linux/lib/ref_tracker.c

276 lines
6.7 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
#define pr_fmt(fmt) "ref_tracker: " fmt
#include <linux/export.h>
#include <linux/list_sort.h>
#include <linux/ref_tracker.h>
#include <linux/slab.h>
#include <linux/stacktrace.h>
#include <linux/stackdepot.h>
#define REF_TRACKER_STACK_ENTRIES 16
#define STACK_BUF_SIZE 1024
struct ref_tracker {
struct list_head head; /* anchor into dir->list or dir->quarantine */
bool dead;
depot_stack_handle_t alloc_stack_handle;
depot_stack_handle_t free_stack_handle;
};
struct ref_tracker_dir_stats {
int total;
int count;
struct {
depot_stack_handle_t stack_handle;
unsigned int count;
} stacks[];
};
static struct ref_tracker_dir_stats *
ref_tracker_get_stats(struct ref_tracker_dir *dir, unsigned int limit)
{
struct ref_tracker_dir_stats *stats;
struct ref_tracker *tracker;
stats = kmalloc(struct_size(stats, stacks, limit),
GFP_NOWAIT | __GFP_NOWARN);
if (!stats)
return ERR_PTR(-ENOMEM);
stats->total = 0;
stats->count = 0;
list_for_each_entry(tracker, &dir->list, head) {
depot_stack_handle_t stack = tracker->alloc_stack_handle;
int i;
++stats->total;
for (i = 0; i < stats->count; ++i)
if (stats->stacks[i].stack_handle == stack)
break;
if (i >= limit)
continue;
if (i >= stats->count) {
stats->stacks[i].stack_handle = stack;
stats->stacks[i].count = 0;
++stats->count;
}
++stats->stacks[i].count;
}
return stats;
}
struct ostream {
char *buf;
int size, used;
};
#define pr_ostream(stream, fmt, args...) \
({ \
struct ostream *_s = (stream); \
\
if (!_s->buf) { \
pr_err(fmt, ##args); \
} else { \
int ret, len = _s->size - _s->used; \
ret = snprintf(_s->buf + _s->used, len, pr_fmt(fmt), ##args); \
_s->used += min(ret, len); \
} \
})
static void
__ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir,
unsigned int display_limit, struct ostream *s)
{
struct ref_tracker_dir_stats *stats;
unsigned int i = 0, skipped;
depot_stack_handle_t stack;
char *sbuf;
lockdep_assert_held(&dir->lock);
if (list_empty(&dir->list))
return;
stats = ref_tracker_get_stats(dir, display_limit);
if (IS_ERR(stats)) {
pr_ostream(s, "%s@%pK: couldn't get stats, error %pe\n",
dir->name, dir, stats);
return;
}
sbuf = kmalloc(STACK_BUF_SIZE, GFP_NOWAIT | __GFP_NOWARN);
for (i = 0, skipped = stats->total; i < stats->count; ++i) {
stack = stats->stacks[i].stack_handle;
if (sbuf && !stack_depot_snprint(stack, sbuf, STACK_BUF_SIZE, 4))
sbuf[0] = 0;
pr_ostream(s, "%s@%pK has %d/%d users at\n%s\n", dir->name, dir,
stats->stacks[i].count, stats->total, sbuf);
skipped -= stats->stacks[i].count;
}
if (skipped)
pr_ostream(s, "%s@%pK skipped reports about %d/%d users.\n",
dir->name, dir, skipped, stats->total);
kfree(sbuf);
kfree(stats);
}
void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir,
unsigned int display_limit)
{
struct ostream os = {};
__ref_tracker_dir_pr_ostream(dir, display_limit, &os);
}
EXPORT_SYMBOL(ref_tracker_dir_print_locked);
void ref_tracker_dir_print(struct ref_tracker_dir *dir,
unsigned int display_limit)
{
unsigned long flags;
spin_lock_irqsave(&dir->lock, flags);
ref_tracker_dir_print_locked(dir, display_limit);
spin_unlock_irqrestore(&dir->lock, flags);
}
EXPORT_SYMBOL(ref_tracker_dir_print);
int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size)
{
struct ostream os = { .buf = buf, .size = size };
unsigned long flags;
spin_lock_irqsave(&dir->lock, flags);
__ref_tracker_dir_pr_ostream(dir, 16, &os);
spin_unlock_irqrestore(&dir->lock, flags);
return os.used;
}
EXPORT_SYMBOL(ref_tracker_dir_snprint);
void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
{
struct ref_tracker *tracker, *n;
unsigned long flags;
bool leak = false;
dir->dead = true;
spin_lock_irqsave(&dir->lock, flags);
list_for_each_entry_safe(tracker, n, &dir->quarantine, head) {
list_del(&tracker->head);
kfree(tracker);
dir->quarantine_avail++;
}
if (!list_empty(&dir->list)) {
ref_tracker_dir_print_locked(dir, 16);
leak = true;
list_for_each_entry_safe(tracker, n, &dir->list, head) {
list_del(&tracker->head);
kfree(tracker);
}
}
spin_unlock_irqrestore(&dir->lock, flags);
WARN_ON_ONCE(leak);
WARN_ON_ONCE(refcount_read(&dir->untracked) != 1);
WARN_ON_ONCE(refcount_read(&dir->no_tracker) != 1);
}
EXPORT_SYMBOL(ref_tracker_dir_exit);
int ref_tracker_alloc(struct ref_tracker_dir *dir,
struct ref_tracker **trackerp,
gfp_t gfp)
{
unsigned long entries[REF_TRACKER_STACK_ENTRIES];
struct ref_tracker *tracker;
unsigned int nr_entries;
gfp_t gfp_mask = gfp | __GFP_NOWARN;
unsigned long flags;
WARN_ON_ONCE(dir->dead);
if (!trackerp) {
refcount_inc(&dir->no_tracker);
return 0;
}
ref_tracker: use __GFP_NOFAIL more carefully syzbot was able to trigger this warning from new_slab() /* * All existing users of the __GFP_NOFAIL are blockable, so warn * of any new users that actually require GFP_NOWAIT */ if (WARN_ON_ONCE(!can_direct_reclaim)) goto fail; Indeed, we should use __GFP_NOFAIL if direct reclaim is possible. Hopefully in the future we will be able to use SLAB_NOFAILSLAB option so that syzbot can benefit from full ref_tracker even in the presence of memory fault injections. WARNING: CPU: 0 PID: 13 at mm/page_alloc.c:5081 __alloc_pages_slowpath.constprop.0+0x1b7b/0x20d0 mm/page_alloc.c:5081 mm/page_alloc.c:5081 Modules linked in: CPU: 0 PID: 13 Comm: ksoftirqd/0 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__alloc_pages_slowpath.constprop.0+0x1b7b/0x20d0 mm/page_alloc.c:5081 mm/page_alloc.c:5081 Code: 90 08 00 00 48 81 c7 d8 04 00 00 48 89 f8 48 c1 e8 03 42 80 3c 30 00 0f 84 f0 ea ff ff e8 3d 82 09 00 e9 e6 ea ff ff 4d 89 fd <0f> 0b 48 b8 00 00 00 00 00 fc ff df 48 8b 54 24 30 48 c1 ea 03 80 RSP: 0018:ffffc90000d272b8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff88813fffc300 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000002 RDI: ffff88813fffc348 RBP: ffff88813fffc300 R08: 00000000000013dc R09: 00000000000013c8 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: ffffc90000d274e8 R14: dffffc0000000000 R15: ffffc90000d274e8 FS: 0000000000000000(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffefe6000f8 CR3: 000000001d21e000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> __alloc_pages+0x412/0x500 mm/page_alloc.c:5382 mm/page_alloc.c:5382 alloc_pages+0x1a7/0x300 mm/mempolicy.c:2191 mm/mempolicy.c:2191 alloc_slab_page mm/slub.c:1793 [inline] allocate_slab mm/slub.c:1938 [inline] alloc_slab_page mm/slub.c:1793 [inline] mm/slub.c:1993 allocate_slab mm/slub.c:1938 [inline] mm/slub.c:1993 new_slab+0x349/0x4a0 mm/slub.c:1993 mm/slub.c:1993 ___slab_alloc+0x918/0xfe0 mm/slub.c:3022 mm/slub.c:3022 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3109 mm/slub.c:3109 slab_alloc_node mm/slub.c:3200 [inline] slab_alloc mm/slub.c:3242 [inline] slab_alloc_node mm/slub.c:3200 [inline] mm/slub.c:3259 slab_alloc mm/slub.c:3242 [inline] mm/slub.c:3259 kmem_cache_alloc_trace+0x289/0x2c0 mm/slub.c:3259 mm/slub.c:3259 kmalloc include/linux/slab.h:590 [inline] kzalloc include/linux/slab.h:724 [inline] kmalloc include/linux/slab.h:590 [inline] lib/ref_tracker.c:74 kzalloc include/linux/slab.h:724 [inline] lib/ref_tracker.c:74 ref_tracker_alloc+0xe1/0x430 lib/ref_tracker.c:74 lib/ref_tracker.c:74 netdev_tracker_alloc include/linux/netdevice.h:3855 [inline] dev_hold_track include/linux/netdevice.h:3872 [inline] netdev_tracker_alloc include/linux/netdevice.h:3855 [inline] net/core/dst.c:52 dev_hold_track include/linux/netdevice.h:3872 [inline] net/core/dst.c:52 dst_init+0xe0/0x520 net/core/dst.c:52 net/core/dst.c:52 dst_alloc+0x16b/0x1f0 net/core/dst.c:96 net/core/dst.c:96 rt_dst_alloc+0x73/0x450 net/ipv4/route.c:1614 net/ipv4/route.c:1614 ip_route_input_mc net/ipv4/route.c:1720 [inline] ip_route_input_mc net/ipv4/route.c:1720 [inline] net/ipv4/route.c:2465 ip_route_input_rcu.part.0+0x4fe/0xcc0 net/ipv4/route.c:2465 net/ipv4/route.c:2465 ip_route_input_rcu net/ipv4/route.c:2420 [inline] ip_route_input_rcu net/ipv4/route.c:2420 [inline] net/ipv4/route.c:2416 ip_route_input_noref+0x1b8/0x2a0 net/ipv4/route.c:2416 net/ipv4/route.c:2416 ip_rcv_finish_core.constprop.0+0x288/0x1e90 net/ipv4/ip_input.c:354 net/ipv4/ip_input.c:354 ip_rcv_finish+0x135/0x2f0 net/ipv4/ip_input.c:427 net/ipv4/ip_input.c:427 NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] net/ipv4/ip_input.c:540 NF_HOOK include/linux/netfilter.h:301 [inline] net/ipv4/ip_input.c:540 ip_rcv+0xaa/0xd0 net/ipv4/ip_input.c:540 net/ipv4/ip_input.c:540 __netif_receive_skb_one_core+0x114/0x180 net/core/dev.c:5350 net/core/dev.c:5350 __netif_receive_skb+0x24/0x1b0 net/core/dev.c:5464 net/core/dev.c:5464 process_backlog+0x2a5/0x6c0 net/core/dev.c:5796 net/core/dev.c:5796 __napi_poll+0xaf/0x440 net/core/dev.c:6364 net/core/dev.c:6364 napi_poll net/core/dev.c:6431 [inline] napi_poll net/core/dev.c:6431 [inline] net/core/dev.c:6518 net_rx_action+0x801/0xb40 net/core/dev.c:6518 net/core/dev.c:6518 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 kernel/softirq.c:558 run_ksoftirqd kernel/softirq.c:921 [inline] run_ksoftirqd kernel/softirq.c:921 [inline] kernel/softirq.c:913 run_ksoftirqd+0x2d/0x60 kernel/softirq.c:913 kernel/softirq.c:913 smpboot_thread_fn+0x645/0x9c0 kernel/smpboot.c:164 kernel/smpboot.c:164 kthread+0x405/0x4f0 kernel/kthread.c:327 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 arch/x86/entry/entry_64.S:295 Fixes: 4e66934eaadc ("lib: add reference counting tracking infrastructure") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-01-12 11:14:45 +00:00
if (gfp & __GFP_DIRECT_RECLAIM)
gfp_mask |= __GFP_NOFAIL;
*trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask);
if (unlikely(!tracker)) {
pr_err_once("memory allocation failure, unreliable refcount tracker.\n");
refcount_inc(&dir->untracked);
return -ENOMEM;
}
nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp);
spin_lock_irqsave(&dir->lock, flags);
list_add(&tracker->head, &dir->list);
spin_unlock_irqrestore(&dir->lock, flags);
return 0;
}
EXPORT_SYMBOL_GPL(ref_tracker_alloc);
int ref_tracker_free(struct ref_tracker_dir *dir,
struct ref_tracker **trackerp)
{
unsigned long entries[REF_TRACKER_STACK_ENTRIES];
depot_stack_handle_t stack_handle;
struct ref_tracker *tracker;
unsigned int nr_entries;
unsigned long flags;
WARN_ON_ONCE(dir->dead);
if (!trackerp) {
refcount_dec(&dir->no_tracker);
return 0;
}
tracker = *trackerp;
if (!tracker) {
refcount_dec(&dir->untracked);
return -EEXIST;
}
nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
stack_handle = stack_depot_save(entries, nr_entries,
GFP_NOWAIT | __GFP_NOWARN);
spin_lock_irqsave(&dir->lock, flags);
if (tracker->dead) {
pr_err("reference already released.\n");
if (tracker->alloc_stack_handle) {
pr_err("allocated in:\n");
stack_depot_print(tracker->alloc_stack_handle);
}
if (tracker->free_stack_handle) {
pr_err("freed in:\n");
stack_depot_print(tracker->free_stack_handle);
}
spin_unlock_irqrestore(&dir->lock, flags);
WARN_ON_ONCE(1);
return -EINVAL;
}
tracker->dead = true;
tracker->free_stack_handle = stack_handle;
list_move_tail(&tracker->head, &dir->quarantine);
if (!dir->quarantine_avail) {
tracker = list_first_entry(&dir->quarantine, struct ref_tracker, head);
list_del(&tracker->head);
} else {
dir->quarantine_avail--;
tracker = NULL;
}
spin_unlock_irqrestore(&dir->lock, flags);
kfree(tracker);
return 0;
}
EXPORT_SYMBOL_GPL(ref_tracker_free);