it up. + */ + if (descr->is_static_object && descr->is_static_object(addr)) { + /* track this static object */ + debug_object_init(addr, descr); + debug_object_activate(addr, descr); + } else { + debug_print_object(&o, "activate"); + ret = debug_object_fixup(descr->fixup_activate, addr, + ODEBUG_STATE_NOTAVAILABLE); + return ret ? 0 : -EINVAL; + } + return 0; +} +EXPORT_SYMBOL_GPL(debug_object_activate); + +/** + * debug_object_deactivate - debug checks when an object is deactivated + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + */ +void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) +{ + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + bool print_object = false; + + if (!debug_objects_enabled) + return; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (obj) { + switch (obj->state) { + case ODEBUG_STATE_INIT: + case ODEBUG_STATE_INACTIVE: + case ODEBUG_STATE_ACTIVE: + if (!obj->astate) + obj->state = ODEBUG_STATE_INACTIVE; + else + print_object = true; + break; + + case ODEBUG_STATE_DESTROYED: + print_object = true; + break; + default: + break; + } + } + + raw_spin_unlock_irqrestore(&db->lock, flags); + if (!obj) { + struct debug_obj o = { .object = addr, + .state = ODEBUG_STATE_NOTAVAILABLE, + .descr = descr }; + + debug_print_object(&o, "deactivate"); + } else if (print_object) { + debug_print_object(obj, "deactivate"); + } +} +EXPORT_SYMBOL_GPL(debug_object_deactivate); + +/** + * debug_object_destroy - debug checks when an object is destroyed + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + */ +void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) +{ + enum debug_obj_state state; + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + bool print_object = false; + + if (!debug_objects_enabled) + return; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (!obj) + goto out_unlock; + + switch (obj->state) { + case ODEBUG_STATE_NONE: + case ODEBUG_STATE_INIT: + case ODEBUG_STATE_INACTIVE: + obj->state = ODEBUG_STATE_DESTROYED; + break; + case ODEBUG_STATE_ACTIVE: + state = obj->state; + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "destroy"); + debug_object_fixup(descr->fixup_destroy, addr, state); + return; + + case ODEBUG_STATE_DESTROYED: + print_object = true; + break; + default: + break; + } +out_unlock: + raw_spin_unlock_irqrestore(&db->lock, flags); + if (print_object) + debug_print_object(obj, "destroy"); +} +EXPORT_SYMBOL_GPL(debug_object_destroy); + +/** + * debug_object_free - debug checks when an object is freed + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + */ +void debug_object_free(void *addr, const struct debug_obj_descr *descr) +{ + enum debug_obj_state state; + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + + if (!debug_objects_enabled) + return; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (!obj) + goto out_unlock; + + switch (obj->state) { + case ODEBUG_STATE_ACTIVE: + state = obj->state; + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "free"); + debug_object_fixup(descr->fixup_free, addr, state); + return; + default: + hlist_del(&obj->node); + raw_spin_unlock_irqrestore(&db->lock, flags); + free_object(obj); + return; + } +out_unlock: + raw_spin_unlock_irqrestore(&db->lock, flags); +} +EXPORT_SYMBOL_GPL(debug_object_free); + +/** + * debug_object_assert_init - debug checks when object should be init-ed + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + */ +void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr) +{ + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + + if (!debug_objects_enabled) + return; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (!obj) { + struct debug_obj o = { .object = addr, + .state = ODEBUG_STATE_NOTAVAILABLE, + .descr = descr }; + + raw_spin_unlock_irqrestore(&db->lock, flags); + /* + * Maybe the object is static, and we let the type specific + * code confirm. Track this static object if true, else invoke + * fixup. + */ + if (descr->is_static_object && descr->is_static_object(addr)) { + /* Track this static object */ + debug_object_init(addr, descr); + } else { + debug_print_object(&o, "assert_init"); + debug_object_fixup(descr->fixup_assert_init, addr, + ODEBUG_STATE_NOTAVAILABLE); + } + return; + } + + raw_spin_unlock_irqrestore(&db->lock, flags); +} +EXPORT_SYMBOL_GPL(debug_object_assert_init); + +/** + * debug_object_active_state - debug checks object usage state machine + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + * @expect: expected state + * @next: state to move to if expected state is found + */ +void +debug_object_active_state(void *addr, const struct debug_obj_descr *descr, + unsigned int expect, unsigned int next) +{ + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + bool print_object = false; + + if (!debug_objects_enabled) + return; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (obj) { + switch (obj->state) { + case ODEBUG_STATE_ACTIVE: + if (obj->astate == expect) + obj->astate = next; + else + print_object = true; + break; + + default: + print_object = true; + break; + } + } + + raw_spin_unlock_irqrestore(&db->lock, flags); + if (!obj) { + struct debug_obj o = { .object = addr, + .state = ODEBUG_STATE_NOTAVAILABLE, + .descr = descr }; + + debug_print_object(&o, "active_state"); + } else if (print_object) { + debug_print_object(obj, "active_state"); + } +} +EXPORT_SYMBOL_GPL(debug_object_active_state); + +#ifdef CONFIG_DEBUG_OBJECTS_FREE +static void __debug_check_no_obj_freed(const void *address, unsigned long size) +{ + unsigned long flags, oaddr, saddr, eaddr, paddr, chunks; + const struct debug_obj_descr *descr; + enum debug_obj_state state; + struct debug_bucket *db; + struct hlist_node *tmp; + struct debug_obj *obj; + int cnt, objs_checked = 0; + + saddr = (unsigned long) address; + eaddr = saddr + size; + paddr = saddr & ODEBUG_CHUNK_MASK; + chunks = ((eaddr - paddr) + (ODEBUG_CHUNK_SIZE - 1)); + chunks >>= ODEBUG_CHUNK_SHIFT; + + for (;chunks > 0; chunks--, paddr += ODEBUG_CHUNK_SIZE) { + db = get_bucket(paddr); + +repeat: + cnt = 0; + raw_spin_lock_irqsave(&db->lock, flags); + hlist_for_each_entry_safe(obj, tmp, &db->list, node) { + cnt++; + oaddr = (unsigned long) obj->object; + if (oaddr < saddr || oaddr >= eaddr) + continue; + + switch (obj->state) { + case ODEBUG_STATE_ACTIVE: + descr = obj->descr; + state = obj->state; + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "free"); + debug_object_fixup(descr->fixup_free, + (void *) oaddr, state); + goto repeat; + default: + hlist_del(&obj->node); + __free_object(obj); + break; + } + } + raw_spin_unlock_irqrestore(&db->lock, flags); + + if (cnt > debug_objects_maxchain) + debug_objects_maxchain = cnt; + + objs_checked += cnt; + } + + if (objs_checked > debug_objects_maxchecked) + debug_objects_maxchecked = objs_checked; + + /* Schedule work to actually kmem_cache_free() objects */ + if (!READ_ONCE(obj_freeing) && READ_ONCE(obj_nr_tofree)) { + WRITE_ONCE(obj_freeing, true); + schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY); + } +} + +void debug_check_no_obj_freed(const void *address, unsigned long size) +{ + if (debug_objects_enabled) + __debug_check_no_obj_freed(address, size); +} +#endif + +#ifdef CONFIG_DEBUG_FS + +static int debug_stats_show(struct seq_file *m, void *v) +{ + int cpu, obj_percpu_free = 0; + + for_each_possible_cpu(cpu) + obj_percpu_free += per_cpu(percpu_obj_pool.obj_free, cpu); + + seq_printf(m, "max_chain :%d\n", debug_objects_maxchain); + seq_printf(m, "max_checked :%d\n", debug_objects_maxchecked); + seq_printf(m, "warnings :%d\n", debug_objects_warnings); + seq_printf(m, "fixups :%d\n", debug_objects_fixups); + seq_printf(m, "pool_free :%d\n", READ_ONCE(obj_pool_free) + obj_percpu_free); + seq_printf(m, "pool_pcp_free :%d\n", obj_percpu_free); + seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free); + seq_printf(m, "pool_used :%d\n", obj_pool_used - obj_percpu_free); + seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used); + seq_printf(m, "on_free_list :%d\n", READ_ONCE(obj_nr_tofree)); + seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated); + seq_printf(m, "objs_freed :%d\n", debug_objects_freed); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(debug_stats); + +static int __init debug_objects_init_debugfs(void) +{ + struct dentry *dbgdir; + + if (!debug_objects_enabled) + return 0; + + dbgdir = debugfs_create_dir("debug_objects", NULL); + + debugfs_create_file("stats", 0444, dbgdir, NULL, &debug_stats_fops); + + return 0; +} +__initcall(debug_objects_init_debugfs); + +#else +static inline void debug_objects_init_debugfs(void) { } +#endif + +#ifdef CONFIG_DEBUG_OBJECTS_SELFTEST + +/* Random data structure for the self test */ +struct self_test { + unsigned long dummy1[6]; + int static_init; + unsigned long dummy2[3]; +}; + +static __initconst const struct debug_obj_descr descr_type_test; + +static bool __init is_static_object(void *addr) +{ + struct self_test *obj = addr; + + return obj->static_init; +} + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static bool __init fixup_init(void *addr, enum debug_obj_state state) +{ + struct self_test *obj = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + debug_object_deactivate(obj, &descr_type_test); + debug_object_init(obj, &descr_type_test); + return true; + default: + return false; + } +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown non-static object is activated + */ +static bool __init fixup_activate(void *addr, enum debug_obj_state state) +{ + struct self_test *obj = addr; + + switch (state) { + case ODEBUG_STATE_NOTAVAILABLE: + return true; + case ODEBUG_STATE_ACTIVE: + debug_object_deactivate(obj, &descr_type_test); + debug_object_activate(obj, &descr_type_test); + return true; + + default: + return false; + } +} + +/* + * fixup_destroy is called when: + * - an active object is destroyed + */ +static bool __init fixup_destroy(void *addr, enum debug_obj_state state) +{ + struct self_test *obj = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + debug_object_deactivate(obj, &descr_type_test); + debug_object_destroy(obj, &descr_type_test); + return true; + default: + return false; + } +} + +/* + * fixup_free is called when: + * - an active object is freed + */ +static bool __init fixup_free(void *addr, enum debug_obj_state state) +{ + struct self_test *obj = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + debug_object_deactivate(obj, &descr_type_test); + debug_object_free(obj, &descr_type_test); + return true; + default: + return false; + } +} + +static int __init +check_results(void *addr, enum debug_obj_state state, int fixups, int warnings) +{ + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + int res = -EINVAL; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (!obj && state != ODEBUG_STATE_NONE) { + WARN(1, KERN_ERR "ODEBUG: selftest object not found\n"); + goto out; + } + if (obj && obj->state != state) { + WARN(1, KERN_ERR "ODEBUG: selftest wrong state: %d != %d\n", + obj->state, state); + goto out; + } + if (fixups != debug_objects_fixups) { + WARN(1, KERN_ERR "ODEBUG: selftest fixups failed %d != %d\n", + fixups, debug_objects_fixups); + goto out; + } + if (warnings != debug_objects_warnings) { + WARN(1, KERN_ERR "ODEBUG: selftest warnings failed %d != %d\n", + warnings, debug_objects_warnings); + goto out; + } + res = 0; +out: + raw_spin_unlock_irqrestore(&db->lock, flags); + if (res) + debug_objects_enabled = 0; + return res; +} + +static __initconst const struct debug_obj_descr descr_type_test = { + .name = "selftest", + .is_static_object = is_static_object, + .fixup_init = fixup_init, + .fixup_activate = fixup_activate, + .fixup_destroy = fixup_destroy, + .fixup_free = fixup_free, +}; + +static __initdata struct self_test obj = { .static_init = 0 }; + +static void __init debug_objects_selftest(void) +{ + int fixups, oldfixups, warnings, oldwarnings; + unsigned long flags; + + local_irq_save(flags); + + fixups = oldfixups = debug_objects_fixups; + warnings = oldwarnings = debug_objects_warnings; + descr_test = &descr_type_test; + + debug_object_init(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_INIT, fixups, warnings)) + goto out; + debug_object_activate(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_ACTIVE, fixups, warnings)) + goto out; + debug_object_activate(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_ACTIVE, ++fixups, ++warnings)) + goto out; + debug_object_deactivate(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_INACTIVE, fixups, warnings)) + goto out; + debug_object_destroy(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_DESTROYED, fixups, warnings)) + goto out; + debug_object_init(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_DESTROYED, fixups, ++warnings)) + goto out; + debug_object_activate(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_DESTROYED, fixups, ++warnings)) + goto out; + debug_object_deactivate(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_DESTROYED, fixups, ++warnings)) + goto out; + debug_object_free(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_NONE, fixups, warnings)) + goto out; + + obj.static_init = 1; + debug_object_activate(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_ACTIVE, fixups, warnings)) + goto out; + debug_object_init(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_INIT, ++fixups, ++warnings)) + goto out; + debug_object_free(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_NONE, fixups, warnings)) + goto out; + +#ifdef CONFIG_DEBUG_OBJECTS_FREE + debug_object_init(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_INIT, fixups, warnings)) + goto out; + debug_object_activate(&obj, &descr_type_test); + if (check_results(&obj, ODEBUG_STATE_ACTIVE, fixups, warnings)) + goto out; + __debug_check_no_obj_freed(&obj, sizeof(obj)); + if (check_results(&obj, ODEBUG_STATE_NONE, ++fixups, ++warnings)) + goto out; +#endif + pr_info("selftest passed\n"); + +out: + debug_objects_fixups = oldfixups; + debug_objects_warnings = oldwarnings; + descr_test = NULL; + + local_irq_restore(flags); +} +#else +static inline void debug_objects_selftest(void) { } +#endif + +/* + * Called during early boot to initialize the hash buckets and link + * the static object pool objects into the poll list. After this call + * the object tracker is fully operational. + */ +void __init debug_objects_early_init(void) +{ + int i; + + for (i = 0; i < ODEBUG_HASH_SIZE; i++) + raw_spin_lock_init(&obj_hash[i].lock); + + for (i = 0; i < ODEBUG_POOL_SIZE; i++) + hlist_add_head(&obj_static_pool[i].node, &obj_pool); +} + +/* + * Convert the statically allocated objects to dynamic ones: + */ +static int __init debug_objects_replace_static_objects(void) +{ + struct debug_bucket *db = obj_hash; + struct hlist_node *tmp; + struct debug_obj *obj, *new; + HLIST_HEAD(objects); + int i, cnt = 0; + + for (i = 0; i < ODEBUG_POOL_SIZE; i++) { + obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL); + if (!obj) + goto free; + hlist_add_head(&obj->node, &objects); + } + + debug_objects_allocated += i; + + /* + * debug_objects_mem_init() is now called early that only one CPU is up + * and interrupts have been disabled, so it is safe to replace the + * active object references. + */ + + /* Remove the statically allocated objects from the pool */ + hlist_for_each_entry_safe(obj, tmp, &obj_pool, node) + hlist_del(&obj->node); + /* Move the allocated objects to the pool */ + hlist_move_list(&objects, &obj_pool); + + /* Replace the active object references */ + for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { + hlist_move_list(&db->list, &objects); + + hlist_for_each_entry(obj, &objects, node) { + new = hlist_entry(obj_pool.first, typeof(*obj), node); + hlist_del(&new->node); + /* copy object data */ + *new = *obj; + hlist_add_head(&new->node, &db->list); + cnt++; + } + } + + pr_debug("%d of %d active objects replaced\n", + cnt, obj_pool_used); + return 0; +free: + hlist_for_each_entry_safe(obj, tmp, &objects, node) { + hlist_del(&obj->node); + kmem_cache_free(obj_cache, obj); + } + return -ENOMEM; +} + +/* + * Called after the kmem_caches are functional to setup a dedicated + * cache pool, which has the SLAB_DEBUG_OBJECTS flag set. This flag + * prevents that the debug code is called on kmem_cache_free() for the + * debug tracker objects to avoid recursive calls. + */ +void __init debug_objects_mem_init(void) +{ + int cpu, extras; + + if (!debug_objects_enabled) + return; + + /* + * Initialize the percpu object pools + * + * Initialization is not strictly necessary, but was done for + * completeness. + */ + for_each_possible_cpu(cpu) + INIT_HLIST_HEAD(&per_cpu(percpu_obj_pool.free_objs, cpu)); + + obj_cache = kmem_cache_create("debug_objects_cache", + sizeof (struct debug_obj), 0, + SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE, + NULL); + + if (!obj_cache || debug_objects_replace_static_objects()) { + debug_objects_enabled = 0; + kmem_cache_destroy(obj_cache); + pr_warn("out of memory.\n"); + return; + } else + debug_objects_selftest(); + +#ifdef CONFIG_HOTPLUG_CPU + cpuhp_setup_state_nocalls(CPUHP_DEBUG_OBJ_DEAD, "object:offline", NULL, + object_cpu_offline); +#endif + + /* + * Increase the thresholds for allocating and freeing objects + * according to the number of possible CPUs available in the system. + */ + extras = num_possible_cpus() * ODEBUG_BATCH_SIZE; + debug_objects_pool_size += extras; + debug_objects_pool_min_level += extras; +} -- cgit v1.2.3