c15c1199d6
Changes in 5.10.216 batman-adv: Avoid infinite loop trying to resize local TT Bluetooth: Fix memory leak in hci_req_sync_complete() media: cec: core: remove length check of Timer Status nouveau: fix function cast warning net: openvswitch: fix unwanted error log on timeout policy probing u64_stats: fix u64_stats_init() for lockdep when used repeatedly in one file xsk: validate user input for XDP_{UMEM|COMPLETION}_FILL_RING geneve: fix header validation in geneve[6]_xmit_skb octeontx2-af: Fix NIX SQ mode and BP config ipv6: fib: hide unused 'pn' variable ipv4/route: avoid unused-but-set-variable warning ipv6: fix race condition between ipv6_get_ifaddr and ipv6_del_addr Bluetooth: SCO: Fix not validating setsockopt user input netfilter: complete validation of user input net/mlx5: Properly link new fs rules into the tree af_unix: Do not use atomic ops for unix_sk(sk)->inflight. af_unix: Fix garbage collector racing against connect() net: ena: Fix potential sign extension issue net: ena: Wrong missing IO completions check order net: ena: Fix incorrect descriptor free behavior iommu/vt-d: Allocate local memory for page request queue mailbox: imx: fix suspend failue btrfs: qgroup: correctly model root qgroup rsv in convert drm/client: Fully protect modes[] with dev->mode_config.mutex vhost: Add smp_rmb() in vhost_vq_avail_empty() x86/cpu: Actually turn off mitigations by default for SPECULATION_MITIGATIONS=n selftests: timers: Fix abs() warning in posix_timers test x86/apic: Force native_apic_mem_read() to use the MOV instruction irqflags: Explicitly ignore lockdep_hrtimer_exit() argument btrfs: record delayed inode root in transaction riscv: Enable per-task stack canaries riscv: process: Fix kernel gp leakage selftests/ftrace: Limit length in subsystem-enable tests kprobes: Fix possible use-after-free issue on kprobe registration Revert "tracing/trigger: Fix to return error if failed to alloc snapshot" netfilter: nf_tables: Fix potential data-race in __nft_expr_type_get() netfilter: nft_set_pipapo: do not free live element tun: limit printing rate when illegal packet received by tun dev RDMA/rxe: Fix the problem "mutex_destroy missing" RDMA/cm: Print the old state when cm_destroy_id gets timeout RDMA/mlx5: Fix port number for counter query in multi-port configuration drm: nv04: Fix out of bounds access drm/panel: visionox-rm69299: don't unregister DSI device clk: Remove prepare_lock hold assertion in __clk_release() clk: Mark 'all_lists' as const clk: remove extra empty line clk: Print an info line before disabling unused clocks clk: Initialize struct clk_core kref earlier clk: Get runtime PM before walking tree during disable_unused x86/cpufeatures: Fix dependencies for GFNI, VAES, and VPCLMULQDQ binder: check offset alignment in binder_get_object() thunderbolt: Avoid notify PM core about runtime PM resume thunderbolt: Fix wake configurations after device unplug comedi: vmk80xx: fix incomplete endpoint checking serial/pmac_zilog: Remove flawed mitigation for rx irq flood USB: serial: option: add Fibocom FM135-GL variants USB: serial: option: add support for Fibocom FM650/FG650 USB: serial: option: add Lonsung U8300/U9300 product USB: serial: option: support Quectel EM060K sub-models USB: serial: option: add Rolling RW101-GL and RW135-GL support USB: serial: option: add Telit FN920C04 rmnet compositions Revert "usb: cdc-wdm: close race between read and workqueue" usb: dwc2: host: Fix dereference issue in DDMA completion flow. usb: Disable USB3 LPM at shutdown mei: me: disable RPL-S on SPS and IGN firmwares speakup: Avoid crash on very long word fs: sysfs: Fix reference leak in sysfs_break_active_protection() init/main.c: Fix potential static_command_line memory overflow drm/amdgpu: validate the parameters of bo mapping operations more clearly nouveau: fix instmem race condition around ptr stores nilfs2: fix OOB in nilfs_set_de_type arm64: dts: rockchip: fix alphabetical ordering RK3399 puma arm64: dts: rockchip: enable internal pull-up on PCIE_WAKE# for RK3399 Puma arm64: dts: rockchip: Remove unsupported node from the Pinebook Pro dts arm64: dts: mediatek: mt7622: add support for coherent DMA arm64: dts: mediatek: mt7622: introduce nodes for Wireless Ethernet Dispatch arm64: dts: mediatek: mt7622: fix clock controllers arm64: dts: mediatek: mt7622: fix IR nodename arm64: dts: mediatek: mt7622: fix ethernet controller "compatible" arm64: dts: mediatek: mt7622: drop "reset-names" from thermal block arm64: dts: mediatek: mt2712: fix validation errors ARC: [plat-hsdk]: Remove misplaced interrupt-cells property wifi: iwlwifi: mvm: remove old PASN station when adding a new one vxlan: drop packets from invalid src-address mlxsw: core: Unregister EMAD trap using FORWARD action NFC: trf7970a: disable all regulators on removal ipv4: check for NULL idev in ip_route_use_hint() net: usb: ax88179_178a: stop lying about skb->truesize net: gtp: Fix Use-After-Free in gtp_dellink ipvs: Fix checksumming on GSO of SCTP packets net: openvswitch: Fix Use-After-Free in ovs_ct_exit mlxsw: spectrum_acl_tcam: Fix race during rehash delayed work mlxsw: spectrum_acl_tcam: Fix possible use-after-free during activity update mlxsw: spectrum_acl_tcam: Fix possible use-after-free during rehash mlxsw: spectrum_acl_tcam: Rate limit error message mlxsw: spectrum_acl_tcam: Fix memory leak during rehash mlxsw: spectrum_acl_tcam: Fix warning during rehash mlxsw: spectrum_acl_tcam: Fix incorrect list API usage mlxsw: spectrum_acl_tcam: Fix memory leak when canceling rehash work netfilter: nf_tables: honor table dormant flag from netdev release event path i40e: Do not use WQ_MEM_RECLAIM flag for workqueue i40e: Report MFS in decimal base instead of hex iavf: Fix TC config comparison with existing adapter TC config net: ethernet: ti: am65-cpts: Fix PTPv1 message type on TX packets af_unix: Suppress false-positive lockdep splat for spin_lock() in __unix_gc(). serial: core: Provide port lock wrappers serial: mxs-auart: add spinlock around changing cts state Revert "crypto: api - Disallow identical driver names" net/mlx5e: Fix a race in command alloc flow tracing: Show size of requested perf buffer tracing: Increase PERF_MAX_TRACE_SIZE to handle Sentinel1 and docker together PM / devfreq: Fix buffer overflow in trans_stat_show Bluetooth: Fix type of len in {l2cap,sco}_sock_getsockopt_old() Bluetooth: btusb: Add Realtek RTL8852BE support ID 0x0bda:0x4853 btrfs: fix information leak in btrfs_ioctl_logical_to_ino() cpu: Re-enable CPU mitigations by default for !X86 architectures arm64: dts: rockchip: enable internal pull-up for Q7_THRM# on RK3399 Puma drm/amdgpu/sdma5.2: use legacy HDP flush for SDMA2/3 drm/amdgpu: Fix leak when GPU memory allocation fails irqchip/gic-v3-its: Prevent double free on error ethernet: Add helper for assigning packet type when dest address does not match device address net: b44: set pause params only when interface is up stackdepot: respect __GFP_NOLOCKDEP allocation flag mtd: diskonchip: work around ubsan link failure tcp: Clean up kernel listener's reqsk in inet_twsk_purge() tcp: Fix NEW_SYN_RECV handling in inet_twsk_purge() dmaengine: owl: fix register access functions idma64: Don't try to serve interrupts when device is powered off dma: xilinx_dpdma: Fix locking riscv: fix VMALLOC_START definition riscv: Fix TASK_SIZE on 64-bit NOMMU i2c: smbus: fix NULL function pointer dereference HID: i2c-hid: remove I2C_HID_READ_PENDING flag to prevent lock-up bounds: Use the right number of bits for power-of-two CONFIG_NR_CPUS udp: preserve the connected status if only UDP cmsg serial: core: fix kernel-doc for uart_port_unlock_irqrestore() riscv: Disable STACKPROTECTOR_PER_TASK if GCC_PLUGIN_RANDSTRUCT is enabled Linux 5.10.216 Change-Id: Ia2bf3ba6ed3f36a56f71543442427eb770a2400b Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
367 lines
10 KiB
C
367 lines
10 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Generic stack depot for storing stack traces.
|
|
*
|
|
* Some debugging tools need to save stack traces of certain events which can
|
|
* be later presented to the user. For example, KASAN needs to safe alloc and
|
|
* free stacks for each object, but storing two stack traces per object
|
|
* requires too much memory (e.g. SLUB_DEBUG needs 256 bytes per object for
|
|
* that).
|
|
*
|
|
* Instead, stack depot maintains a hashtable of unique stacktraces. Since alloc
|
|
* and free stacks repeat a lot, we save about 100x space.
|
|
* Stacks are never removed from depot, so we store them contiguously one after
|
|
* another in a contiguos memory allocation.
|
|
*
|
|
* Author: Alexander Potapenko <glider@google.com>
|
|
* Copyright (C) 2016 Google, Inc.
|
|
*
|
|
* Based on code by Dmitry Chernenkov.
|
|
*/
|
|
|
|
#include <linux/gfp.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/jhash.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/printk.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/stacktrace.h>
|
|
#include <linux/stackdepot.h>
|
|
#include <linux/string.h>
|
|
#include <linux/types.h>
|
|
#include <linux/memblock.h>
|
|
|
|
#define DEPOT_STACK_BITS (sizeof(depot_stack_handle_t) * 8)
|
|
|
|
#define STACK_ALLOC_NULL_PROTECTION_BITS 1
|
|
#define STACK_ALLOC_ORDER 2 /* 'Slab' size order for stack depot, 4 pages */
|
|
#define STACK_ALLOC_SIZE (1LL << (PAGE_SHIFT + STACK_ALLOC_ORDER))
|
|
#define STACK_ALLOC_ALIGN 4
|
|
#define STACK_ALLOC_OFFSET_BITS (STACK_ALLOC_ORDER + PAGE_SHIFT - \
|
|
STACK_ALLOC_ALIGN)
|
|
#define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - \
|
|
STACK_ALLOC_NULL_PROTECTION_BITS - STACK_ALLOC_OFFSET_BITS)
|
|
#define STACK_ALLOC_SLABS_CAP 8192
|
|
#define STACK_ALLOC_MAX_SLABS \
|
|
(((1LL << (STACK_ALLOC_INDEX_BITS)) < STACK_ALLOC_SLABS_CAP) ? \
|
|
(1LL << (STACK_ALLOC_INDEX_BITS)) : STACK_ALLOC_SLABS_CAP)
|
|
|
|
/* The compact structure to store the reference to stacks. */
|
|
union handle_parts {
|
|
depot_stack_handle_t handle;
|
|
struct {
|
|
u32 slabindex : STACK_ALLOC_INDEX_BITS;
|
|
u32 offset : STACK_ALLOC_OFFSET_BITS;
|
|
u32 valid : STACK_ALLOC_NULL_PROTECTION_BITS;
|
|
};
|
|
};
|
|
|
|
struct stack_record {
|
|
struct stack_record *next; /* Link in the hashtable */
|
|
u32 hash; /* Hash in the hastable */
|
|
u32 size; /* Number of frames in the stack */
|
|
union handle_parts handle;
|
|
unsigned long entries[]; /* Variable-sized array of entries. */
|
|
};
|
|
|
|
static void *stack_slabs[STACK_ALLOC_MAX_SLABS];
|
|
|
|
static int depot_index;
|
|
static int next_slab_inited;
|
|
static size_t depot_offset;
|
|
static DEFINE_RAW_SPINLOCK(depot_lock);
|
|
|
|
static bool init_stack_slab(void **prealloc)
|
|
{
|
|
if (!*prealloc)
|
|
return false;
|
|
/*
|
|
* This smp_load_acquire() pairs with smp_store_release() to
|
|
* |next_slab_inited| below and in depot_alloc_stack().
|
|
*/
|
|
if (smp_load_acquire(&next_slab_inited))
|
|
return true;
|
|
if (stack_slabs[depot_index] == NULL) {
|
|
stack_slabs[depot_index] = *prealloc;
|
|
*prealloc = NULL;
|
|
} else {
|
|
/* If this is the last depot slab, do not touch the next one. */
|
|
if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) {
|
|
stack_slabs[depot_index + 1] = *prealloc;
|
|
*prealloc = NULL;
|
|
}
|
|
/*
|
|
* This smp_store_release pairs with smp_load_acquire() from
|
|
* |next_slab_inited| above and in stack_depot_save().
|
|
*/
|
|
smp_store_release(&next_slab_inited, 1);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
/* Allocation of a new stack in raw storage */
|
|
static struct stack_record *depot_alloc_stack(unsigned long *entries, int size,
|
|
u32 hash, void **prealloc, gfp_t alloc_flags)
|
|
{
|
|
struct stack_record *stack;
|
|
size_t required_size = struct_size(stack, entries, size);
|
|
|
|
required_size = ALIGN(required_size, 1 << STACK_ALLOC_ALIGN);
|
|
|
|
if (unlikely(depot_offset + required_size > STACK_ALLOC_SIZE)) {
|
|
if (unlikely(depot_index + 1 >= STACK_ALLOC_MAX_SLABS)) {
|
|
WARN_ONCE(1, "Stack depot reached limit capacity");
|
|
return NULL;
|
|
}
|
|
depot_index++;
|
|
depot_offset = 0;
|
|
/*
|
|
* smp_store_release() here pairs with smp_load_acquire() from
|
|
* |next_slab_inited| in stack_depot_save() and
|
|
* init_stack_slab().
|
|
*/
|
|
if (depot_index + 1 < STACK_ALLOC_MAX_SLABS)
|
|
smp_store_release(&next_slab_inited, 0);
|
|
}
|
|
init_stack_slab(prealloc);
|
|
if (stack_slabs[depot_index] == NULL)
|
|
return NULL;
|
|
|
|
stack = stack_slabs[depot_index] + depot_offset;
|
|
|
|
stack->hash = hash;
|
|
stack->size = size;
|
|
stack->handle.slabindex = depot_index;
|
|
stack->handle.offset = depot_offset >> STACK_ALLOC_ALIGN;
|
|
stack->handle.valid = 1;
|
|
memcpy(stack->entries, entries, flex_array_size(stack, entries, size));
|
|
depot_offset += required_size;
|
|
|
|
return stack;
|
|
}
|
|
|
|
#define STACK_HASH_SIZE (1L << CONFIG_STACK_HASH_ORDER)
|
|
#define STACK_HASH_MASK (STACK_HASH_SIZE - 1)
|
|
#define STACK_HASH_SEED 0x9747b28c
|
|
|
|
static bool stack_depot_disable;
|
|
static struct stack_record **stack_table;
|
|
|
|
static int __init is_stack_depot_disabled(char *str)
|
|
{
|
|
int ret;
|
|
|
|
ret = kstrtobool(str, &stack_depot_disable);
|
|
if (!ret && stack_depot_disable) {
|
|
pr_info("Stack Depot is disabled\n");
|
|
stack_table = NULL;
|
|
}
|
|
return 0;
|
|
}
|
|
early_param("stack_depot_disable", is_stack_depot_disabled);
|
|
|
|
int __init stack_depot_init(void)
|
|
{
|
|
if (!stack_depot_disable) {
|
|
size_t size = (STACK_HASH_SIZE * sizeof(struct stack_record *));
|
|
int i;
|
|
|
|
stack_table = memblock_alloc(size, size);
|
|
for (i = 0; i < STACK_HASH_SIZE; i++)
|
|
stack_table[i] = NULL;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Calculate hash for a stack */
|
|
static inline u32 hash_stack(unsigned long *entries, unsigned int size)
|
|
{
|
|
return jhash2((u32 *)entries,
|
|
array_size(size, sizeof(*entries)) / sizeof(u32),
|
|
STACK_HASH_SEED);
|
|
}
|
|
|
|
/* Use our own, non-instrumented version of memcmp().
|
|
*
|
|
* We actually don't care about the order, just the equality.
|
|
*/
|
|
static inline
|
|
int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2,
|
|
unsigned int n)
|
|
{
|
|
for ( ; n-- ; u1++, u2++) {
|
|
if (*u1 != *u2)
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Find a stack that is equal to the one stored in entries in the hash */
|
|
static inline struct stack_record *find_stack(struct stack_record *bucket,
|
|
unsigned long *entries, int size,
|
|
u32 hash)
|
|
{
|
|
struct stack_record *found;
|
|
|
|
for (found = bucket; found; found = found->next) {
|
|
if (found->hash == hash &&
|
|
found->size == size &&
|
|
!stackdepot_memcmp(entries, found->entries, size))
|
|
return found;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
/**
|
|
* stack_depot_fetch - Fetch stack entries from a depot
|
|
*
|
|
* @handle: Stack depot handle which was returned from
|
|
* stack_depot_save().
|
|
* @entries: Pointer to store the entries address
|
|
*
|
|
* Return: The number of trace entries for this depot.
|
|
*/
|
|
unsigned int stack_depot_fetch(depot_stack_handle_t handle,
|
|
unsigned long **entries)
|
|
{
|
|
union handle_parts parts = { .handle = handle };
|
|
void *slab;
|
|
size_t offset = parts.offset << STACK_ALLOC_ALIGN;
|
|
struct stack_record *stack;
|
|
|
|
*entries = NULL;
|
|
if (parts.slabindex > depot_index) {
|
|
WARN(1, "slab index %d out of bounds (%d) for stack id %08x\n",
|
|
parts.slabindex, depot_index, handle);
|
|
return 0;
|
|
}
|
|
slab = stack_slabs[parts.slabindex];
|
|
if (!slab)
|
|
return 0;
|
|
stack = slab + offset;
|
|
|
|
*entries = stack->entries;
|
|
return stack->size;
|
|
}
|
|
EXPORT_SYMBOL_GPL(stack_depot_fetch);
|
|
|
|
/**
|
|
* stack_depot_save - Save a stack trace from an array
|
|
*
|
|
* @entries: Pointer to storage array
|
|
* @nr_entries: Size of the storage array
|
|
* @alloc_flags: Allocation gfp flags
|
|
*
|
|
* Return: The handle of the stack struct stored in depot
|
|
*/
|
|
depot_stack_handle_t stack_depot_save(unsigned long *entries,
|
|
unsigned int nr_entries,
|
|
gfp_t alloc_flags)
|
|
{
|
|
struct stack_record *found = NULL, **bucket;
|
|
depot_stack_handle_t retval = 0;
|
|
struct page *page = NULL;
|
|
void *prealloc = NULL;
|
|
unsigned long flags;
|
|
u32 hash;
|
|
|
|
if (unlikely(nr_entries == 0) || stack_depot_disable)
|
|
goto fast_exit;
|
|
|
|
hash = hash_stack(entries, nr_entries);
|
|
bucket = &stack_table[hash & STACK_HASH_MASK];
|
|
|
|
/*
|
|
* Fast path: look the stack trace up without locking.
|
|
* The smp_load_acquire() here pairs with smp_store_release() to
|
|
* |bucket| below.
|
|
*/
|
|
found = find_stack(smp_load_acquire(bucket), entries,
|
|
nr_entries, hash);
|
|
if (found)
|
|
goto exit;
|
|
|
|
/*
|
|
* Check if the current or the next stack slab need to be initialized.
|
|
* If so, allocate the memory - we won't be able to do that under the
|
|
* lock.
|
|
*
|
|
* The smp_load_acquire() here pairs with smp_store_release() to
|
|
* |next_slab_inited| in depot_alloc_stack() and init_stack_slab().
|
|
*/
|
|
if (unlikely(!smp_load_acquire(&next_slab_inited))) {
|
|
/*
|
|
* Zero out zone modifiers, as we don't have specific zone
|
|
* requirements. Keep the flags related to allocation in atomic
|
|
* contexts, I/O, nolockdep.
|
|
*/
|
|
alloc_flags &= ~GFP_ZONEMASK;
|
|
alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP);
|
|
alloc_flags |= __GFP_NOWARN;
|
|
page = alloc_pages(alloc_flags, STACK_ALLOC_ORDER);
|
|
if (page)
|
|
prealloc = page_address(page);
|
|
}
|
|
|
|
raw_spin_lock_irqsave(&depot_lock, flags);
|
|
|
|
found = find_stack(*bucket, entries, nr_entries, hash);
|
|
if (!found) {
|
|
struct stack_record *new =
|
|
depot_alloc_stack(entries, nr_entries,
|
|
hash, &prealloc, alloc_flags);
|
|
if (new) {
|
|
new->next = *bucket;
|
|
/*
|
|
* This smp_store_release() pairs with
|
|
* smp_load_acquire() from |bucket| above.
|
|
*/
|
|
smp_store_release(bucket, new);
|
|
found = new;
|
|
}
|
|
} else if (prealloc) {
|
|
/*
|
|
* We didn't need to store this stack trace, but let's keep
|
|
* the preallocated memory for the future.
|
|
*/
|
|
WARN_ON(!init_stack_slab(&prealloc));
|
|
}
|
|
|
|
raw_spin_unlock_irqrestore(&depot_lock, flags);
|
|
exit:
|
|
if (prealloc) {
|
|
/* Nobody used this memory, ok to free it. */
|
|
free_pages((unsigned long)prealloc, STACK_ALLOC_ORDER);
|
|
}
|
|
if (found)
|
|
retval = found->handle.handle;
|
|
fast_exit:
|
|
return retval;
|
|
}
|
|
EXPORT_SYMBOL_GPL(stack_depot_save);
|
|
|
|
static inline int in_irqentry_text(unsigned long ptr)
|
|
{
|
|
return (ptr >= (unsigned long)&__irqentry_text_start &&
|
|
ptr < (unsigned long)&__irqentry_text_end) ||
|
|
(ptr >= (unsigned long)&__softirqentry_text_start &&
|
|
ptr < (unsigned long)&__softirqentry_text_end);
|
|
}
|
|
|
|
unsigned int filter_irq_stacks(unsigned long *entries,
|
|
unsigned int nr_entries)
|
|
{
|
|
unsigned int i;
|
|
|
|
for (i = 0; i < nr_entries; i++) {
|
|
if (in_irqentry_text(entries[i])) {
|
|
/* Include the irqentry function into the stack. */
|
|
return i + 1;
|
|
}
|
|
}
|
|
return nr_entries;
|
|
}
|
|
EXPORT_SYMBOL_GPL(filter_irq_stacks);
|