linux_dsm_epyc7002/kernel/bpf/hashtab.c

388 lines
9.6 KiB
C
Raw Normal View History

/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/vmalloc.h>
struct bpf_htab {
struct bpf_map map;
struct hlist_head *buckets;
bpf: convert hashtab lock to raw lock When running bpf samples on rt kernel, it reports the below warning: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 in_atomic(): 1, irqs_disabled(): 128, pid: 477, name: ping Preemption disabled at:[<ffff80000017db58>] kprobe_perf_func+0x30/0x228 CPU: 3 PID: 477 Comm: ping Not tainted 4.1.10-rt8 #4 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [<ffff80000008a5b0>] dump_backtrace+0x0/0x128 [<ffff80000008a6f8>] show_stack+0x20/0x30 [<ffff8000007da90c>] dump_stack+0x7c/0xa0 [<ffff8000000e4830>] ___might_sleep+0x188/0x1a0 [<ffff8000007e2200>] rt_spin_lock+0x28/0x40 [<ffff80000018bf9c>] htab_map_update_elem+0x124/0x320 [<ffff80000018c718>] bpf_map_update_elem+0x40/0x58 [<ffff800000187658>] __bpf_prog_run+0xd48/0x1640 [<ffff80000017ca6c>] trace_call_bpf+0x8c/0x100 [<ffff80000017db58>] kprobe_perf_func+0x30/0x228 [<ffff80000017dd84>] kprobe_dispatcher+0x34/0x58 [<ffff8000007e399c>] kprobe_handler+0x114/0x250 [<ffff8000007e3bf4>] kprobe_breakpoint_handler+0x1c/0x30 [<ffff800000085b80>] brk_handler+0x88/0x98 [<ffff8000000822f0>] do_debug_exception+0x50/0xb8 Exception stack(0xffff808349687460 to 0xffff808349687580) 7460: 4ca2b600 ffff8083 4a3a7000 ffff8083 49687620 ffff8083 0069c5f8 ffff8000 7480: 00000001 00000000 007e0628 ffff8000 496874b0 ffff8083 007e1de8 ffff8000 74a0: 496874d0 ffff8083 0008e04c ffff8000 00000001 00000000 4ca2b600 ffff8083 74c0: 00ba2e80 ffff8000 49687528 ffff8083 49687510 ffff8083 000e5c70 ffff8000 74e0: 00c22348 ffff8000 00000000 ffff8083 49687510 ffff8083 000e5c74 ffff8000 7500: 4ca2b600 ffff8083 49401800 ffff8083 00000001 00000000 00000000 00000000 7520: 496874d0 ffff8083 00000000 00000000 00000000 00000000 00000000 00000000 7540: 2f2e2d2c 33323130 00000000 00000000 4c944500 ffff8083 00000000 00000000 7560: 00000000 00000000 008751e0 ffff8000 00000001 00000000 124e2d1d 00107b77 Convert hashtab lock to raw lock to avoid such warning. Signed-off-by: Yang Shi <yang.shi@linaro.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-31 05:16:26 +07:00
raw_spinlock_t lock;
u32 count; /* number of elements in this hashtable */
u32 n_buckets; /* number of hash buckets */
u32 elem_size; /* size of each element in bytes */
};
/* each htab element is struct htab_elem + key + value */
struct htab_elem {
struct hlist_node hash_node;
struct rcu_head rcu;
u32 hash;
char key[0] __aligned(8);
};
/* Called from syscall */
static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
{
struct bpf_htab *htab;
int err, i;
htab = kzalloc(sizeof(*htab), GFP_USER);
if (!htab)
return ERR_PTR(-ENOMEM);
/* mandatory map attributes */
htab->map.key_size = attr->key_size;
htab->map.value_size = attr->value_size;
htab->map.max_entries = attr->max_entries;
/* check sanity of attributes.
* value_size == 0 may be allowed in the future to use map as a set
*/
err = -EINVAL;
if (htab->map.max_entries == 0 || htab->map.key_size == 0 ||
htab->map.value_size == 0)
goto free_htab;
/* hash table size must be power of 2 */
htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
err = -E2BIG;
if (htab->map.key_size > MAX_BPF_STACK)
/* eBPF programs initialize keys on stack, so they cannot be
* larger than max stack size
*/
goto free_htab;
bpf: fix allocation warnings in bpf maps and integer overflow For large map->value_size the user space can trigger memory allocation warnings like: WARNING: CPU: 2 PID: 11122 at mm/page_alloc.c:2989 __alloc_pages_nodemask+0x695/0x14e0() Call Trace: [< inline >] __dump_stack lib/dump_stack.c:15 [<ffffffff82743b56>] dump_stack+0x68/0x92 lib/dump_stack.c:50 [<ffffffff81244ec9>] warn_slowpath_common+0xd9/0x140 kernel/panic.c:460 [<ffffffff812450f9>] warn_slowpath_null+0x29/0x30 kernel/panic.c:493 [< inline >] __alloc_pages_slowpath mm/page_alloc.c:2989 [<ffffffff81554e95>] __alloc_pages_nodemask+0x695/0x14e0 mm/page_alloc.c:3235 [<ffffffff816188fe>] alloc_pages_current+0xee/0x340 mm/mempolicy.c:2055 [< inline >] alloc_pages include/linux/gfp.h:451 [<ffffffff81550706>] alloc_kmem_pages+0x16/0xf0 mm/page_alloc.c:3414 [<ffffffff815a1c89>] kmalloc_order+0x19/0x60 mm/slab_common.c:1007 [<ffffffff815a1cef>] kmalloc_order_trace+0x1f/0xa0 mm/slab_common.c:1018 [< inline >] kmalloc_large include/linux/slab.h:390 [<ffffffff81627784>] __kmalloc+0x234/0x250 mm/slub.c:3525 [< inline >] kmalloc include/linux/slab.h:463 [< inline >] map_update_elem kernel/bpf/syscall.c:288 [< inline >] SYSC_bpf kernel/bpf/syscall.c:744 To avoid never succeeding kmalloc with order >= MAX_ORDER check that elem->value_size and computed elem_size are within limits for both hash and array type maps. Also add __GFP_NOWARN to kmalloc(value_size | elem_size) to avoid OOM warnings. Note kmalloc(key_size) is highly unlikely to trigger OOM, since key_size <= 512, so keep those kmalloc-s as-is. Large value_size can cause integer overflows in elem_size and map.pages formulas, so check for that as well. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-30 07:59:35 +07:00
if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) -
MAX_BPF_STACK - sizeof(struct htab_elem))
/* if value_size is bigger, the user space won't be able to
* access the elements via bpf syscall. This check also makes
* sure that the elem_size doesn't overflow and it's
* kmalloc-able later in htab_map_update_elem()
*/
goto free_htab;
htab->elem_size = sizeof(struct htab_elem) +
round_up(htab->map.key_size, 8) +
htab->map.value_size;
/* prevent zero size kmalloc and check for u32 overflow */
if (htab->n_buckets == 0 ||
htab->n_buckets > U32_MAX / sizeof(struct hlist_head))
goto free_htab;
bpf: fix allocation warnings in bpf maps and integer overflow For large map->value_size the user space can trigger memory allocation warnings like: WARNING: CPU: 2 PID: 11122 at mm/page_alloc.c:2989 __alloc_pages_nodemask+0x695/0x14e0() Call Trace: [< inline >] __dump_stack lib/dump_stack.c:15 [<ffffffff82743b56>] dump_stack+0x68/0x92 lib/dump_stack.c:50 [<ffffffff81244ec9>] warn_slowpath_common+0xd9/0x140 kernel/panic.c:460 [<ffffffff812450f9>] warn_slowpath_null+0x29/0x30 kernel/panic.c:493 [< inline >] __alloc_pages_slowpath mm/page_alloc.c:2989 [<ffffffff81554e95>] __alloc_pages_nodemask+0x695/0x14e0 mm/page_alloc.c:3235 [<ffffffff816188fe>] alloc_pages_current+0xee/0x340 mm/mempolicy.c:2055 [< inline >] alloc_pages include/linux/gfp.h:451 [<ffffffff81550706>] alloc_kmem_pages+0x16/0xf0 mm/page_alloc.c:3414 [<ffffffff815a1c89>] kmalloc_order+0x19/0x60 mm/slab_common.c:1007 [<ffffffff815a1cef>] kmalloc_order_trace+0x1f/0xa0 mm/slab_common.c:1018 [< inline >] kmalloc_large include/linux/slab.h:390 [<ffffffff81627784>] __kmalloc+0x234/0x250 mm/slub.c:3525 [< inline >] kmalloc include/linux/slab.h:463 [< inline >] map_update_elem kernel/bpf/syscall.c:288 [< inline >] SYSC_bpf kernel/bpf/syscall.c:744 To avoid never succeeding kmalloc with order >= MAX_ORDER check that elem->value_size and computed elem_size are within limits for both hash and array type maps. Also add __GFP_NOWARN to kmalloc(value_size | elem_size) to avoid OOM warnings. Note kmalloc(key_size) is highly unlikely to trigger OOM, since key_size <= 512, so keep those kmalloc-s as-is. Large value_size can cause integer overflows in elem_size and map.pages formulas, so check for that as well. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-30 07:59:35 +07:00
if ((u64) htab->n_buckets * sizeof(struct hlist_head) +
(u64) htab->elem_size * htab->map.max_entries >=
U32_MAX - PAGE_SIZE)
/* make sure page count doesn't overflow */
goto free_htab;
htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) +
htab->elem_size * htab->map.max_entries,
PAGE_SIZE) >> PAGE_SHIFT;
err = -ENOMEM;
htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head),
GFP_USER | __GFP_NOWARN);
if (!htab->buckets) {
htab->buckets = vmalloc(htab->n_buckets * sizeof(struct hlist_head));
if (!htab->buckets)
goto free_htab;
}
for (i = 0; i < htab->n_buckets; i++)
INIT_HLIST_HEAD(&htab->buckets[i]);
bpf: convert hashtab lock to raw lock When running bpf samples on rt kernel, it reports the below warning: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 in_atomic(): 1, irqs_disabled(): 128, pid: 477, name: ping Preemption disabled at:[<ffff80000017db58>] kprobe_perf_func+0x30/0x228 CPU: 3 PID: 477 Comm: ping Not tainted 4.1.10-rt8 #4 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [<ffff80000008a5b0>] dump_backtrace+0x0/0x128 [<ffff80000008a6f8>] show_stack+0x20/0x30 [<ffff8000007da90c>] dump_stack+0x7c/0xa0 [<ffff8000000e4830>] ___might_sleep+0x188/0x1a0 [<ffff8000007e2200>] rt_spin_lock+0x28/0x40 [<ffff80000018bf9c>] htab_map_update_elem+0x124/0x320 [<ffff80000018c718>] bpf_map_update_elem+0x40/0x58 [<ffff800000187658>] __bpf_prog_run+0xd48/0x1640 [<ffff80000017ca6c>] trace_call_bpf+0x8c/0x100 [<ffff80000017db58>] kprobe_perf_func+0x30/0x228 [<ffff80000017dd84>] kprobe_dispatcher+0x34/0x58 [<ffff8000007e399c>] kprobe_handler+0x114/0x250 [<ffff8000007e3bf4>] kprobe_breakpoint_handler+0x1c/0x30 [<ffff800000085b80>] brk_handler+0x88/0x98 [<ffff8000000822f0>] do_debug_exception+0x50/0xb8 Exception stack(0xffff808349687460 to 0xffff808349687580) 7460: 4ca2b600 ffff8083 4a3a7000 ffff8083 49687620 ffff8083 0069c5f8 ffff8000 7480: 00000001 00000000 007e0628 ffff8000 496874b0 ffff8083 007e1de8 ffff8000 74a0: 496874d0 ffff8083 0008e04c ffff8000 00000001 00000000 4ca2b600 ffff8083 74c0: 00ba2e80 ffff8000 49687528 ffff8083 49687510 ffff8083 000e5c70 ffff8000 74e0: 00c22348 ffff8000 00000000 ffff8083 49687510 ffff8083 000e5c74 ffff8000 7500: 4ca2b600 ffff8083 49401800 ffff8083 00000001 00000000 00000000 00000000 7520: 496874d0 ffff8083 00000000 00000000 00000000 00000000 00000000 00000000 7540: 2f2e2d2c 33323130 00000000 00000000 4c944500 ffff8083 00000000 00000000 7560: 00000000 00000000 008751e0 ffff8000 00000001 00000000 124e2d1d 00107b77 Convert hashtab lock to raw lock to avoid such warning. Signed-off-by: Yang Shi <yang.shi@linaro.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-31 05:16:26 +07:00
raw_spin_lock_init(&htab->lock);
htab->count = 0;
return &htab->map;
free_htab:
kfree(htab);
return ERR_PTR(err);
}
static inline u32 htab_map_hash(const void *key, u32 key_len)
{
return jhash(key, key_len, 0);
}
static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
{
return &htab->buckets[hash & (htab->n_buckets - 1)];
}
static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,
void *key, u32 key_size)
{
struct htab_elem *l;
hlist_for_each_entry_rcu(l, head, hash_node)
if (l->hash == hash && !memcmp(&l->key, key, key_size))
return l;
return NULL;
}
/* Called from syscall or from eBPF program */
static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct hlist_head *head;
struct htab_elem *l;
u32 hash, key_size;
/* Must be called with rcu_read_lock. */
WARN_ON_ONCE(!rcu_read_lock_held());
key_size = map->key_size;
hash = htab_map_hash(key, key_size);
head = select_bucket(htab, hash);
l = lookup_elem_raw(head, hash, key, key_size);
if (l)
return l->key + round_up(map->key_size, 8);
return NULL;
}
/* Called from syscall */
static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct hlist_head *head;
struct htab_elem *l, *next_l;
u32 hash, key_size;
int i;
WARN_ON_ONCE(!rcu_read_lock_held());
key_size = map->key_size;
hash = htab_map_hash(key, key_size);
head = select_bucket(htab, hash);
/* lookup the key */
l = lookup_elem_raw(head, hash, key, key_size);
if (!l) {
i = 0;
goto find_first_elem;
}
/* key was found, get next key in the same bucket */
next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
struct htab_elem, hash_node);
if (next_l) {
/* if next elem in this hash list is non-zero, just return it */
memcpy(next_key, next_l->key, key_size);
return 0;
}
/* no more elements in this hash list, go to the next bucket */
i = hash & (htab->n_buckets - 1);
i++;
find_first_elem:
/* iterate over buckets */
for (; i < htab->n_buckets; i++) {
head = select_bucket(htab, i);
/* pick first element in the bucket */
next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
struct htab_elem, hash_node);
if (next_l) {
/* if it's not empty, just return it */
memcpy(next_key, next_l->key, key_size);
return 0;
}
}
/* itereated over all buckets and all elements */
return -ENOENT;
}
/* Called from syscall or from eBPF program */
static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct htab_elem *l_new, *l_old;
struct hlist_head *head;
unsigned long flags;
u32 key_size;
int ret;
if (map_flags > BPF_EXIST)
/* unknown flags */
return -EINVAL;
WARN_ON_ONCE(!rcu_read_lock_held());
/* allocate new element outside of lock */
bpf: fix allocation warnings in bpf maps and integer overflow For large map->value_size the user space can trigger memory allocation warnings like: WARNING: CPU: 2 PID: 11122 at mm/page_alloc.c:2989 __alloc_pages_nodemask+0x695/0x14e0() Call Trace: [< inline >] __dump_stack lib/dump_stack.c:15 [<ffffffff82743b56>] dump_stack+0x68/0x92 lib/dump_stack.c:50 [<ffffffff81244ec9>] warn_slowpath_common+0xd9/0x140 kernel/panic.c:460 [<ffffffff812450f9>] warn_slowpath_null+0x29/0x30 kernel/panic.c:493 [< inline >] __alloc_pages_slowpath mm/page_alloc.c:2989 [<ffffffff81554e95>] __alloc_pages_nodemask+0x695/0x14e0 mm/page_alloc.c:3235 [<ffffffff816188fe>] alloc_pages_current+0xee/0x340 mm/mempolicy.c:2055 [< inline >] alloc_pages include/linux/gfp.h:451 [<ffffffff81550706>] alloc_kmem_pages+0x16/0xf0 mm/page_alloc.c:3414 [<ffffffff815a1c89>] kmalloc_order+0x19/0x60 mm/slab_common.c:1007 [<ffffffff815a1cef>] kmalloc_order_trace+0x1f/0xa0 mm/slab_common.c:1018 [< inline >] kmalloc_large include/linux/slab.h:390 [<ffffffff81627784>] __kmalloc+0x234/0x250 mm/slub.c:3525 [< inline >] kmalloc include/linux/slab.h:463 [< inline >] map_update_elem kernel/bpf/syscall.c:288 [< inline >] SYSC_bpf kernel/bpf/syscall.c:744 To avoid never succeeding kmalloc with order >= MAX_ORDER check that elem->value_size and computed elem_size are within limits for both hash and array type maps. Also add __GFP_NOWARN to kmalloc(value_size | elem_size) to avoid OOM warnings. Note kmalloc(key_size) is highly unlikely to trigger OOM, since key_size <= 512, so keep those kmalloc-s as-is. Large value_size can cause integer overflows in elem_size and map.pages formulas, so check for that as well. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-30 07:59:35 +07:00
l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
if (!l_new)
return -ENOMEM;
key_size = map->key_size;
memcpy(l_new->key, key, key_size);
memcpy(l_new->key + round_up(key_size, 8), value, map->value_size);
l_new->hash = htab_map_hash(l_new->key, key_size);
/* bpf_map_update_elem() can be called in_irq() */
bpf: convert hashtab lock to raw lock When running bpf samples on rt kernel, it reports the below warning: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 in_atomic(): 1, irqs_disabled(): 128, pid: 477, name: ping Preemption disabled at:[<ffff80000017db58>] kprobe_perf_func+0x30/0x228 CPU: 3 PID: 477 Comm: ping Not tainted 4.1.10-rt8 #4 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [<ffff80000008a5b0>] dump_backtrace+0x0/0x128 [<ffff80000008a6f8>] show_stack+0x20/0x30 [<ffff8000007da90c>] dump_stack+0x7c/0xa0 [<ffff8000000e4830>] ___might_sleep+0x188/0x1a0 [<ffff8000007e2200>] rt_spin_lock+0x28/0x40 [<ffff80000018bf9c>] htab_map_update_elem+0x124/0x320 [<ffff80000018c718>] bpf_map_update_elem+0x40/0x58 [<ffff800000187658>] __bpf_prog_run+0xd48/0x1640 [<ffff80000017ca6c>] trace_call_bpf+0x8c/0x100 [<ffff80000017db58>] kprobe_perf_func+0x30/0x228 [<ffff80000017dd84>] kprobe_dispatcher+0x34/0x58 [<ffff8000007e399c>] kprobe_handler+0x114/0x250 [<ffff8000007e3bf4>] kprobe_breakpoint_handler+0x1c/0x30 [<ffff800000085b80>] brk_handler+0x88/0x98 [<ffff8000000822f0>] do_debug_exception+0x50/0xb8 Exception stack(0xffff808349687460 to 0xffff808349687580) 7460: 4ca2b600 ffff8083 4a3a7000 ffff8083 49687620 ffff8083 0069c5f8 ffff8000 7480: 00000001 00000000 007e0628 ffff8000 496874b0 ffff8083 007e1de8 ffff8000 74a0: 496874d0 ffff8083 0008e04c ffff8000 00000001 00000000 4ca2b600 ffff8083 74c0: 00ba2e80 ffff8000 49687528 ffff8083 49687510 ffff8083 000e5c70 ffff8000 74e0: 00c22348 ffff8000 00000000 ffff8083 49687510 ffff8083 000e5c74 ffff8000 7500: 4ca2b600 ffff8083 49401800 ffff8083 00000001 00000000 00000000 00000000 7520: 496874d0 ffff8083 00000000 00000000 00000000 00000000 00000000 00000000 7540: 2f2e2d2c 33323130 00000000 00000000 4c944500 ffff8083 00000000 00000000 7560: 00000000 00000000 008751e0 ffff8000 00000001 00000000 124e2d1d 00107b77 Convert hashtab lock to raw lock to avoid such warning. Signed-off-by: Yang Shi <yang.shi@linaro.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-31 05:16:26 +07:00
raw_spin_lock_irqsave(&htab->lock, flags);
head = select_bucket(htab, l_new->hash);
l_old = lookup_elem_raw(head, l_new->hash, key, key_size);
if (!l_old && unlikely(htab->count >= map->max_entries)) {
/* if elem with this 'key' doesn't exist and we've reached
* max_entries limit, fail insertion of new elem
*/
ret = -E2BIG;
goto err;
}
if (l_old && map_flags == BPF_NOEXIST) {
/* elem already exists */
ret = -EEXIST;
goto err;
}
if (!l_old && map_flags == BPF_EXIST) {
/* elem doesn't exist, cannot update it */
ret = -ENOENT;
goto err;
}
/* add new element to the head of the list, so that concurrent
* search will find it before old elem
*/
hlist_add_head_rcu(&l_new->hash_node, head);
if (l_old) {
hlist_del_rcu(&l_old->hash_node);
kfree_rcu(l_old, rcu);
} else {
htab->count++;
}
bpf: convert hashtab lock to raw lock When running bpf samples on rt kernel, it reports the below warning: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 in_atomic(): 1, irqs_disabled(): 128, pid: 477, name: ping Preemption disabled at:[<ffff80000017db58>] kprobe_perf_func+0x30/0x228 CPU: 3 PID: 477 Comm: ping Not tainted 4.1.10-rt8 #4 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [<ffff80000008a5b0>] dump_backtrace+0x0/0x128 [<ffff80000008a6f8>] show_stack+0x20/0x30 [<ffff8000007da90c>] dump_stack+0x7c/0xa0 [<ffff8000000e4830>] ___might_sleep+0x188/0x1a0 [<ffff8000007e2200>] rt_spin_lock+0x28/0x40 [<ffff80000018bf9c>] htab_map_update_elem+0x124/0x320 [<ffff80000018c718>] bpf_map_update_elem+0x40/0x58 [<ffff800000187658>] __bpf_prog_run+0xd48/0x1640 [<ffff80000017ca6c>] trace_call_bpf+0x8c/0x100 [<ffff80000017db58>] kprobe_perf_func+0x30/0x228 [<ffff80000017dd84>] kprobe_dispatcher+0x34/0x58 [<ffff8000007e399c>] kprobe_handler+0x114/0x250 [<ffff8000007e3bf4>] kprobe_breakpoint_handler+0x1c/0x30 [<ffff800000085b80>] brk_handler+0x88/0x98 [<ffff8000000822f0>] do_debug_exception+0x50/0xb8 Exception stack(0xffff808349687460 to 0xffff808349687580) 7460: 4ca2b600 ffff8083 4a3a7000 ffff8083 49687620 ffff8083 0069c5f8 ffff8000 7480: 00000001 00000000 007e0628 ffff8000 496874b0 ffff8083 007e1de8 ffff8000 74a0: 496874d0 ffff8083 0008e04c ffff8000 00000001 00000000 4ca2b600 ffff8083 74c0: 00ba2e80 ffff8000 49687528 ffff8083 49687510 ffff8083 000e5c70 ffff8000 74e0: 00c22348 ffff8000 00000000 ffff8083 49687510 ffff8083 000e5c74 ffff8000 7500: 4ca2b600 ffff8083 49401800 ffff8083 00000001 00000000 00000000 00000000 7520: 496874d0 ffff8083 00000000 00000000 00000000 00000000 00000000 00000000 7540: 2f2e2d2c 33323130 00000000 00000000 4c944500 ffff8083 00000000 00000000 7560: 00000000 00000000 008751e0 ffff8000 00000001 00000000 124e2d1d 00107b77 Convert hashtab lock to raw lock to avoid such warning. Signed-off-by: Yang Shi <yang.shi@linaro.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-31 05:16:26 +07:00
raw_spin_unlock_irqrestore(&htab->lock, flags);
return 0;
err:
bpf: convert hashtab lock to raw lock When running bpf samples on rt kernel, it reports the below warning: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 in_atomic(): 1, irqs_disabled(): 128, pid: 477, name: ping Preemption disabled at:[<ffff80000017db58>] kprobe_perf_func+0x30/0x228 CPU: 3 PID: 477 Comm: ping Not tainted 4.1.10-rt8 #4 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [<ffff80000008a5b0>] dump_backtrace+0x0/0x128 [<ffff80000008a6f8>] show_stack+0x20/0x30 [<ffff8000007da90c>] dump_stack+0x7c/0xa0 [<ffff8000000e4830>] ___might_sleep+0x188/0x1a0 [<ffff8000007e2200>] rt_spin_lock+0x28/0x40 [<ffff80000018bf9c>] htab_map_update_elem+0x124/0x320 [<ffff80000018c718>] bpf_map_update_elem+0x40/0x58 [<ffff800000187658>] __bpf_prog_run+0xd48/0x1640 [<ffff80000017ca6c>] trace_call_bpf+0x8c/0x100 [<ffff80000017db58>] kprobe_perf_func+0x30/0x228 [<ffff80000017dd84>] kprobe_dispatcher+0x34/0x58 [<ffff8000007e399c>] kprobe_handler+0x114/0x250 [<ffff8000007e3bf4>] kprobe_breakpoint_handler+0x1c/0x30 [<ffff800000085b80>] brk_handler+0x88/0x98 [<ffff8000000822f0>] do_debug_exception+0x50/0xb8 Exception stack(0xffff808349687460 to 0xffff808349687580) 7460: 4ca2b600 ffff8083 4a3a7000 ffff8083 49687620 ffff8083 0069c5f8 ffff8000 7480: 00000001 00000000 007e0628 ffff8000 496874b0 ffff8083 007e1de8 ffff8000 74a0: 496874d0 ffff8083 0008e04c ffff8000 00000001 00000000 4ca2b600 ffff8083 74c0: 00ba2e80 ffff8000 49687528 ffff8083 49687510 ffff8083 000e5c70 ffff8000 74e0: 00c22348 ffff8000 00000000 ffff8083 49687510 ffff8083 000e5c74 ffff8000 7500: 4ca2b600 ffff8083 49401800 ffff8083 00000001 00000000 00000000 00000000 7520: 496874d0 ffff8083 00000000 00000000 00000000 00000000 00000000 00000000 7540: 2f2e2d2c 33323130 00000000 00000000 4c944500 ffff8083 00000000 00000000 7560: 00000000 00000000 008751e0 ffff8000 00000001 00000000 124e2d1d 00107b77 Convert hashtab lock to raw lock to avoid such warning. Signed-off-by: Yang Shi <yang.shi@linaro.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-31 05:16:26 +07:00
raw_spin_unlock_irqrestore(&htab->lock, flags);
kfree(l_new);
return ret;
}
/* Called from syscall or from eBPF program */
static int htab_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct hlist_head *head;
struct htab_elem *l;
unsigned long flags;
u32 hash, key_size;
int ret = -ENOENT;
WARN_ON_ONCE(!rcu_read_lock_held());
key_size = map->key_size;
hash = htab_map_hash(key, key_size);
bpf: convert hashtab lock to raw lock When running bpf samples on rt kernel, it reports the below warning: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 in_atomic(): 1, irqs_disabled(): 128, pid: 477, name: ping Preemption disabled at:[<ffff80000017db58>] kprobe_perf_func+0x30/0x228 CPU: 3 PID: 477 Comm: ping Not tainted 4.1.10-rt8 #4 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [<ffff80000008a5b0>] dump_backtrace+0x0/0x128 [<ffff80000008a6f8>] show_stack+0x20/0x30 [<ffff8000007da90c>] dump_stack+0x7c/0xa0 [<ffff8000000e4830>] ___might_sleep+0x188/0x1a0 [<ffff8000007e2200>] rt_spin_lock+0x28/0x40 [<ffff80000018bf9c>] htab_map_update_elem+0x124/0x320 [<ffff80000018c718>] bpf_map_update_elem+0x40/0x58 [<ffff800000187658>] __bpf_prog_run+0xd48/0x1640 [<ffff80000017ca6c>] trace_call_bpf+0x8c/0x100 [<ffff80000017db58>] kprobe_perf_func+0x30/0x228 [<ffff80000017dd84>] kprobe_dispatcher+0x34/0x58 [<ffff8000007e399c>] kprobe_handler+0x114/0x250 [<ffff8000007e3bf4>] kprobe_breakpoint_handler+0x1c/0x30 [<ffff800000085b80>] brk_handler+0x88/0x98 [<ffff8000000822f0>] do_debug_exception+0x50/0xb8 Exception stack(0xffff808349687460 to 0xffff808349687580) 7460: 4ca2b600 ffff8083 4a3a7000 ffff8083 49687620 ffff8083 0069c5f8 ffff8000 7480: 00000001 00000000 007e0628 ffff8000 496874b0 ffff8083 007e1de8 ffff8000 74a0: 496874d0 ffff8083 0008e04c ffff8000 00000001 00000000 4ca2b600 ffff8083 74c0: 00ba2e80 ffff8000 49687528 ffff8083 49687510 ffff8083 000e5c70 ffff8000 74e0: 00c22348 ffff8000 00000000 ffff8083 49687510 ffff8083 000e5c74 ffff8000 7500: 4ca2b600 ffff8083 49401800 ffff8083 00000001 00000000 00000000 00000000 7520: 496874d0 ffff8083 00000000 00000000 00000000 00000000 00000000 00000000 7540: 2f2e2d2c 33323130 00000000 00000000 4c944500 ffff8083 00000000 00000000 7560: 00000000 00000000 008751e0 ffff8000 00000001 00000000 124e2d1d 00107b77 Convert hashtab lock to raw lock to avoid such warning. Signed-off-by: Yang Shi <yang.shi@linaro.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-31 05:16:26 +07:00
raw_spin_lock_irqsave(&htab->lock, flags);
head = select_bucket(htab, hash);
l = lookup_elem_raw(head, hash, key, key_size);
if (l) {
hlist_del_rcu(&l->hash_node);
htab->count--;
kfree_rcu(l, rcu);
ret = 0;
}
bpf: convert hashtab lock to raw lock When running bpf samples on rt kernel, it reports the below warning: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 in_atomic(): 1, irqs_disabled(): 128, pid: 477, name: ping Preemption disabled at:[<ffff80000017db58>] kprobe_perf_func+0x30/0x228 CPU: 3 PID: 477 Comm: ping Not tainted 4.1.10-rt8 #4 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [<ffff80000008a5b0>] dump_backtrace+0x0/0x128 [<ffff80000008a6f8>] show_stack+0x20/0x30 [<ffff8000007da90c>] dump_stack+0x7c/0xa0 [<ffff8000000e4830>] ___might_sleep+0x188/0x1a0 [<ffff8000007e2200>] rt_spin_lock+0x28/0x40 [<ffff80000018bf9c>] htab_map_update_elem+0x124/0x320 [<ffff80000018c718>] bpf_map_update_elem+0x40/0x58 [<ffff800000187658>] __bpf_prog_run+0xd48/0x1640 [<ffff80000017ca6c>] trace_call_bpf+0x8c/0x100 [<ffff80000017db58>] kprobe_perf_func+0x30/0x228 [<ffff80000017dd84>] kprobe_dispatcher+0x34/0x58 [<ffff8000007e399c>] kprobe_handler+0x114/0x250 [<ffff8000007e3bf4>] kprobe_breakpoint_handler+0x1c/0x30 [<ffff800000085b80>] brk_handler+0x88/0x98 [<ffff8000000822f0>] do_debug_exception+0x50/0xb8 Exception stack(0xffff808349687460 to 0xffff808349687580) 7460: 4ca2b600 ffff8083 4a3a7000 ffff8083 49687620 ffff8083 0069c5f8 ffff8000 7480: 00000001 00000000 007e0628 ffff8000 496874b0 ffff8083 007e1de8 ffff8000 74a0: 496874d0 ffff8083 0008e04c ffff8000 00000001 00000000 4ca2b600 ffff8083 74c0: 00ba2e80 ffff8000 49687528 ffff8083 49687510 ffff8083 000e5c70 ffff8000 74e0: 00c22348 ffff8000 00000000 ffff8083 49687510 ffff8083 000e5c74 ffff8000 7500: 4ca2b600 ffff8083 49401800 ffff8083 00000001 00000000 00000000 00000000 7520: 496874d0 ffff8083 00000000 00000000 00000000 00000000 00000000 00000000 7540: 2f2e2d2c 33323130 00000000 00000000 4c944500 ffff8083 00000000 00000000 7560: 00000000 00000000 008751e0 ffff8000 00000001 00000000 124e2d1d 00107b77 Convert hashtab lock to raw lock to avoid such warning. Signed-off-by: Yang Shi <yang.shi@linaro.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-31 05:16:26 +07:00
raw_spin_unlock_irqrestore(&htab->lock, flags);
return ret;
}
static void delete_all_elements(struct bpf_htab *htab)
{
int i;
for (i = 0; i < htab->n_buckets; i++) {
struct hlist_head *head = select_bucket(htab, i);
struct hlist_node *n;
struct htab_elem *l;
hlist_for_each_entry_safe(l, n, head, hash_node) {
hlist_del_rcu(&l->hash_node);
htab->count--;
kfree(l);
}
}
}
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void htab_map_free(struct bpf_map *map)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the programs (can be more than one that used this map) were
* disconnected from events. Wait for outstanding critical sections in
* these programs to complete
*/
synchronize_rcu();
/* some of kfree_rcu() callbacks for elements of this map may not have
* executed. It's ok. Proceed to free residual elements and map itself
*/
delete_all_elements(htab);
kvfree(htab->buckets);
kfree(htab);
}
static const struct bpf_map_ops htab_ops = {
.map_alloc = htab_map_alloc,
.map_free = htab_map_free,
.map_get_next_key = htab_map_get_next_key,
.map_lookup_elem = htab_map_lookup_elem,
.map_update_elem = htab_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
};
static struct bpf_map_type_list htab_type __read_mostly = {
.ops = &htab_ops,
.type = BPF_MAP_TYPE_HASH,
};
static int __init register_htab_map(void)
{
bpf_register_map_type(&htab_type);
return 0;
}
late_initcall(register_htab_map);