2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 05:04:00 +08:00
linux-next/include/linux/filter.h
Alexei Starovoitov d45ed4a4e3 net: fix unsafe set_memory_rw from softirq
on x86 system with net.core.bpf_jit_enable = 1

sudo tcpdump -i eth1 'tcp port 22'

causes the warning:
[   56.766097]  Possible unsafe locking scenario:
[   56.766097]
[   56.780146]        CPU0
[   56.786807]        ----
[   56.793188]   lock(&(&vb->lock)->rlock);
[   56.799593]   <Interrupt>
[   56.805889]     lock(&(&vb->lock)->rlock);
[   56.812266]
[   56.812266]  *** DEADLOCK ***
[   56.812266]
[   56.830670] 1 lock held by ksoftirqd/1/13:
[   56.836838]  #0:  (rcu_read_lock){.+.+..}, at: [<ffffffff8118f44c>] vm_unmap_aliases+0x8c/0x380
[   56.849757]
[   56.849757] stack backtrace:
[   56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45
[   56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012
[   56.882004]  ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007
[   56.895630]  ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001
[   56.909313]  ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001
[   56.923006] Call Trace:
[   56.929532]  [<ffffffff8175a145>] dump_stack+0x55/0x76
[   56.936067]  [<ffffffff81755b14>] print_usage_bug+0x1f7/0x208
[   56.942445]  [<ffffffff8101178f>] ? save_stack_trace+0x2f/0x50
[   56.948932]  [<ffffffff810cc0a0>] ? check_usage_backwards+0x150/0x150
[   56.955470]  [<ffffffff810ccb52>] mark_lock+0x282/0x2c0
[   56.961945]  [<ffffffff810ccfed>] __lock_acquire+0x45d/0x1d50
[   56.968474]  [<ffffffff810cce6e>] ? __lock_acquire+0x2de/0x1d50
[   56.975140]  [<ffffffff81393bf5>] ? cpumask_next_and+0x55/0x90
[   56.981942]  [<ffffffff810cef72>] lock_acquire+0x92/0x1d0
[   56.988745]  [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380
[   56.995619]  [<ffffffff817628f1>] _raw_spin_lock+0x41/0x50
[   57.002493]  [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380
[   57.009447]  [<ffffffff8118f52a>] vm_unmap_aliases+0x16a/0x380
[   57.016477]  [<ffffffff8118f44c>] ? vm_unmap_aliases+0x8c/0x380
[   57.023607]  [<ffffffff810436b0>] change_page_attr_set_clr+0xc0/0x460
[   57.030818]  [<ffffffff810cfb8d>] ? trace_hardirqs_on+0xd/0x10
[   57.037896]  [<ffffffff811a8330>] ? kmem_cache_free+0xb0/0x2b0
[   57.044789]  [<ffffffff811b59c3>] ? free_object_rcu+0x93/0xa0
[   57.051720]  [<ffffffff81043d9f>] set_memory_rw+0x2f/0x40
[   57.058727]  [<ffffffff8104e17c>] bpf_jit_free+0x2c/0x40
[   57.065577]  [<ffffffff81642cba>] sk_filter_release_rcu+0x1a/0x30
[   57.072338]  [<ffffffff811108e2>] rcu_process_callbacks+0x202/0x7c0
[   57.078962]  [<ffffffff81057f17>] __do_softirq+0xf7/0x3f0
[   57.085373]  [<ffffffff81058245>] run_ksoftirqd+0x35/0x70

cannot reuse jited filter memory, since it's readonly,
so use original bpf insns memory to hold work_struct

defer kfree of sk_filter until jit completed freeing

tested on x86_64 and i386

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-07 15:16:45 -04:00

155 lines
3.5 KiB
C

/*
* Linux Socket Filter Data Structures
*/
#ifndef __LINUX_FILTER_H__
#define __LINUX_FILTER_H__
#include <linux/atomic.h>
#include <linux/compat.h>
#include <linux/workqueue.h>
#include <uapi/linux/filter.h>
#ifdef CONFIG_COMPAT
/*
* A struct sock_filter is architecture independent.
*/
struct compat_sock_fprog {
u16 len;
compat_uptr_t filter; /* struct sock_filter * */
};
#endif
struct sk_buff;
struct sock;
struct sk_filter
{
atomic_t refcnt;
unsigned int len; /* Number of filter blocks */
struct rcu_head rcu;
unsigned int (*bpf_func)(const struct sk_buff *skb,
const struct sock_filter *filter);
union {
struct sock_filter insns[0];
struct work_struct work;
};
};
static inline unsigned int sk_filter_size(unsigned int proglen)
{
return max(sizeof(struct sk_filter),
offsetof(struct sk_filter, insns[proglen]));
}
extern int sk_filter(struct sock *sk, struct sk_buff *skb);
extern unsigned int sk_run_filter(const struct sk_buff *skb,
const struct sock_filter *filter);
extern int sk_unattached_filter_create(struct sk_filter **pfp,
struct sock_fprog *fprog);
extern void sk_unattached_filter_destroy(struct sk_filter *fp);
extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
extern int sk_detach_filter(struct sock *sk);
extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
#ifdef CONFIG_BPF_JIT
#include <stdarg.h>
#include <linux/linkage.h>
#include <linux/printk.h>
extern void bpf_jit_compile(struct sk_filter *fp);
extern void bpf_jit_free(struct sk_filter *fp);
static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
u32 pass, void *image)
{
pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
flen, proglen, pass, image);
if (image)
print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
16, 1, image, proglen, false);
}
#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns)
#else
#include <linux/slab.h>
static inline void bpf_jit_compile(struct sk_filter *fp)
{
}
static inline void bpf_jit_free(struct sk_filter *fp)
{
kfree(fp);
}
#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns)
#endif
enum {
BPF_S_RET_K = 1,
BPF_S_RET_A,
BPF_S_ALU_ADD_K,
BPF_S_ALU_ADD_X,
BPF_S_ALU_SUB_K,
BPF_S_ALU_SUB_X,
BPF_S_ALU_MUL_K,
BPF_S_ALU_MUL_X,
BPF_S_ALU_DIV_X,
BPF_S_ALU_MOD_K,
BPF_S_ALU_MOD_X,
BPF_S_ALU_AND_K,
BPF_S_ALU_AND_X,
BPF_S_ALU_OR_K,
BPF_S_ALU_OR_X,
BPF_S_ALU_XOR_K,
BPF_S_ALU_XOR_X,
BPF_S_ALU_LSH_K,
BPF_S_ALU_LSH_X,
BPF_S_ALU_RSH_K,
BPF_S_ALU_RSH_X,
BPF_S_ALU_NEG,
BPF_S_LD_W_ABS,
BPF_S_LD_H_ABS,
BPF_S_LD_B_ABS,
BPF_S_LD_W_LEN,
BPF_S_LD_W_IND,
BPF_S_LD_H_IND,
BPF_S_LD_B_IND,
BPF_S_LD_IMM,
BPF_S_LDX_W_LEN,
BPF_S_LDX_B_MSH,
BPF_S_LDX_IMM,
BPF_S_MISC_TAX,
BPF_S_MISC_TXA,
BPF_S_ALU_DIV_K,
BPF_S_LD_MEM,
BPF_S_LDX_MEM,
BPF_S_ST,
BPF_S_STX,
BPF_S_JMP_JA,
BPF_S_JMP_JEQ_K,
BPF_S_JMP_JEQ_X,
BPF_S_JMP_JGE_K,
BPF_S_JMP_JGE_X,
BPF_S_JMP_JGT_K,
BPF_S_JMP_JGT_X,
BPF_S_JMP_JSET_K,
BPF_S_JMP_JSET_X,
/* Ancillary data */
BPF_S_ANC_PROTOCOL,
BPF_S_ANC_PKTTYPE,
BPF_S_ANC_IFINDEX,
BPF_S_ANC_NLATTR,
BPF_S_ANC_NLATTR_NEST,
BPF_S_ANC_MARK,
BPF_S_ANC_QUEUE,
BPF_S_ANC_HATYPE,
BPF_S_ANC_RXHASH,
BPF_S_ANC_CPU,
BPF_S_ANC_ALU_XOR_X,
BPF_S_ANC_SECCOMP_LD_W,
BPF_S_ANC_VLAN_TAG,
BPF_S_ANC_VLAN_TAG_PRESENT,
BPF_S_ANC_PAY_OFFSET,
};
#endif /* __LINUX_FILTER_H__ */