int audit_filter_user(int type)
{
enum audit_state state = AUDIT_DISABLED;
struct audit_entry *e;
int rc, ret;
ret = 1; /* Audit by default */
rcu_read_lock();
list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) {
rc = audit_filter_user_rules(&e->rule, type, &state);
if (rc) {
if (rc > 0 && state == AUDIT_DISABLED)
ret = 0;
break;
}
}
rcu_read_unlock();
return ret;
}
int audit_filter_type(int type)
{
struct audit_entry *e;
int result = 0;
rcu_read_lock();
if (list_empty(&audit_filter_list[AUDIT_FILTER_TYPE]))
goto unlock_and_return;
list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TYPE],
list) {
int i;
for (i = 0; i < e->rule.field_count; i++) {
struct audit_field *f = &e->rule.fields[i];
if (f->type == AUDIT_MSGTYPE) {
result = audit_comparator(type, f->op, f->val);
if (!result)
break;
}
}
if (result)
goto unlock_and_return;
}
unlock_and_return:
rcu_read_unlock();
return result;
}
static int update_lsm_rule(struct audit_krule *r)
{
struct audit_entry *entry = container_of(r, struct audit_entry, rule);
struct audit_entry *nentry;
int err = 0;
if (!security_audit_rule_known(r))
return 0;
nentry = audit_dupe_rule(r);
if (IS_ERR(nentry)) {
/* save the first error encountered for the
* return value */
err = PTR_ERR(nentry);
audit_panic("error updating LSM filters");
if (r->watch)
list_del(&r->rlist);
list_del_rcu(&entry->list);
list_del(&r->list);
} else {
if (r->watch || r->tree)
list_replace_init(&r->rlist, &nentry->rule.rlist);
list_replace_rcu(&entry->list, &nentry->list);
list_replace(&r->list, &nentry->rule.list);
}
call_rcu(&entry->rcu, audit_free_rule_rcu);
return err;
}
/* This function will re-initialize the lsm_rule field of all applicable rules.
* It will traverse the filter lists serarching for rules that contain LSM
* specific filter fields. When such a rule is found, it is copied, the
* LSM field is re-initialized, and the old rule is replaced with the
* updated rule. */
int audit_update_lsm_rules(void)
{
struct audit_krule *r, *n;
int i, err = 0;
/* audit_filter_mutex synchronizes the writers */
mutex_lock(&audit_filter_mutex);
for (i = 0; i < AUDIT_NR_FILTERS; i++) {
list_for_each_entry_safe(r, n, &audit_rules_list[i], list) {
int res = update_lsm_rule(r);
if (!err)
err = res;
}
}
mutex_unlock(&audit_filter_mutex);
return err;
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/auditsc.c
/* auditsc.c -- System-call auditing support
* Handles all system-call specific auditing features.
*
* Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
* Copyright 2005 Hewlett-Packard Development Company, L.P.
* Copyright (C) 2005, 2006 IBM Corporation
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* 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.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Written by Rickard E. (Rik) Faith <faith@redhat.com>
*
* Many of the ideas implemented here are from Stephen C. Tweedie,
* especially the idea of avoiding a copy by using getname.
*
* The method for actual interception of syscall entry and exit (not in
* this file -- see entry.S) is based on a GPL'd patch written by
* okir@suse.de and Copyright 2003 SuSE Linux AG.
*
* POSIX message queue support added by George Wilson <ltcgcw@us.ibm.com>,
* 2006.
*
* The support of additional filter rules compares (>, <, >=, <=) was
* added by Dustin Kirkland <dustin.kirkland@us.ibm.com>, 2005.
*
* Modified by Amy Griffis <amy.griffis@hp.com> to collect additional
* filesystem information.
*
* Subject and object context labeling support added by <danjones@us.ibm.com>
* and <dustin.kirkland@us.ibm.com> for LSPP certification compliance.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/init.h>
#include <asm/types.h>
#include <linux/atomic.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/socket.h>
#include <linux/mqueue.h>
#include <linux/audit.h>
#include <linux/personality.h>
#include <linux/time.h>
#include <linux/netlink.h>
#include <linux/compiler.h>
#include <asm/unistd.h>
#include <linux/security.h>
#include <linux/list.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
#include <asm/syscall.h>
#include <linux/capability.h>
#include <linux/fs_struct.h>
#include <linux/compat.h>
#include <linux/ctype.h>
#include <linux/string.h>
#include <uapi/linux/limits.h>
#include "audit.h"
/* flags stating the success for a syscall */
#define AUDITSC_INVALID 0
#define AUDITSC_SUCCESS 1
#define AUDITSC_FAILURE 2
/* no execve audit message should be longer than this (userspace limits) */
#define MAX_EXECVE_AUDIT_LEN 7500
/* max length to print of cmdline/proctitle value during audit */
#define MAX_PROCTITLE_AUDIT_LEN 128
/* number of audit rules */
int audit_n_rules;
/* determines whether we collect data for signals sent */
int audit_signals;
struct audit_aux_data {
struct audit_aux_data *next;
int type;
};
#define AUDIT_AUX_IPCPERM 0
/* Number of target pids per aux struct. */
#define AUDIT_AUX_PIDS 16
struct audit_aux_data_pids {
struct audit_aux_data d;
pid_t target_pid[AUDIT_AUX_PIDS];
kuid_t target_auid[AUDIT_AUX_PIDS];
kuid_t target_uid[AUDIT_AUX_PIDS];
unsigned int target_sessionid[AUDIT_AUX_PIDS];
u32 target_sid[AUDIT_AUX_PIDS];
char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN];
int pid_count;
};
struct audit_aux_data_bprm_fcaps {
struct audit_aux_data d;
struct audit_cap_data fcap;
unsigned int fcap_ver;
struct audit_cap_data old_pcap;
struct audit_cap_data new_pcap;
};
struct audit_tree_refs {
struct audit_tree_refs *next;
struct audit_chunk *c[31];
};
static int audit_match_perm(struct audit_context *ctx, int mask)
{
unsigned n;
if (unlikely(!ctx))
return 0;
n = ctx->major;
switch (audit_classify_syscall(ctx->arch, n)) {
case 0: /* native */
if ((mask & AUDIT_PERM_WRITE) &&
audit_match_class(AUDIT_CLASS_WRITE, n))
return 1;
if ((mask & AUDIT_PERM_READ) &&
audit_match_class(AUDIT_CLASS_READ, n))
return 1;
if ((mask & AUDIT_PERM_ATTR) &&
audit_match_class(AUDIT_CLASS_CHATTR, n))
return 1;
return 0;
case 1: /* 32bit on biarch */
if ((mask & AUDIT_PERM_WRITE) &&
audit_match_class(AUDIT_CLASS_WRITE_32, n))
return 1;
if ((mask & AUDIT_PERM_READ) &&
audit_match_class(AUDIT_CLASS_READ_32, n))
return 1;
if ((mask & AUDIT_PERM_ATTR) &&
audit_match_class(AUDIT_CLASS_CHATTR_32, n))
return 1;
return 0;
case 2: /* open */
return mask & ACC_MODE(ctx->argv[1]);
case 3: /* openat */
return mask & ACC_MODE(ctx->argv[2]);
case 4: /* socketcall */
return ((mask & AUDIT_PERM_WRITE) && ctx->argv[0] == SYS_BIND);
case 5: /* execve */
return mask & AUDIT_PERM_EXEC;
default:
return 0;
}
}
static int audit_match_filetype(struct audit_context *ctx, int val)
{
struct audit_names *n;
umode_t mode = (umode_t)val;
if (unlikely(!ctx))
return 0;
list_for_each_entry(n, &ctx->names_list, list) {
if ((n->ino != -1) &&
((n->mode & S_IFMT) == mode))
return 1;
}
return 0;
}
/*
* We keep a linked list of fixed-sized (31 pointer) arrays of audit_chunk *;
* ->first_trees points to its beginning, ->trees - to the current end of data.
* ->tree_count is the number of free entries in array pointed to by ->trees.
* Original condition is (NULL, NULL, 0); as soon as it grows we never revert to NULL,
* "empty" becomes (p, p, 31) afterwards. We don't shrink the list (and seriously,
* it's going to remain 1-element for almost any setup) until we free context itself.
* References in it _are_ dropped - at the same time we free/drop aux stuff.
*/
#ifdef CONFIG_AUDIT_TREE
static void audit_set_auditable(struct audit_context *ctx)
{
if (!ctx->prio) {
ctx->prio = 1;
ctx->current_state = AUDIT_RECORD_CONTEXT;
}
}
static int put_tree_ref(struct audit_context *ctx, struct audit_chunk *chunk)
{
struct audit_tree_refs *p = ctx->trees;
int left = ctx->tree_count;
if (likely(left)) {
p->c[--left] = chunk;
ctx->tree_count = left;
return 1;
}
if (!p)
return 0;
p = p->next;
if (p) {
p->c[30] = chunk;
ctx->trees = p;
ctx->tree_count = 30;
return 1;
}
return 0;
}
static int grow_tree_refs(struct audit_context *ctx)
{
struct audit_tree_refs *p = ctx->trees;
ctx->trees = kzalloc(sizeof(struct audit_tree_refs), GFP_KERNEL);
if (!ctx->trees) {
ctx->trees = p;
return 0;
}
if (p)
p->next = ctx->trees;
else
ctx->first_trees = ctx->trees;
ctx->tree_count = 31;
return 1;
}
#endif
static void unroll_tree_refs(struct audit_context *ctx,
struct audit_tree_refs *p, int count)
{
#ifdef CONFIG_AUDIT_TREE
struct audit_tree_refs *q;
int n;
if (!p) {
/* we started with empty chain */
p = ctx->first_trees;
count = 31;
/* if the very first allocation has failed, nothing to do */
if (!p)
return;
}
n = count;
for (q = p; q != ctx->trees; q = q->next, n = 31) {
while (n--) {
audit_put_chunk(q->c[n]);
q->c[n] = NULL;
}
}
while (n-- > ctx->tree_count) {
audit_put_chunk(q->c[n]);
q->c[n] = NULL;
}
ctx->trees = p;
ctx->tree_count = count;
#endif
}
static void free_tree_refs(struct audit_context *ctx)
{
struct audit_tree_refs *p, *q;
for (p = ctx->first_trees; p; p = q) {
q = p->next;
kfree(p);
}
}
static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree)
{
#ifdef CONFIG_AUDIT_TREE
struct audit_tree_refs *p;
int n;
if (!tree)
return 0;
/* full ones */
for (p = ctx->first_trees; p != ctx->trees; p = p->next) {
for (n = 0; n < 31; n++)
if (audit_tree_match(p->c[n], tree))
return 1;
}
/* partial */
if (p) {
for (n = ctx->tree_count; n < 31; n++)
if (audit_tree_match(p->c[n], tree))
return 1;
}
#endif
return 0;
}
static int audit_compare_uid(kuid_t uid,
struct audit_names *name,
struct audit_field *f,
struct audit_context *ctx)
{
struct audit_names *n;
int rc;
if (name) {
rc = audit_uid_comparator(uid, f->op, name->uid);
if (rc)
return rc;
}
if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
rc = audit_uid_comparator(uid, f->op, n->uid);
if (rc)
return rc;
}
}
return 0;
}
static int audit_compare_gid(kgid_t gid,
struct audit_names *name,
struct audit_field *f,
struct audit_context *ctx)
{
struct audit_names *n;
int rc;
if (name) {
rc = audit_gid_comparator(gid, f->op, name->gid);
if (rc)
return rc;
}
if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
rc = audit_gid_comparator(gid, f->op, n->gid);
if (rc)
return rc;
}
}
return 0;
}
static int audit_field_compare(struct task_struct *tsk,
const struct cred *cred,
struct audit_field *f,
struct audit_context *ctx,
struct audit_names *name)
{
switch (f->val) {
/* process to file object comparisons */
case AUDIT_COMPARE_UID_TO_OBJ_UID:
return audit_compare_uid(cred->uid, name, f, ctx);
case AUDIT_COMPARE_GID_TO_OBJ_GID:
return audit_compare_gid(cred->gid, name, f, ctx);
case AUDIT_COMPARE_EUID_TO_OBJ_UID:
return audit_compare_uid(cred->euid, name, f, ctx);
case AUDIT_COMPARE_EGID_TO_OBJ_GID:
return audit_compare_gid(cred->egid, name, f, ctx);
case AUDIT_COMPARE_AUID_TO_OBJ_UID:
return audit_compare_uid(tsk->loginuid, name, f, ctx);
case AUDIT_COMPARE_SUID_TO_OBJ_UID:
return audit_compare_uid(cred->suid, name, f, ctx);
case AUDIT_COMPARE_SGID_TO_OBJ_GID:
return audit_compare_gid(cred->sgid, name, f, ctx);
case AUDIT_COMPARE_FSUID_TO_OBJ_UID:
return audit_compare_uid(cred->fsuid, name, f, ctx);
case AUDIT_COMPARE_FSGID_TO_OBJ_GID:
return audit_compare_gid(cred->fsgid, name, f, ctx);
/* uid comparisons */
case AUDIT_COMPARE_UID_TO_AUID:
return audit_uid_comparator(cred->uid, f->op, tsk->loginuid);
case AUDIT_COMPARE_UID_TO_EUID:
return audit_uid_comparator(cred->uid, f->op, cred->euid);
case AUDIT_COMPARE_UID_TO_SUID:
return audit_uid_comparator(cred->uid, f->op, cred->suid);
case AUDIT_COMPARE_UID_TO_FSUID:
return audit_uid_comparator(cred->uid, f->op, cred->fsuid);
/* auid comparisons */
case AUDIT_COMPARE_AUID_TO_EUID:
return audit_uid_comparator(tsk->loginuid, f->op, cred->euid);
case AUDIT_COMPARE_AUID_TO_SUID:
return audit_uid_comparator(tsk->loginuid, f->op, cred->suid);
case AUDIT_COMPARE_AUID_TO_FSUID:
return audit_uid_comparator(tsk->loginuid, f->op, cred->fsuid);
/* euid comparisons */
case AUDIT_COMPARE_EUID_TO_SUID:
return audit_uid_comparator(cred->euid, f->op, cred->suid);
case AUDIT_COMPARE_EUID_TO_FSUID:
return audit_uid_comparator(cred->euid, f->op, cred->fsuid);
/* suid comparisons */
case AUDIT_COMPARE_SUID_TO_FSUID:
return audit_uid_comparator(cred->suid, f->op, cred->fsuid);
/* gid comparisons */
case AUDIT_COMPARE_GID_TO_EGID:
return audit_gid_comparator(cred->gid, f->op, cred->egid);
case AUDIT_COMPARE_GID_TO_SGID:
return audit_gid_comparator(cred->gid, f->op, cred->sgid);
case AUDIT_COMPARE_GID_TO_FSGID:
return audit_gid_comparator(cred->gid, f->op, cred->fsgid);
/* egid comparisons */
case AUDIT_COMPARE_EGID_TO_SGID:
return audit_gid_comparator(cred->egid, f->op, cred->sgid);
case AUDIT_COMPARE_EGID_TO_FSGID:
return audit_gid_comparator(cred->egid, f->op, cred->fsgid);
/* sgid comparison */
case AUDIT_COMPARE_SGID_TO_FSGID:
return audit_gid_comparator(cred->sgid, f->op, cred->fsgid);
default:
WARN(1, "Missing AUDIT_COMPARE define. Report as a bug\n");
return 0;
}
return 0;
}
/* Determine if any context name data matches a rule's watch data */
/* Compare a task_struct with an audit_rule. Return 1 on match, 0
* otherwise.
*
* If task_creation is true, this is an explicit indication that we are
* filtering a task rule at task creation time. This and tsk == current are
* the only situations where tsk->cred may be accessed without an rcu read lock.
*/
static int audit_filter_rules(struct task_struct *tsk,
struct audit_krule *rule,
struct audit_context *ctx,
struct audit_names *name,
enum audit_state *state,
bool task_creation)
{
const struct cred *cred;
int i, need_sid = 1;
u32 sid;
cred = rcu_dereference_check(tsk->cred, tsk == current || task_creation);
for (i = 0; i < rule->field_count; i++) {
struct audit_field *f = &rule->fields[i];
struct audit_names *n;
int result = 0;
pid_t pid;
switch (f->type) {
case AUDIT_PID:
pid = task_pid_nr(tsk);
result = audit_comparator(pid, f->op, f->val);
break;
case AUDIT_PPID:
if (ctx) {
if (!ctx->ppid)
ctx->ppid = task_ppid_nr(tsk);
result = audit_comparator(ctx->ppid, f->op, f->val);
}
break;
case AUDIT_UID:
result = audit_uid_comparator(cred->uid, f->op, f->uid);
break;
case AUDIT_EUID:
result = audit_uid_comparator(cred->euid, f->op, f->uid);
break;
case AUDIT_SUID:
result = audit_uid_comparator(cred->suid, f->op, f->uid);
break;
case AUDIT_FSUID:
result = audit_uid_comparator(cred->fsuid, f->op, f->uid);
break;
case AUDIT_GID:
result = audit_gid_comparator(cred->gid, f->op, f->gid);
if (f->op == Audit_equal) {
if (!result)
result = in_group_p(f->gid);
} else if (f->op == Audit_not_equal) {
if (result)
result = !in_group_p(f->gid);
}
break;
case AUDIT_EGID:
result = audit_gid_comparator(cred->egid, f->op, f->gid);
if (f->op == Audit_equal) {
if (!result)
result = in_egroup_p(f->gid);
} else if (f->op == Audit_not_equal) {
if (result)
result = !in_egroup_p(f->gid);
}
break;
case AUDIT_SGID:
result = audit_gid_comparator(cred->sgid, f->op, f->gid);
break;
case AUDIT_FSGID:
result = audit_gid_comparator(cred->fsgid, f->op, f->gid);
break;
case AUDIT_PERS:
result = audit_comparator(tsk->personality, f->op, f->val);
break;
case AUDIT_ARCH:
if (ctx)
result = audit_comparator(ctx->arch, f->op, f->val);
break;
case AUDIT_EXIT:
if (ctx && ctx->return_valid)
result = audit_comparator(ctx->return_code, f->op, f->val);
break;
case AUDIT_SUCCESS:
if (ctx && ctx->return_valid) {
if (f->val)
result = audit_comparator(ctx->return_valid, f->op, AUDITSC_SUCCESS);
else
result = audit_comparator(ctx->return_valid, f->op, AUDITSC_FAILURE);
}
break;
case AUDIT_DEVMAJOR:
if (name) {
if (audit_comparator(MAJOR(name->dev), f->op, f->val) ||
audit_comparator(MAJOR(name->rdev), f->op, f->val))
++result;
} else if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
if (audit_comparator(MAJOR(n->dev), f->op, f->val) ||
audit_comparator(MAJOR(n->rdev), f->op, f->val)) {
++result;
break;
}
}
}
break;
case AUDIT_DEVMINOR:
if (name) {
if (audit_comparator(MINOR(name->dev), f->op, f->val) ||
audit_comparator(MINOR(name->rdev), f->op, f->val))
++result;
} else if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
if (audit_comparator(MINOR(n->dev), f->op, f->val) ||
audit_comparator(MINOR(n->rdev), f->op, f->val)) {
++result;
break;
}
}
}
break;
case AUDIT_INODE:
if (name)
result = audit_comparator(name->ino, f->op, f->val);
else if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
if (audit_comparator(n->ino, f->op, f->val)) {
++result;
break;
}
}
}
break;
case AUDIT_OBJ_UID:
if (name) {
result = audit_uid_comparator(name->uid, f->op, f->uid);
} else if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
if (audit_uid_comparator(n->uid, f->op, f->uid)) {
++result;
break;
}
}
}
break;
case AUDIT_OBJ_GID:
if (name) {
result = audit_gid_comparator(name->gid, f->op, f->gid);
} else if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
if (audit_gid_comparator(n->gid, f->op, f->gid)) {
++result;
break;
}
}
}
break;
case AUDIT_WATCH:
if (name)
result = audit_watch_compare(rule->watch, name->ino, name->dev);
break;
case AUDIT_DIR:
if (ctx)
result = match_tree_refs(ctx, rule->tree);
break;
case AUDIT_LOGINUID:
result = audit_uid_comparator(tsk->loginuid, f->op, f->uid);
break;
case AUDIT_LOGINUID_SET:
result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val);
break;
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
/* NOTE: this may return negative values indicating
a temporary error. We simply treat this as a
match for now to avoid losing information that
may be wanted. An error message will also be
logged upon error */
if (f->lsm_rule) {
if (need_sid) {
security_task_getsecid(tsk, &sid);
need_sid = 0;
}
result = security_audit_rule_match(sid, f->type,
f->op,
f->lsm_rule,
ctx);
}
break;
case AUDIT_OBJ_USER:
case AUDIT_OBJ_ROLE:
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
/* The above note for AUDIT_SUBJ_USER...AUDIT_SUBJ_CLR
also applies here */
if (f->lsm_rule) {
/* Find files that match */
if (name) {
result = security_audit_rule_match(
name->osid, f->type, f->op,
f->lsm_rule, ctx);
} else if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
if (security_audit_rule_match(n->osid, f->type,
f->op, f->lsm_rule,
ctx)) {
++result;
break;
}
}
}
/* Find ipc objects that match */
if (!ctx || ctx->type != AUDIT_IPC)
break;
if (security_audit_rule_match(ctx->ipc.osid,
f->type, f->op,
f->lsm_rule, ctx))
++result;
}
break;
case AUDIT_ARG0:
case AUDIT_ARG1:
case AUDIT_ARG2:
case AUDIT_ARG3:
if (ctx)
result = audit_comparator(ctx->argv[f->type-AUDIT_ARG0], f->op, f->val);
break;
case AUDIT_FILTERKEY:
/* ignore this field for filtering */
result = 1;
break;
case AUDIT_PERM:
result = audit_match_perm(ctx, f->val);
break;
case AUDIT_FILETYPE:
result = audit_match_filetype(ctx, f->val);
break;
case AUDIT_FIELD_COMPARE:
result = audit_field_compare(tsk, cred, f, ctx, name);
break;
}
if (!result)
return 0;
}
if (ctx) {
if (rule->prio <= ctx->prio)
return 0;
if (rule->filterkey) {
kfree(ctx->filterkey);
ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
}
ctx->prio = rule->prio;
}
switch (rule->action) {
case AUDIT_NEVER: *state = AUDIT_DISABLED; break;
case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break;
}
return 1;
}
/* At process creation time, we can determine if system-call auditing is
* completely disabled for this task. Since we only have the task
* structure at this point, we can only check uid and gid.
*/
static enum audit_state audit_filter_task(struct task_struct *tsk, char **key)
{
struct audit_entry *e;
enum audit_state state;
rcu_read_lock();
list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) {
if (audit_filter_rules(tsk, &e->rule, NULL, NULL,
&state, true)) {
if (state == AUDIT_RECORD_CONTEXT)
*key = kstrdup(e->rule.filterkey, GFP_ATOMIC);
rcu_read_unlock();
return state;
}
}
rcu_read_unlock();
return AUDIT_BUILD_CONTEXT;
}
static int audit_in_mask(const struct audit_krule *rule, unsigned long val)
{
int word, bit;
if (val > 0xffffffff)
return false;
word = AUDIT_WORD(val);
if (word >= AUDIT_BITMASK_SIZE)
return false;
bit = AUDIT_BIT(val);
return rule->mask[word] & bit;
}
/* At syscall entry and exit time, this filter is called if the
* audit_state is not low enough that auditing cannot take place, but is
* also not high enough that we already know we have to write an audit
* record (i.e., the state is AUDIT_SETUP_CONTEXT or AUDIT_BUILD_CONTEXT).
*/
static enum audit_state audit_filter_syscall(struct task_struct *tsk,
struct audit_context *ctx,
struct list_head *list)
{
struct audit_entry *e;
enum audit_state state;
if (audit_pid && tsk->tgid == audit_pid)
return AUDIT_DISABLED;
rcu_read_lock();
if (!list_empty(list)) {
list_for_each_entry_rcu(e, list, list) {
if (audit_in_mask(&e->rule, ctx->major) &&
audit_filter_rules(tsk, &e->rule, ctx, NULL,
&state, false)) {
rcu_read_unlock();
ctx->current_state = state;
return state;
}
}
}
rcu_read_unlock();
return AUDIT_BUILD_CONTEXT;
}
/*
* Given an audit_name check the inode hash table to see if they match.
* Called holding the rcu read lock to protect the use of audit_inode_hash
*/
static int audit_filter_inode_name(struct task_struct *tsk,
struct audit_names *n,
struct audit_context *ctx) {
int h = audit_hash_ino((u32)n->ino);
struct list_head *list = &audit_inode_hash[h];
struct audit_entry *e;
enum audit_state state;
if (list_empty(list))
return 0;
list_for_each_entry_rcu(e, list, list) {
if (audit_in_mask(&e->rule, ctx->major) &&
audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) {
ctx->current_state = state;
return 1;
}
}
return 0;
}
/* At syscall exit time, this filter is called if any audit_names have been
* collected during syscall processing. We only check rules in sublists at hash
* buckets applicable to the inode numbers in audit_names.
* Regarding audit_state, same rules apply as for audit_filter_syscall().
*/
void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
{
struct audit_names *n;
if (audit_pid && tsk->tgid == audit_pid)
return;
rcu_read_lock();
list_for_each_entry(n, &ctx->names_list, list) {
if (audit_filter_inode_name(tsk, n, ctx))
break;
}
rcu_read_unlock();
}
/* Transfer the audit context pointer to the caller, clearing it in the tsk's struct */
static inline struct audit_context *audit_take_context(struct task_struct *tsk,
int return_valid,
long return_code)
{
struct audit_context *context = tsk->audit_context;
if (!context)
return NULL;
context->return_valid = return_valid;
/*
* we need to fix up the return code in the audit logs if the actual
* return codes are later going to be fixed up by the arch specific
* signal handlers
*
* This is actually a test for:
* (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) ||
* (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK)
*
* but is faster than a bunch of ||
*/
if (unlikely(return_code <= -ERESTARTSYS) &&
(return_code >= -ERESTART_RESTARTBLOCK) &&
(return_code != -ENOIOCTLCMD))
context->return_code = -EINTR;
else
context->return_code = return_code;
if (context->in_syscall && !context->dummy) {
audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
audit_filter_inodes(tsk, context);
}
tsk->audit_context = NULL;
return context;
}
static inline void audit_proctitle_free(struct audit_context *context)
{
kfree(context->proctitle.value);
context->proctitle.value = NULL;
context->proctitle.len = 0;
}
static inline void audit_free_names(struct audit_context *context)
{
struct audit_names *n, *next;
list_for_each_entry_safe(n, next, &context->names_list, list) {
list_del(&n->list);
if (n->name)
putname(n->name);
if (n->should_free)
kfree(n);
}
context->name_count = 0;
path_put(&context->pwd);
context->pwd.dentry = NULL;
context->pwd.mnt = NULL;
}
static inline void audit_free_aux(struct audit_context *context)
{
struct audit_aux_data *aux;
while ((aux = context->aux)) {
context->aux = aux->next;
kfree(aux);
}
while ((aux = context->aux_pids)) {
context->aux_pids = aux->next;
kfree(aux);
}
}
static inline struct audit_context *audit_alloc_context(enum audit_state state)
{
struct audit_context *context;
context = kzalloc(sizeof(*context), GFP_KERNEL);
if (!context)
return NULL;
context->state = state;
context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
INIT_LIST_HEAD(&context->killed_trees);
INIT_LIST_HEAD(&context->names_list);
return context;
}
/**
* audit_alloc - allocate an audit context block for a task
* @tsk: task
*
* Filter on the task information and allocate a per-task audit context
* if necessary. Doing so turns on system call auditing for the
* specified task. This is called from copy_process, so no lock is
* needed.
*/
int audit_alloc(struct task_struct *tsk)
{
struct audit_context *context;
enum audit_state state;
char *key = NULL;
if (likely(!audit_ever_enabled))
return 0; /* Return if not auditing. */
state = audit_filter_task(tsk, &key);
if (state == AUDIT_DISABLED) {
clear_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
return 0;
}
if (!(context = audit_alloc_context(state))) {
kfree(key);
audit_log_lost("out of memory in audit_alloc");
return -ENOMEM;
}
context->filterkey = key;
tsk->audit_context = context;
set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
return 0;
}
static inline void audit_free_context(struct audit_context *context)
{
audit_free_names(context);
unroll_tree_refs(context, NULL, 0);
free_tree_refs(context);
audit_free_aux(context);
kfree(context->filterkey);
kfree(context->sockaddr);
audit_proctitle_free(context);
kfree(context);
}
static int audit_log_pid_context(struct audit_context *context, pid_t pid,
kuid_t auid, kuid_t uid, unsigned int sessionid,
u32 sid, char *comm)
{
struct audit_buffer *ab;
char *ctx = NULL;
u32 len;
int rc = 0;
ab = audit_log_start(context, GFP_KERNEL, AUDIT_OBJ_PID);
if (!ab)
return rc;
audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid,
from_kuid(&init_user_ns, auid),
from_kuid(&init_user_ns, uid), sessionid);
if (sid) {
if (security_secid_to_secctx(sid, &ctx, &len)) {
audit_log_format(ab, " obj=(none)");
rc = 1;
} else {
audit_log_format(ab, " obj=%s", ctx);
security_release_secctx(ctx, len);
}
}
audit_log_format(ab, " ocomm=");
audit_log_untrustedstring(ab, comm);
audit_log_end(ab);
return rc;
}
/*
* to_send and len_sent accounting are very loose estimates. We aren't
* really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being
* within about 500 bytes (next page boundary)
*
* why snprintf? an int is up to 12 digits long. if we just assumed when
* logging that a[%d]= was going to be 16 characters long we would be wasting
* space in every audit message. In one 7500 byte message we can log up to
* about 1000 min size arguments. That comes down to about 50% waste of space
* if we didn't do the snprintf to find out how long arg_num_len was.
*/
static int audit_log_single_execve_arg(struct audit_context *context,
struct audit_buffer **ab,
int arg_num,
size_t *len_sent,
const char __user *p,
char *buf)
{
char arg_num_len_buf[12];
const char __user *tmp_p = p;
/* how many digits are in arg_num? 5 is the length of ' a=""' */
size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5;
size_t len, len_left, to_send;
size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN;
unsigned int i, has_cntl = 0, too_long = 0;
int ret;
/* strnlen_user includes the null we don't want to send */
len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1;
/*
* We just created this mm, if we can't find the strings
* we just copied into it something is _very_ wrong. Similar
* for strings that are too long, we should not have created
* any.
*/
if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
send_sig(SIGKILL, current, 0);
return -1;
}
/* walk the whole argument looking for non-ascii chars */
do {
if (len_left > MAX_EXECVE_AUDIT_LEN)
to_send = MAX_EXECVE_AUDIT_LEN;
else
to_send = len_left;
ret = copy_from_user(buf, tmp_p, to_send);
/*
* There is no reason for this copy to be short. We just
* copied them here, and the mm hasn't been exposed to user-
* space yet.
*/
if (ret) {
WARN_ON(1);
send_sig(SIGKILL, current, 0);
return -1;
}
buf[to_send] = '\0';
has_cntl = audit_string_contains_control(buf, to_send);
if (has_cntl) {
/*
* hex messages get logged as 2 bytes, so we can only
* send half as much in each message
*/
max_execve_audit_len = MAX_EXECVE_AUDIT_LEN / 2;
break;
}
len_left -= to_send;
tmp_p += to_send;
} while (len_left > 0);
len_left = len;
if (len > max_execve_audit_len)
too_long = 1;
/* rewalk the argument actually logging the message */
for (i = 0; len_left > 0; i++) {
int room_left;
if (len_left > max_execve_audit_len)
to_send = max_execve_audit_len;
else
to_send = len_left;
/* do we have space left to send this argument in this ab? */
room_left = MAX_EXECVE_AUDIT_LEN - arg_num_len - *len_sent;
if (has_cntl)
room_left -= (to_send * 2);
else
room_left -= to_send;
if (room_left < 0) {
*len_sent = 0;
audit_log_end(*ab);
*ab = audit_log_start(context, GFP_KERNEL, AUDIT_EXECVE);
if (!*ab)
return 0;
}
/*
* first record needs to say how long the original string was
* so we can be sure nothing was lost.
*/
if ((i == 0) && (too_long))
audit_log_format(*ab, " a%d_len=%zu", arg_num,
has_cntl ? 2*len : len);
/*
* normally arguments are small enough to fit and we already
* filled buf above when we checked for control characters
* so don't bother with another copy_from_user
*/
if (len >= max_execve_audit_len)
ret = copy_from_user(buf, p, to_send);
else
ret = 0;
if (ret) {
WARN_ON(1);
send_sig(SIGKILL, current, 0);
return -1;
}
buf[to_send] = '\0';
/* actually log it */
audit_log_format(*ab, " a%d", arg_num);
if (too_long)
audit_log_format(*ab, "[%d]", i);
audit_log_format(*ab, "=");
if (has_cntl)
audit_log_n_hex(*ab, buf, to_send);
else
audit_log_string(*ab, buf);
p += to_send;
len_left -= to_send;
*len_sent += arg_num_len;
if (has_cntl)
*len_sent += to_send * 2;
else
*len_sent += to_send;
}
/* include the null we didn't log */
return len + 1;
}
static void audit_log_execve_info(struct audit_context *context,
struct audit_buffer **ab)
{
int i, len;
size_t len_sent = 0;
const char __user *p;
char *buf;
p = (const char __user *)current->mm->arg_start;
audit_log_format(*ab, "argc=%d", context->execve.argc);
/*
* we need some kernel buffer to hold the userspace args. Just
* allocate one big one rather than allocating one of the right size
* for every single argument inside audit_log_single_execve_arg()
* should be <8k allocation so should be pretty safe.
*/
buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL);
if (!buf) {
audit_panic("out of memory for argv string");
return;
}
for (i = 0; i < context->execve.argc; i++) {
len = audit_log_single_execve_arg(context, ab, i,
&len_sent, p, buf);
if (len <= 0)
break;
p += len;
}
kfree(buf);
}
static void show_special(struct audit_context *context, int *call_panic)
{
struct audit_buffer *ab;
int i;
ab = audit_log_start(context, GFP_KERNEL, context->type);
if (!ab)
return;
switch (context->type) {
case AUDIT_SOCKETCALL: {
int nargs = context->socketcall.nargs;
audit_log_format(ab, "nargs=%d", nargs);
for (i = 0; i < nargs; i++)
audit_log_format(ab, " a%d=%lx", i,
context->socketcall.args[i]);
break; }
case AUDIT_IPC: {
u32 osid = context->ipc.osid;
audit_log_format(ab, "ouid=%u ogid=%u mode=%#ho",
from_kuid(&init_user_ns, context->ipc.uid),
from_kgid(&init_user_ns, context->ipc.gid),
context->ipc.mode);
if (osid) {
char *ctx = NULL;
u32 len;
if (security_secid_to_secctx(osid, &ctx, &len)) {
audit_log_format(ab, " osid=%u", osid);
*call_panic = 1;
} else {
audit_log_format(ab, " obj=%s", ctx);
security_release_secctx(ctx, len);
}
}
if (context->ipc.has_perm) {
audit_log_end(ab);
ab = audit_log_start(context, GFP_KERNEL,
AUDIT_IPC_SET_PERM);
if (unlikely(!ab))
return;
audit_log_format(ab,
"qbytes=%lx ouid=%u ogid=%u mode=%#ho",
context->ipc.qbytes,
context->ipc.perm_uid,
context->ipc.perm_gid,
context->ipc.perm_mode);
}
break; }
case AUDIT_MQ_OPEN: {
audit_log_format(ab,
"oflag=0x%x mode=%#ho mq_flags=0x%lx mq_maxmsg=%ld "
"mq_msgsize=%ld mq_curmsgs=%ld",
context->mq_open.oflag, context->mq_open.mode,
context->mq_open.attr.mq_flags,
context->mq_open.attr.mq_maxmsg,
context->mq_open.attr.mq_msgsize,
context->mq_open.attr.mq_curmsgs);
break; }
case AUDIT_MQ_SENDRECV: {
audit_log_format(ab,
"mqdes=%d msg_len=%zd msg_prio=%u "
"abs_timeout_sec=%ld abs_timeout_nsec=%ld",
context->mq_sendrecv.mqdes,
context->mq_sendrecv.msg_len,
context->mq_sendrecv.msg_prio,
context->mq_sendrecv.abs_timeout.tv_sec,
context->mq_sendrecv.abs_timeout.tv_nsec);
break; }
case AUDIT_MQ_NOTIFY: {
audit_log_format(ab, "mqdes=%d sigev_signo=%d",
context->mq_notify.mqdes,
context->mq_notify.sigev_signo);
break; }
case AUDIT_MQ_GETSETATTR: {
struct mq_attr *attr = &context->mq_getsetattr.mqstat;
audit_log_format(ab,
"mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld "
"mq_curmsgs=%ld ",
context->mq_getsetattr.mqdes,
attr->mq_flags, attr->mq_maxmsg,
attr->mq_msgsize, attr->mq_curmsgs);
break; }
case AUDIT_CAPSET: {
audit_log_format(ab, "pid=%d", context->capset.pid);
audit_log_cap(ab, "cap_pi", &context->capset.cap.inheritable);
audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted);
audit_log_cap(ab, "cap_pe", &context->capset.cap.effective);
break; }
case AUDIT_MMAP: {
audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd,
context->mmap.flags);
break; }
case AUDIT_EXECVE: {
audit_log_execve_info(context, &ab);
break; }
}
audit_log_end(ab);
}
static inline int audit_proctitle_rtrim(char *proctitle, int len)
{
char *end = proctitle + len - 1;
while (end > proctitle && !isprint(*end))
end--;
/* catch the case where proctitle is only 1 non-print character */
len = end - proctitle + 1;
len -= isprint(proctitle[len-1]) == 0;
return len;
}
static void audit_log_proctitle(struct task_struct *tsk,
struct audit_context *context)
{
int res;
char *buf;
char *msg = "(null)";
int len = strlen(msg);
struct audit_buffer *ab;
ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE);
if (!ab)
return; /* audit_panic or being filtered */
audit_log_format(ab, "proctitle=");
/* Not cached */
if (!context->proctitle.value) {
buf = kmalloc(MAX_PROCTITLE_AUDIT_LEN, GFP_KERNEL);
if (!buf)
goto out;
/* Historically called this from procfs naming */
res = get_cmdline(tsk, buf, MAX_PROCTITLE_AUDIT_LEN);
if (res == 0) {
kfree(buf);
goto out;
}
res = audit_proctitle_rtrim(buf, res);
if (res == 0) {
kfree(buf);
goto out;
}
context->proctitle.value = buf;
context->proctitle.len = res;
}
msg = context->proctitle.value;
len = context->proctitle.len;
out:
audit_log_n_untrustedstring(ab, msg, len);
audit_log_end(ab);
}
static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
{
int i, call_panic = 0;
struct audit_buffer *ab;
struct audit_aux_data *aux;
struct audit_names *n;
/* tsk == current */
context->personality = tsk->personality;
ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL);
if (!ab)
return; /* audit_panic has been called */
audit_log_format(ab, "arch=%x syscall=%d",
context->arch, context->major);
if (context->personality != PER_LINUX)
audit_log_format(ab, " per=%lx", context->personality);
if (context->return_valid)
audit_log_format(ab, " success=%s exit=%ld",
(context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
context->return_code);
audit_log_format(ab,
" a0=%lx a1=%lx a2=%lx a3=%lx items=%d",
context->argv[0],
context->argv[1],
context->argv[2],
context->argv[3],
context->name_count);
audit_log_task_info(ab, tsk);
audit_log_key(ab, context->filterkey);
audit_log_end(ab);
for (aux = context->aux; aux; aux = aux->next) {
ab = audit_log_start(context, GFP_KERNEL, aux->type);
if (!ab)
continue; /* audit_panic has been called */
switch (aux->type) {
case AUDIT_BPRM_FCAPS: {
struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
audit_log_format(ab, "fver=%x", axs->fcap_ver);
audit_log_cap(ab, "fp", &axs->fcap.permitted);
audit_log_cap(ab, "fi", &axs->fcap.inheritable);
audit_log_format(ab, " fe=%d", axs->fcap.fE);
audit_log_cap(ab, "old_pp", &axs->old_pcap.permitted);
audit_log_cap(ab, "old_pi", &axs->old_pcap.inheritable);
audit_log_cap(ab, "old_pe", &axs->old_pcap.effective);
audit_log_cap(ab, "new_pp", &axs->new_pcap.permitted);
audit_log_cap(ab, "new_pi", &axs->new_pcap.inheritable);
audit_log_cap(ab, "new_pe", &axs->new_pcap.effective);
break; }
}
audit_log_end(ab);
}
if (context->type)
show_special(context, &call_panic);
if (context->fds[0] >= 0) {
ab = audit_log_start(context, GFP_KERNEL, AUDIT_FD_PAIR);
if (ab) {
audit_log_format(ab, "fd0=%d fd1=%d",
context->fds[0], context->fds[1]);
audit_log_end(ab);
}
}
if (context->sockaddr_len) {
ab = audit_log_start(context, GFP_KERNEL, AUDIT_SOCKADDR);
if (ab) {
audit_log_format(ab, "saddr=");
audit_log_n_hex(ab, (void *)context->sockaddr,
context->sockaddr_len);
audit_log_end(ab);
}
}
for (aux = context->aux_pids; aux; aux = aux->next) {
struct audit_aux_data_pids *axs = (void *)aux;
for (i = 0; i < axs->pid_count; i++)
if (audit_log_pid_context(context, axs->target_pid[i],
axs->target_auid[i],
axs->target_uid[i],
axs->target_sessionid[i],
axs->target_sid[i],
axs->target_comm[i]))
call_panic = 1;
}
if (context->target_pid &&
audit_log_pid_context(context, context->target_pid,
context->target_auid, context->target_uid,
context->target_sessionid,
context->target_sid, context->target_comm))
call_panic = 1;
if (context->pwd.dentry && context->pwd.mnt) {
ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD);
if (ab) {
audit_log_d_path(ab, " cwd=", &context->pwd);
audit_log_end(ab);
}
}
i = 0;
list_for_each_entry(n, &context->names_list, list) {
if (n->hidden)
continue;
audit_log_name(context, n, NULL, i++, &call_panic);
}
audit_log_proctitle(tsk, context);
/* Send end of event record to help user space know we are finished */
ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
if (ab)
audit_log_end(ab);
if (call_panic)
audit_panic("error converting sid to string");
}
/**
* audit_free - free a per-task audit context
* @tsk: task whose audit context block to free
*
* Called from copy_process and do_exit
*/
void __audit_free(struct task_struct *tsk)
{
struct audit_context *context;
context = audit_take_context(tsk, 0, 0);
if (!context)
return;
/* Check for system calls that do not go through the exit
* function (e.g., exit_group), then free context block.
* We use GFP_ATOMIC here because we might be doing this
* in the context of the idle thread */
/* that can happen only if we are called from do_exit() */
if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
audit_log_exit(context, tsk);
if (!list_empty(&context->killed_trees))
audit_kill_trees(&context->killed_trees);
audit_free_context(context);
}
/**
* audit_syscall_entry - fill in an audit record at syscall entry
* @major: major syscall type (function)
* @a1: additional syscall register 1
* @a2: additional syscall register 2
* @a3: additional syscall register 3
* @a4: additional syscall register 4
*
* Fill in audit context at syscall entry. This only happens if the
* audit context was created when the task was created and the state or
* filters demand the audit context be built. If the state from the
* per-task filter or from the per-syscall filter is AUDIT_RECORD_CONTEXT,
* then the record will be written at syscall exit time (otherwise, it
* will only be written if another part of the kernel requests that it
* be written).
*/
void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
unsigned long a3, unsigned long a4)
{
struct task_struct *tsk = current;
struct audit_context *context = tsk->audit_context;
enum audit_state state;
if (!context)
return;
BUG_ON(context->in_syscall || context->name_count);
if (!audit_enabled)
return;
context->arch = syscall_get_arch();
context->major = major;
context->argv[0] = a1;
context->argv[1] = a2;
context->argv[2] = a3;
context->argv[3] = a4;
state = context->state;
context->dummy = !audit_n_rules;
if (!context->dummy && state == AUDIT_BUILD_CONTEXT) {
context->prio = 0;
state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);
}
if (state == AUDIT_DISABLED)
return;
context->serial = 0;
context->ctime = CURRENT_TIME;
context->in_syscall = 1;
context->current_state = state;
context->ppid = 0;
}
/**
* audit_syscall_exit - deallocate audit context after a system call
* @success: success value of the syscall
* @return_code: return value of the syscall
*
* Tear down after system call. If the audit context has been marked as
* auditable (either because of the AUDIT_RECORD_CONTEXT state from
* filtering, or because some other part of the kernel wrote an audit
* message), then write out the syscall information. In call cases,
* free the names stored from getname().
*/
void __audit_syscall_exit(int success, long return_code)
{
struct task_struct *tsk = current;
struct audit_context *context;
if (success)
success = AUDITSC_SUCCESS;
else
success = AUDITSC_FAILURE;
context = audit_take_context(tsk, success, return_code);
if (!context)
return;
if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
audit_log_exit(context, tsk);
context->in_syscall = 0;
context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
if (!list_empty(&context->killed_trees))
audit_kill_trees(&context->killed_trees);
audit_free_names(context);
unroll_tree_refs(context, NULL, 0);
audit_free_aux(context);
context->aux = NULL;
context->aux_pids = NULL;
context->target_pid = 0;
context->target_sid = 0;
context->sockaddr_len = 0;
context->type = 0;
context->fds[0] = -1;
if (context->state != AUDIT_RECORD_CONTEXT) {
kfree(context->filterkey);
context->filterkey = NULL;
}
tsk->audit_context = context;
}
static inline void handle_one(const struct inode *inode)
{
#ifdef CONFIG_AUDIT_TREE
struct audit_context *context;
struct audit_tree_refs *p;
struct audit_chunk *chunk;
int count;
if (likely(hlist_empty(&inode->i_fsnotify_marks)))
return;
context = current->audit_context;
p = context->trees;
count = context->tree_count;
rcu_read_lock();
chunk = audit_tree_lookup(inode);
rcu_read_unlock();
if (!chunk)
return;
if (likely(put_tree_ref(context, chunk)))
return;
if (unlikely(!grow_tree_refs(context))) {
pr_warn("out of memory, audit has lost a tree reference\n");
audit_set_auditable(context);
audit_put_chunk(chunk);
unroll_tree_refs(context, p, count);
return;
}
put_tree_ref(context, chunk);
#endif
}
static void handle_path(const struct dentry *dentry)
{
#ifdef CONFIG_AUDIT_TREE
struct audit_context *context;
struct audit_tree_refs *p;
const struct dentry *d, *parent;
struct audit_chunk *drop;
unsigned long seq;
int count;
context = current->audit_context;
p = context->trees;
count = context->tree_count;
retry:
drop = NULL;
d = dentry;
rcu_read_lock();
seq = read_seqbegin(&rename_lock);
for(;;) {
struct inode *inode = d_backing_inode(d);
if (inode && unlikely(!hlist_empty(&inode->i_fsnotify_marks))) {
struct audit_chunk *chunk;
chunk = audit_tree_lookup(inode);
if (chunk) {
if (unlikely(!put_tree_ref(context, chunk))) {
drop = chunk;
break;
}
}
}
parent = d->d_parent;
if (parent == d)
break;
d = parent;
}
if (unlikely(read_seqretry(&rename_lock, seq) || drop)) { /* in this order */
rcu_read_unlock();
if (!drop) {
/* just a race with rename */
unroll_tree_refs(context, p, count);
goto retry;
}
audit_put_chunk(drop);
if (grow_tree_refs(context)) {
/* OK, got more space */
unroll_tree_refs(context, p, count);
goto retry;
}
/* too bad */
pr_warn("out of memory, audit has lost a tree reference\n");
unroll_tree_refs(context, p, count);
audit_set_auditable(context);
return;
}
rcu_read_unlock();
#endif
}
static struct audit_names *audit_alloc_name(struct audit_context *context,
unsigned char type)
{
struct audit_names *aname;
if (context->name_count < AUDIT_NAMES) {
aname = &context->preallocated_names[context->name_count];
memset(aname, 0, sizeof(*aname));
} else {
aname = kzalloc(sizeof(*aname), GFP_NOFS);
if (!aname)
return NULL;
aname->should_free = true;
}
aname->ino = (unsigned long)-1;
aname->type = type;
list_add_tail(&aname->list, &context->names_list);
context->name_count++;
return aname;
}
/**
* audit_reusename - fill out filename with info from existing entry
* @uptr: userland ptr to pathname
*
* Search the audit_names list for the current audit context. If there is an
* existing entry with a matching "uptr" then return the filename
* associated with that audit_name. If not, return NULL.
*/
struct filename *
__audit_reusename(const __user char *uptr)
{
struct audit_context *context = current->audit_context;
struct audit_names *n;
list_for_each_entry(n, &context->names_list, list) {
if (!n->name)
continue;
if (n->name->uptr == uptr) {
n->name->refcnt++;
return n->name;
}
}
return NULL;
}
/**
* audit_getname - add a name to the list
* @name: name to add
*
* Add a name to the list of audit names for this context.
* Called from fs/namei.c:getname().
*/
void __audit_getname(struct filename *name)
{
struct audit_context *context = current->audit_context;
struct audit_names *n;
if (!context->in_syscall)
return;
n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN);
if (!n)
return;
n->name = name;
n->name_len = AUDIT_NAME_FULL;
name->aname = n;
name->refcnt++;
if (!context->pwd.dentry)
get_fs_pwd(current->fs, &context->pwd);
}
/**
* __audit_inode - store the inode and device from a lookup
* @name: name being audited
* @dentry: dentry being audited
* @flags: attributes for this particular entry
*/
void __audit_inode(struct filename *name, const struct dentry *dentry,
unsigned int flags)
{
struct audit_context *context = current->audit_context;
const struct inode *inode = d_backing_inode(dentry);
struct audit_names *n;
bool parent = flags & AUDIT_INODE_PARENT;
if (!context->in_syscall)
return;
if (!name)
goto out_alloc;
/*
* If we have a pointer to an audit_names entry already, then we can
* just use it directly if the type is correct.
*/
n = name->aname;
if (n) {
if (parent) {
if (n->type == AUDIT_TYPE_PARENT ||
n->type == AUDIT_TYPE_UNKNOWN)
goto out;
} else {
if (n->type != AUDIT_TYPE_PARENT)
goto out;
}
}
list_for_each_entry_reverse(n, &context->names_list, list) {
if (n->ino) {
/* valid inode number, use that for the comparison */
if (n->ino != inode->i_ino ||
n->dev != inode->i_sb->s_dev)
continue;
} else if (n->name) {
/* inode number has not been set, check the name */
if (strcmp(n->name->name, name->name))
continue;
} else
/* no inode and no name (?!) ... this is odd ... */
continue;
/* match the correct record type */
if (parent) {
if (n->type == AUDIT_TYPE_PARENT ||
n->type == AUDIT_TYPE_UNKNOWN)
goto out;
} else {
if (n->type != AUDIT_TYPE_PARENT)
goto out;
}
}
out_alloc:
/* unable to find an entry with both a matching name and type */
n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN);
if (!n)
return;
if (name) {
n->name = name;
name->refcnt++;
}
out:
if (parent) {
n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
n->type = AUDIT_TYPE_PARENT;
if (flags & AUDIT_INODE_HIDDEN)
n->hidden = true;
} else {
n->name_len = AUDIT_NAME_FULL;
n->type = AUDIT_TYPE_NORMAL;
}
handle_path(dentry);
audit_copy_inode(n, dentry, inode);
}
void __audit_file(const struct file *file)
{
__audit_inode(NULL, file->f_path.dentry, 0);
}
/**
* __audit_inode_child - collect inode info for created/removed objects
* @parent: inode of dentry parent
* @dentry: dentry being audited
* @type: AUDIT_TYPE_* value that we're looking for
*
* For syscalls that create or remove filesystem objects, audit_inode
* can only collect information for the filesystem object's parent.
* This call updates the audit context with the child's information.
* Syscalls that create a new filesystem object must be hooked after
* the object is created. Syscalls that remove a filesystem object
* must be hooked prior, in order to capture the target inode during
* unsuccessful attempts.
*/
void __audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
const unsigned char type)
{
struct audit_context *context = current->audit_context;
const struct inode *inode = d_backing_inode(dentry);
const char *dname = dentry->d_name.name;
struct audit_names *n, *found_parent = NULL, *found_child = NULL;
if (!context->in_syscall)
return;
if (inode)
handle_one(inode);
/* look for a parent entry first */
list_for_each_entry(n, &context->names_list, list) {
if (!n->name ||
(n->type != AUDIT_TYPE_PARENT &&
n->type != AUDIT_TYPE_UNKNOWN))
continue;
if (n->ino == parent->i_ino && n->dev == parent->i_sb->s_dev &&
!audit_compare_dname_path(dname,
n->name->name, n->name_len)) {
if (n->type == AUDIT_TYPE_UNKNOWN)
n->type = AUDIT_TYPE_PARENT;
found_parent = n;
break;
}
}
/* is there a matching child entry? */
list_for_each_entry(n, &context->names_list, list) {
/* can only match entries that have a name */
if (!n->name ||
(n->type != type && n->type != AUDIT_TYPE_UNKNOWN))
continue;
if (!strcmp(dname, n->name->name) ||
!audit_compare_dname_path(dname, n->name->name,
found_parent ?
found_parent->name_len :
AUDIT_NAME_FULL)) {
if (n->type == AUDIT_TYPE_UNKNOWN)
n->type = type;
found_child = n;
break;
}
}
if (!found_parent) {
/* create a new, "anonymous" parent record */
n = audit_alloc_name(context, AUDIT_TYPE_PARENT);
if (!n)
return;
audit_copy_inode(n, NULL, parent);
}
if (!found_child) {
found_child = audit_alloc_name(context, type);
if (!found_child)
return;
/* Re-use the name belonging to the slot for a matching parent
* directory. All names for this context are relinquished in
* audit_free_names() */
if (found_parent) {
found_child->name = found_parent->name;
found_child->name_len = AUDIT_NAME_FULL;
found_child->name->refcnt++;
}
}
if (inode)
audit_copy_inode(found_child, dentry, inode);
else
found_child->ino = (unsigned long)-1;
}
EXPORT_SYMBOL_GPL(__audit_inode_child);
/**
* auditsc_get_stamp - get local copies of audit_context values
* @ctx: audit_context for the task
* @t: timespec to store time recorded in the audit_context
* @serial: serial value that is recorded in the audit_context
*
* Also sets the context as auditable.
*/
int auditsc_get_stamp(struct audit_context *ctx,
struct timespec *t, unsigned int *serial)
{
if (!ctx->in_syscall)
return 0;
if (!ctx->serial)
ctx->serial = audit_serial();
t->tv_sec = ctx->ctime.tv_sec;
t->tv_nsec = ctx->ctime.tv_nsec;
*serial = ctx->serial;
if (!ctx->prio) {
ctx->prio = 1;
ctx->current_state = AUDIT_RECORD_CONTEXT;
}
return 1;
}
/* global counter which is incremented every time something logs in */
static atomic_t session_id = ATOMIC_INIT(0);
static int audit_set_loginuid_perm(kuid_t loginuid)
{
/* if we are unset, we don't need privs */
if (!audit_loginuid_set(current))
return 0;
/* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/
if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE))
return -EPERM;
/* it is set, you need permission */
if (!capable(CAP_AUDIT_CONTROL))
return -EPERM;
/* reject if this is not an unset and we don't allow that */
if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid))
return -EPERM;
return 0;
}
static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
unsigned int oldsessionid, unsigned int sessionid,
int rc)
{
struct audit_buffer *ab;
uid_t uid, oldloginuid, loginuid;
if (!audit_enabled)
return;
uid = from_kuid(&init_user_ns, task_uid(current));
oldloginuid = from_kuid(&init_user_ns, koldloginuid);
loginuid = from_kuid(&init_user_ns, kloginuid),
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
if (!ab)
return;
audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid);
audit_log_task_context(ab);
audit_log_format(ab, " old-auid=%u auid=%u old-ses=%u ses=%u res=%d",
oldloginuid, loginuid, oldsessionid, sessionid, !rc);
audit_log_end(ab);
}
/**
* audit_set_loginuid - set current task's audit_context loginuid
* @loginuid: loginuid value
*
* Returns 0.
*
* Called (set) from fs/proc/base.c::proc_loginuid_write().
*/
int audit_set_loginuid(kuid_t loginuid)
{
struct task_struct *task = current;
unsigned int oldsessionid, sessionid = (unsigned int)-1;
kuid_t oldloginuid;
int rc;
oldloginuid = audit_get_loginuid(current);
oldsessionid = audit_get_sessionid(current);
rc = audit_set_loginuid_perm(loginuid);
if (rc)
goto out;
/* are we setting or clearing? */
if (uid_valid(loginuid))
sessionid = (unsigned int)atomic_inc_return(&session_id);
task->sessionid = sessionid;
task->loginuid = loginuid;
out:
audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
return rc;
}
/**
* __audit_mq_open - record audit data for a POSIX MQ open
* @oflag: open flag
* @mode: mode bits
* @attr: queue attributes
*
*/
void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr)
{
struct audit_context *context = current->audit_context;
if (attr)
memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr));
else
memset(&context->mq_open.attr, 0, sizeof(struct mq_attr));
context->mq_open.oflag = oflag;
context->mq_open.mode = mode;
context->type = AUDIT_MQ_OPEN;
}
/**
* __audit_mq_sendrecv - record audit data for a POSIX MQ timed send/receive
* @mqdes: MQ descriptor
* @msg_len: Message length
* @msg_prio: Message priority
* @abs_timeout: Message timeout in absolute time
*
*/
void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
const struct timespec *abs_timeout)
{
struct audit_context *context = current->audit_context;
struct timespec *p = &context->mq_sendrecv.abs_timeout;
if (abs_timeout)
memcpy(p, abs_timeout, sizeof(struct timespec));
else
memset(p, 0, sizeof(struct timespec));
context->mq_sendrecv.mqdes = mqdes;
context->mq_sendrecv.msg_len = msg_len;
context->mq_sendrecv.msg_prio = msg_prio;
context->type = AUDIT_MQ_SENDRECV;
}
/**
* __audit_mq_notify - record audit data for a POSIX MQ notify
* @mqdes: MQ descriptor
* @notification: Notification event
*
*/
void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification)
{
struct audit_context *context = current->audit_context;
if (notification)
context->mq_notify.sigev_signo = notification->sigev_signo;
else
context->mq_notify.sigev_signo = 0;
context->mq_notify.mqdes = mqdes;
context->type = AUDIT_MQ_NOTIFY;
}
/**
* __audit_mq_getsetattr - record audit data for a POSIX MQ get/set attribute
* @mqdes: MQ descriptor
* @mqstat: MQ flags
*
*/
void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
{
struct audit_context *context = current->audit_context;
context->mq_getsetattr.mqdes = mqdes;
context->mq_getsetattr.mqstat = *mqstat;
context->type = AUDIT_MQ_GETSETATTR;
}
/**
* audit_ipc_obj - record audit data for ipc object
* @ipcp: ipc permissions
*
*/
void __audit_ipc_obj(struct kern_ipc_perm *ipcp)
{
struct audit_context *context = current->audit_context;
context->ipc.uid = ipcp->uid;
context->ipc.gid = ipcp->gid;
context->ipc.mode = ipcp->mode;
context->ipc.has_perm = 0;
security_ipc_getsecid(ipcp, &context->ipc.osid);
context->type = AUDIT_IPC;
}
/**
* audit_ipc_set_perm - record audit data for new ipc permissions
* @qbytes: msgq bytes
* @uid: msgq user id
* @gid: msgq group id
* @mode: msgq mode (permissions)
*
* Called only after audit_ipc_obj().
*/
void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode)
{
struct audit_context *context = current->audit_context;
context->ipc.qbytes = qbytes;
context->ipc.perm_uid = uid;
context->ipc.perm_gid = gid;
context->ipc.perm_mode = mode;
context->ipc.has_perm = 1;
}
void __audit_bprm(struct linux_binprm *bprm)
{
struct audit_context *context = current->audit_context;
context->type = AUDIT_EXECVE;
context->execve.argc = bprm->argc;
}
/**
* audit_socketcall - record audit data for sys_socketcall
* @nargs: number of args, which should not be more than AUDITSC_ARGS.
* @args: args array
*
*/
int __audit_socketcall(int nargs, unsigned long *args)
{
struct audit_context *context = current->audit_context;
if (nargs <= 0 || nargs > AUDITSC_ARGS || !args)
return -EINVAL;
context->type = AUDIT_SOCKETCALL;
context->socketcall.nargs = nargs;
memcpy(context->socketcall.args, args, nargs * sizeof(unsigned long));
return 0;
}
/**
* __audit_fd_pair - record audit data for pipe and socketpair
* @fd1: the first file descriptor
* @fd2: the second file descriptor
*
*/
void __audit_fd_pair(int fd1, int fd2)
{
struct audit_context *context = current->audit_context;
context->fds[0] = fd1;
context->fds[1] = fd2;
}
/**
* audit_sockaddr - record audit data for sys_bind, sys_connect, sys_sendto
* @len: data length in user space
* @a: data address in kernel space
*
* Returns 0 for success or NULL context or < 0 on error.
*/
int __audit_sockaddr(int len, void *a)
{
struct audit_context *context = current->audit_context;
if (!context->sockaddr) {
void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL);
if (!p)
return -ENOMEM;
context->sockaddr = p;
}
context->sockaddr_len = len;
memcpy(context->sockaddr, a, len);
return 0;
}
void __audit_ptrace(struct task_struct *t)
{
struct audit_context *context = current->audit_context;
context->target_pid = task_pid_nr(t);
context->target_auid = audit_get_loginuid(t);
context->target_uid = task_uid(t);
context->target_sessionid = audit_get_sessionid(t);
security_task_getsecid(t, &context->target_sid);
memcpy(context->target_comm, t->comm, TASK_COMM_LEN);
}
/**
* audit_signal_info - record signal info for shutting down audit subsystem
* @sig: signal value
* @t: task being signaled
*
* If the audit subsystem is being terminated, record the task (pid)
* and uid that is doing that.
*/
int __audit_signal_info(int sig, struct task_struct *t)
{
struct audit_aux_data_pids *axp;
struct task_struct *tsk = current;
struct audit_context *ctx = tsk->audit_context;
kuid_t uid = current_uid(), t_uid = task_uid(t);
if (audit_pid && t->tgid == audit_pid) {
if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
audit_sig_pid = task_pid_nr(tsk);
if (uid_valid(tsk->loginuid))
audit_sig_uid = tsk->loginuid;
else
audit_sig_uid = uid;
security_task_getsecid(tsk, &audit_sig_sid);
}
if (!audit_signals || audit_dummy_context())
return 0;
}
/* optimize the common case by putting first signal recipient directly
* in audit_context */
if (!ctx->target_pid) {
ctx->target_pid = task_tgid_nr(t);
ctx->target_auid = audit_get_loginuid(t);
ctx->target_uid = t_uid;
ctx->target_sessionid = audit_get_sessionid(t);
security_task_getsecid(t, &ctx->target_sid);
memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN);
return 0;
}
axp = (void *)ctx->aux_pids;
if (!axp || axp->pid_count == AUDIT_AUX_PIDS) {
axp = kzalloc(sizeof(*axp), GFP_ATOMIC);
if (!axp)
return -ENOMEM;
axp->d.type = AUDIT_OBJ_PID;
axp->d.next = ctx->aux_pids;
ctx->aux_pids = (void *)axp;
}
BUG_ON(axp->pid_count >= AUDIT_AUX_PIDS);
axp->target_pid[axp->pid_count] = task_tgid_nr(t);
axp->target_auid[axp->pid_count] = audit_get_loginuid(t);
axp->target_uid[axp->pid_count] = t_uid;
axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t);
security_task_getsecid(t, &axp->target_sid[axp->pid_count]);
memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN);
axp->pid_count++;
return 0;
}
/**
* __audit_log_bprm_fcaps - store information about a loading bprm and relevant fcaps
* @bprm: pointer to the bprm being processed
* @new: the proposed new credentials
* @old: the old credentials
*
* Simply check if the proc already has the caps given by the file and if not
* store the priv escalation info for later auditing at the end of the syscall
*
* -Eric
*/
int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
const struct cred *new, const struct cred *old)
{
struct audit_aux_data_bprm_fcaps *ax;
struct audit_context *context = current->audit_context;
struct cpu_vfs_cap_data vcaps;
ax = kmalloc(sizeof(*ax), GFP_KERNEL);
if (!ax)
return -ENOMEM;
ax->d.type = AUDIT_BPRM_FCAPS;
ax->d.next = context->aux;
context->aux = (void *)ax;
get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps);
ax->fcap.permitted = vcaps.permitted;
ax->fcap.inheritable = vcaps.inheritable;
ax->fcap.fE = !!(vcaps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
ax->fcap_ver = (vcaps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT;
ax->old_pcap.permitted = old->cap_permitted;
ax->old_pcap.inheritable = old->cap_inheritable;
ax->old_pcap.effective = old->cap_effective;
ax->new_pcap.permitted = new->cap_permitted;
ax->new_pcap.inheritable = new->cap_inheritable;
ax->new_pcap.effective = new->cap_effective;
return 0;
}
/**
* __audit_log_capset - store information about the arguments to the capset syscall
* @new: the new credentials
* @old: the old (current) credentials
*
* Record the arguments userspace sent to sys_capset for later printing by the
* audit system if applicable
*/
void __audit_log_capset(const struct cred *new, const struct cred *old)
{
struct audit_context *context = current->audit_context;
context->capset.pid = task_pid_nr(current);
context->capset.cap.effective = new->cap_effective;
context->capset.cap.inheritable = new->cap_effective;
context->capset.cap.permitted = new->cap_permitted;
context->type = AUDIT_CAPSET;
}
void __audit_mmap_fd(int fd, int flags)
{
struct audit_context *context = current->audit_context;
context->mmap.fd = fd;
context->mmap.flags = flags;
context->type = AUDIT_MMAP;
}
static void audit_log_task(struct audit_buffer *ab)
{
kuid_t auid, uid;
kgid_t gid;
unsigned int sessionid;
char comm[sizeof(current->comm)];
auid = audit_get_loginuid(current);
sessionid = audit_get_sessionid(current);
current_uid_gid(&uid, &gid);
audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u",
from_kuid(&init_user_ns, auid),
from_kuid(&init_user_ns, uid),
from_kgid(&init_user_ns, gid),
sessionid);
audit_log_task_context(ab);
audit_log_format(ab, " pid=%d comm=", task_pid_nr(current));
audit_log_untrustedstring(ab, get_task_comm(comm, current));
audit_log_d_path_exe(ab, current->mm);
}
/**
* audit_core_dumps - record information about processes that end abnormally
* @signr: signal value
*
* If a process ends with a core dump, something fishy is going on and we
* should record the event for investigation.
*/
void audit_core_dumps(long signr)
{
struct audit_buffer *ab;
if (!audit_enabled)
return;
if (signr == SIGQUIT) /* don't care for those */
return;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
if (unlikely(!ab))
return;
audit_log_task(ab);
audit_log_format(ab, " sig=%ld", signr);
audit_log_end(ab);
}
void __audit_seccomp(unsigned long syscall, long signr, int code)
{
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP);
if (unlikely(!ab))
return;
audit_log_task(ab);
audit_log_format(ab, " sig=%ld arch=%x syscall=%ld compat=%d ip=0x%lx code=0x%x",
signr, syscall_get_arch(), syscall, is_compat_task(),
KSTK_EIP(current), code);
audit_log_end(ab);
}
struct list_head *audit_killed_trees(void)
{
struct audit_context *ctx = current->audit_context;
if (likely(!ctx || !ctx->in_syscall))
return NULL;
return &ctx->killed_trees;
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/audit_tree.c
#include "audit.h"
#include <linux/fsnotify_backend.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/kthread.h>
#include <linux/slab.h>
struct audit_tree;
struct audit_chunk;
struct audit_tree {
atomic_t count;
int goner;
struct audit_chunk *root;
struct list_head chunks;
struct list_head rules;
struct list_head list;
struct list_head same_root;
struct rcu_head head;
char pathname[];
};
struct audit_chunk {
struct list_head hash;
struct fsnotify_mark mark;
struct list_head trees; /* with root here */
int dead;
int count;
atomic_long_t refs;
struct rcu_head head;
struct node {
struct list_head list;
struct audit_tree *owner;
unsigned index; /* index; upper bit indicates 'will prune' */
} owners[];
};
static LIST_HEAD(tree_list);
static LIST_HEAD(prune_list);
static struct task_struct *prune_thread;
/*
* One struct chunk is attached to each inode of interest.
* We replace struct chunk on tagging/untagging.
* Rules have pointer to struct audit_tree.
* Rules have struct list_head rlist forming a list of rules over
* the same tree.
* References to struct chunk are collected at audit_inode{,_child}()
* time and used in AUDIT_TREE rule matching.
* These references are dropped at the same time we are calling
* audit_free_names(), etc.
*
* Cyclic lists galore:
* tree.chunks anchors chunk.owners[].list hash_lock
* tree.rules anchors rule.rlist audit_filter_mutex
* chunk.trees anchors tree.same_root hash_lock
* chunk.hash is a hash with middle bits of watch.inode as
* a hash function. RCU, hash_lock
*
* tree is refcounted; one reference for "some rules on rules_list refer to
* it", one for each chunk with pointer to it.
*
* chunk is refcounted by embedded fsnotify_mark + .refs (non-zero refcount
* of watch contributes 1 to .refs).
*
* node.index allows to get from node.list to containing chunk.
* MSB of that sucker is stolen to mark taggings that we might have to
* revert - several operations have very unpleasant cleanup logics and
* that makes a difference. Some.
*/
static struct fsnotify_group *audit_tree_group;
static struct audit_tree *alloc_tree(const char *s)
{
struct audit_tree *tree;
tree = kmalloc(sizeof(struct audit_tree) + strlen(s) + 1, GFP_KERNEL);
if (tree) {
atomic_set(&tree->count, 1);
tree->goner = 0;
INIT_LIST_HEAD(&tree->chunks);
INIT_LIST_HEAD(&tree->rules);
INIT_LIST_HEAD(&tree->list);
INIT_LIST_HEAD(&tree->same_root);
tree->root = NULL;
strcpy(tree->pathname, s);
}
return tree;
}
static inline void get_tree(struct audit_tree *tree)
{
atomic_inc(&tree->count);
}
static inline void put_tree(struct audit_tree *tree)
{
if (atomic_dec_and_test(&tree->count))
kfree_rcu(tree, head);
}
/* to avoid bringing the entire thing in audit.h */
const char *audit_tree_path(struct audit_tree *tree)
{
return tree->pathname;
}
static void free_chunk(struct audit_chunk *chunk)
{
int i;
for (i = 0; i < chunk->count; i++) {
if (chunk->owners[i].owner)
put_tree(chunk->owners[i].owner);
}
kfree(chunk);
}
void audit_put_chunk(struct audit_chunk *chunk)
{
if (atomic_long_dec_and_test(&chunk->refs))
free_chunk(chunk);
}
static void __put_chunk(struct rcu_head *rcu)
{
struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head);
audit_put_chunk(chunk);
}
static void audit_tree_destroy_watch(struct fsnotify_mark *entry)
{
struct audit_chunk *chunk = container_of(entry, struct audit_chunk, mark);
call_rcu(&chunk->head, __put_chunk);
}
static struct audit_chunk *alloc_chunk(int count)
{
struct audit_chunk *chunk;
size_t size;
int i;
size = offsetof(struct audit_chunk, owners) + count * sizeof(struct node);
chunk = kzalloc(size, GFP_KERNEL);
if (!chunk)
return NULL;
INIT_LIST_HEAD(&chunk->hash);
INIT_LIST_HEAD(&chunk->trees);
chunk->count = count;
atomic_long_set(&chunk->refs, 1);
for (i = 0; i < count; i++) {
INIT_LIST_HEAD(&chunk->owners[i].list);
chunk->owners[i].index = i;
}
fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
chunk->mark.mask = FS_IN_IGNORED;
return chunk;
}
enum {HASH_SIZE = 128};
static struct list_head chunk_hash_heads[HASH_SIZE];
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(hash_lock);
static inline struct list_head *chunk_hash(const struct inode *inode)
{
unsigned long n = (unsigned long)inode / L1_CACHE_BYTES;
return chunk_hash_heads + n % HASH_SIZE;
}
/* hash_lock & entry->lock is held by caller */
static void insert_hash(struct audit_chunk *chunk)
{
struct fsnotify_mark *entry = &chunk->mark;
struct list_head *list;
if (!entry->inode)
return;
list = chunk_hash(entry->inode);
list_add_rcu(&chunk->hash, list);
}
/* called under rcu_read_lock */
struct audit_chunk *audit_tree_lookup(const struct inode *inode)
{
struct list_head *list = chunk_hash(inode);
struct audit_chunk *p;
list_for_each_entry_rcu(p, list, hash) {
/* mark.inode may have gone NULL, but who cares? */
if (p->mark.inode == inode) {
atomic_long_inc(&p->refs);
return p;
}
}
return NULL;
}
int audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree)
{
int n;
for (n = 0; n < chunk->count; n++)
if (chunk->owners[n].owner == tree)
return 1;
return 0;
}
/* tagging and untagging inodes with trees */
static struct audit_chunk *find_chunk(struct node *p)
{
int index = p->index & ~(1U<<31);
p -= index;
return container_of(p, struct audit_chunk, owners[0]);
}
static void untag_chunk(struct node *p)
{
struct audit_chunk *chunk = find_chunk(p);
struct fsnotify_mark *entry = &chunk->mark;
struct audit_chunk *new = NULL;
struct audit_tree *owner;
int size = chunk->count - 1;
int i, j;
fsnotify_get_mark(entry);
spin_unlock(&hash_lock);
if (size)
new = alloc_chunk(size);
spin_lock(&entry->lock);
if (chunk->dead || !entry->inode) {
spin_unlock(&entry->lock);
if (new)
free_chunk(new);
goto out;
}
owner = p->owner;
if (!size) {
chunk->dead = 1;
spin_lock(&hash_lock);
list_del_init(&chunk->trees);
if (owner->root == chunk)
owner->root = NULL;
list_del_init(&p->list);
list_del_rcu(&chunk->hash);
spin_unlock(&hash_lock);
spin_unlock(&entry->lock);
fsnotify_destroy_mark(entry, audit_tree_group);
goto out;
}
if (!new)
goto Fallback;
fsnotify_duplicate_mark(&new->mark, entry);
if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.inode, NULL, 1)) {
fsnotify_put_mark(&new->mark);
goto Fallback;
}
chunk->dead = 1;
spin_lock(&hash_lock);
list_replace_init(&chunk->trees, &new->trees);
if (owner->root == chunk) {
list_del_init(&owner->same_root);
owner->root = NULL;
}
for (i = j = 0; j <= size; i++, j++) {
struct audit_tree *s;
if (&chunk->owners[j] == p) {
list_del_init(&p->list);
i--;
continue;
}
s = chunk->owners[j].owner;
new->owners[i].owner = s;
new->owners[i].index = chunk->owners[j].index - j + i;
if (!s) /* result of earlier fallback */
continue;
get_tree(s);
list_replace_init(&chunk->owners[j].list, &new->owners[i].list);
}
list_replace_rcu(&chunk->hash, &new->hash);
list_for_each_entry(owner, &new->trees, same_root)
owner->root = new;
spin_unlock(&hash_lock);
spin_unlock(&entry->lock);
fsnotify_destroy_mark(entry, audit_tree_group);
fsnotify_put_mark(&new->mark); /* drop initial reference */
goto out;
Fallback:
// do the best we can
spin_lock(&hash_lock);
if (owner->root == chunk) {
list_del_init(&owner->same_root);
owner->root = NULL;
}
list_del_init(&p->list);
p->owner = NULL;
put_tree(owner);
spin_unlock(&hash_lock);
spin_unlock(&entry->lock);
out:
fsnotify_put_mark(entry);
spin_lock(&hash_lock);
}
static int create_chunk(struct inode *inode, struct audit_tree *tree)
{
struct fsnotify_mark *entry;
struct audit_chunk *chunk = alloc_chunk(1);
if (!chunk)
return -ENOMEM;
entry = &chunk->mark;
if (fsnotify_add_mark(entry, audit_tree_group, inode, NULL, 0)) {
fsnotify_put_mark(entry);
return -ENOSPC;
}
spin_lock(&entry->lock);
spin_lock(&hash_lock);
if (tree->goner) {
spin_unlock(&hash_lock);
chunk->dead = 1;
spin_unlock(&entry->lock);
fsnotify_destroy_mark(entry, audit_tree_group);
fsnotify_put_mark(entry);
return 0;
}
chunk->owners[0].index = (1U << 31);
chunk->owners[0].owner = tree;
get_tree(tree);
list_add(&chunk->owners[0].list, &tree->chunks);
if (!tree->root) {
tree->root = chunk;
list_add(&tree->same_root, &chunk->trees);
}
insert_hash(chunk);
spin_unlock(&hash_lock);
spin_unlock(&entry->lock);
fsnotify_put_mark(entry); /* drop initial reference */
return 0;
}
/* the first tagged inode becomes root of tree */
static int tag_chunk(struct inode *inode, struct audit_tree *tree)
{
struct fsnotify_mark *old_entry, *chunk_entry;
struct audit_tree *owner;
struct audit_chunk *chunk, *old;
struct node *p;
int n;
old_entry = fsnotify_find_inode_mark(audit_tree_group, inode);
if (!old_entry)
return create_chunk(inode, tree);
old = container_of(old_entry, struct audit_chunk, mark);
/* are we already there? */
spin_lock(&hash_lock);
for (n = 0; n < old->count; n++) {
if (old->owners[n].owner == tree) {
spin_unlock(&hash_lock);
fsnotify_put_mark(old_entry);
return 0;
}
}
spin_unlock(&hash_lock);
chunk = alloc_chunk(old->count + 1);
if (!chunk) {
fsnotify_put_mark(old_entry);
return -ENOMEM;
}
chunk_entry = &chunk->mark;
spin_lock(&old_entry->lock);
if (!old_entry->inode) {
/* old_entry is being shot, lets just lie */
spin_unlock(&old_entry->lock);
fsnotify_put_mark(old_entry);
free_chunk(chunk);
return -ENOENT;
}
fsnotify_duplicate_mark(chunk_entry, old_entry);
if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->inode, NULL, 1)) {
spin_unlock(&old_entry->lock);
fsnotify_put_mark(chunk_entry);
fsnotify_put_mark(old_entry);
return -ENOSPC;
}
/* even though we hold old_entry->lock, this is safe since chunk_entry->lock could NEVER have been grabbed before */
spin_lock(&chunk_entry->lock);
spin_lock(&hash_lock);
/* we now hold old_entry->lock, chunk_entry->lock, and hash_lock */
if (tree->goner) {
spin_unlock(&hash_lock);
chunk->dead = 1;
spin_unlock(&chunk_entry->lock);
spin_unlock(&old_entry->lock);
fsnotify_destroy_mark(chunk_entry, audit_tree_group);
fsnotify_put_mark(chunk_entry);
fsnotify_put_mark(old_entry);
return 0;
}
list_replace_init(&old->trees, &chunk->trees);
for (n = 0, p = chunk->owners; n < old->count; n++, p++) {
struct audit_tree *s = old->owners[n].owner;
p->owner = s;
p->index = old->owners[n].index;
if (!s) /* result of fallback in untag */
continue;
get_tree(s);
list_replace_init(&old->owners[n].list, &p->list);
}
p->index = (chunk->count - 1) | (1U<<31);
p->owner = tree;
get_tree(tree);
list_add(&p->list, &tree->chunks);
list_replace_rcu(&old->hash, &chunk->hash);
list_for_each_entry(owner, &chunk->trees, same_root)
owner->root = chunk;
old->dead = 1;
if (!tree->root) {
tree->root = chunk;
list_add(&tree->same_root, &chunk->trees);
}
spin_unlock(&hash_lock);
spin_unlock(&chunk_entry->lock);
spin_unlock(&old_entry->lock);
fsnotify_destroy_mark(old_entry, audit_tree_group);
fsnotify_put_mark(chunk_entry); /* drop initial reference */
fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */
return 0;
}
static void audit_tree_log_remove_rule(struct audit_krule *rule)
{
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return;
audit_log_format(ab, "op=");
audit_log_string(ab, "remove_rule");
audit_log_format(ab, " dir=");
audit_log_untrustedstring(ab, rule->tree->pathname);
audit_log_key(ab, rule->filterkey);
audit_log_format(ab, " list=%d res=1", rule->listnr);
audit_log_end(ab);
}
static void kill_rules(struct audit_tree *tree)
{
struct audit_krule *rule, *next;
struct audit_entry *entry;
list_for_each_entry_safe(rule, next, &tree->rules, rlist) {
entry = container_of(rule, struct audit_entry, rule);
list_del_init(&rule->rlist);
if (rule->tree) {
/* not a half-baked one */
audit_tree_log_remove_rule(rule);
rule->tree = NULL;
list_del_rcu(&entry->list);
list_del(&entry->rule.list);
call_rcu(&entry->rcu, audit_free_rule_rcu);
}
}
}
/*
* finish killing struct audit_tree
*/
static void prune_one(struct audit_tree *victim)
{
spin_lock(&hash_lock);
while (!list_empty(&victim->chunks)) {
struct node *p;
p = list_entry(victim->chunks.next, struct node, list);
untag_chunk(p);
}
spin_unlock(&hash_lock);
put_tree(victim);
}
/* trim the uncommitted chunks from tree */
static void trim_marked(struct audit_tree *tree)
{
struct list_head *p, *q;
spin_lock(&hash_lock);
if (tree->goner) {
spin_unlock(&hash_lock);
return;
}
/* reorder */
for (p = tree->chunks.next; p != &tree->chunks; p = q) {
struct node *node = list_entry(p, struct node, list);
q = p->next;
if (node->index & (1U<<31)) {
list_del_init(p);
list_add(p, &tree->chunks);
}
}
while (!list_empty(&tree->chunks)) {
struct node *node;
node = list_entry(tree->chunks.next, struct node, list);
/* have we run out of marked? */
if (!(node->index & (1U<<31)))
break;
untag_chunk(node);
}
if (!tree->root && !tree->goner) {
tree->goner = 1;
spin_unlock(&hash_lock);
mutex_lock(&audit_filter_mutex);
kill_rules(tree);
list_del_init(&tree->list);
mutex_unlock(&audit_filter_mutex);
prune_one(tree);
} else {
spin_unlock(&hash_lock);
}
}
static void audit_schedule_prune(void);
/* called with audit_filter_mutex */
int audit_remove_tree_rule(struct audit_krule *rule)
{
struct audit_tree *tree;
tree = rule->tree;
if (tree) {
spin_lock(&hash_lock);
list_del_init(&rule->rlist);
if (list_empty(&tree->rules) && !tree->goner) {
tree->root = NULL;
list_del_init(&tree->same_root);
tree->goner = 1;
list_move(&tree->list, &prune_list);
rule->tree = NULL;
spin_unlock(&hash_lock);
audit_schedule_prune();
return 1;
}
rule->tree = NULL;
spin_unlock(&hash_lock);
return 1;
}
return 0;
}
static int compare_root(struct vfsmount *mnt, void *arg)
{
return d_backing_inode(mnt->mnt_root) == arg;
}
void audit_trim_trees(void)
{
struct list_head cursor;
mutex_lock(&audit_filter_mutex);
list_add(&cursor, &tree_list);
while (cursor.next != &tree_list) {
struct audit_tree *tree;
struct path path;
struct vfsmount *root_mnt;
struct node *node;
int err;
tree = container_of(cursor.next, struct audit_tree, list);
get_tree(tree);
list_del(&cursor);
list_add(&cursor, &tree->list);
mutex_unlock(&audit_filter_mutex);
err = kern_path(tree->pathname, 0, &path);
if (err)
goto skip_it;
root_mnt = collect_mounts(&path);
path_put(&path);
if (IS_ERR(root_mnt))
goto skip_it;
spin_lock(&hash_lock);
list_for_each_entry(node, &tree->chunks, list) {
struct audit_chunk *chunk = find_chunk(node);
/* this could be NULL if the watch is dying else where... */
struct inode *inode = chunk->mark.inode;
node->index |= 1U<<31;
if (iterate_mounts(compare_root, inode, root_mnt))
node->index &= ~(1U<<31);
}
spin_unlock(&hash_lock);
trim_marked(tree);
drop_collected_mounts(root_mnt);
skip_it:
put_tree(tree);
mutex_lock(&audit_filter_mutex);
}
list_del(&cursor);
mutex_unlock(&audit_filter_mutex);
}
int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
{
if (pathname[0] != '/' ||
rule->listnr != AUDIT_FILTER_EXIT ||
op != Audit_equal ||
rule->inode_f || rule->watch || rule->tree)
return -EINVAL;
rule->tree = alloc_tree(pathname);
if (!rule->tree)
return -ENOMEM;
return 0;
}
void audit_put_tree(struct audit_tree *tree)
{
put_tree(tree);
}
static int tag_mount(struct vfsmount *mnt, void *arg)
{
return tag_chunk(d_backing_inode(mnt->mnt_root), arg);
}
/*
* That gets run when evict_chunk() ends up needing to kill audit_tree.
* Runs from a separate thread.
*/
static int prune_tree_thread(void *unused)
{
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (list_empty(&prune_list))
schedule();
__set_current_state(TASK_RUNNING);
mutex_lock(&audit_cmd_mutex);
mutex_lock(&audit_filter_mutex);
while (!list_empty(&prune_list)) {
struct audit_tree *victim;
victim = list_entry(prune_list.next,
struct audit_tree, list);
list_del_init(&victim->list);
mutex_unlock(&audit_filter_mutex);
prune_one(victim);
mutex_lock(&audit_filter_mutex);
}
mutex_unlock(&audit_filter_mutex);
mutex_unlock(&audit_cmd_mutex);
}
return 0;
}
static int audit_launch_prune(void)
{
if (prune_thread)
return 0;
prune_thread = kthread_create(prune_tree_thread, NULL,
"audit_prune_tree");
if (IS_ERR(prune_thread)) {
pr_err("cannot start thread audit_prune_tree");
prune_thread = NULL;
return -ENOMEM;
} else {
wake_up_process(prune_thread);
return 0;
}
}
/* called with audit_filter_mutex */
int audit_add_tree_rule(struct audit_krule *rule)
{
struct audit_tree *seed = rule->tree, *tree;
struct path path;
struct vfsmount *mnt;
int err;
rule->tree = NULL;
list_for_each_entry(tree, &tree_list, list) {
if (!strcmp(seed->pathname, tree->pathname)) {
put_tree(seed);
rule->tree = tree;
list_add(&rule->rlist, &tree->rules);
return 0;
}
}
tree = seed;
list_add(&tree->list, &tree_list);
list_add(&rule->rlist, &tree->rules);
/* do not set rule->tree yet */
mutex_unlock(&audit_filter_mutex);
if (unlikely(!prune_thread)) {
err = audit_launch_prune();
if (err)
goto Err;
}
err = kern_path(tree->pathname, 0, &path);
if (err)
goto Err;
mnt = collect_mounts(&path);
path_put(&path);
if (IS_ERR(mnt)) {
err = PTR_ERR(mnt);
goto Err;
}
get_tree(tree);
err = iterate_mounts(tag_mount, tree, mnt);
drop_collected_mounts(mnt);
if (!err) {
struct node *node;
spin_lock(&hash_lock);
list_for_each_entry(node, &tree->chunks, list)
node->index &= ~(1U<<31);
spin_unlock(&hash_lock);
} else {
trim_marked(tree);
goto Err;
}
mutex_lock(&audit_filter_mutex);
if (list_empty(&rule->rlist)) {
put_tree(tree);
return -ENOENT;
}
rule->tree = tree;
put_tree(tree);
return 0;
Err:
mutex_lock(&audit_filter_mutex);
list_del_init(&tree->list);
list_del_init(&tree->rules);
put_tree(tree);
return err;
}
int audit_tag_tree(char *old, char *new)
{
struct list_head cursor, barrier;
int failed = 0;
struct path path1, path2;
struct vfsmount *tagged;
int err;
err = kern_path(new, 0, &path2);
if (err)
return err;
tagged = collect_mounts(&path2);
path_put(&path2);
if (IS_ERR(tagged))
return PTR_ERR(tagged);
err = kern_path(old, 0, &path1);
if (err) {
drop_collected_mounts(tagged);
return err;
}
mutex_lock(&audit_filter_mutex);
list_add(&barrier, &tree_list);
list_add(&cursor, &barrier);
while (cursor.next != &tree_list) {
struct audit_tree *tree;
int good_one = 0;
tree = container_of(cursor.next, struct audit_tree, list);
get_tree(tree);
list_del(&cursor);
list_add(&cursor, &tree->list);
mutex_unlock(&audit_filter_mutex);
err = kern_path(tree->pathname, 0, &path2);
if (!err) {
good_one = path_is_under(&path1, &path2);
path_put(&path2);
}
if (!good_one) {
put_tree(tree);
mutex_lock(&audit_filter_mutex);
continue;
}
failed = iterate_mounts(tag_mount, tree, tagged);
if (failed) {
put_tree(tree);
mutex_lock(&audit_filter_mutex);
break;
}
mutex_lock(&audit_filter_mutex);
spin_lock(&hash_lock);
if (!tree->goner) {
list_del(&tree->list);
list_add(&tree->list, &tree_list);
}
spin_unlock(&hash_lock);
put_tree(tree);
}
while (barrier.prev != &tree_list) {
struct audit_tree *tree;
tree = container_of(barrier.prev, struct audit_tree, list);
get_tree(tree);
list_del(&tree->list);
list_add(&tree->list, &barrier);
mutex_unlock(&audit_filter_mutex);
if (!failed) {
struct node *node;
spin_lock(&hash_lock);
list_for_each_entry(node, &tree->chunks, list)
node->index &= ~(1U<<31);
spin_unlock(&hash_lock);
} else {
trim_marked(tree);
}
put_tree(tree);
mutex_lock(&audit_filter_mutex);
}
list_del(&barrier);
list_del(&cursor);
mutex_unlock(&audit_filter_mutex);
path_put(&path1);
drop_collected_mounts(tagged);
return failed;
}
static void audit_schedule_prune(void)
{
wake_up_process(prune_thread);
}
/*
* ... and that one is done if evict_chunk() decides to delay until the end
* of syscall. Runs synchronously.
*/
void audit_kill_trees(struct list_head *list)
{
mutex_lock(&audit_cmd_mutex);
mutex_lock(&audit_filter_mutex);
while (!list_empty(list)) {
struct audit_tree *victim;
victim = list_entry(list->next, struct audit_tree, list);
kill_rules(victim);
list_del_init(&victim->list);
mutex_unlock(&audit_filter_mutex);
prune_one(victim);
mutex_lock(&audit_filter_mutex);
}
mutex_unlock(&audit_filter_mutex);
mutex_unlock(&audit_cmd_mutex);
}
/*
* Here comes the stuff asynchronous to auditctl operations
*/
static void evict_chunk(struct audit_chunk *chunk)
{
struct audit_tree *owner;
struct list_head *postponed = audit_killed_trees();
int need_prune = 0;
int n;
if (chunk->dead)
return;
chunk->dead = 1;
mutex_lock(&audit_filter_mutex);
spin_lock(&hash_lock);
while (!list_empty(&chunk->trees)) {
owner = list_entry(chunk->trees.next,
struct audit_tree, same_root);
owner->goner = 1;
owner->root = NULL;
list_del_init(&owner->same_root);
spin_unlock(&hash_lock);
if (!postponed) {
kill_rules(owner);
list_move(&owner->list, &prune_list);
need_prune = 1;
} else {
list_move(&owner->list, postponed);
}
spin_lock(&hash_lock);
}
list_del_rcu(&chunk->hash);
for (n = 0; n < chunk->count; n++)
list_del_init(&chunk->owners[n].list);
spin_unlock(&hash_lock);
mutex_unlock(&audit_filter_mutex);
if (need_prune)
audit_schedule_prune();
}
static int audit_tree_handle_event(struct fsnotify_group *group,
struct inode *to_tell,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
const unsigned char *file_name, u32 cookie)
{
return 0;
}
static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify_group *group)
{
struct audit_chunk *chunk = container_of(entry, struct audit_chunk, mark);
evict_chunk(chunk);
/*
* We are guaranteed to have at least one reference to the mark from
* either the inode or the caller of fsnotify_destroy_mark().
*/
BUG_ON(atomic_read(&entry->refcnt) < 1);
}
static const struct fsnotify_ops audit_tree_ops = {
.handle_event = audit_tree_handle_event,
.freeing_mark = audit_tree_freeing_mark,
};
static int __init audit_tree_init(void)
{
int i;
audit_tree_group = fsnotify_alloc_group(&audit_tree_ops);
if (IS_ERR(audit_tree_group))
audit_panic("cannot initialize fsnotify group for rectree watches");
for (i = 0; i < HASH_SIZE; i++)
INIT_LIST_HEAD(&chunk_hash_heads[i]);
return 0;
}
__initcall(audit_tree_init);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/audit_watch.c
/* audit_watch.c -- watching inodes
*
* Copyright 2003-2009 Red Hat, Inc.
* Copyright 2005 Hewlett-Packard Development Company, L.P.
* Copyright 2005 IBM Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* 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.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/kernel.h>
#include <linux/audit.h>
#include <linux/kthread.h>
#include <linux/mutex.h>
#include <linux/fs.h>
#include <linux/fsnotify_backend.h>
#include <linux/namei.h>
#include <linux/netlink.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/security.h>
#include "audit.h"
/*
* Reference counting:
*
* audit_parent: lifetime is from audit_init_parent() to receipt of an FS_IGNORED
* event. Each audit_watch holds a reference to its associated parent.
*
* audit_watch: if added to lists, lifetime is from audit_init_watch() to
* audit_remove_watch(). Additionally, an audit_watch may exist
* temporarily to assist in searching existing filter data. Each
* audit_krule holds a reference to its associated watch.
*/
struct audit_watch {
atomic_t count; /* reference count */
dev_t dev; /* associated superblock device */
char *path; /* insertion path */
unsigned long ino; /* associated inode number */
struct audit_parent *parent; /* associated parent */
struct list_head wlist; /* entry in parent->watches list */
struct list_head rules; /* anchor for krule->rlist */
};
struct audit_parent {
struct list_head watches; /* anchor for audit_watch->wlist */
struct fsnotify_mark mark; /* fsnotify mark on the inode */
};
/* fsnotify handle. */
static struct fsnotify_group *audit_watch_group;
/* fsnotify events we care about. */
#define AUDIT_FS_WATCH (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\
FS_MOVE_SELF | FS_EVENT_ON_CHILD)
static void audit_free_parent(struct audit_parent *parent)
{
WARN_ON(!list_empty(&parent->watches));
kfree(parent);
}
static void audit_watch_free_mark(struct fsnotify_mark *entry)
{
struct audit_parent *parent;
parent = container_of(entry, struct audit_parent, mark);
audit_free_parent(parent);
}
static void audit_get_parent(struct audit_parent *parent)
{
if (likely(parent))
fsnotify_get_mark(&parent->mark);
}
static void audit_put_parent(struct audit_parent *parent)
{
if (likely(parent))
fsnotify_put_mark(&parent->mark);
}
/*
* Find and return the audit_parent on the given inode. If found a reference
* is taken on this parent.
*/
static inline struct audit_parent *audit_find_parent(struct inode *inode)
{
struct audit_parent *parent = NULL;
struct fsnotify_mark *entry;
entry = fsnotify_find_inode_mark(audit_watch_group, inode);
if (entry)
parent = container_of(entry, struct audit_parent, mark);
return parent;
}
void audit_get_watch(struct audit_watch *watch)
{
atomic_inc(&watch->count);
}
void audit_put_watch(struct audit_watch *watch)
{
if (atomic_dec_and_test(&watch->count)) {
WARN_ON(watch->parent);
WARN_ON(!list_empty(&watch->rules));
kfree(watch->path);
kfree(watch);
}
}
static void audit_remove_watch(struct audit_watch *watch)
{
list_del(&watch->wlist);
audit_put_parent(watch->parent);
watch->parent = NULL;
audit_put_watch(watch); /* match initial get */
}
char *audit_watch_path(struct audit_watch *watch)
{
return watch->path;
}
int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev)
{
return (watch->ino != (unsigned long)-1) &&
(watch->ino == ino) &&
(watch->dev == dev);
}
/* Initialize a parent watch entry. */
static struct audit_parent *audit_init_parent(struct path *path)
{
struct inode *inode = d_backing_inode(path->dentry);
struct audit_parent *parent;
int ret;
parent = kzalloc(sizeof(*parent), GFP_KERNEL);
if (unlikely(!parent))
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&parent->watches);
fsnotify_init_mark(&parent->mark, audit_watch_free_mark);
parent->mark.mask = AUDIT_FS_WATCH;
ret = fsnotify_add_mark(&parent->mark, audit_watch_group, inode, NULL, 0);
if (ret < 0) {
audit_free_parent(parent);
return ERR_PTR(ret);
}
return parent;
}
/* Initialize a watch entry. */
static struct audit_watch *audit_init_watch(char *path)
{
struct audit_watch *watch;
watch = kzalloc(sizeof(*watch), GFP_KERNEL);
if (unlikely(!watch))
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&watch->rules);
atomic_set(&watch->count, 1);
watch->path = path;
watch->dev = (dev_t)-1;
watch->ino = (unsigned long)-1;
return watch;
}
/* Translate a watch string to kernel respresentation. */
int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op)
{
struct audit_watch *watch;
if (!audit_watch_group)
return -EOPNOTSUPP;
if (path[0] != '/' || path[len-1] == '/' ||
krule->listnr != AUDIT_FILTER_EXIT ||
op != Audit_equal ||
krule->inode_f || krule->watch || krule->tree)
return -EINVAL;
watch = audit_init_watch(path);
if (IS_ERR(watch))
return PTR_ERR(watch);
audit_get_watch(watch);
krule->watch = watch;
return 0;
}
/* Duplicate the given audit watch. The new watch's rules list is initialized
* to an empty list and wlist is undefined. */
static struct audit_watch *audit_dupe_watch(struct audit_watch *old)
{
char *path;
struct audit_watch *new;
path = kstrdup(old->path, GFP_KERNEL);
if (unlikely(!path))
return ERR_PTR(-ENOMEM);
new = audit_init_watch(path);
if (IS_ERR(new)) {
kfree(path);
goto out;
}
new->dev = old->dev;
new->ino = old->ino;
audit_get_parent(old->parent);
new->parent = old->parent;
out:
return new;
}
static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watch *w, char *op)
{
if (audit_enabled) {
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return;
audit_log_format(ab, "auid=%u ses=%u op=",
from_kuid(&init_user_ns, audit_get_loginuid(current)),
audit_get_sessionid(current));
audit_log_string(ab, op);
audit_log_format(ab, " path=");
audit_log_untrustedstring(ab, w->path);
audit_log_key(ab, r->filterkey);
audit_log_format(ab, " list=%d res=1", r->listnr);
audit_log_end(ab);
}
}
/* Update inode info in audit rules based on filesystem event. */
static void audit_update_watch(struct audit_parent *parent,
const char *dname, dev_t dev,
unsigned long ino, unsigned invalidating)
{
struct audit_watch *owatch, *nwatch, *nextw;
struct audit_krule *r, *nextr;
struct audit_entry *oentry, *nentry;
mutex_lock(&audit_filter_mutex);
/* Run all of the watches on this parent looking for the one that
* matches the given dname */
list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) {
if (audit_compare_dname_path(dname, owatch->path,
AUDIT_NAME_FULL))
continue;
/* If the update involves invalidating rules, do the inode-based
* filtering now, so we don't omit records. */
if (invalidating && !audit_dummy_context())
audit_filter_inodes(current, current->audit_context);
/* updating ino will likely change which audit_hash_list we
* are on so we need a new watch for the new list */
nwatch = audit_dupe_watch(owatch);
if (IS_ERR(nwatch)) {
mutex_unlock(&audit_filter_mutex);
audit_panic("error updating watch, skipping");
return;
}
nwatch->dev = dev;
nwatch->ino = ino;
list_for_each_entry_safe(r, nextr, &owatch->rules, rlist) {
oentry = container_of(r, struct audit_entry, rule);
list_del(&oentry->rule.rlist);
list_del_rcu(&oentry->list);
nentry = audit_dupe_rule(&oentry->rule);
if (IS_ERR(nentry)) {
list_del(&oentry->rule.list);
audit_panic("error updating watch, removing");
} else {
int h = audit_hash_ino((u32)ino);
/*
* nentry->rule.watch == oentry->rule.watch so
* we must drop that reference and set it to our
* new watch.
*/
audit_put_watch(nentry->rule.watch);
audit_get_watch(nwatch);
nentry->rule.watch = nwatch;
list_add(&nentry->rule.rlist, &nwatch->rules);
list_add_rcu(&nentry->list, &audit_inode_hash[h]);
list_replace(&oentry->rule.list,
&nentry->rule.list);
}
audit_watch_log_rule_change(r, owatch, "updated_rules");
call_rcu(&oentry->rcu, audit_free_rule_rcu);
}
audit_remove_watch(owatch);
goto add_watch_to_parent; /* event applies to a single watch */
}
mutex_unlock(&audit_filter_mutex);
return;
add_watch_to_parent:
list_add(&nwatch->wlist, &parent->watches);
mutex_unlock(&audit_filter_mutex);
return;
}
/* Remove all watches & rules associated with a parent that is going away. */
static void audit_remove_parent_watches(struct audit_parent *parent)
{
struct audit_watch *w, *nextw;
struct audit_krule *r, *nextr;
struct audit_entry *e;
mutex_lock(&audit_filter_mutex);
list_for_each_entry_safe(w, nextw, &parent->watches, wlist) {
list_for_each_entry_safe(r, nextr, &w->rules, rlist) {
e = container_of(r, struct audit_entry, rule);
audit_watch_log_rule_change(r, w, "remove_rule");
list_del(&r->rlist);
list_del(&r->list);
list_del_rcu(&e->list);
call_rcu(&e->rcu, audit_free_rule_rcu);
}
audit_remove_watch(w);
}
mutex_unlock(&audit_filter_mutex);
fsnotify_destroy_mark(&parent->mark, audit_watch_group);
}
/* Get path information necessary for adding watches. */
static int audit_get_nd(struct audit_watch *watch, struct path *parent)
{
struct dentry *d = kern_path_locked(watch->path, parent);
if (IS_ERR(d))
return PTR_ERR(d);
mutex_unlock(&d_backing_inode(parent->dentry)->i_mutex);
if (d_is_positive(d)) {
/* update watch filter fields */
watch->dev = d_backing_inode(d)->i_sb->s_dev;
watch->ino = d_backing_inode(d)->i_ino;
}
dput(d);
return 0;
}
/* Associate the given rule with an existing parent.
* Caller must hold audit_filter_mutex. */
static void audit_add_to_parent(struct audit_krule *krule,
struct audit_parent *parent)
{
struct audit_watch *w, *watch = krule->watch;
int watch_found = 0;
BUG_ON(!mutex_is_locked(&audit_filter_mutex));
list_for_each_entry(w, &parent->watches, wlist) {
if (strcmp(watch->path, w->path))
continue;
watch_found = 1;
/* put krule's and initial refs to temporary watch */
audit_put_watch(watch);
audit_put_watch(watch);
audit_get_watch(w);
krule->watch = watch = w;
break;
}
if (!watch_found) {
audit_get_parent(parent);
watch->parent = parent;
list_add(&watch->wlist, &parent->watches);
}
list_add(&krule->rlist, &watch->rules);
}
/* Find a matching watch entry, or add this one.
* Caller must hold audit_filter_mutex. */
int audit_add_watch(struct audit_krule *krule, struct list_head **list)
{
struct audit_watch *watch = krule->watch;
struct audit_parent *parent;
struct path parent_path;
int h, ret = 0;
mutex_unlock(&audit_filter_mutex);
/* Avoid calling path_lookup under audit_filter_mutex. */
ret = audit_get_nd(watch, &parent_path);
/* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
if (ret)
return ret;
/* either find an old parent or attach a new one */
parent = audit_find_parent(d_backing_inode(parent_path.dentry));
if (!parent) {
parent = audit_init_parent(&parent_path);
if (IS_ERR(parent)) {
ret = PTR_ERR(parent);
goto error;
}
}
audit_add_to_parent(krule, parent);
/* match get in audit_find_parent or audit_init_parent */
audit_put_parent(parent);
h = audit_hash_ino((u32)watch->ino);
*list = &audit_inode_hash[h];
error:
path_put(&parent_path);
return ret;
}
void audit_remove_watch_rule(struct audit_krule *krule)
{
struct audit_watch *watch = krule->watch;
struct audit_parent *parent = watch->parent;
list_del(&krule->rlist);
if (list_empty(&watch->rules)) {
audit_remove_watch(watch);
if (list_empty(&parent->watches)) {
audit_get_parent(parent);
fsnotify_destroy_mark(&parent->mark, audit_watch_group);
audit_put_parent(parent);
}
}
}
/* Update watch data in audit rules based on fsnotify events. */
static int audit_watch_handle_event(struct fsnotify_group *group,
struct inode *to_tell,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
const unsigned char *dname, u32 cookie)
{
struct inode *inode;
struct audit_parent *parent;
parent = container_of(inode_mark, struct audit_parent, mark);
BUG_ON(group != audit_watch_group);
switch (data_type) {
case (FSNOTIFY_EVENT_PATH):
inode = d_backing_inode(((struct path *)data)->dentry);
break;
case (FSNOTIFY_EVENT_INODE):
inode = (struct inode *)data;
break;
default:
BUG();
inode = NULL;
break;
};
if (mask & (FS_CREATE|FS_MOVED_TO) && inode)
audit_update_watch(parent, dname, inode->i_sb->s_dev, inode->i_ino, 0);
else if (mask & (FS_DELETE|FS_MOVED_FROM))
audit_update_watch(parent, dname, (dev_t)-1, (unsigned long)-1, 1);
else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF))
audit_remove_parent_watches(parent);
return 0;
}
static const struct fsnotify_ops audit_watch_fsnotify_ops = {
.handle_event = audit_watch_handle_event,
};
static int __init audit_watch_init(void)
{
audit_watch_group = fsnotify_alloc_group(&audit_watch_fsnotify_ops);
if (IS_ERR(audit_watch_group)) {
audit_watch_group = NULL;
audit_panic("cannot create audit fsnotify group");
}
return 0;
}
device_initcall(audit_watch_init);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/backtracetest.c
/*
* Simple stack backtrace regression test module
*
* (C) Copyright 2008 Intel Corporation
* Author: Arjan van de Ven <arjan@linux.intel.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; version 2
* of the License.
*/
#include <linux/completion.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/stacktrace.h>
static void backtrace_test_normal(void)
{
pr_info("Testing a backtrace from process context.\n");
pr_info("The following trace is a kernel self test and not a bug!\n");
dump_stack();
}
static DECLARE_COMPLETION(backtrace_work);
static void backtrace_test_irq_callback(unsigned long data)
{
dump_stack();
complete(&backtrace_work);
}
static DECLARE_TASKLET(backtrace_tasklet, &backtrace_test_irq_callback, 0);
static void backtrace_test_irq(void)
{
pr_info("Testing a backtrace from irq context.\n");
pr_info("The following trace is a kernel self test and not a bug!\n");
init_completion(&backtrace_work);
tasklet_schedule(&backtrace_tasklet);
wait_for_completion(&backtrace_work);
}
#ifdef CONFIG_STACKTRACE
static void backtrace_test_saved(void)
{
struct stack_trace trace;
unsigned long entries[8];
pr_info("Testing a saved backtrace.\n");
pr_info("The following trace is a kernel self test and not a bug!\n");
trace.nr_entries = 0;
trace.max_entries = ARRAY_SIZE(entries);
trace.entries = entries;
trace.skip = 0;
save_stack_trace(&trace);
print_stack_trace(&trace, 0);
}
#else
static void backtrace_test_saved(void)
{
pr_info("Saved backtrace test skipped.\n");
}
#endif
static int backtrace_regression_test(void)
{
pr_info("====[ backtrace testing ]===========\n");
backtrace_test_normal();
backtrace_test_irq();
backtrace_test_saved();
pr_info("====[ end of backtrace testing ]====\n");
return 0;
}
static void exitf(void)
{
}
module_init(backtrace_regression_test);
module_exit(exitf);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/bounds.c
/*
* Generate definitions needed by the preprocessor.
* This code generates raw asm output which is post-processed
* to extract and format the required data.
*/
#define __GENERATING_BOUNDS_H
/* Include headers that define the enum constants of interest */
#include <linux/page-flags.h>
#include <linux/mmzone.h>
#include <linux/kbuild.h>
#include <linux/log2.h>
#include <linux/spinlock_types.h>
void foo(void)
{
/* The enum constants to put into include/generated/bounds.h */
DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
#ifdef CONFIG_SMP
DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
#endif
DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
/* End of constants */
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/bpf/arraymap.c
/* 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/err.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/filter.h>
/* Called from syscall */
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
struct bpf_array *array;
u32 elem_size, array_size;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size == 0)
return ERR_PTR(-EINVAL);
elem_size = round_up(attr->value_size, 8);
/* check round_up into zero and u32 overflow */
if (elem_size == 0 ||
attr->max_entries > (U32_MAX - sizeof(*array)) / elem_size)
return ERR_PTR(-ENOMEM);
array_size = sizeof(*array) + attr->max_entries * elem_size;
/* allocate all map elements and zero-initialize them */
array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
if (!array) {
array = vzalloc(array_size);
if (!array)
return ERR_PTR(-ENOMEM);
}
/* copy mandatory map attributes */
array->map.key_size = attr->key_size;
array->map.value_size = attr->value_size;
array->map.max_entries = attr->max_entries;
array->elem_size = elem_size;
return &array->map;
}
/* Called from syscall or from eBPF program */
static void *array_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (index >= array->map.max_entries)
return NULL;
return array->value + array->elem_size * index;
}
/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
u32 *next = (u32 *)next_key;
if (index >= array->map.max_entries) {
*next = 0;
return 0;
}
if (index == array->map.max_entries - 1)
return -ENOENT;
*next = index + 1;
return 0;
}
/* Called from syscall or from eBPF program */
static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (map_flags > BPF_EXIST)
/* unknown flags */
return -EINVAL;
if (index >= array->map.max_entries)
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
if (map_flags == BPF_NOEXIST)
/* all elements already exist */
return -EEXIST;
memcpy(array->value + array->elem_size * index, value, map->value_size);
return 0;
}
/* Called from syscall or from eBPF program */
static int array_map_delete_elem(struct bpf_map *map, void *key)
{
return -EINVAL;
}
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void array_map_free(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, 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 programs to complete
* and free the array
*/
synchronize_rcu();
kvfree(array);
}
static const struct bpf_map_ops array_ops = {
.map_alloc = array_map_alloc,
.map_free = array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
};
static struct bpf_map_type_list array_type __read_mostly = {
.ops = &array_ops,
.type = BPF_MAP_TYPE_ARRAY,
};
static int __init register_array_map(void)
{
bpf_register_map_type(&array_type);
return 0;
}
late_initcall(register_array_map);
static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
{
/* only bpf_prog file descriptors can be stored in prog_array map */
if (attr->value_size != sizeof(u32))
return ERR_PTR(-EINVAL);
return array_map_alloc(attr);
}
static void prog_array_map_free(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
synchronize_rcu();
/* make sure it's empty */
for (i = 0; i < array->map.max_entries; i++)
BUG_ON(array->prog[i] != NULL);
kvfree(array);
}
static void *prog_array_map_lookup_elem(struct bpf_map *map, void *key)
{
return NULL;
}
/* only called from syscall */
static int prog_array_map_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog, *old_prog;
u32 index = *(u32 *)key, ufd;
if (map_flags != BPF_ANY)
return -EINVAL;
if (index >= array->map.max_entries)
return -E2BIG;
ufd = *(u32 *)value;
prog = bpf_prog_get(ufd);
if (IS_ERR(prog))
return PTR_ERR(prog);
if (!bpf_prog_array_compatible(array, prog)) {
bpf_prog_put(prog);
return -EINVAL;
}
old_prog = xchg(array->prog + index, prog);
if (old_prog)
bpf_prog_put_rcu(old_prog);
return 0;
}
static int prog_array_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *old_prog;
u32 index = *(u32 *)key;
if (index >= array->map.max_entries)
return -E2BIG;
old_prog = xchg(array->prog + index, NULL);
if (old_prog) {
bpf_prog_put_rcu(old_prog);
return 0;
} else {
return -ENOENT;
}
}
/* decrement refcnt of all bpf_progs that are stored in this map */
void bpf_prog_array_map_clear(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
for (i = 0; i < array->map.max_entries; i++)
prog_array_map_delete_elem(map, &i);
}
static const struct bpf_map_ops prog_array_ops = {
.map_alloc = prog_array_map_alloc,
.map_free = prog_array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = prog_array_map_lookup_elem,
.map_update_elem = prog_array_map_update_elem,
.map_delete_elem = prog_array_map_delete_elem,
};
static struct bpf_map_type_list prog_array_type __read_mostly = {
.ops = &prog_array_ops,
.type = BPF_MAP_TYPE_PROG_ARRAY,
};
static int __init register_prog_array_map(void)
{
bpf_register_map_type(&prog_array_type);
return 0;
}
late_initcall(register_prog_array_map);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/bpf/core.c
/*
* Linux Socket Filter - Kernel level socket filtering
*
* Based on the design of the Berkeley Packet Filter. The new
* internal format has been designed by PLUMgrid:
*
* Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
*
* Authors:
*
* Jay Schulist <jschlst@samba.org>
* Alexei Starovoitov <ast@plumgrid.com>
* Daniel Borkmann <dborkman@redhat.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Andi Kleen - Fix a few bad bugs and races.
* Kris Katterjohn - Added many additional checks in bpf_check_classic()
*/
#include <linux/filter.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/random.h>
#include <linux/moduleloader.h>
#include <linux/bpf.h>
#include <asm/unaligned.h>
/* Registers */
#define BPF_R0 regs[BPF_REG_0]
#define BPF_R1 regs[BPF_REG_1]
#define BPF_R2 regs[BPF_REG_2]
#define BPF_R3 regs[BPF_REG_3]
#define BPF_R4 regs[BPF_REG_4]
#define BPF_R5 regs[BPF_REG_5]
#define BPF_R6 regs[BPF_REG_6]
#define BPF_R7 regs[BPF_REG_7]
#define BPF_R8 regs[BPF_REG_8]
#define BPF_R9 regs[BPF_REG_9]
#define BPF_R10 regs[BPF_REG_10]
/* Named registers */
#define DST regs[insn->dst_reg]
#define SRC regs[insn->src_reg]
#define FP regs[BPF_REG_FP]
#define ARG1 regs[BPF_REG_ARG1]
#define CTX regs[BPF_REG_CTX]
#define IMM insn->imm
/* No hurry in this branch
*
* Exported for the bpf jit load helper.
*/
void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
{
u8 *ptr = NULL;
if (k >= SKF_NET_OFF)
ptr = skb_network_header(skb) + k - SKF_NET_OFF;
else if (k >= SKF_LL_OFF)
ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
return ptr;
return NULL;
}
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
gfp_extra_flags;
struct bpf_prog_aux *aux;
struct bpf_prog *fp;
size = round_up(size, PAGE_SIZE);
fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
if (fp == NULL)
return NULL;
aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
if (aux == NULL) {
vfree(fp);
return NULL;
}
fp->pages = size / PAGE_SIZE;
fp->aux = aux;
return fp;
}
EXPORT_SYMBOL_GPL(bpf_prog_alloc);
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
gfp_extra_flags;
struct bpf_prog *fp;
BUG_ON(fp_old == NULL);
size = round_up(size, PAGE_SIZE);
if (size <= fp_old->pages * PAGE_SIZE)
return fp_old;
fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
if (fp != NULL) {
memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
fp->pages = size / PAGE_SIZE;
/* We keep fp->aux from fp_old around in the new
* reallocated structure.
*/
fp_old->aux = NULL;
__bpf_prog_free(fp_old);
}
return fp;
}
EXPORT_SYMBOL_GPL(bpf_prog_realloc);
void __bpf_prog_free(struct bpf_prog *fp)
{
kfree(fp->aux);
vfree(fp);
}
EXPORT_SYMBOL_GPL(__bpf_prog_free);
#ifdef CONFIG_BPF_JIT
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
unsigned int alignment,
bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
struct bpf_binary_header *hdr;
unsigned int size, hole, start;
/* Most of BPF filters are really small, but if some of them
* fill a page, allow at least 128 extra bytes to insert a
* random section of illegal instructions.
*/
size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE);
hdr = module_alloc(size);
if (hdr == NULL)
return NULL;
/* Fill space with illegal/arch-dep instructions. */
bpf_fill_ill_insns(hdr, size);
hdr->pages = size / PAGE_SIZE;
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (prandom_u32() % hole) & ~(alignment - 1);
/* Leave a random number of instructions before BPF code. */
*image_ptr = &hdr->image[start];
return hdr;
}
void bpf_jit_binary_free(struct bpf_binary_header *hdr)
{
module_memfree(hdr);
}
#endif /* CONFIG_BPF_JIT */
/* Base function for offset calculation. Needs to go into .text section,
* therefore keeping it non-static as well; will also be used by JITs
* anyway later on, so do not let the compiler omit it.
*/
noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
return 0;
}
/**
* __bpf_prog_run - run eBPF program on a given context
* @ctx: is the data we are operating on
* @insn: is the array of eBPF instructions
*
* Decode and execute eBPF instructions.
*/
static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn)
{
u64 stack[MAX_BPF_STACK / sizeof(u64)];
u64 regs[MAX_BPF_REG], tmp;
static const void *jumptable[256] = {
[0 ... 255] = &&default_label,
/* Now overwrite non-defaults ... */
/* 32 bit ALU operations */
[BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
[BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
[BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
[BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
[BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
[BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
[BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X,
[BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K,
[BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
[BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
[BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
[BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
[BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
[BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
[BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
[BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
[BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
[BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
[BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
[BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
[BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
[BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
[BPF_ALU | BPF_NEG] = &&ALU_NEG,
[BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
[BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
/* 64 bit ALU operations */
[BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
[BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
[BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
[BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
[BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
[BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
[BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
[BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
[BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
[BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
[BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
[BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
[BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
[BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
[BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
[BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
[BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
[BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
[BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
[BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
[BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
[BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
[BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
[BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
[BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
/* Call instruction */
[BPF_JMP | BPF_CALL] = &&JMP_CALL,
[BPF_JMP | BPF_CALL | BPF_X] = &&JMP_TAIL_CALL,
/* Jumps */
[BPF_JMP | BPF_JA] = &&JMP_JA,
[BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
[BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
[BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
[BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
[BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
[BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
[BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
[BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
[BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
[BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
[BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
[BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
[BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
[BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
/* Program return */
[BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
/* Store instructions */
[BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
[BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
[BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
[BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
[BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
[BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
[BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
[BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
[BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
[BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
/* Load instructions */
[BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
[BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
[BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
[BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
[BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
[BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
[BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
[BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
[BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
[BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
[BPF_LD | BPF_IMM | BPF_DW] = &&LD_IMM_DW,
};
u32 tail_call_cnt = 0;
void *ptr;
int off;
#define CONT ({ insn++; goto select_insn; })
#define CONT_JMP ({ insn++; goto select_insn; })
FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
ARG1 = (u64) (unsigned long) ctx;
/* Registers used in classic BPF programs need to be reset first. */
regs[BPF_REG_A] = 0;
regs[BPF_REG_X] = 0;
select_insn:
goto *jumptable[insn->code];
/* ALU */
#define ALU(OPCODE, OP) \
ALU64_##OPCODE##_X: \
DST = DST OP SRC; \
CONT; \
ALU_##OPCODE##_X: \
DST = (u32) DST OP (u32) SRC; \
CONT; \
ALU64_##OPCODE##_K: \
DST = DST OP IMM; \
CONT; \
ALU_##OPCODE##_K: \
DST = (u32) DST OP (u32) IMM; \
CONT;
ALU(ADD, +)
ALU(SUB, -)
ALU(AND, &)
ALU(OR, |)
ALU(LSH, <<)
ALU(RSH, >>)
ALU(XOR, ^)
ALU(MUL, *)
#undef ALU
ALU_NEG:
DST = (u32) -DST;
CONT;
ALU64_NEG:
DST = -DST;
CONT;
ALU_MOV_X:
DST = (u32) SRC;
CONT;
ALU_MOV_K:
DST = (u32) IMM;
CONT;
ALU64_MOV_X:
DST = SRC;
CONT;
ALU64_MOV_K:
DST = IMM;
CONT;
LD_IMM_DW:
DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32;
insn++;
CONT;
ALU64_ARSH_X:
(*(s64 *) &DST) >>= SRC;
CONT;
ALU64_ARSH_K:
(*(s64 *) &DST) >>= IMM;
CONT;
ALU64_MOD_X:
if (unlikely(SRC == 0))
return 0;
div64_u64_rem(DST, SRC, &tmp);
DST = tmp;
CONT;
ALU_MOD_X:
if (unlikely(SRC == 0))
return 0;
tmp = (u32) DST;
DST = do_div(tmp, (u32) SRC);
CONT;
ALU64_MOD_K:
div64_u64_rem(DST, IMM, &tmp);
DST = tmp;
CONT;
ALU_MOD_K:
tmp = (u32) DST;
DST = do_div(tmp, (u32) IMM);
CONT;
ALU64_DIV_X:
if (unlikely(SRC == 0))
return 0;
DST = div64_u64(DST, SRC);
CONT;
ALU_DIV_X:
if (unlikely(SRC == 0))
return 0;
tmp = (u32) DST;
do_div(tmp, (u32) SRC);
DST = (u32) tmp;
CONT;
ALU64_DIV_K:
DST = div64_u64(DST, IMM);
CONT;
ALU_DIV_K:
tmp = (u32) DST;
do_div(tmp, (u32) IMM);
DST = (u32) tmp;
CONT;
ALU_END_TO_BE:
switch (IMM) {
case 16:
DST = (__force u16) cpu_to_be16(DST);
break;
case 32:
DST = (__force u32) cpu_to_be32(DST);
break;
case 64:
DST = (__force u64) cpu_to_be64(DST);
break;
}
CONT;
ALU_END_TO_LE:
switch (IMM) {
case 16:
DST = (__force u16) cpu_to_le16(DST);
break;
case 32:
DST = (__force u32) cpu_to_le32(DST);
break;
case 64:
DST = (__force u64) cpu_to_le64(DST);
break;
}
CONT;
/* CALL */
JMP_CALL:
/* Function call scratches BPF_R1-BPF_R5 registers,
* preserves BPF_R6-BPF_R9, and stores return value
* into BPF_R0.
*/
BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3,
BPF_R4, BPF_R5);
CONT;
JMP_TAIL_CALL: {
struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog;
u64 index = BPF_R3;
if (unlikely(index >= array->map.max_entries))
goto out;
if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
goto out;
tail_call_cnt++;
prog = READ_ONCE(array->prog[index]);
if (unlikely(!prog))
goto out;
ARG1 = BPF_R1;
insn = prog->insnsi;
goto select_insn;
out:
CONT;
}
/* JMP */
JMP_JA:
insn += insn->off;
CONT;
JMP_JEQ_X:
if (DST == SRC) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JEQ_K:
if (DST == IMM) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JNE_X:
if (DST != SRC) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JNE_K:
if (DST != IMM) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JGT_X:
if (DST > SRC) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JGT_K:
if (DST > IMM) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JGE_X:
if (DST >= SRC) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JGE_K:
if (DST >= IMM) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JSGT_X:
if (((s64) DST) > ((s64) SRC)) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JSGT_K:
if (((s64) DST) > ((s64) IMM)) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JSGE_X:
if (((s64) DST) >= ((s64) SRC)) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JSGE_K:
if (((s64) DST) >= ((s64) IMM)) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JSET_X:
if (DST & SRC) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_JSET_K:
if (DST & IMM) {
insn += insn->off;
CONT_JMP;
}
CONT;
JMP_EXIT:
return BPF_R0;
/* STX and ST and LDX*/
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
CONT; \
ST_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = IMM; \
CONT; \
LDX_MEM_##SIZEOP: \
DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
CONT;
LDST(B, u8)
LDST(H, u16)
LDST(W, u32)
LDST(DW, u64)
#undef LDST
STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
atomic_add((u32) SRC, (atomic_t *)(unsigned long)
(DST + insn->off));
CONT;
STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
(DST + insn->off));
CONT;
LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
off = IMM;
load_word:
/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are
* only appearing in the programs where ctx ==
* skb. All programs keep 'ctx' in regs[BPF_REG_CTX]
* == BPF_R6, bpf_convert_filter() saves it in BPF_R6,
* internal BPF verifier will check that BPF_R6 ==
* ctx.
*
* BPF_ABS and BPF_IND are wrappers of function calls,
* so they scratch BPF_R1-BPF_R5 registers, preserve
* BPF_R6-BPF_R9, and store return value into BPF_R0.
*
* Implicit input:
* ctx == skb == BPF_R6 == CTX
*
* Explicit input:
* SRC == any register
* IMM == 32-bit immediate
*
* Output:
* BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
*/
ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp);
if (likely(ptr != NULL)) {
BPF_R0 = get_unaligned_be32(ptr);
CONT;
}
return 0;
LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */
off = IMM;
load_half:
ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp);
if (likely(ptr != NULL)) {
BPF_R0 = get_unaligned_be16(ptr);
CONT;
}
return 0;
LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */
off = IMM;
load_byte:
ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp);
if (likely(ptr != NULL)) {
BPF_R0 = *(u8 *)ptr;
CONT;
}
return 0;
LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */
off = IMM + SRC;
goto load_word;
LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */
off = IMM + SRC;
goto load_half;
LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */
off = IMM + SRC;
goto load_byte;
default_label:
/* If we ever reach this, we have a bug somewhere. */
WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
return 0;
}
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
if (!array->owner_prog_type) {
/* There's no owner yet where we could check for
* compatibility.
*/
array->owner_prog_type = fp->type;
array->owner_jited = fp->jited;
return true;
}
return array->owner_prog_type == fp->type &&
array->owner_jited == fp->jited;
}
static int bpf_check_tail_call(const struct bpf_prog *fp)
{
struct bpf_prog_aux *aux = fp->aux;
int i;
for (i = 0; i < aux->used_map_cnt; i++) {
struct bpf_map *map = aux->used_maps[i];
struct bpf_array *array;
if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
continue;
array = container_of(map, struct bpf_array, map);
if (!bpf_prog_array_compatible(array, fp))
return -EINVAL;
}
return 0;
}
/**
* bpf_prog_select_runtime - select exec runtime for BPF program
* @fp: bpf_prog populated with internal BPF program
*
* Try to JIT eBPF program, if JIT is not available, use interpreter.
* The BPF program will be executed via BPF_PROG_RUN() macro.
*/
int bpf_prog_select_runtime(struct bpf_prog *fp)
{
fp->bpf_func = (void *) __bpf_prog_run;
bpf_int_jit_compile(fp);
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
* this late stage as we need to determine, if we deal
* with JITed or non JITed program concatenations and not
* all eBPF JITs might immediately support all features.
*/
return bpf_check_tail_call(fp);
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
static void bpf_prog_free_deferred(struct work_struct *work)
{
struct bpf_prog_aux *aux;
aux = container_of(work, struct bpf_prog_aux, work);
bpf_jit_free(aux->prog);
}
/* Free internal BPF program */
void bpf_prog_free(struct bpf_prog *fp)
{
struct bpf_prog_aux *aux = fp->aux;
INIT_WORK(&aux->work, bpf_prog_free_deferred);
aux->prog = fp;
schedule_work(&aux->work);
}
EXPORT_SYMBOL_GPL(bpf_prog_free);
/* Weak definitions of helper functions in case we don't have bpf syscall. */
const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
const struct bpf_func_proto bpf_map_update_elem_proto __weak;
const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
const struct bpf_func_proto bpf_get_current_comm_proto __weak;
const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
{
return NULL;
}
/* Always built-in helper functions. */
const struct bpf_func_proto bpf_tail_call_proto = {
.func = NULL,
.gpl_only = false,
.ret_type = RET_VOID,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
};
/* For classic BPF JITs that don't implement bpf_int_jit_compile(). */
void __weak bpf_int_jit_compile(struct bpf_prog *prog)
{
}
/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
* skb_copy_bits(), so provide a weak definition of it for NET-less config.
*/
int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
int len)
{
return -EFAULT;
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/bpf/hashtab.c
/* 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;
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;
err = -ENOMEM;
/* 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;
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]);
spin_lock_init(&htab->lock);
htab->count = 0;
htab->elem_size = sizeof(struct htab_elem) +
round_up(htab->map.key_size, 8) +
htab->map.value_size;
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 */
l_new = kmalloc(htab->elem_size, GFP_ATOMIC);
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() */
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++;
}
spin_unlock_irqrestore(&htab->lock, flags);
return 0;
err:
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);
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;
}
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);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/bpf/helpers.c
/* 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/rcupdate.h>
#include <linux/random.h>
#include <linux/smp.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/uidgid.h>
/* If kernel subsystem is allowing eBPF programs to call this function,
* inside its own verifier_ops->get_func_proto() callback it should return
* bpf_map_lookup_elem_proto, so that verifier can properly check the arguments
*
* Different map implementations will rely on rcu in map methods
* lookup/update/delete, therefore eBPF programs must run under rcu lock
* if program is allowed to access maps, so check rcu_read_lock_held in
* all three functions.
*/
static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
/* verifier checked that R1 contains a valid pointer to bpf_map
* and R2 points to a program stack and map->key_size bytes were
* initialized
*/
struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
void *key = (void *) (unsigned long) r2;
void *value;
WARN_ON_ONCE(!rcu_read_lock_held());
value = map->ops->map_lookup_elem(map, key);
/* lookup() returns either pointer to element value or NULL
* which is the meaning of PTR_TO_MAP_VALUE_OR_NULL type
*/
return (unsigned long) value;
}
const struct bpf_func_proto bpf_map_lookup_elem_proto = {
.func = bpf_map_lookup_elem,
.gpl_only = false,
.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_MAP_KEY,
};
static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
void *key = (void *) (unsigned long) r2;
void *value = (void *) (unsigned long) r3;
WARN_ON_ONCE(!rcu_read_lock_held());
return map->ops->map_update_elem(map, key, value, r4);
}
const struct bpf_func_proto bpf_map_update_elem_proto = {
.func = bpf_map_update_elem,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_MAP_KEY,
.arg3_type = ARG_PTR_TO_MAP_VALUE,
.arg4_type = ARG_ANYTHING,
};
static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
void *key = (void *) (unsigned long) r2;
WARN_ON_ONCE(!rcu_read_lock_held());
return map->ops->map_delete_elem(map, key);
}
const struct bpf_func_proto bpf_map_delete_elem_proto = {
.func = bpf_map_delete_elem,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_MAP_KEY,
};
static u64 bpf_get_prandom_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
return prandom_u32();
}
const struct bpf_func_proto bpf_get_prandom_u32_proto = {
.func = bpf_get_prandom_u32,
.gpl_only = false,
.ret_type = RET_INTEGER,
};
static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
return raw_smp_processor_id();
}
const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
.func = bpf_get_smp_processor_id,
.gpl_only = false,
.ret_type = RET_INTEGER,
};
static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
/* NMI safe access to clock monotonic */
return ktime_get_mono_fast_ns();
}
const struct bpf_func_proto bpf_ktime_get_ns_proto = {
.func = bpf_ktime_get_ns,
.gpl_only = true,
.ret_type = RET_INTEGER,
};
static u64 bpf_get_current_pid_tgid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
struct task_struct *task = current;
if (!task)
return -EINVAL;
return (u64) task->tgid << 32 | task->pid;
}
const struct bpf_func_proto bpf_get_current_pid_tgid_proto = {
.func = bpf_get_current_pid_tgid,
.gpl_only = false,
.ret_type = RET_INTEGER,
};
static u64 bpf_get_current_uid_gid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
struct task_struct *task = current;
kuid_t uid;
kgid_t gid;
if (!task)
return -EINVAL;
current_uid_gid(&uid, &gid);
return (u64) from_kgid(&init_user_ns, gid) << 32 |
from_kuid(&init_user_ns, uid);
}
const struct bpf_func_proto bpf_get_current_uid_gid_proto = {
.func = bpf_get_current_uid_gid,
.gpl_only = false,
.ret_type = RET_INTEGER,
};
static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5)
{
struct task_struct *task = current;
char *buf = (char *) (long) r1;
if (!task)
return -EINVAL;
memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
return 0;
}
const struct bpf_func_proto bpf_get_current_comm_proto = {
.func = bpf_get_current_comm,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_STACK,
.arg2_type = ARG_CONST_STACK_SIZE,
};
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/bpf/Makefile
obj-y := core.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o helpers.o
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/bpf/syscall.c
/* 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/syscalls.h>
#include <linux/slab.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/license.h>
#include <linux/filter.h>
#include <linux/version.h>
static LIST_HEAD(bpf_map_types);
static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
{
struct bpf_map_type_list *tl;
struct bpf_map *map;
list_for_each_entry(tl, &bpf_map_types, list_node) {
if (tl->type == attr->map_type) {
map = tl->ops->map_alloc(attr);
if (IS_ERR(map))
return map;
map->ops = tl->ops;
map->map_type = attr->map_type;
return map;
}
}
return ERR_PTR(-EINVAL);
}
/* boot time registration of different map implementations */
void bpf_register_map_type(struct bpf_map_type_list *tl)
{
list_add(&tl->list_node, &bpf_map_types);
}
/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
/* implementation dependent freeing */
map->ops->map_free(map);
}
/* decrement map refcnt and schedule it for freeing via workqueue
* (unrelying map implementation ops->map_free() might sleep)
*/
void bpf_map_put(struct bpf_map *map)
{
if (atomic_dec_and_test(&map->refcnt)) {
INIT_WORK(&map->work, bpf_map_free_deferred);
schedule_work(&map->work);
}
}
static int bpf_map_release(struct inode *inode, struct file *filp)
{
struct bpf_map *map = filp->private_data;
if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
/* prog_array stores refcnt-ed bpf_prog pointers
* release them all when user space closes prog_array_fd
*/
bpf_prog_array_map_clear(map);
bpf_map_put(map);
return 0;
}
static const struct file_operations bpf_map_fops = {
.release = bpf_map_release,
};
/* helper macro to check that unused fields 'union bpf_attr' are zero */
#define CHECK_ATTR(CMD) \
memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
sizeof(attr->CMD##_LAST_FIELD), 0, \
sizeof(*attr) - \
offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
sizeof(attr->CMD##_LAST_FIELD)) != NULL
#define BPF_MAP_CREATE_LAST_FIELD max_entries
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
struct bpf_map *map;
int err;
err = CHECK_ATTR(BPF_MAP_CREATE);
if (err)
return -EINVAL;
/* find map type and init map: hashtable vs rbtree vs bloom vs ... */
map = find_and_alloc_map(attr);
if (IS_ERR(map))
return PTR_ERR(map);
atomic_set(&map->refcnt, 1);
err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC);
if (err < 0)
/* failed to allocate fd */
goto free_map;
return err;
free_map:
map->ops->map_free(map);
return err;
}
/* if error is returned, fd is released.
* On success caller should complete fd access with matching fdput()
*/
struct bpf_map *bpf_map_get(struct fd f)
{
struct bpf_map *map;
if (!f.file)
return ERR_PTR(-EBADF);
if (f.file->f_op != &bpf_map_fops) {
fdput(f);
return ERR_PTR(-EINVAL);
}
map = f.file->private_data;
return map;
}
/* helper to convert user pointers passed inside __aligned_u64 fields */
static void __user *u64_to_ptr(__u64 val)
{
return (void __user *) (unsigned long) val;
}
/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
static int map_lookup_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_ptr(attr->key);
void __user *uvalue = u64_to_ptr(attr->value);
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
void *key, *value, *ptr;
int err;
if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
return -EINVAL;
map = bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
goto err_put;
err = -EFAULT;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
err = -ENOMEM;
value = kmalloc(map->value_size, GFP_USER);
if (!value)
goto free_key;
rcu_read_lock();
ptr = map->ops->map_lookup_elem(map, key);
if (ptr)
memcpy(value, ptr, map->value_size);
rcu_read_unlock();
err = -ENOENT;
if (!ptr)
goto free_value;
err = -EFAULT;
if (copy_to_user(uvalue, value, map->value_size) != 0)
goto free_value;
err = 0;
free_value:
kfree(value);
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
static int map_update_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_ptr(attr->key);
void __user *uvalue = u64_to_ptr(attr->value);
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
void *key, *value;
int err;
if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
return -EINVAL;
map = bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
goto err_put;
err = -EFAULT;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
err = -ENOMEM;
value = kmalloc(map->value_size, GFP_USER);
if (!value)
goto free_key;
err = -EFAULT;
if (copy_from_user(value, uvalue, map->value_size) != 0)
goto free_value;
/* eBPF program that use maps are running under rcu_read_lock(),
* therefore all map accessors rely on this fact, so do the same here
*/
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, attr->flags);
rcu_read_unlock();
free_value:
kfree(value);
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
#define BPF_MAP_DELETE_ELEM_LAST_FIELD key
static int map_delete_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_ptr(attr->key);
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
void *key;
int err;
if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
return -EINVAL;
map = bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
goto err_put;
err = -EFAULT;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
rcu_read_lock();
err = map->ops->map_delete_elem(map, key);
rcu_read_unlock();
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key
static int map_get_next_key(union bpf_attr *attr)
{
void __user *ukey = u64_to_ptr(attr->key);
void __user *unext_key = u64_to_ptr(attr->next_key);
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
void *key, *next_key;
int err;
if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
return -EINVAL;
map = bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
goto err_put;
err = -EFAULT;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
err = -ENOMEM;
next_key = kmalloc(map->key_size, GFP_USER);
if (!next_key)
goto free_key;
rcu_read_lock();
err = map->ops->map_get_next_key(map, key, next_key);
rcu_read_unlock();
if (err)
goto free_next_key;
err = -EFAULT;
if (copy_to_user(unext_key, next_key, map->key_size) != 0)
goto free_next_key;
err = 0;
free_next_key:
kfree(next_key);
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
static LIST_HEAD(bpf_prog_types);
static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
{
struct bpf_prog_type_list *tl;
list_for_each_entry(tl, &bpf_prog_types, list_node) {
if (tl->type == type) {
prog->aux->ops = tl->ops;
prog->type = type;
return 0;
}
}
return -EINVAL;
}
void bpf_register_prog_type(struct bpf_prog_type_list *tl)
{
list_add(&tl->list_node, &bpf_prog_types);
}
/* fixup insn->imm field of bpf_call instructions:
* if (insn->imm == BPF_FUNC_map_lookup_elem)
* insn->imm = bpf_map_lookup_elem - __bpf_call_base;
* else if (insn->imm == BPF_FUNC_map_update_elem)
* insn->imm = bpf_map_update_elem - __bpf_call_base;
* else ...
*
* this function is called after eBPF program passed verification
*/
static void fixup_bpf_calls(struct bpf_prog *prog)
{
const struct bpf_func_proto *fn;
int i;
for (i = 0; i < prog->len; i++) {
struct bpf_insn *insn = &prog->insnsi[i];
if (insn->code == (BPF_JMP | BPF_CALL)) {
/* we reach here when program has bpf_call instructions
* and it passed bpf_check(), means that
* ops->get_func_proto must have been supplied, check it
*/
BUG_ON(!prog->aux->ops->get_func_proto);
if (insn->imm == BPF_FUNC_tail_call) {
/* mark bpf_tail_call as different opcode
* to avoid conditional branch in
* interpeter for every normal call
* and to prevent accidental JITing by
* JIT compiler that doesn't support
* bpf_tail_call yet
*/
insn->imm = 0;
insn->code |= BPF_X;
continue;
}
fn = prog->aux->ops->get_func_proto(insn->imm);
/* all functions that have prototype and verifier allowed
* programs to call them, must be real in-kernel functions
*/
BUG_ON(!fn->func);
insn->imm = fn->func - __bpf_call_base;
}
}
}
/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
int i;
for (i = 0; i < aux->used_map_cnt; i++)
bpf_map_put(aux->used_maps[i]);
kfree(aux->used_maps);
}
static void __prog_put_rcu(struct rcu_head *rcu)
{
struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
free_used_maps(aux);
bpf_prog_free(aux->prog);
}
/* version of bpf_prog_put() that is called after a grace period */
void bpf_prog_put_rcu(struct bpf_prog *prog)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
prog->aux->prog = prog;
call_rcu(&prog->aux->rcu, __prog_put_rcu);
}
}
void bpf_prog_put(struct bpf_prog *prog)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
free_used_maps(prog->aux);
bpf_prog_free(prog);
}
}
EXPORT_SYMBOL_GPL(bpf_prog_put);
static int bpf_prog_release(struct inode *inode, struct file *filp)
{
struct bpf_prog *prog = filp->private_data;
bpf_prog_put_rcu(prog);
return 0;
}
static const struct file_operations bpf_prog_fops = {
.release = bpf_prog_release,
};
static struct bpf_prog *get_prog(struct fd f)
{
struct bpf_prog *prog;
if (!f.file)
return ERR_PTR(-EBADF);
if (f.file->f_op != &bpf_prog_fops) {
fdput(f);
return ERR_PTR(-EINVAL);
}
prog = f.file->private_data;
return prog;
}
/* called by sockets/tracing/seccomp before attaching program to an event
* pairs with bpf_prog_put()
*/
struct bpf_prog *bpf_prog_get(u32 ufd)
{
struct fd f = fdget(ufd);
struct bpf_prog *prog;
prog = get_prog(f);
if (IS_ERR(prog))
return prog;
atomic_inc(&prog->aux->refcnt);
fdput(f);
return prog;
}
EXPORT_SYMBOL_GPL(bpf_prog_get);
/* last field in 'union bpf_attr' used by this command */
#define BPF_PROG_LOAD_LAST_FIELD kern_version
static int bpf_prog_load(union bpf_attr *attr)
{
enum bpf_prog_type type = attr->prog_type;
struct bpf_prog *prog;
int err;
char license[128];
bool is_gpl;
if (CHECK_ATTR(BPF_PROG_LOAD))
return -EINVAL;
/* copy eBPF program license from user space */
if (strncpy_from_user(license, u64_to_ptr(attr->license),
sizeof(license) - 1) < 0)
return -EFAULT;
license[sizeof(license) - 1] = 0;
/* eBPF programs must be GPL compatible to use GPL-ed functions */
is_gpl = license_is_gpl_compatible(license);
if (attr->insn_cnt >= BPF_MAXINSNS)
return -EINVAL;
if (type == BPF_PROG_TYPE_KPROBE &&
attr->kern_version != LINUX_VERSION_CODE)
return -EINVAL;
/* plain bpf_prog allocation */
prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
if (!prog)
return -ENOMEM;
prog->len = attr->insn_cnt;
err = -EFAULT;
if (copy_from_user(prog->insns, u64_to_ptr(attr->insns),
prog->len * sizeof(struct bpf_insn)) != 0)
goto free_prog;
prog->orig_prog = NULL;
prog->jited = false;
atomic_set(&prog->aux->refcnt, 1);
prog->gpl_compatible = is_gpl;
/* find program type: socket_filter vs tracing_filter */
err = find_prog_type(type, prog);
if (err < 0)
goto free_prog;
/* run eBPF verifier */
err = bpf_check(&prog, attr);
if (err < 0)
goto free_used_maps;
/* fixup BPF_CALL->imm field */
fixup_bpf_calls(prog);
/* eBPF program is ready to be JITed */
err = bpf_prog_select_runtime(prog);
if (err < 0)
goto free_used_maps;
err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);
if (err < 0)
/* failed to allocate fd */
goto free_used_maps;
return err;
free_used_maps:
free_used_maps(prog->aux);
free_prog:
bpf_prog_free(prog);
return err;
}
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
int err;
/* the syscall is limited to root temporarily. This restriction will be
* lifted when security audit is clean. Note that eBPF+tracing must have
* this restriction, since it may pass kernel data to user space
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!access_ok(VERIFY_READ, uattr, 1))
return -EFAULT;
if (size > PAGE_SIZE) /* silly large */
return -E2BIG;
/* If we're handed a bigger struct than we know of,
* ensure all the unknown bits are 0 - i.e. new
* user-space does not rely on any kernel feature
* extensions we dont know about yet.
*/
if (size > sizeof(attr)) {
unsigned char __user *addr;
unsigned char __user *end;
unsigned char val;
addr = (void __user *)uattr + sizeof(attr);
end = (void __user *)uattr + size;
for (; addr < end; addr++) {
err = get_user(val, addr);
if (err)
return err;
if (val)
return -E2BIG;
}
size = sizeof(attr);
}
/* copy attributes from user space, may be less than sizeof(bpf_attr) */
if (copy_from_user(&attr, uattr, size) != 0)
return -EFAULT;
switch (cmd) {
case BPF_MAP_CREATE:
err = map_create(&attr);
break;
case BPF_MAP_LOOKUP_ELEM:
err = map_lookup_elem(&attr);
break;
case BPF_MAP_UPDATE_ELEM:
err = map_update_elem(&attr);
break;
case BPF_MAP_DELETE_ELEM:
err = map_delete_elem(&attr);
break;
case BPF_MAP_GET_NEXT_KEY:
err = map_get_next_key(&attr);
break;
case BPF_PROG_LOAD:
err = bpf_prog_load(&attr);
break;
default:
err = -EINVAL;
break;
}
return err;
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/bpf/verifier.c
/* 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/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>
/* bpf_check() is a static code analyzer that walks eBPF program
* instruction by instruction and updates register/stack state.
* All paths of conditional branches are analyzed until 'bpf_exit' insn.
*
* The first pass is depth-first-search to check that the program is a DAG.
* It rejects the following programs:
* - larger than BPF_MAXINSNS insns
* - if loop is present (detected via back-edge)
* - unreachable insns exist (shouldn't be a forest. program = one function)
* - out of bounds or malformed jumps
* The second pass is all possible path descent from the 1st insn.
* Since it's analyzing all pathes through the program, the length of the
* analysis is limited to 32k insn, which may be hit even if total number of
* insn is less then 4K, but there are too many branches that change stack/regs.
* Number of 'branches to be analyzed' is limited to 1k
*
* On entry to each instruction, each register has a type, and the instruction
* changes the types of the registers depending on instruction semantics.
* If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
* copied to R1.
*
* All registers are 64-bit.
* R0 - return register
* R1-R5 argument passing registers
* R6-R9 callee saved registers
* R10 - frame pointer read-only
*
* At the start of BPF program the register R1 contains a pointer to bpf_context
* and has type PTR_TO_CTX.
*
* Verifier tracks arithmetic operations on pointers in case:
* BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
* BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
* 1st insn copies R10 (which has FRAME_PTR) type into R1
* and 2nd arithmetic instruction is pattern matched to recognize
* that it wants to construct a pointer to some element within stack.
* So after 2nd insn, the register R1 has type PTR_TO_STACK
* (and -20 constant is saved for further stack bounds checking).
* Meaning that this reg is a pointer to stack plus known immediate constant.
*
* Most of the time the registers have UNKNOWN_VALUE type, which
* means the register has some value, but it's not a valid pointer.
* (like pointer plus pointer becomes UNKNOWN_VALUE type)
*
* When verifier sees load or store instructions the type of base register
* can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, FRAME_PTR. These are three pointer
* types recognized by check_mem_access() function.
*
* PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
* and the range of [ptr, ptr + map's value_size) is accessible.
*
* registers used to pass values to function calls are checked against
* function argument constraints.
*
* ARG_PTR_TO_MAP_KEY is one of such argument constraints.
* It means that the register type passed to this function must be
* PTR_TO_STACK and it will be used inside the function as
* 'pointer to map element key'
*
* For example the argument constraints for bpf_map_lookup_elem():
* .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
* .arg1_type = ARG_CONST_MAP_PTR,
* .arg2_type = ARG_PTR_TO_MAP_KEY,
*
* ret_type says that this function returns 'pointer to map elem value or null'
* function expects 1st argument to be a const pointer to 'struct bpf_map' and
* 2nd argument should be a pointer to stack, which will be used inside
* the helper function as a pointer to map element key.
*
* On the kernel side the helper function looks like:
* u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
* {
* struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
* void *key = (void *) (unsigned long) r2;
* void *value;
*
* here kernel can access 'key' and 'map' pointers safely, knowing that
* [key, key + map->key_size) bytes are valid and were initialized on
* the stack of eBPF program.
* }
*
* Corresponding eBPF program may look like:
* BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR
* BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
* BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP
* BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
* here verifier looks at prototype of map_lookup_elem() and sees:
* .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
* Now verifier knows that this map has key of R1->map_ptr->key_size bytes
*
* Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
* Now verifier checks that [R2, R2 + map's key_size) are within stack limits
* and were initialized prior to this call.
* If it's ok, then verifier allows this BPF_CALL insn and looks at
* .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
* R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
* returns ether pointer to map value or NULL.
*
* When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
* insn, the register holding that pointer in the true branch changes state to
* PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
* branch. See check_cond_jmp_op().
*
* After the call R0 is set to return type of the function and registers R1-R5
* are set to NOT_INIT to indicate that they are no longer readable.
*/
/* types of values stored in eBPF registers */
enum bpf_reg_type {
NOT_INIT = 0, /* nothing was written into register */
UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */
PTR_TO_CTX, /* reg points to bpf_context */
CONST_PTR_TO_MAP, /* reg points to struct bpf_map */
PTR_TO_MAP_VALUE, /* reg points to map element value */
PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
FRAME_PTR, /* reg == frame_pointer */
PTR_TO_STACK, /* reg == frame_pointer + imm */
CONST_IMM, /* constant integer value */
};
struct reg_state {
enum bpf_reg_type type;
union {
/* valid when type == CONST_IMM | PTR_TO_STACK */
int imm;
/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
* PTR_TO_MAP_VALUE_OR_NULL
*/
struct bpf_map *map_ptr;
};
};
enum bpf_stack_slot_type {
STACK_INVALID, /* nothing was stored in this stack slot */
STACK_SPILL, /* register spilled into stack */
STACK_MISC /* BPF program wrote some data into this slot */
};
#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */
/* state of the program:
* type of all registers and stack info
*/
struct verifier_state {
struct reg_state regs[MAX_BPF_REG];
u8 stack_slot_type[MAX_BPF_STACK];
struct reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE];
};
/* linked list of verifier states used to prune search */
struct verifier_state_list {
struct verifier_state state;
struct verifier_state_list *next;
};
/* verifier_state + insn_idx are pushed to stack when branch is encountered */
struct verifier_stack_elem {
/* verifer state is 'st'
* before processing instruction 'insn_idx'
* and after processing instruction 'prev_insn_idx'
*/
struct verifier_state st;
int insn_idx;
int prev_insn_idx;
struct verifier_stack_elem *next;
};
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
/* single container for all structs
* one verifier_env per bpf_check() call
*/
struct verifier_env {
struct bpf_prog *prog; /* eBPF program being verified */
struct verifier_stack_elem *head; /* stack of verifier states to be processed */
int stack_size; /* number of states to be processed */
struct verifier_state cur_state; /* current verifier state */
struct verifier_state_list **explored_states; /* search pruning optimization */
struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
u32 used_map_cnt; /* number of used maps */
};
/* verbose verifier prints what it's seeing
* bpf_check() is called under lock, so no race to access these global vars
*/
static u32 log_level, log_size, log_len;
static char *log_buf;
static DEFINE_MUTEX(bpf_verifier_lock);
/* log_level controls verbosity level of eBPF verifier.
* verbose() is used to dump the verification trace to the log, so the user
* can figure out what's wrong with the program
*/
static void verbose(const char *fmt, ...)
{
va_list args;
if (log_level == 0 || log_len >= log_size - 1)
return;
va_start(args, fmt);
log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args);
va_end(args);
}
/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
[NOT_INIT] = "?",
[UNKNOWN_VALUE] = "inv",
[PTR_TO_CTX] = "ctx",
[CONST_PTR_TO_MAP] = "map_ptr",
[PTR_TO_MAP_VALUE] = "map_value",
[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
[FRAME_PTR] = "fp",
[PTR_TO_STACK] = "fp",
[CONST_IMM] = "imm",
};
static void print_verifier_state(struct verifier_env *env)
{
enum bpf_reg_type t;
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
t = env->cur_state.regs[i].type;
if (t == NOT_INIT)
continue;
verbose(" R%d=%s", i, reg_type_str[t]);
if (t == CONST_IMM || t == PTR_TO_STACK)
verbose("%d", env->cur_state.regs[i].imm);
else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
t == PTR_TO_MAP_VALUE_OR_NULL)
verbose("(ks=%d,vs=%d)",
env->cur_state.regs[i].map_ptr->key_size,
env->cur_state.regs[i].map_ptr->value_size);
}
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
if (env->cur_state.stack_slot_type[i] == STACK_SPILL)
verbose(" fp%d=%s", -MAX_BPF_STACK + i,
reg_type_str[env->cur_state.spilled_regs[i / BPF_REG_SIZE].type]);
}
verbose("\n");
}
static const char *const bpf_class_string[] = {
[BPF_LD] = "ld",
[BPF_LDX] = "ldx",
[BPF_ST] = "st",
[BPF_STX] = "stx",
[BPF_ALU] = "alu",
[BPF_JMP] = "jmp",
[BPF_RET] = "BUG",
[BPF_ALU64] = "alu64",
};
static const char *const bpf_alu_string[] = {
[BPF_ADD >> 4] = "+=",
[BPF_SUB >> 4] = "-=",
[BPF_MUL >> 4] = "*=",
[BPF_DIV >> 4] = "/=",
[BPF_OR >> 4] = "|=",
[BPF_AND >> 4] = "&=",
[BPF_LSH >> 4] = "<<=",
[BPF_RSH >> 4] = ">>=",
[BPF_NEG >> 4] = "neg",
[BPF_MOD >> 4] = "%=",
[BPF_XOR >> 4] = "^=",
[BPF_MOV >> 4] = "=",
[BPF_ARSH >> 4] = "s>>=",
[BPF_END >> 4] = "endian",
};
static const char *const bpf_ldst_string[] = {
[BPF_W >> 3] = "u32",
[BPF_H >> 3] = "u16",
[BPF_B >> 3] = "u8",
[BPF_DW >> 3] = "u64",
};
static const char *const bpf_jmp_string[] = {
[BPF_JA >> 4] = "jmp",
[BPF_JEQ >> 4] = "==",
[BPF_JGT >> 4] = ">",
[BPF_JGE >> 4] = ">=",
[BPF_JSET >> 4] = "&",
[BPF_JNE >> 4] = "!=",
[BPF_JSGT >> 4] = "s>",
[BPF_JSGE >> 4] = "s>=",
[BPF_CALL >> 4] = "call",
[BPF_EXIT >> 4] = "exit",
};
static void print_bpf_insn(struct bpf_insn *insn)
{
u8 class = BPF_CLASS(insn->code);
if (class == BPF_ALU || class == BPF_ALU64) {
if (BPF_SRC(insn->code) == BPF_X)
verbose("(%02x) %sr%d %s %sr%d\n",
insn->code, class == BPF_ALU ? "(u32) " : "",
insn->dst_reg,
bpf_alu_string[BPF_OP(insn->code) >> 4],
class == BPF_ALU ? "(u32) " : "",
insn->src_reg);
else
verbose("(%02x) %sr%d %s %s%d\n",
insn->code, class == BPF_ALU ? "(u32) " : "",
insn->dst_reg,
bpf_alu_string[BPF_OP(insn->code) >> 4],
class == BPF_ALU ? "(u32) " : "",
insn->imm);
} else if (class == BPF_STX) {
if (BPF_MODE(insn->code) == BPF_MEM)
verbose("(%02x) *(%s *)(r%d %+d) = r%d\n",
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->dst_reg,
insn->off, insn->src_reg);
else if (BPF_MODE(insn->code) == BPF_XADD)
verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n",
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->dst_reg, insn->off,
insn->src_reg);
else
verbose("BUG_%02x\n", insn->code);
} else if (class == BPF_ST) {
if (BPF_MODE(insn->code) != BPF_MEM) {
verbose("BUG_st_%02x\n", insn->code);
return;
}
verbose("(%02x) *(%s *)(r%d %+d) = %d\n",
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->dst_reg,
insn->off, insn->imm);
} else if (class == BPF_LDX) {
if (BPF_MODE(insn->code) != BPF_MEM) {
verbose("BUG_ldx_%02x\n", insn->code);
return;
}
verbose("(%02x) r%d = *(%s *)(r%d %+d)\n",
insn->code, insn->dst_reg,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->src_reg, insn->off);
} else if (class == BPF_LD) {
if (BPF_MODE(insn->code) == BPF_ABS) {
verbose("(%02x) r0 = *(%s *)skb[%d]\n",
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->imm);
} else if (BPF_MODE(insn->code) == BPF_IND) {
verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n",
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->src_reg, insn->imm);
} else if (BPF_MODE(insn->code) == BPF_IMM) {
verbose("(%02x) r%d = 0x%x\n",
insn->code, insn->dst_reg, insn->imm);
} else {
verbose("BUG_ld_%02x\n", insn->code);
return;
}
} else if (class == BPF_JMP) {
u8 opcode = BPF_OP(insn->code);
if (opcode == BPF_CALL) {
verbose("(%02x) call %d\n", insn->code, insn->imm);
} else if (insn->code == (BPF_JMP | BPF_JA)) {
verbose("(%02x) goto pc%+d\n",
insn->code, insn->off);
} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
verbose("(%02x) exit\n", insn->code);
} else if (BPF_SRC(insn->code) == BPF_X) {
verbose("(%02x) if r%d %s r%d goto pc%+d\n",
insn->code, insn->dst_reg,
bpf_jmp_string[BPF_OP(insn->code) >> 4],
insn->src_reg, insn->off);
} else {
verbose("(%02x) if r%d %s 0x%x goto pc%+d\n",
insn->code, insn->dst_reg,
bpf_jmp_string[BPF_OP(insn->code) >> 4],
insn->imm, insn->off);
}
} else {
verbose("(%02x) %s\n", insn->code, bpf_class_string[class]);
}
}
static int pop_stack(struct verifier_env *env, int *prev_insn_idx)
{
struct verifier_stack_elem *elem;
int insn_idx;
if (env->head == NULL)
return -1;
memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state));
insn_idx = env->head->insn_idx;
if (prev_insn_idx)
*prev_insn_idx = env->head->prev_insn_idx;
elem = env->head->next;
kfree(env->head);
env->head = elem;
env->stack_size--;
return insn_idx;
}
static struct verifier_state *push_stack(struct verifier_env *env, int insn_idx,
int prev_insn_idx)
{
struct verifier_stack_elem *elem;
elem = kmalloc(sizeof(struct verifier_stack_elem), GFP_KERNEL);
if (!elem)
goto err;
memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state));
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
elem->next = env->head;
env->head = elem;
env->stack_size++;
if (env->stack_size > 1024) {
verbose("BPF program is too complex\n");
goto err;
}
return &elem->st;
err:
/* pop all elements and return */
while (pop_stack(env, NULL) >= 0);
return NULL;
}
#define CALLER_SAVED_REGS 6
static const int caller_saved[CALLER_SAVED_REGS] = {
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
static void init_reg_state(struct reg_state *regs)
{
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
regs[i].type = NOT_INIT;
regs[i].imm = 0;
regs[i].map_ptr = NULL;
}
/* frame pointer */
regs[BPF_REG_FP].type = FRAME_PTR;
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
}
static void mark_reg_unknown_value(struct reg_state *regs, u32 regno)
{
BUG_ON(regno >= MAX_BPF_REG);
regs[regno].type = UNKNOWN_VALUE;
regs[regno].imm = 0;
regs[regno].map_ptr = NULL;
}
enum reg_arg_type {
SRC_OP, /* register is used as source operand */
DST_OP, /* register is used as destination operand */
DST_OP_NO_MARK /* same as above, check only, don't mark */
};
static int check_reg_arg(struct reg_state *regs, u32 regno,
enum reg_arg_type t)
{
if (regno >= MAX_BPF_REG) {
verbose("R%d is invalid\n", regno);
return -EINVAL;
}
if (t == SRC_OP) {
/* check whether register used as source operand can be read */
if (regs[regno].type == NOT_INIT) {
verbose("R%d !read_ok\n", regno);
return -EACCES;
}
} else {
/* check whether register used as dest operand can be written to */
if (regno == BPF_REG_FP) {
verbose("frame pointer is read only\n");
return -EACCES;
}
if (t == DST_OP)
mark_reg_unknown_value(regs, regno);
}
return 0;
}
static int bpf_size_to_bytes(int bpf_size)
{
if (bpf_size == BPF_W)
return 4;
else if (bpf_size == BPF_H)
return 2;
else if (bpf_size == BPF_B)
return 1;
else if (bpf_size == BPF_DW)
return 8;
else
return -EINVAL;
}
/* check_stack_read/write functions track spill/fill of registers,
* stack boundary and alignment are checked in check_mem_access()
*/
static int check_stack_write(struct verifier_state *state, int off, int size,
int value_regno)
{
int i;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
* so it's aligned access and [off, off + size) are within stack limits
*/
if (value_regno >= 0 &&
(state->regs[value_regno].type == PTR_TO_MAP_VALUE ||
state->regs[value_regno].type == PTR_TO_STACK ||
state->regs[value_regno].type == PTR_TO_CTX)) {
/* register containing pointer is being spilled into stack */
if (size != BPF_REG_SIZE) {
verbose("invalid size of register spill\n");
return -EACCES;
}
/* save register state */
state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
state->regs[value_regno];
for (i = 0; i < BPF_REG_SIZE; i++)
state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL;
} else {
/* regular write of data into stack */
state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
(struct reg_state) {};
for (i = 0; i < size; i++)
state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC;
}
return 0;
}
static int check_stack_read(struct verifier_state *state, int off, int size,
int value_regno)
{
u8 *slot_type;
int i;
slot_type = &state->stack_slot_type[MAX_BPF_STACK + off];
if (slot_type[0] == STACK_SPILL) {
if (size != BPF_REG_SIZE) {
verbose("invalid size of register spill\n");
return -EACCES;
}
for (i = 1; i < BPF_REG_SIZE; i++) {
if (slot_type[i] != STACK_SPILL) {
verbose("corrupted spill memory\n");
return -EACCES;
}
}
if (value_regno >= 0)
/* restore register state from stack */
state->regs[value_regno] =
state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE];
return 0;
} else {
for (i = 0; i < size; i++) {
if (slot_type[i] != STACK_MISC) {
verbose("invalid read from stack off %d+%d size %d\n",
off, i, size);
return -EACCES;
}
}
if (value_regno >= 0)
/* have read misc data from the stack */
mark_reg_unknown_value(state->regs, value_regno);
return 0;
}
}
/* check read/write into map element returned by bpf_map_lookup_elem() */
static int check_map_access(struct verifier_env *env, u32 regno, int off,
int size)
{
struct bpf_map *map = env->cur_state.regs[regno].map_ptr;
if (off < 0 || off + size > map->value_size) {
verbose("invalid access to map value, value_size=%d off=%d size=%d\n",
map->value_size, off, size);
return -EACCES;
}
return 0;
}
/* check access to 'struct bpf_context' fields */
static int check_ctx_access(struct verifier_env *env, int off, int size,
enum bpf_access_type t)
{
if (env->prog->aux->ops->is_valid_access &&
env->prog->aux->ops->is_valid_access(off, size, t))
return 0;
verbose("invalid bpf_context access off=%d size=%d\n", off, size);
return -EACCES;
}
/* check whether memory at (regno + off) is accessible for t = (read | write)
* if t==write, value_regno is a register which value is stored into memory
* if t==read, value_regno is a register which will receive the value from memory
* if t==write && value_regno==-1, some unknown value is stored into memory
* if t==read && value_regno==-1, don't care what we read from memory
*/
static int check_mem_access(struct verifier_env *env, u32 regno, int off,
int bpf_size, enum bpf_access_type t,
int value_regno)
{
struct verifier_state *state = &env->cur_state;
int size, err = 0;
size = bpf_size_to_bytes(bpf_size);
if (size < 0)
return size;
if (off % size != 0) {
verbose("misaligned access off %d size %d\n", off, size);
return -EACCES;
}
if (state->regs[regno].type == PTR_TO_MAP_VALUE) {
err = check_map_access(env, regno, off, size);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown_value(state->regs, value_regno);
} else if (state->regs[regno].type == PTR_TO_CTX) {
err = check_ctx_access(env, off, size, t);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown_value(state->regs, value_regno);
} else if (state->regs[regno].type == FRAME_PTR) {
if (off >= 0 || off < -MAX_BPF_STACK) {
verbose("invalid stack off=%d size=%d\n", off, size);
return -EACCES;
}
if (t == BPF_WRITE)
err = check_stack_write(state, off, size, value_regno);
else
err = check_stack_read(state, off, size, value_regno);
} else {
verbose("R%d invalid mem access '%s'\n",
regno, reg_type_str[state->regs[regno].type]);
return -EACCES;
}
return err;
}
static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
{
struct reg_state *regs = env->cur_state.regs;
int err;
if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
insn->imm != 0) {
verbose("BPF_XADD uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(regs, insn->src_reg, SRC_OP);
if (err)
return err;
/* check src2 operand */
err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
if (err)
return err;
/* check whether atomic_add can read the memory */
err = check_mem_access(env, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, -1);
if (err)
return err;
/* check whether atomic_add can write into the same memory */
return check_mem_access(env, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1);
}
/* when register 'regno' is passed into function that will read 'access_size'
* bytes from that pointer, make sure that it's within stack boundary
* and all elements of stack are initialized
*/
static int check_stack_boundary(struct verifier_env *env,
int regno, int access_size)
{
struct verifier_state *state = &env->cur_state;
struct reg_state *regs = state->regs;
int off, i;
if (regs[regno].type != PTR_TO_STACK)
return -EACCES;
off = regs[regno].imm;
if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
access_size <= 0) {
verbose("invalid stack type R%d off=%d access_size=%d\n",
regno, off, access_size);
return -EACCES;
}
for (i = 0; i < access_size; i++) {
if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) {
verbose("invalid indirect read from stack off %d+%d size %d\n",
off, i, access_size);
return -EACCES;
}
}
return 0;
}
static int check_func_arg(struct verifier_env *env, u32 regno,
enum bpf_arg_type arg_type, struct bpf_map **mapp)
{
struct reg_state *reg = env->cur_state.regs + regno;
enum bpf_reg_type expected_type;
int err = 0;
if (arg_type == ARG_DONTCARE)
return 0;
if (reg->type == NOT_INIT) {
verbose("R%d !read_ok\n", regno);
return -EACCES;
}
if (arg_type == ARG_ANYTHING)
return 0;
if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE) {
expected_type = PTR_TO_STACK;
} else if (arg_type == ARG_CONST_STACK_SIZE) {
expected_type = CONST_IMM;
} else if (arg_type == ARG_CONST_MAP_PTR) {
expected_type = CONST_PTR_TO_MAP;
} else if (arg_type == ARG_PTR_TO_CTX) {
expected_type = PTR_TO_CTX;
} else {
verbose("unsupported arg_type %d\n", arg_type);
return -EFAULT;
}
if (reg->type != expected_type) {
verbose("R%d type=%s expected=%s\n", regno,
reg_type_str[reg->type], reg_type_str[expected_type]);
return -EACCES;
}
if (arg_type == ARG_CONST_MAP_PTR) {
/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
*mapp = reg->map_ptr;
} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
/* bpf_map_xxx(..., map_ptr, ..., key) call:
* check that [key, key + map->key_size) are within
* stack limits and initialized
*/
if (!*mapp) {
/* in function declaration map_ptr must come before
* map_key, so that it's verified and known before
* we have to check map_key here. Otherwise it means
* that kernel subsystem misconfigured verifier
*/
verbose("invalid map_ptr to access map->key\n");
return -EACCES;
}
err = check_stack_boundary(env, regno, (*mapp)->key_size);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
*/
if (!*mapp) {
/* kernel subsystem misconfigured verifier */
verbose("invalid map_ptr to access map->value\n");
return -EACCES;
}
err = check_stack_boundary(env, regno, (*mapp)->value_size);
} else if (arg_type == ARG_CONST_STACK_SIZE) {
/* bpf_xxx(..., buf, len) call will access 'len' bytes
* from stack pointer 'buf'. Check it
* note: regno == len, regno - 1 == buf
*/
if (regno == 0) {
/* kernel subsystem misconfigured verifier */
verbose("ARG_CONST_STACK_SIZE cannot be first argument\n");
return -EACCES;
}
err = check_stack_boundary(env, regno - 1, reg->imm);
}
return err;
}
static int check_call(struct verifier_env *env, int func_id)
{
struct verifier_state *state = &env->cur_state;
const struct bpf_func_proto *fn = NULL;
struct reg_state *regs = state->regs;
struct bpf_map *map = NULL;
struct reg_state *reg;
int i, err;
/* find function prototype */
if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
verbose("invalid func %d\n", func_id);
return -EINVAL;
}
if (env->prog->aux->ops->get_func_proto)
fn = env->prog->aux->ops->get_func_proto(func_id);
if (!fn) {
verbose("unknown func %d\n", func_id);
return -EINVAL;
}
/* eBPF programs must be GPL compatible to use GPL-ed functions */
if (!env->prog->gpl_compatible && fn->gpl_only) {
verbose("cannot call GPL only function from proprietary program\n");
return -EINVAL;
}
/* check args */
err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &map);
if (err)
return err;
err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &map);
if (err)
return err;
err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &map);
if (err)
return err;
err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &map);
if (err)
return err;
err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &map);
if (err)
return err;
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
reg = regs + caller_saved[i];
reg->type = NOT_INIT;
reg->imm = 0;
}
/* update return register */
if (fn->ret_type == RET_INTEGER) {
regs[BPF_REG_0].type = UNKNOWN_VALUE;
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* remember map_ptr, so that check_map_access()
* can check 'value_size' boundary of memory access
* to map element returned from bpf_map_lookup_elem()
*/
if (map == NULL) {
verbose("kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
regs[BPF_REG_0].map_ptr = map;
} else {
verbose("unknown return type %d of func %d\n",
fn->ret_type, func_id);
return -EINVAL;
}
if (map && map->map_type == BPF_MAP_TYPE_PROG_ARRAY &&
func_id != BPF_FUNC_tail_call)
/* prog_array map type needs extra care:
* only allow to pass it into bpf_tail_call() for now.
* bpf_map_delete_elem() can be allowed in the future,
* while bpf_map_update_elem() must only be done via syscall
*/
return -EINVAL;
if (func_id == BPF_FUNC_tail_call &&
map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
/* don't allow any other map type to be passed into
* bpf_tail_call()
*/
return -EINVAL;
return 0;
}
kernel02
最新推荐文章于 2024-08-31 10:26:32 发布