mirror of
https://git.proxmox.com/git/mirror_ubuntu-kernels.git
synced 2025-12-09 20:16:13 +00:00
3484f06317
In the new GC, we use a simple graph algorithm, Tarjan's Strongly
Connected Components (SCC) algorithm, to find cyclic references.
The algorithm visits every vertex exactly once using depth-first
search (DFS).
DFS starts by pushing an input vertex to a stack and assigning it
a unique number. Two fields, index and lowlink, are initialised
with the number, but lowlink could be updated later during DFS.
If a vertex has an edge to an unvisited inflight vertex, we visit
it and do the same processing. So, we will have vertices in the
stack in the order they appear and number them consecutively in
the same order.
If a vertex has a back-edge to a visited vertex in the stack,
we update the predecessor's lowlink with the successor's index.
After iterating edges from the vertex, we check if its index
equals its lowlink.
If the lowlink is different from the index, it shows there was a
back-edge. Then, we go backtracking and propagate the lowlink to
its predecessor and resume the previous edge iteration from the
next edge.
If the lowlink is the same as the index, we pop vertices before
and including the vertex from the stack. Then, the set of vertices
is SCC, possibly forming a cycle. At the same time, we move the
vertices to unix_visited_vertices.
When we finish the algorithm, all vertices in each SCC will be
linked via unix_vertex.scc_entry.
Let's take an example. We have a graph including five inflight
vertices (F is not inflight):
A -> B -> C -> D -> E (-> F)
^ |
`---------'
Suppose that we start DFS from C. We will visit C, D, and B first
and initialise their index and lowlink. Then, the stack looks like
this:
> B = (3, 3) (index, lowlink)
D = (2, 2)
C = (1, 1)
When checking B's edge to C, we update B's lowlink with C's index
and propagate it to D.
B = (3, 1) (index, lowlink)
> D = (2, 1)
C = (1, 1)
Next, we visit E, which has no edge to an inflight vertex.
> E = (4, 4) (index, lowlink)
B = (3, 1)
D = (2, 1)
C = (1, 1)
When we leave from E, its index and lowlink are the same, so we
pop E from the stack as single-vertex SCC. Next, we leave from
B and D but do nothing because their lowlink are different from
their index.
B = (3, 1) (index, lowlink)
D = (2, 1)
> C = (1, 1)
Then, we leave from C, whose index and lowlink are the same, so
we pop B, D and C as SCC.
Last, we do DFS for the rest of vertices, A, which is also a
single-vertex SCC.
Finally, each unix_vertex.scc_entry is linked as follows:
A -. B -> C -> D E -.
^ | ^ | ^ |
`--' `---------' `--'
We use SCC later to decide whether we can garbage-collect the
sockets.
Note that we still cannot detect SCC properly if an edge points
to an embryo socket. The following two patches will sort it out.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240325202425.60930-7-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
147 lines
3.8 KiB
C
147 lines
3.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_NET_AFUNIX_H
|
|
#define __LINUX_NET_AFUNIX_H
|
|
|
|
#include <linux/socket.h>
|
|
#include <linux/un.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/refcount.h>
|
|
#include <net/sock.h>
|
|
|
|
#if IS_ENABLED(CONFIG_UNIX)
|
|
struct unix_sock *unix_get_socket(struct file *filp);
|
|
#else
|
|
static inline struct unix_sock *unix_get_socket(struct file *filp)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif
|
|
|
|
extern spinlock_t unix_gc_lock;
|
|
extern unsigned int unix_tot_inflight;
|
|
|
|
void unix_inflight(struct user_struct *user, struct file *fp);
|
|
void unix_notinflight(struct user_struct *user, struct file *fp);
|
|
void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver);
|
|
void unix_del_edges(struct scm_fp_list *fpl);
|
|
int unix_prepare_fpl(struct scm_fp_list *fpl);
|
|
void unix_destroy_fpl(struct scm_fp_list *fpl);
|
|
void unix_gc(void);
|
|
void wait_for_unix_gc(struct scm_fp_list *fpl);
|
|
|
|
struct unix_vertex {
|
|
struct list_head edges;
|
|
struct list_head entry;
|
|
struct list_head scc_entry;
|
|
unsigned long out_degree;
|
|
unsigned long index;
|
|
unsigned long lowlink;
|
|
bool on_stack;
|
|
};
|
|
|
|
struct unix_edge {
|
|
struct unix_sock *predecessor;
|
|
struct unix_sock *successor;
|
|
struct list_head vertex_entry;
|
|
struct list_head stack_entry;
|
|
};
|
|
|
|
struct sock *unix_peer_get(struct sock *sk);
|
|
|
|
#define UNIX_HASH_MOD (256 - 1)
|
|
#define UNIX_HASH_SIZE (256 * 2)
|
|
#define UNIX_HASH_BITS 8
|
|
|
|
struct unix_address {
|
|
refcount_t refcnt;
|
|
int len;
|
|
struct sockaddr_un name[];
|
|
};
|
|
|
|
struct unix_skb_parms {
|
|
struct pid *pid; /* Skb credentials */
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
struct scm_fp_list *fp; /* Passed files */
|
|
#ifdef CONFIG_SECURITY_NETWORK
|
|
u32 secid; /* Security ID */
|
|
#endif
|
|
u32 consumed;
|
|
} __randomize_layout;
|
|
|
|
struct scm_stat {
|
|
atomic_t nr_fds;
|
|
};
|
|
|
|
#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb))
|
|
|
|
/* The AF_UNIX socket */
|
|
struct unix_sock {
|
|
/* WARNING: sk has to be the first member */
|
|
struct sock sk;
|
|
struct unix_address *addr;
|
|
struct path path;
|
|
struct mutex iolock, bindlock;
|
|
struct sock *peer;
|
|
struct unix_vertex *vertex;
|
|
struct list_head link;
|
|
unsigned long inflight;
|
|
spinlock_t lock;
|
|
unsigned long gc_flags;
|
|
#define UNIX_GC_CANDIDATE 0
|
|
#define UNIX_GC_MAYBE_CYCLE 1
|
|
struct socket_wq peer_wq;
|
|
wait_queue_entry_t peer_wake;
|
|
struct scm_stat scm_stat;
|
|
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
|
|
struct sk_buff *oob_skb;
|
|
#endif
|
|
};
|
|
|
|
#define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
|
|
#define unix_peer(sk) (unix_sk(sk)->peer)
|
|
|
|
#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock)
|
|
#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock)
|
|
enum unix_socket_lock_class {
|
|
U_LOCK_NORMAL,
|
|
U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */
|
|
U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
|
|
};
|
|
|
|
static inline void unix_state_lock_nested(struct sock *sk,
|
|
enum unix_socket_lock_class subclass)
|
|
{
|
|
spin_lock_nested(&unix_sk(sk)->lock, subclass);
|
|
}
|
|
|
|
#define peer_wait peer_wq.wait
|
|
|
|
long unix_inq_len(struct sock *sk);
|
|
long unix_outq_len(struct sock *sk);
|
|
|
|
int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
|
|
int flags);
|
|
int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
|
|
int flags);
|
|
#ifdef CONFIG_SYSCTL
|
|
int unix_sysctl_register(struct net *net);
|
|
void unix_sysctl_unregister(struct net *net);
|
|
#else
|
|
static inline int unix_sysctl_register(struct net *net) { return 0; }
|
|
static inline void unix_sysctl_unregister(struct net *net) {}
|
|
#endif
|
|
|
|
#ifdef CONFIG_BPF_SYSCALL
|
|
extern struct proto unix_dgram_proto;
|
|
extern struct proto unix_stream_proto;
|
|
|
|
int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
|
|
int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
|
|
void __init unix_bpf_build_proto(void);
|
|
#else
|
|
static inline void __init unix_bpf_build_proto(void)
|
|
{}
|
|
#endif
|
|
#endif
|