mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-13 23:34:05 +08:00
89ed5b5190
When an application is run that: a) Sets its scheduler to be SCHED_FIFO and b) Opens a memory mapped AF_PACKET socket, and sends frames with the MSG_DONTWAIT flag cleared, its possible for the application to hang forever in the kernel. This occurs because when waiting, the code in tpacket_snd calls schedule, which under normal circumstances allows other tasks to run, including ksoftirqd, which in some cases is responsible for freeing the transmitted skb (which in AF_PACKET calls a destructor that flips the status bit of the transmitted frame back to available, allowing the transmitting task to complete). However, when the calling application is SCHED_FIFO, its priority is such that the schedule call immediately places the task back on the cpu, preventing ksoftirqd from freeing the skb, which in turn prevents the transmitting task from detecting that the transmission is complete. We can fix this by converting the schedule call to a completion mechanism. By using a completion queue, we force the calling task, when it detects there are no more frames to send, to schedule itself off the cpu until such time as the last transmitted skb is freed, allowing forward progress to be made. Tested by myself and the reporter, with good results Change Notes: V1->V2: Enhance the sleep logic to support being interruptible and allowing for honoring to SK_SNDTIMEO (Willem de Bruijn) V2->V3: Rearrage the point at which we wait for the completion queue, to avoid needing to check for ph/skb being null at the end of the loop. Also move the complete call to the skb destructor to avoid needing to modify __packet_set_status. Also gate calling complete on packet_read_pending returning zero to avoid multiple calls to complete. (Willem de Bruijn) Move timeo computation within loop, to re-fetch the socket timeout since we also use the timeo variable to record the return code from the wait_for_complete call (Neil Horman) V3->V4: Willem has requested that the control flow be restored to the previous state. Doing so lets us eliminate the need for the po->wait_on_complete flag variable, and lets us get rid of the packet_next_frame function, but introduces another complexity. Specifically, but using the packet pending count, we can, if an applications calls sendmsg multiple times with MSG_DONTWAIT set, each set of transmitted frames, when complete, will cause tpacket_destruct_skb to issue a complete call, for which there will never be a wait_on_completion call. This imbalance will lead to any future call to wait_for_completion here to return early, when the frames they sent may not have completed. To correct this, we need to re-init the completion queue on every call to tpacket_snd before we enter the loop so as to ensure we wait properly for the frames we send in this iteration. Change the timeout and interrupted gotos to out_put rather than out_status so that we don't try to free a non-existant skb Clean up some extra newlines (Willem de Bruijn) Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reported-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
143 lines
3.2 KiB
C
143 lines
3.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __PACKET_INTERNAL_H__
|
|
#define __PACKET_INTERNAL_H__
|
|
|
|
#include <linux/refcount.h>
|
|
|
|
struct packet_mclist {
|
|
struct packet_mclist *next;
|
|
int ifindex;
|
|
int count;
|
|
unsigned short type;
|
|
unsigned short alen;
|
|
unsigned char addr[MAX_ADDR_LEN];
|
|
};
|
|
|
|
/* kbdq - kernel block descriptor queue */
|
|
struct tpacket_kbdq_core {
|
|
struct pgv *pkbdq;
|
|
unsigned int feature_req_word;
|
|
unsigned int hdrlen;
|
|
unsigned char reset_pending_on_curr_blk;
|
|
unsigned char delete_blk_timer;
|
|
unsigned short kactive_blk_num;
|
|
unsigned short blk_sizeof_priv;
|
|
|
|
/* last_kactive_blk_num:
|
|
* trick to see if user-space has caught up
|
|
* in order to avoid refreshing timer when every single pkt arrives.
|
|
*/
|
|
unsigned short last_kactive_blk_num;
|
|
|
|
char *pkblk_start;
|
|
char *pkblk_end;
|
|
int kblk_size;
|
|
unsigned int max_frame_len;
|
|
unsigned int knum_blocks;
|
|
uint64_t knxt_seq_num;
|
|
char *prev;
|
|
char *nxt_offset;
|
|
struct sk_buff *skb;
|
|
|
|
atomic_t blk_fill_in_prog;
|
|
|
|
/* Default is set to 8ms */
|
|
#define DEFAULT_PRB_RETIRE_TOV (8)
|
|
|
|
unsigned short retire_blk_tov;
|
|
unsigned short version;
|
|
unsigned long tov_in_jiffies;
|
|
|
|
/* timer to retire an outstanding block */
|
|
struct timer_list retire_blk_timer;
|
|
};
|
|
|
|
struct pgv {
|
|
char *buffer;
|
|
};
|
|
|
|
struct packet_ring_buffer {
|
|
struct pgv *pg_vec;
|
|
|
|
unsigned int head;
|
|
unsigned int frames_per_block;
|
|
unsigned int frame_size;
|
|
unsigned int frame_max;
|
|
|
|
unsigned int pg_vec_order;
|
|
unsigned int pg_vec_pages;
|
|
unsigned int pg_vec_len;
|
|
|
|
unsigned int __percpu *pending_refcnt;
|
|
|
|
struct tpacket_kbdq_core prb_bdqc;
|
|
};
|
|
|
|
extern struct mutex fanout_mutex;
|
|
#define PACKET_FANOUT_MAX 256
|
|
|
|
struct packet_fanout {
|
|
possible_net_t net;
|
|
unsigned int num_members;
|
|
u16 id;
|
|
u8 type;
|
|
u8 flags;
|
|
union {
|
|
atomic_t rr_cur;
|
|
struct bpf_prog __rcu *bpf_prog;
|
|
};
|
|
struct list_head list;
|
|
struct sock *arr[PACKET_FANOUT_MAX];
|
|
spinlock_t lock;
|
|
refcount_t sk_ref;
|
|
struct packet_type prot_hook ____cacheline_aligned_in_smp;
|
|
};
|
|
|
|
struct packet_rollover {
|
|
int sock;
|
|
atomic_long_t num;
|
|
atomic_long_t num_huge;
|
|
atomic_long_t num_failed;
|
|
#define ROLLOVER_HLEN (L1_CACHE_BYTES / sizeof(u32))
|
|
u32 history[ROLLOVER_HLEN] ____cacheline_aligned;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
struct packet_sock {
|
|
/* struct sock has to be the first member of packet_sock */
|
|
struct sock sk;
|
|
struct packet_fanout *fanout;
|
|
union tpacket_stats_u stats;
|
|
struct packet_ring_buffer rx_ring;
|
|
struct packet_ring_buffer tx_ring;
|
|
int copy_thresh;
|
|
spinlock_t bind_lock;
|
|
struct mutex pg_vec_lock;
|
|
unsigned int running; /* bind_lock must be held */
|
|
unsigned int auxdata:1, /* writer must hold sock lock */
|
|
origdev:1,
|
|
has_vnet_hdr:1,
|
|
tp_loss:1,
|
|
tp_tx_has_off:1;
|
|
int pressure;
|
|
int ifindex; /* bound device */
|
|
__be16 num;
|
|
struct packet_rollover *rollover;
|
|
struct packet_mclist *mclist;
|
|
atomic_t mapped;
|
|
enum tpacket_versions tp_version;
|
|
unsigned int tp_hdrlen;
|
|
unsigned int tp_reserve;
|
|
unsigned int tp_tstamp;
|
|
struct completion skb_completion;
|
|
struct net_device __rcu *cached_dev;
|
|
int (*xmit)(struct sk_buff *skb);
|
|
struct packet_type prot_hook ____cacheline_aligned_in_smp;
|
|
};
|
|
|
|
static struct packet_sock *pkt_sk(struct sock *sk)
|
|
{
|
|
return (struct packet_sock *)sk;
|
|
}
|
|
|
|
#endif
|