std r12,_MSR(r1)
std r0,GPR0(r1)
std r10,GPR1(r1)
+ beq 2f /* if from kernel mode */
ACCOUNT_CPU_USER_ENTRY(r10, r11)
- std r2,GPR2(r1)
+2: std r2,GPR2(r1)
std r3,GPR3(r1)
mfcr r2
std r4,GPR4(r1)
addi r9,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)
std r11,-16(r9) /* "regshere" marker */
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR)
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
BEGIN_FW_FTR_SECTION
beq 33f
/* if from user, see if there are any DTL entries to process */
addi r9,r1,STACK_FRAME_OVERHEAD
33:
END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING && CONFIG_PPC_SPLPAR */
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */
/*
* A syscall should always be called with interrupts enabled
CURRENT_THREAD_INFO(r11, r1)
ld r10,TI_FLAGS(r11)
andi. r11,r10,_TIF_SYSCALL_T_OR_A
- bne- syscall_dotrace
+ bne syscall_dotrace
.Lsyscall_dotrace_cont:
cmpldi 0,r0,NR_syscalls
bge- syscall_enosys
beq- 1f
ACCOUNT_CPU_USER_EXIT(r11, r12)
+ HMT_MEDIUM_LOW_HAS_PPR
ld r13,GPR13(r1) /* only restore r13 if returning to usermode */
1: ld r2,GPR2(r1)
ld r1,GPR1(r1)
subi r12,r12,TI_FLAGS
4: /* Anything else left to do? */
+ SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */
andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
beq .ret_from_except_lite
std r23,_CCR(r1)
std r1,KSP(r3) /* Set old stack pointer */
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+ /*
+ * Back up the TAR across context switches. Note that the TAR is not
+ * available for use in the kernel. (To provide this, the TAR should
+ * be backed up/restored on exception entry/exit instead, and be in
+ * pt_regs. FIXME, this should be in pt_regs anyway (for debug).)
+ */
+ mfspr r0,SPRN_TAR
+ std r0,THREAD_TAR(r3)
+
+ /* Event based branch registers */
+ mfspr r0, SPRN_BESCR
+ std r0, THREAD_BESCR(r3)
+ mfspr r0, SPRN_EBBHR
+ std r0, THREAD_EBBHR(r3)
+ mfspr r0, SPRN_EBBRR
+ std r0, THREAD_EBBRR(r3)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+#endif
+
#ifdef CONFIG_SMP
/* We need a sync somewhere here to make sure that if the
* previous task gets rescheduled on another CPU, it sees all
mr r1,r8 /* start using new stack pointer */
std r7,PACAKSAVE(r13)
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+ /* Event based branch registers */
+ ld r0, THREAD_BESCR(r4)
+ mtspr SPRN_BESCR, r0
+ ld r0, THREAD_EBBHR(r4)
+ mtspr SPRN_EBBHR, r0
+ ld r0, THREAD_EBBRR(r4)
+ mtspr SPRN_EBBRR, r0
+
+ ld r0,THREAD_TAR(r4)
+ mtspr SPRN_TAR,r0
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+#endif
+
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
ld r0,THREAD_VRSAVE(r4)
/* Clear _TIF_EMULATE_STACK_STORE flag */
lis r11,_TIF_EMULATE_STACK_STORE@h
addi r5,r9,TI_FLAGS
- ldarx r4,0,r5
+0: ldarx r4,0,r5
andc r4,r4,r11
stdcx. r4,0,r5
bne- 0b
andc r4,r4,r0 /* r0 contains MSR_RI here */
mtmsrd r4,1
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* TM debug */
+ std r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
+#endif
/*
* r13 is our per cpu area, only restore it if we are returning to
* userspace the value stored in the stack frame may belong to
andi. r0,r3,MSR_PR
beq 1f
ACCOUNT_CPU_USER_EXIT(r2, r4)
+ RESTORE_PPR(r2, r4)
REST_GPR(13, r1)
1:
mtspr SPRN_SRR1,r3
addi r3,r1,STACK_FRAME_OVERHEAD;
bl .timer_interrupt
b .ret_from_except
+#ifdef CONFIG_PPC_DOORBELL
+1:
#ifdef CONFIG_PPC_BOOK3E
-1: cmpwi cr0,r3,0x280
+ cmpwi cr0,r3,0x280
+#else
+ BEGIN_FTR_SECTION
+ cmpwi cr0,r3,0xe80
+ FTR_SECTION_ELSE
+ cmpwi cr0,r3,0xa00
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
+#endif /* CONFIG_PPC_BOOK3E */
bne 1f
addi r3,r1,STACK_FRAME_OVERHEAD;
bl .doorbell_exception
b .ret_from_except
-#endif /* CONFIG_PPC_BOOK3E */
+#endif /* CONFIG_PPC_DOORBELL */
1: b .ret_from_except /* What else to do here ? */
unrecov_restore:
*
* Given a path increment the reference count to the dentry and the vfsmount.
*/
-void path_get(struct path *path)
+void path_get(const struct path *path)
{
mntget(path->mnt);
dget(path->dentry);
*
* Given a path decrement the reference count to the dentry and the vfsmount.
*/
-void path_put(struct path *path)
+void path_put(const struct path *path)
{
dput(path->dentry);
mntput(path->mnt);
if (likely(!(nd->flags & LOOKUP_JUMPED)))
return 0;
- if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
+ if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
return 0;
- if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
- return 0;
-
- /* Note: we do not d_invalidate() */
- status = d_revalidate(dentry, nd->flags);
+ status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
if (status > 0)
return 0;
nd->path = *path;
nd->inode = nd->path.dentry->d_inode;
nd->flags |= LOOKUP_JUMPED;
-
- BUG_ON(nd->inode->i_op->follow_link);
}
static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
* small and for now I'd prefer to have fast path as straight as possible.
* It _is_ time-critical.
*/
-static int lookup_fast(struct nameidata *nd, struct qstr *name,
+static int lookup_fast(struct nameidata *nd,
struct path *path, struct inode **inode)
{
struct vfsmount *mnt = nd->path.mnt;
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
- dentry = __d_lookup_rcu(parent, name, &seq, nd->inode);
+ dentry = __d_lookup_rcu(parent, &nd->last, &seq, nd->inode);
if (!dentry)
goto unlazy;
if (unlazy_walk(nd, dentry))
return -ECHILD;
} else {
- dentry = __d_lookup(parent, name);
+ dentry = __d_lookup(parent, &nd->last);
}
if (unlikely(!dentry))
}
/* Fast lookup failed, do it the slow way */
-static int lookup_slow(struct nameidata *nd, struct qstr *name,
- struct path *path)
+static int lookup_slow(struct nameidata *nd, struct path *path)
{
struct dentry *dentry, *parent;
int err;
BUG_ON(nd->inode != parent->d_inode);
mutex_lock(&parent->d_inode->i_mutex);
- dentry = __lookup_hash(name, parent, nd->flags);
+ dentry = __lookup_hash(&nd->last, parent, nd->flags);
mutex_unlock(&parent->d_inode->i_mutex);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
}
static inline int walk_component(struct nameidata *nd, struct path *path,
- struct qstr *name, int type, int follow)
+ int follow)
{
struct inode *inode;
int err;
* to be able to know about the current root directory and
* parent relationships.
*/
- if (unlikely(type != LAST_NORM))
- return handle_dots(nd, type);
- err = lookup_fast(nd, name, path, &inode);
+ if (unlikely(nd->last_type != LAST_NORM))
+ return handle_dots(nd, nd->last_type);
+ err = lookup_fast(nd, path, &inode);
if (unlikely(err)) {
if (err < 0)
goto out_err;
- err = lookup_slow(nd, name, path);
+ err = lookup_slow(nd, path);
if (err < 0)
goto out_err;
res = follow_link(&link, nd, &cookie);
if (res)
break;
- res = walk_component(nd, path, &nd->last,
- nd->last_type, LOOKUP_FOLLOW);
+ res = walk_component(nd, path, LOOKUP_FOLLOW);
put_link(nd, &link, cookie);
} while (res > 0);
}
}
+ nd->last = this;
+ nd->last_type = type;
+
if (!name[len])
- goto last_component;
+ return 0;
/*
* If it wasn't NUL, we know it was '/'. Skip that
* slash, and continue until no more slashes.
len++;
} while (unlikely(name[len] == '/'));
if (!name[len])
- goto last_component;
+ return 0;
+
name += len;
- err = walk_component(nd, &next, &this, type, LOOKUP_FOLLOW);
+ err = walk_component(nd, &next, LOOKUP_FOLLOW);
if (err < 0)
return err;
if (err)
return err;
}
- if (can_lookup(nd->inode))
- continue;
- err = -ENOTDIR;
- break;
- /* here ends the main loop */
-
-last_component:
- nd->last = this;
- nd->last_type = type;
- return 0;
+ if (!can_lookup(nd->inode)) {
+ err = -ENOTDIR;
+ break;
+ }
}
terminate_walk(nd);
return err;
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
nd->flags &= ~LOOKUP_PARENT;
- return walk_component(nd, path, &nd->last, nd->last_type,
- nd->flags & LOOKUP_FOLLOW);
+ return walk_component(nd, path, nd->flags & LOOKUP_FOLLOW);
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
symlink_ok = true;
/* we _can_ be in RCU mode here */
- error = lookup_fast(nd, &nd->last, path, &inode);
+ error = lookup_fast(nd, path, &inode);
if (likely(!error))
goto finish_lookup;
if (error)
return error;
- audit_inode(name, dir, 0);
+ audit_inode(name, dir, LOOKUP_PARENT);
error = -EISDIR;
/* trailing slashes? */
if (nd->last.name[nd->last.len])
goto out;
if ((*opened & FILE_CREATED) ||
- !S_ISREG(file->f_path.dentry->d_inode->i_mode))
+ !S_ISREG(file_inode(file)->i_mode))
will_truncate = false;
audit_inode(name, file->f_path.dentry, 0);
int error;
file = get_empty_filp();
- if (!file)
- return ERR_PTR(-ENFILE);
+ if (IS_ERR(file))
+ return file;
file->f_flags = op->open_flag;
#include <linux/cred.h>
#include <linux/llist.h>
#include <linux/uidgid.h>
+#include <linux/gfp.h>
#include <asm/processor.h>
DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned long nr_running(void);
-extern unsigned long nr_uninterruptible(void);
extern unsigned long nr_iowait(void);
extern unsigned long nr_iowait_cpu(int cpu);
extern unsigned long this_cpu_load(void);
extern void proc_sched_set_task(struct task_struct *p);
extern void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
-#else
-static inline void
-proc_sched_show_task(struct task_struct *p, struct seq_file *m)
-{
-}
-static inline void proc_sched_set_task(struct task_struct *p)
-{
-}
-static inline void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
-{
-}
#endif
/*
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
-#define TASK_STATE_MAX 512
+#define TASK_PARKED 512
+#define TASK_STATE_MAX 1024
-#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
extern char ___assert_task_state[1 - 2*!!(
sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
extern int runqueue_is_locked(int cpu);
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void nohz_balance_enter_idle(int cpu);
extern void set_cpu_sd_state_idle(void);
extern int get_nohz_timer_target(void);
}
#endif
-#ifdef CONFIG_DETECT_HUNG_TASK
-extern unsigned int sysctl_hung_task_panic;
-extern unsigned long sysctl_hung_task_check_count;
-extern unsigned long sysctl_hung_task_timeout_secs;
-extern unsigned long sysctl_hung_task_warnings;
-extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos);
-#else
-/* Avoid need for ifdefs elsewhere in the code */
-enum { sysctl_hung_task_timeout_secs = 0 };
-#endif
-
/* Attach to any functions which should be ignored in wchan output. */
#define __sched __attribute__((__section__(".sched.text")))
extern signed long schedule_timeout_uninterruptible(signed long timeout);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
-extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
struct nsproxy;
struct user_namespace;
-/*
- * Default maximum number of active map areas, this limits the number of vmas
- * per mm struct. Users can overwrite this number by sysctl but there is a
- * problem.
- *
- * When a program's coredump is generated as ELF format, a section is created
- * per a vma. In ELF, the number of sections is represented in unsigned short.
- * This means the number of sections should be smaller than 65535 at coredump.
- * Because the kernel adds some informative sections to a image of program at
- * generating coredump, we need some margin. The number of extra sections is
- * 1-3 now and depends on arch. We use "5" as safe margin, here.
- */
-#define MAPCOUNT_ELF_CORE_MARGIN (5)
-#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
-
-extern int sysctl_max_map_count;
-
-#include <linux/aio.h>
-
#ifdef CONFIG_MMU
extern void arch_pick_mmap_layout(struct mm_struct *mm);
extern unsigned long
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
-/* get/set_dumpable() values */
-#define SUID_DUMPABLE_DISABLED 0
-#define SUID_DUMPABLE_ENABLED 1
-#define SUID_DUMPABLE_SAFE 2
-
/* mm flags */
/* dumpable bits */
#define MMF_DUMPABLE 0 /* core dump is permitted */
unsigned int has_child_subreaper:1;
/* POSIX.1b Interval Timers */
- struct list_head posix_timers;
+ int posix_timer_id;
+ struct list_head posix_timers;
/* ITIMER_REAL timer for the process */
struct hrtimer real_timer;
cputime_t utime, stime, cutime, cstime;
cputime_t gtime;
cputime_t cgtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
struct cputime prev_cputime;
#endif
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
#endif
#ifdef CONFIG_AUDIT
unsigned audit_tty;
+ unsigned audit_tty_log_passwd;
struct tty_audit_buf *tty_audit_buf;
#endif
#ifdef CONFIG_CGROUPS
#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */
+#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */
/*
* Pending notifications to parent.
*/
CPU_MAX_IDLE_TYPES
};
-/*
- * Increase resolution of nice-level calculations for 64-bit architectures.
- * The extra resolution improves shares distribution and load balancing of
- * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
- * hierarchies, especially on larger systems. This is not a user-visible change
- * and does not change the user-interface for setting shares/weights.
- *
- * We increase resolution only if we have enough bits to allow this increased
- * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
- * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
- * increased costs.
- */
-#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */
-# define SCHED_LOAD_RESOLUTION 10
-# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION)
-# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION)
-#else
-# define SCHED_LOAD_RESOLUTION 0
-# define scale_load(w) (w)
-# define scale_load_down(w) (w)
-#endif
-
-#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION)
-#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT)
-
/*
* Increase resolution of cpu_power calculations
*/
extern int __weak arch_sd_sibiling_asym_packing(void);
-struct sched_group_power {
- atomic_t ref;
- /*
- * CPU power of this group, SCHED_LOAD_SCALE being max power for a
- * single CPU.
- */
- unsigned int power, power_orig;
- unsigned long next_update;
- /*
- * Number of busy cpus in this group.
- */
- atomic_t nr_busy_cpus;
-
- unsigned long cpumask[0]; /* iteration mask */
-};
-
-struct sched_group {
- struct sched_group *next; /* Must be a circular list */
- atomic_t ref;
-
- unsigned int group_weight;
- struct sched_group_power *sgp;
-
- /*
- * The CPUs this group covers.
- *
- * NOTE: this field is variable length. (Allocated dynamically
- * by attaching extra space to the end of the structure,
- * depending on how many CPUs the kernel has booted up with)
- */
- unsigned long cpumask[0];
-};
-
-static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
-{
- return to_cpumask(sg->cpumask);
-}
-
-/*
- * cpumask masking which cpus in the group are allowed to iterate up the domain
- * tree.
- */
-static inline struct cpumask *sched_group_mask(struct sched_group *sg)
-{
- return to_cpumask(sg->sgp->cpumask);
-}
-
-/**
- * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
- * @group: The group whose first cpu is to be returned.
- */
-static inline unsigned int group_first_cpu(struct sched_group *group)
-{
- return cpumask_first(sched_group_cpus(group));
-}
-
struct sched_domain_attr {
int relax_domain_level;
};
extern int sched_domain_level_max;
+struct sched_group;
+
struct sched_domain {
/* These fields must be setup */
struct sched_domain *parent; /* top domain must be null terminated */
unsigned int wake_idx;
unsigned int forkexec_idx;
unsigned int smt_gain;
+
+ int nohz_idle; /* NOHZ IDLE status */
int flags; /* See SD_* */
int level;
cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
-/* Test a flag in parent sched domain */
-static inline int test_sd_parent(struct sched_domain *sd, int flag)
-{
- if (sd->parent && (sd->parent->flags & flag))
- return 1;
-
- return 0;
-}
-
-unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
-unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
-
bool cpus_share_cache(int this_cpu, int that_cpu);
#else /* CONFIG_SMP */
struct pipe_inode_info;
struct uts_namespace;
-struct rq;
-struct sched_domain;
-
-/*
- * wake flags
- */
-#define WF_SYNC 0x01 /* waker goes to sleep after wakup */
-#define WF_FORK 0x02 /* child wakeup after fork */
-#define WF_MIGRATED 0x04 /* internal use, task got migrated */
-
-#define ENQUEUE_WAKEUP 1
-#define ENQUEUE_HEAD 2
-#ifdef CONFIG_SMP
-#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */
-#else
-#define ENQUEUE_WAKING 0
-#endif
-
-#define DEQUEUE_SLEEP 1
-
-struct sched_class {
- const struct sched_class *next;
-
- void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
- void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
- void (*yield_task) (struct rq *rq);
- bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
-
- void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
-
- struct task_struct * (*pick_next_task) (struct rq *rq);
- void (*put_prev_task) (struct rq *rq, struct task_struct *p);
-
-#ifdef CONFIG_SMP
- int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
- void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
-
- void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
- void (*post_schedule) (struct rq *this_rq);
- void (*task_waking) (struct task_struct *task);
- void (*task_woken) (struct rq *this_rq, struct task_struct *task);
-
- void (*set_cpus_allowed)(struct task_struct *p,
- const struct cpumask *newmask);
-
- void (*rq_online)(struct rq *rq);
- void (*rq_offline)(struct rq *rq);
-#endif
-
- void (*set_curr_task) (struct rq *rq);
- void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
- void (*task_fork) (struct task_struct *p);
-
- void (*switched_from) (struct rq *this_rq, struct task_struct *task);
- void (*switched_to) (struct rq *this_rq, struct task_struct *task);
- void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
- int oldprio);
-
- unsigned int (*get_rr_interval) (struct rq *rq,
- struct task_struct *task);
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
- void (*task_move_group) (struct task_struct *p, int on_rq);
-#endif
-};
-
struct load_weight {
unsigned long weight, inv_weight;
};
/* rq "owned" by this entity/group: */
struct cfs_rq *my_q;
#endif
+
/*
* Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
* removed when useful for applications beyond shares distribution (e.g.
struct sched_rt_entity {
struct list_head run_list;
unsigned long timeout;
+ unsigned long watchdog_stamp;
unsigned int time_slice;
struct sched_rt_entity *back;
#endif
};
-/*
- * default timeslice is 100 msecs (used only for SCHED_RR tasks).
- * Timeslices get refilled after they expire.
- */
-#define RR_TIMESLICE (100 * HZ / 1000)
struct rcu_node;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
unsigned int jobctl; /* JOBCTL_*, siglock protected */
- /* ??? */
+
+ /* Used for emulating ABI behavior of previous Linux versions */
unsigned int personality;
+
unsigned did_exec:1;
unsigned in_execve:1; /* Tell the LSMs that the process is doing an
* execve */
cputime_t utime, stime, utimescaled, stimescaled;
cputime_t gtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
struct cputime prev_cputime;
+#endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+ seqlock_t vtime_seqlock;
+ unsigned long long vtime_snap;
+ enum {
+ VTIME_SLEEPING = 0,
+ VTIME_USER,
+ VTIME_SYS,
+ } vtime_snap_whence;
#endif
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time; /* monotonic time */
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
#endif
+#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
+ unsigned int sequential_io;
+ unsigned int sequential_io_avg;
+#endif
};
/* Future-safe accessor for struct task_struct's cpus_allowed. */
}
#endif
-/*
- * Priority of a process goes from 0..MAX_PRIO-1, valid RT
- * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
- * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
- * values are inverted: lower p->prio value means higher priority.
- *
- * The MAX_USER_RT_PRIO value allows the actual maximum
- * RT priority to be separate from the value exported to
- * user-space. This allows kernel threads to set their
- * priority to a value higher than any user task. Note:
- * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
- */
-
-#define MAX_USER_RT_PRIO 100
-#define MAX_RT_PRIO MAX_USER_RT_PRIO
-
-#define MAX_PRIO (MAX_RT_PRIO + 40)
-#define DEFAULT_PRIO (MAX_RT_PRIO + 20)
-
-static inline int rt_prio(int prio)
-{
- if (unlikely(prio < MAX_RT_PRIO))
- return 1;
- return 0;
-}
-
-static inline int rt_task(struct task_struct *p)
-{
- return rt_prio(p->prio);
-}
-
static inline struct pid *task_pid(struct task_struct *task)
{
return task->pids[PIDTYPE_PID].pid;
__put_task_struct(t);
}
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern void task_cputime(struct task_struct *t,
+ cputime_t *utime, cputime_t *stime);
+extern void task_cputime_scaled(struct task_struct *t,
+ cputime_t *utimescaled, cputime_t *stimescaled);
+extern cputime_t task_gtime(struct task_struct *t);
+#else
+static inline void task_cputime(struct task_struct *t,
+ cputime_t *utime, cputime_t *stime)
+{
+ if (utime)
+ *utime = t->utime;
+ if (stime)
+ *stime = t->stime;
+}
+
+static inline void task_cputime_scaled(struct task_struct *t,
+ cputime_t *utimescaled,
+ cputime_t *stimescaled)
+{
+ if (utimescaled)
+ *utimescaled = t->utimescaled;
+ if (stimescaled)
+ *stimescaled = t->stimescaled;
+}
+
+static inline cputime_t task_gtime(struct task_struct *t)
+{
+ return t->gtime;
+}
+#endif
extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
#define PF_FROZEN 0x00010000 /* frozen for system suspend */
#define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */
#define PF_KSWAPD 0x00040000 /* I am kswapd */
+#define PF_MEMALLOC_NOIO 0x00080000 /* Allocating memory without IO involved */
#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
#define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */
#define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */
-#define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */
+#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+static inline gfp_t memalloc_noio_flags(gfp_t flags)
+{
+ if (unlikely(current->flags & PF_MEMALLOC_NOIO))
+ flags &= ~__GFP_IO;
+ return flags;
+}
+
+static inline unsigned int memalloc_noio_save(void)
+{
+ unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
+ current->flags |= PF_MEMALLOC_NOIO;
+ return flags;
+}
+
+static inline void memalloc_noio_restore(unsigned int flags)
+{
+ current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
+}
+
/*
* task->jobctl flags
*/
}
#endif
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
void calc_load_enter_idle(void);
void calc_load_exit_idle(void);
#else
static inline void calc_load_enter_idle(void) { }
static inline void calc_load_exit_idle(void) { }
-#endif /* CONFIG_NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
#ifndef CONFIG_CPUMASK_OFFSTACK
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
static inline void idle_task_exit(void) {}
#endif
-#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
-extern void wake_up_idle_cpu(int cpu);
+#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
+extern void wake_up_nohz_cpu(int cpu);
#else
-static inline void wake_up_idle_cpu(int cpu) { }
+static inline void wake_up_nohz_cpu(int cpu) { }
#endif
-extern unsigned int sysctl_sched_latency;
-extern unsigned int sysctl_sched_min_granularity;
-extern unsigned int sysctl_sched_wakeup_granularity;
-extern unsigned int sysctl_sched_child_runs_first;
-
-enum sched_tunable_scaling {
- SCHED_TUNABLESCALING_NONE,
- SCHED_TUNABLESCALING_LOG,
- SCHED_TUNABLESCALING_LINEAR,
- SCHED_TUNABLESCALING_END,
-};
-extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
-
-extern unsigned int sysctl_numa_balancing_scan_delay;
-extern unsigned int sysctl_numa_balancing_scan_period_min;
-extern unsigned int sysctl_numa_balancing_scan_period_max;
-extern unsigned int sysctl_numa_balancing_scan_period_reset;
-extern unsigned int sysctl_numa_balancing_scan_size;
-extern unsigned int sysctl_numa_balancing_settle_count;
-
-#ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_migration_cost;
-extern unsigned int sysctl_sched_nr_migrate;
-extern unsigned int sysctl_sched_time_avg;
-extern unsigned int sysctl_timer_migration;
-extern unsigned int sysctl_sched_shares_window;
-
-int sched_proc_update_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length,
- loff_t *ppos);
-#endif
-#ifdef CONFIG_SCHED_DEBUG
-static inline unsigned int get_sysctl_timer_migration(void)
-{
- return sysctl_timer_migration;
-}
+#ifdef CONFIG_NO_HZ_FULL
+extern bool sched_can_stop_tick(void);
+extern u64 scheduler_tick_max_deferment(void);
#else
-static inline unsigned int get_sysctl_timer_migration(void)
-{
- return 1;
-}
+static inline bool sched_can_stop_tick(void) { return false; }
#endif
-extern unsigned int sysctl_sched_rt_period;
-extern int sysctl_sched_rt_runtime;
-
-int sched_rt_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos);
#ifdef CONFIG_SCHED_AUTOGROUP
-extern unsigned int sysctl_sched_autogroup_enabled;
-
extern void sched_autogroup_create_attach(struct task_struct *p);
extern void sched_autogroup_detach(struct task_struct *p);
extern void sched_autogroup_fork(struct signal_struct *sig);
static inline void sched_autogroup_exit(struct signal_struct *sig) { }
#endif
-#ifdef CONFIG_CFS_BANDWIDTH
-extern unsigned int sysctl_sched_cfs_bandwidth_slice;
-#endif
-
-#ifdef CONFIG_RT_MUTEXES
-extern int rt_mutex_getprio(struct task_struct *p);
-extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern void rt_mutex_adjust_pi(struct task_struct *p);
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
- return tsk->pi_blocked_on != NULL;
-}
-#else
-static inline int rt_mutex_getprio(struct task_struct *p)
-{
- return p->normal_prio;
-}
-# define rt_mutex_adjust_pi(p) do { } while (0)
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
- return false;
-}
-#endif
-
extern bool yield_to(struct task_struct *p, bool preempt);
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
extern void sigqueue_free(struct sigqueue *);
extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group);
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
-extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);
static inline void restore_saved_sigmask(void)
{
: on_sig_stack(sp) ? SS_ONSTACK : 0);
}
+static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
+{
+ if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp))
+#ifdef CONFIG_STACK_GROWSUP
+ return current->sas_ss_sp;
+#else
+ return current->sas_ss_sp + current->sas_ss_size;
+#endif
+ return sp;
+}
+
/*
* Routines for handling mm_structs
*/
*
* Lock the threadgroup @tsk belongs to. No new task is allowed to enter
* and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
- * perform exec. This is useful for cases where the threadgroup needs to
- * stay stable across blockable operations.
+ * change ->group_leader/pid. This is useful for cases where the threadgroup
+ * needs to stay stable across blockable operations.
*
* fork and exit paths explicitly call threadgroup_change_{begin|end}() for
* synchronization. While held, no new task will be added to threadgroup
* and no existing live task will have its PF_EXITING set.
*
- * During exec, a task goes and puts its thread group through unusual
- * changes. After de-threading, exclusive access is assumed to resources
- * which are usually shared by tasks in the same group - e.g. sighand may
- * be replaced with a new one. Also, the exec'ing task takes over group
- * leader role including its pid. Exclude these changes while locked by
- * grabbing cred_guard_mutex which is used to synchronize exec path.
+ * de_thread() does threadgroup_change_{begin|end}() when a non-leader
+ * sub-thread becomes a new leader.
*/
static inline void threadgroup_lock(struct task_struct *tsk)
{
- /*
- * exec uses exit for de-threading nesting group_rwsem inside
- * cred_guard_mutex. Grab cred_guard_mutex first.
- */
- mutex_lock(&tsk->signal->cred_guard_mutex);
down_write(&tsk->signal->group_rwsem);
}
static inline void threadgroup_unlock(struct task_struct *tsk)
{
up_write(&tsk->signal->group_rwsem);
- mutex_unlock(&tsk->signal->cred_guard_mutex);
}
#else
static inline void threadgroup_change_begin(struct task_struct *tsk) {}
#endif
}
+/*
+ * Idle thread specific functions to determine the need_resched
+ * polling state. We have two versions, one based on TS_POLLING in
+ * thread_info.status and one based on TIF_POLLING_NRFLAG in
+ * thread_info.flags
+ */
+#ifdef TS_POLLING
+static inline int tsk_is_polling(struct task_struct *p)
+{
+ return task_thread_info(p)->status & TS_POLLING;
+}
+static inline void current_set_polling(void)
+{
+ current_thread_info()->status |= TS_POLLING;
+}
+
+static inline void current_clr_polling(void)
+{
+ current_thread_info()->status &= ~TS_POLLING;
+ smp_mb__after_clear_bit();
+}
+#elif defined(TIF_POLLING_NRFLAG)
+static inline int tsk_is_polling(struct task_struct *p)
+{
+ return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
+}
+static inline void current_set_polling(void)
+{
+ set_thread_flag(TIF_POLLING_NRFLAG);
+}
+
+static inline void current_clr_polling(void)
+{
+ clear_thread_flag(TIF_POLLING_NRFLAG);
+}
+#else
+static inline int tsk_is_polling(struct task_struct *p) { return 0; }
+static inline void current_set_polling(void) { }
+static inline void current_clr_polling(void) { }
+#endif
+
/*
* Thread group CPU time accounting.
*/
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
-extern void normalize_rt_tasks(void);
-
#ifdef CONFIG_CGROUP_SCHED
-
extern struct task_group root_task_group;
-
-extern struct task_group *sched_create_group(struct task_group *parent);
-extern void sched_destroy_group(struct task_group *tg);
-extern void sched_move_task(struct task_struct *tsk);
-#ifdef CONFIG_FAIR_GROUP_SCHED
-extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
-extern unsigned long sched_group_shares(struct task_group *tg);
-#endif
-#ifdef CONFIG_RT_GROUP_SCHED
-extern int sched_group_set_rt_runtime(struct task_group *tg,
- long rt_runtime_us);
-extern long sched_group_rt_runtime(struct task_group *tg);
-extern int sched_group_set_rt_period(struct task_group *tg,
- long rt_period_us);
-extern long sched_group_rt_period(struct task_group *tg);
-extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
-#endif
#endif /* CONFIG_CGROUP_SCHED */
extern int task_can_switch_user(struct user_struct *up,
unsigned long iflags; /* TTYP_ internal flags */
#define TTYP_FLUSHING 1 /* Flushing to ldisc in progress */
#define TTYP_FLUSHPENDING 2 /* Queued buffer flush pending */
- unsigned char console:1; /* port is a console */
+ unsigned char console:1, /* port is a console */
+ low_latency:1; /* direct buffer flush */
struct mutex mutex; /* Locking */
struct mutex buf_mutex; /* Buffer alloc lock */
unsigned char *xmit_buf; /* Optional buffer */
int count;
struct winsize winsize; /* termios mutex */
unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1;
- unsigned char low_latency:1, warned:1;
unsigned char ctrl_status; /* ctrl_lock */
unsigned int receive_room; /* Bytes free for queue */
+ int flow_change;
struct tty_struct *link;
struct fasync_struct *fasync;
#define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */
#define TTY_HUPPED 18 /* Post driver->hangup() */
#define TTY_HUPPING 21 /* ->hangup() in progress */
+#define TTY_LDISC_HALTED 22 /* Line discipline is halted */
#define TTY_WRITE_FLUSH(tty) tty_write_flush((tty))
+/* Values for tty->flow_change */
+#define TTY_THROTTLE_SAFE 1
+#define TTY_UNTHROTTLE_SAFE 2
+
+static inline void __tty_set_flow_change(struct tty_struct *tty, int val)
+{
+ tty->flow_change = val;
+}
+
+static inline void tty_set_flow_change(struct tty_struct *tty, int val)
+{
+ tty->flow_change = val;
+ smp_mb();
+}
+
+#ifdef CONFIG_TTY
+extern void console_init(void);
+extern void tty_kref_put(struct tty_struct *tty);
+extern struct pid *tty_get_pgrp(struct tty_struct *tty);
+extern void tty_vhangup_self(void);
+extern void disassociate_ctty(int priv);
+extern dev_t tty_devnum(struct tty_struct *tty);
+extern void proc_clear_tty(struct task_struct *p);
+extern struct tty_struct *get_current_tty(void);
+/* tty_io.c */
+extern int __init tty_init(void);
+#else
+static inline void console_init(void)
+{ }
+static inline void tty_kref_put(struct tty_struct *tty)
+{ }
+static inline struct pid *tty_get_pgrp(struct tty_struct *tty)
+{ return NULL; }
+static inline void tty_vhangup_self(void)
+{ }
+static inline void disassociate_ctty(int priv)
+{ }
+static inline dev_t tty_devnum(struct tty_struct *tty)
+{ return 0; }
+static inline void proc_clear_tty(struct task_struct *p)
+{ }
+static inline struct tty_struct *get_current_tty(void)
+{ return NULL; }
+/* tty_io.c */
+static inline int __init tty_init(void)
+{ return 0; }
+#endif
+
extern void tty_write_flush(struct tty_struct *);
extern struct ktermios tty_std_termios;
-extern void console_init(void);
extern int vcs_init(void);
extern struct class *tty_class;
kref_get(&tty->kref);
return tty;
}
-extern void tty_kref_put(struct tty_struct *tty);
extern int tty_paranoia_check(struct tty_struct *tty, struct inode *inode,
const char *routine);
extern void tty_driver_flush_buffer(struct tty_struct *tty);
extern void tty_throttle(struct tty_struct *tty);
extern void tty_unthrottle(struct tty_struct *tty);
+extern int tty_throttle_safe(struct tty_struct *tty);
+extern int tty_unthrottle_safe(struct tty_struct *tty);
extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws);
extern void tty_driver_remove_tty(struct tty_driver *driver,
struct tty_struct *tty);
extern void tty_free_termios(struct tty_struct *tty);
extern int is_current_pgrp_orphaned(void);
-extern struct pid *tty_get_pgrp(struct tty_struct *tty);
extern int is_ignored(int sig);
extern int tty_signal(int sig, struct tty_struct *tty);
extern void tty_hangup(struct tty_struct *tty);
extern void tty_vhangup(struct tty_struct *tty);
extern void tty_vhangup_locked(struct tty_struct *tty);
-extern void tty_vhangup_self(void);
extern void tty_unhangup(struct file *filp);
extern int tty_hung_up_p(struct file *filp);
extern void do_SAK(struct tty_struct *tty);
extern void __do_SAK(struct tty_struct *tty);
-extern void disassociate_ctty(int priv);
extern void no_tty(void);
-extern void tty_flip_buffer_push(struct tty_struct *tty);
extern void tty_flush_to_ldisc(struct tty_struct *tty);
extern void tty_buffer_free_all(struct tty_port *port);
extern void tty_buffer_flush(struct tty_struct *tty);
extern void tty_buffer_init(struct tty_port *port);
-extern speed_t tty_get_baud_rate(struct tty_struct *tty);
extern speed_t tty_termios_baud_rate(struct ktermios *termios);
extern speed_t tty_termios_input_baud_rate(struct ktermios *termios);
extern void tty_termios_encode_baud_rate(struct ktermios *termios,
speed_t ibaud, speed_t obaud);
extern void tty_encode_baud_rate(struct tty_struct *tty,
speed_t ibaud, speed_t obaud);
+
+/**
+ * tty_get_baud_rate - get tty bit rates
+ * @tty: tty to query
+ *
+ * Returns the baud rate as an integer for this terminal. The
+ * termios lock must be held by the caller and the terminal bit
+ * flags may be updated.
+ *
+ * Locking: none
+ */
+static inline speed_t tty_get_baud_rate(struct tty_struct *tty)
+{
+ return tty_termios_baud_rate(&tty->termios);
+}
+
extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old);
extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b);
extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt);
extern int tty_mode_ioctl(struct tty_struct *tty, struct file *file,
unsigned int cmd, unsigned long arg);
extern int tty_perform_flush(struct tty_struct *tty, unsigned long arg);
-extern dev_t tty_devnum(struct tty_struct *tty);
-extern void proc_clear_tty(struct task_struct *p);
-extern struct tty_struct *get_current_tty(void);
extern void tty_default_fops(struct file_operations *fops);
extern struct tty_struct *alloc_tty_struct(void);
extern int tty_alloc_file(struct file *file);
extern void tty_port_raise_dtr_rts(struct tty_port *port);
extern void tty_port_lower_dtr_rts(struct tty_port *port);
extern void tty_port_hangup(struct tty_port *port);
+extern void tty_port_tty_hangup(struct tty_port *port, bool check_clocal);
+extern void tty_port_tty_wakeup(struct tty_port *port);
extern int tty_port_block_til_ready(struct tty_port *port,
struct tty_struct *tty, struct file *filp);
extern int tty_port_close_start(struct tty_port *port,
extern void tty_ldisc_init(struct tty_struct *tty);
extern void tty_ldisc_deinit(struct tty_struct *tty);
extern void tty_ldisc_begin(void);
-/* This last one is just for the tty layer internals and shouldn't be used elsewhere */
-extern void tty_ldisc_enable(struct tty_struct *tty);
/* n_tty.c */
extern void tty_audit_fork(struct signal_struct *sig);
extern void tty_audit_tiocsti(struct tty_struct *tty, char ch);
extern void tty_audit_push(struct tty_struct *tty);
- extern int tty_audit_push_task(struct task_struct *tsk,
- kuid_t loginuid, u32 sessionid);
+ extern int tty_audit_push_current(void);
#else
static inline void tty_audit_add_data(struct tty_struct *tty,
unsigned char *data, size_t size, unsigned icanon)
static inline void tty_audit_push(struct tty_struct *tty)
{
}
- static inline int tty_audit_push_task(struct task_struct *tsk,
- kuid_t loginuid, u32 sessionid)
+ static inline int tty_audit_push_current(void)
{
return 0;
}
#endif
-/* tty_io.c */
-extern int __init tty_init(void);
-
/* tty_ioctl.c */
extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file,
unsigned int cmd, unsigned long arg);
finish_wait(&wq, &__wait); \
} while (0)
+#ifdef CONFIG_PROC_FS
+extern void proc_tty_register_driver(struct tty_driver *);
+extern void proc_tty_unregister_driver(struct tty_driver *);
+#else
+static inline void proc_tty_register_driver(struct tty_driver *d) {}
+static inline void proc_tty_unregister_driver(struct tty_driver *d) {}
+#endif
#endif
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/kthread.h>
+ #include <linux/kernel.h>
+ #include <linux/syscalls.h>
#include <linux/audit.h>
#ifdef CONFIG_SECURITY
#include <linux/security.h>
#endif
-#include <linux/netlink.h>
+#include <net/netlink.h>
#include <linux/freezer.h>
#include <linux/tty.h>
#include <linux/pid_namespace.h>
}
static int audit_log_config_change(char *function_name, int new, int old,
- kuid_t loginuid, u32 sessionid, u32 sid,
int allow_changes)
{
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return rc;
- audit_log_format(ab, "%s=%d old=%d auid=%u ses=%u", function_name, new,
- old, from_kuid(&init_user_ns, loginuid), sessionid);
- if (sid) {
- char *ctx = NULL;
- u32 len;
-
- rc = security_secid_to_secctx(sid, &ctx, &len);
- if (rc) {
- audit_log_format(ab, " sid=%u", sid);
- allow_changes = 0; /* Something weird, deny request */
- } else {
- audit_log_format(ab, " subj=%s", ctx);
- security_release_secctx(ctx, len);
- }
- }
+ audit_log_format(ab, "%s=%d old=%d", function_name, new, old);
+ audit_log_session_info(ab);
+ rc = audit_log_task_context(ab);
+ if (rc)
+ allow_changes = 0; /* Something weird, deny request */
audit_log_format(ab, " res=%d", allow_changes);
audit_log_end(ab);
return rc;
}
- static int audit_do_config_change(char *function_name, int *to_change,
- int new, kuid_t loginuid, u32 sessionid,
- u32 sid)
+ static int audit_do_config_change(char *function_name, int *to_change, int new)
{
int allow_changes, rc = 0, old = *to_change;
allow_changes = 1;
if (audit_enabled != AUDIT_OFF) {
- rc = audit_log_config_change(function_name, new, old, loginuid,
- sessionid, sid, allow_changes);
+ rc = audit_log_config_change(function_name, new, old, allow_changes);
if (rc)
allow_changes = 0;
}
return rc;
}
- static int audit_set_rate_limit(int limit, kuid_t loginuid, u32 sessionid,
- u32 sid)
+ static int audit_set_rate_limit(int limit)
{
- return audit_do_config_change("audit_rate_limit", &audit_rate_limit,
- limit, loginuid, sessionid, sid);
+ return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit);
}
- static int audit_set_backlog_limit(int limit, kuid_t loginuid, u32 sessionid,
- u32 sid)
+ static int audit_set_backlog_limit(int limit)
{
- return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit,
- limit, loginuid, sessionid, sid);
+ return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit);
}
- static int audit_set_enabled(int state, kuid_t loginuid, u32 sessionid, u32 sid)
+ static int audit_set_enabled(int state)
{
int rc;
if (state < AUDIT_OFF || state > AUDIT_LOCKED)
return -EINVAL;
- rc = audit_do_config_change("audit_enabled", &audit_enabled, state,
- loginuid, sessionid, sid);
-
+ rc = audit_do_config_change("audit_enabled", &audit_enabled, state);
if (!rc)
audit_ever_enabled |= !!state;
return rc;
}
- static int audit_set_failure(int state, kuid_t loginuid, u32 sessionid, u32 sid)
+ static int audit_set_failure(int state)
{
if (state != AUDIT_FAIL_SILENT
&& state != AUDIT_FAIL_PRINTK
&& state != AUDIT_FAIL_PANIC)
return -EINVAL;
- return audit_do_config_change("audit_failure", &audit_failure, state,
- loginuid, sessionid, sid);
+ return audit_do_config_change("audit_failure", &audit_failure, state);
}
/*
consume_skb(skb);
}
- static int kauditd_thread(void *dummy)
+ /*
+ * flush_hold_queue - empty the hold queue if auditd appears
+ *
+ * If auditd just started, drain the queue of messages already
+ * sent to syslog/printk. Remember loss here is ok. We already
+ * called audit_log_lost() if it didn't go out normally. so the
+ * race between the skb_dequeue and the next check for audit_pid
+ * doesn't matter.
+ *
+ * If you ever find kauditd to be too slow we can get a perf win
+ * by doing our own locking and keeping better track if there
+ * are messages in this queue. I don't see the need now, but
+ * in 5 years when I want to play with this again I'll see this
+ * note and still have no friggin idea what i'm thinking today.
+ */
+ static void flush_hold_queue(void)
{
struct sk_buff *skb;
+ if (!audit_default || !audit_pid)
+ return;
+
+ skb = skb_dequeue(&audit_skb_hold_queue);
+ if (likely(!skb))
+ return;
+
+ while (skb && audit_pid) {
+ kauditd_send_skb(skb);
+ skb = skb_dequeue(&audit_skb_hold_queue);
+ }
+
+ /*
+ * if auditd just disappeared but we
+ * dequeued an skb we need to drop ref
+ */
+ if (skb)
+ consume_skb(skb);
+ }
+
+ static int kauditd_thread(void *dummy)
+ {
set_freezable();
while (!kthread_should_stop()) {
- /*
- * if auditd just started drain the queue of messages already
- * sent to syslog/printk. remember loss here is ok. we already
- * called audit_log_lost() if it didn't go out normally. so the
- * race between the skb_dequeue and the next check for audit_pid
- * doesn't matter.
- *
- * if you ever find kauditd to be too slow we can get a perf win
- * by doing our own locking and keeping better track if there
- * are messages in this queue. I don't see the need now, but
- * in 5 years when I want to play with this again I'll see this
- * note and still have no friggin idea what i'm thinking today.
- */
- if (audit_default && audit_pid) {
- skb = skb_dequeue(&audit_skb_hold_queue);
- if (unlikely(skb)) {
- while (skb && audit_pid) {
- kauditd_send_skb(skb);
- skb = skb_dequeue(&audit_skb_hold_queue);
- }
- }
- }
+ struct sk_buff *skb;
+ DECLARE_WAITQUEUE(wait, current);
+
+ flush_hold_queue();
skb = skb_dequeue(&audit_skb_queue);
wake_up(&audit_backlog_wait);
kauditd_send_skb(skb);
else
audit_printk_skb(skb);
- } else {
- DECLARE_WAITQUEUE(wait, current);
- set_current_state(TASK_INTERRUPTIBLE);
- add_wait_queue(&kauditd_wait, &wait);
-
- if (!skb_queue_len(&audit_skb_queue)) {
- try_to_freeze();
- schedule();
- }
+ continue;
+ }
+ set_current_state(TASK_INTERRUPTIBLE);
+ add_wait_queue(&kauditd_wait, &wait);
- __set_current_state(TASK_RUNNING);
- remove_wait_queue(&kauditd_wait, &wait);
+ if (!skb_queue_len(&audit_skb_queue)) {
+ try_to_freeze();
+ schedule();
}
+
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&kauditd_wait, &wait);
}
return 0;
}
return -EPERM;
switch (msg_type) {
- case AUDIT_GET:
case AUDIT_LIST:
- case AUDIT_LIST_RULES:
- case AUDIT_SET:
case AUDIT_ADD:
- case AUDIT_ADD_RULE:
case AUDIT_DEL:
+ return -EOPNOTSUPP;
+ case AUDIT_GET:
+ case AUDIT_SET:
+ case AUDIT_LIST_RULES:
+ case AUDIT_ADD_RULE:
case AUDIT_DEL_RULE:
case AUDIT_SIGNAL_INFO:
case AUDIT_TTY_GET:
return err;
}
- static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type,
- kuid_t auid, u32 ses, u32 sid)
+ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
{
int rc = 0;
- char *ctx = NULL;
- u32 len;
+ uid_t uid = from_kuid(&init_user_ns, current_uid());
if (!audit_enabled) {
*ab = NULL;
*ab = audit_log_start(NULL, GFP_KERNEL, msg_type);
if (unlikely(!*ab))
return rc;
- audit_log_format(*ab, "pid=%d uid=%u auid=%u ses=%u",
- task_tgid_vnr(current),
- from_kuid(&init_user_ns, current_uid()),
- from_kuid(&init_user_ns, auid), ses);
- if (sid) {
- rc = security_secid_to_secctx(sid, &ctx, &len);
- if (rc)
- audit_log_format(*ab, " ssid=%u", sid);
- else {
- audit_log_format(*ab, " subj=%s", ctx);
- security_release_secctx(ctx, len);
- }
- }
+ audit_log_format(*ab, "pid=%d uid=%u", task_tgid_vnr(current), uid);
+ audit_log_session_info(*ab);
+ audit_log_task_context(*ab);
return rc;
}
static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
- u32 seq, sid;
+ u32 seq;
void *data;
struct audit_status *status_get, status_set;
int err;
struct audit_buffer *ab;
u16 msg_type = nlh->nlmsg_type;
- kuid_t loginuid; /* loginuid of sender */
- u32 sessionid;
struct audit_sig_info *sig_data;
char *ctx = NULL;
u32 len;
/* As soon as there's any sign of userspace auditd,
* start kauditd to talk to it */
- if (!kauditd_task)
+ if (!kauditd_task) {
kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd");
- if (IS_ERR(kauditd_task)) {
- err = PTR_ERR(kauditd_task);
- kauditd_task = NULL;
- return err;
+ if (IS_ERR(kauditd_task)) {
+ err = PTR_ERR(kauditd_task);
+ kauditd_task = NULL;
+ return err;
+ }
}
- loginuid = audit_get_loginuid(current);
- sessionid = audit_get_sessionid(current);
- security_task_getsecid(current, &sid);
-
seq = nlh->nlmsg_seq;
data = nlmsg_data(nlh);
return -EINVAL;
status_get = (struct audit_status *)data;
if (status_get->mask & AUDIT_STATUS_ENABLED) {
- err = audit_set_enabled(status_get->enabled,
- loginuid, sessionid, sid);
+ err = audit_set_enabled(status_get->enabled);
if (err < 0)
return err;
}
if (status_get->mask & AUDIT_STATUS_FAILURE) {
- err = audit_set_failure(status_get->failure,
- loginuid, sessionid, sid);
+ err = audit_set_failure(status_get->failure);
if (err < 0)
return err;
}
int new_pid = status_get->pid;
if (audit_enabled != AUDIT_OFF)
- audit_log_config_change("audit_pid", new_pid,
- audit_pid, loginuid,
- sessionid, sid, 1);
-
+ audit_log_config_change("audit_pid", new_pid, audit_pid, 1);
audit_pid = new_pid;
audit_nlk_portid = NETLINK_CB(skb).portid;
}
if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) {
- err = audit_set_rate_limit(status_get->rate_limit,
- loginuid, sessionid, sid);
+ err = audit_set_rate_limit(status_get->rate_limit);
if (err < 0)
return err;
}
if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
- err = audit_set_backlog_limit(status_get->backlog_limit,
- loginuid, sessionid, sid);
+ err = audit_set_backlog_limit(status_get->backlog_limit);
break;
case AUDIT_USER:
case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
if (!audit_enabled && msg_type != AUDIT_USER_AVC)
return 0;
- err = audit_filter_user();
+ err = audit_filter_user(msg_type);
if (err == 1) {
err = 0;
if (msg_type == AUDIT_USER_TTY) {
- err = tty_audit_push_task(current, loginuid,
- sessionid);
+ err = tty_audit_push_current();
if (err)
break;
}
- audit_log_common_recv_msg(&ab, msg_type,
- loginuid, sessionid, sid);
-
+ audit_log_common_recv_msg(&ab, msg_type);
if (msg_type != AUDIT_USER_TTY)
audit_log_format(ab, " msg='%.1024s'",
(char *)data);
else {
int size;
- audit_log_format(ab, " msg=");
+ audit_log_format(ab, " data=");
size = nlmsg_len(nlh);
if (size > 0 &&
((unsigned char *)data)[size - 1] == '\0')
audit_log_end(ab);
}
break;
- case AUDIT_ADD:
- case AUDIT_DEL:
- if (nlmsg_len(nlh) < sizeof(struct audit_rule))
- return -EINVAL;
- if (audit_enabled == AUDIT_LOCKED) {
- audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE,
- loginuid, sessionid, sid);
-
- audit_log_format(ab, " audit_enabled=%d res=0",
- audit_enabled);
- audit_log_end(ab);
- return -EPERM;
- }
- /* fallthrough */
- case AUDIT_LIST:
- err = audit_receive_filter(msg_type, NETLINK_CB(skb).portid,
- seq, data, nlmsg_len(nlh),
- loginuid, sessionid, sid);
- break;
case AUDIT_ADD_RULE:
case AUDIT_DEL_RULE:
if (nlmsg_len(nlh) < sizeof(struct audit_rule_data))
return -EINVAL;
if (audit_enabled == AUDIT_LOCKED) {
- audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE,
- loginuid, sessionid, sid);
-
- audit_log_format(ab, " audit_enabled=%d res=0",
- audit_enabled);
+ audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE);
+ audit_log_format(ab, " audit_enabled=%d res=0", audit_enabled);
audit_log_end(ab);
return -EPERM;
}
/* fallthrough */
case AUDIT_LIST_RULES:
err = audit_receive_filter(msg_type, NETLINK_CB(skb).portid,
- seq, data, nlmsg_len(nlh),
- loginuid, sessionid, sid);
+ seq, data, nlmsg_len(nlh));
break;
case AUDIT_TRIM:
audit_trim_trees();
-
- audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE,
- loginuid, sessionid, sid);
-
+ audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE);
audit_log_format(ab, " op=trim res=1");
audit_log_end(ab);
break;
/* OK, here comes... */
err = audit_tag_tree(old, new);
- audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE,
- loginuid, sessionid, sid);
+ audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE);
audit_log_format(ab, " op=make_equiv old=");
audit_log_untrustedstring(ab, old);
struct audit_tty_status s;
struct task_struct *tsk = current;
- spin_lock_irq(&tsk->sighand->siglock);
+ spin_lock(&tsk->sighand->siglock);
s.enabled = tsk->signal->audit_tty != 0;
- spin_unlock_irq(&tsk->sighand->siglock);
+ s.log_passwd = tsk->signal->audit_tty_log_passwd;
+ spin_unlock(&tsk->sighand->siglock);
audit_send_reply(NETLINK_CB(skb).portid, seq,
AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_TTY_SET: {
- struct audit_tty_status *s;
+ struct audit_tty_status s;
struct task_struct *tsk = current;
- if (nlh->nlmsg_len < sizeof(struct audit_tty_status))
- return -EINVAL;
- s = data;
- if (s->enabled != 0 && s->enabled != 1)
+ memset(&s, 0, sizeof(s));
+ /* guard against past and future API changes */
+ memcpy(&s, data, min(sizeof(s), (size_t)nlh->nlmsg_len));
+ if ((s.enabled != 0 && s.enabled != 1) ||
+ (s.log_passwd != 0 && s.log_passwd != 1))
return -EINVAL;
- spin_lock_irq(&tsk->sighand->siglock);
- tsk->signal->audit_tty = s->enabled != 0;
- spin_unlock_irq(&tsk->sighand->siglock);
+ spin_lock(&tsk->sighand->siglock);
+ tsk->signal->audit_tty = s.enabled;
+ tsk->signal->audit_tty_log_passwd = s.log_passwd;
+ spin_unlock(&tsk->sighand->siglock);
break;
}
default:
{
struct nlmsghdr *nlh;
/*
- * len MUST be signed for NLMSG_NEXT to be able to dec it below 0
+ * len MUST be signed for nlmsg_next to be able to dec it below 0
* if the nlmsg_len was not aligned
*/
int len;
nlh = nlmsg_hdr(skb);
len = skb->len;
- while (NLMSG_OK(nlh, len)) {
+ while (nlmsg_ok(nlh, len)) {
err = audit_receive_msg(skb, nlh);
/* if err or if this message says it wants a response */
if (err || (nlh->nlmsg_flags & NLM_F_ACK))
netlink_ack(skb, nlh, err);
- nlh = NLMSG_NEXT(nlh, len);
+ nlh = nlmsg_next(nlh, &len);
}
}
kfree(pathname);
}
+ void audit_log_session_info(struct audit_buffer *ab)
+ {
+ u32 sessionid = audit_get_sessionid(current);
+ uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current));
+
+ audit_log_format(ab, " auid=%u ses=%u\n", auid, sessionid);
+ }
+
void audit_log_key(struct audit_buffer *ab, char *key)
{
audit_log_format(ab, " key=");
audit_log_format(ab, "(null)");
}
+ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
+ {
+ int i;
+
+ audit_log_format(ab, " %s=", prefix);
+ CAP_FOR_EACH_U32(i) {
+ audit_log_format(ab, "%08x",
+ cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]);
+ }
+ }
+
+ void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
+ {
+ kernel_cap_t *perm = &name->fcap.permitted;
+ kernel_cap_t *inh = &name->fcap.inheritable;
+ int log = 0;
+
+ if (!cap_isclear(*perm)) {
+ audit_log_cap(ab, "cap_fp", perm);
+ log = 1;
+ }
+ if (!cap_isclear(*inh)) {
+ audit_log_cap(ab, "cap_fi", inh);
+ log = 1;
+ }
+
+ if (log)
+ audit_log_format(ab, " cap_fe=%d cap_fver=%x",
+ name->fcap.fE, name->fcap_ver);
+ }
+
+ static inline int audit_copy_fcaps(struct audit_names *name,
+ const struct dentry *dentry)
+ {
+ struct cpu_vfs_cap_data caps;
+ int rc;
+
+ if (!dentry)
+ return 0;
+
+ rc = get_vfs_caps_from_disk(dentry, &caps);
+ if (rc)
+ return rc;
+
+ name->fcap.permitted = caps.permitted;
+ name->fcap.inheritable = caps.inheritable;
+ name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
+ name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >>
+ VFS_CAP_REVISION_SHIFT;
+
+ return 0;
+ }
+
+ /* Copy inode data into an audit_names. */
+ void audit_copy_inode(struct audit_names *name, const struct dentry *dentry,
+ const struct inode *inode)
+ {
+ name->ino = inode->i_ino;
+ name->dev = inode->i_sb->s_dev;
+ name->mode = inode->i_mode;
+ name->uid = inode->i_uid;
+ name->gid = inode->i_gid;
+ name->rdev = inode->i_rdev;
+ security_inode_getsecid(inode, &name->osid);
+ audit_copy_fcaps(name, dentry);
+ }
+
+ /**
+ * audit_log_name - produce AUDIT_PATH record from struct audit_names
+ * @context: audit_context for the task
+ * @n: audit_names structure with reportable details
+ * @path: optional path to report instead of audit_names->name
+ * @record_num: record number to report when handling a list of names
+ * @call_panic: optional pointer to int that will be updated if secid fails
+ */
+ void audit_log_name(struct audit_context *context, struct audit_names *n,
+ struct path *path, int record_num, int *call_panic)
+ {
+ struct audit_buffer *ab;
+ ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH);
+ if (!ab)
+ return;
+
+ audit_log_format(ab, "item=%d", record_num);
+
+ if (path)
+ audit_log_d_path(ab, " name=", path);
+ else if (n->name) {
+ switch (n->name_len) {
+ case AUDIT_NAME_FULL:
+ /* log the full path */
+ audit_log_format(ab, " name=");
+ audit_log_untrustedstring(ab, n->name->name);
+ break;
+ case 0:
+ /* name was specified as a relative path and the
+ * directory component is the cwd */
+ audit_log_d_path(ab, " name=", &context->pwd);
+ break;
+ default:
+ /* log the name's directory component */
+ audit_log_format(ab, " name=");
+ audit_log_n_untrustedstring(ab, n->name->name,
+ n->name_len);
+ }
+ } else
+ audit_log_format(ab, " name=(null)");
+
+ if (n->ino != (unsigned long)-1) {
+ audit_log_format(ab, " inode=%lu"
+ " dev=%02x:%02x mode=%#ho"
+ " ouid=%u ogid=%u rdev=%02x:%02x",
+ n->ino,
+ MAJOR(n->dev),
+ MINOR(n->dev),
+ n->mode,
+ from_kuid(&init_user_ns, n->uid),
+ from_kgid(&init_user_ns, n->gid),
+ MAJOR(n->rdev),
+ MINOR(n->rdev));
+ }
+ if (n->osid != 0) {
+ char *ctx = NULL;
+ u32 len;
+ if (security_secid_to_secctx(
+ n->osid, &ctx, &len)) {
+ audit_log_format(ab, " osid=%u", n->osid);
+ if (call_panic)
+ *call_panic = 2;
+ } else {
+ audit_log_format(ab, " obj=%s", ctx);
+ security_release_secctx(ctx, len);
+ }
+ }
+
+ audit_log_fcaps(ab, n);
+ audit_log_end(ab);
+ }
+
+ int audit_log_task_context(struct audit_buffer *ab)
+ {
+ char *ctx = NULL;
+ unsigned len;
+ int error;
+ u32 sid;
+
+ security_task_getsecid(current, &sid);
+ if (!sid)
+ return 0;
+
+ error = security_secid_to_secctx(sid, &ctx, &len);
+ if (error) {
+ if (error != -EINVAL)
+ goto error_path;
+ return 0;
+ }
+
+ audit_log_format(ab, " subj=%s", ctx);
+ security_release_secctx(ctx, len);
+ return 0;
+
+ error_path:
+ audit_panic("error in audit_log_task_context");
+ return error;
+ }
+ EXPORT_SYMBOL(audit_log_task_context);
+
+ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
+ {
+ const struct cred *cred;
+ char name[sizeof(tsk->comm)];
+ struct mm_struct *mm = tsk->mm;
+ char *tty;
+
+ if (!ab)
+ return;
+
+ /* tsk == current */
+ cred = current_cred();
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name)
+ tty = tsk->signal->tty->name;
+ else
+ tty = "(none)";
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ audit_log_format(ab,
+ " ppid=%ld pid=%d auid=%u uid=%u gid=%u"
+ " euid=%u suid=%u fsuid=%u"
+ " egid=%u sgid=%u fsgid=%u ses=%u tty=%s",
+ sys_getppid(),
+ tsk->pid,
+ from_kuid(&init_user_ns, audit_get_loginuid(tsk)),
+ from_kuid(&init_user_ns, cred->uid),
+ from_kgid(&init_user_ns, cred->gid),
+ from_kuid(&init_user_ns, cred->euid),
+ from_kuid(&init_user_ns, cred->suid),
+ from_kuid(&init_user_ns, cred->fsuid),
+ from_kgid(&init_user_ns, cred->egid),
+ from_kgid(&init_user_ns, cred->sgid),
+ from_kgid(&init_user_ns, cred->fsgid),
+ audit_get_sessionid(tsk), tty);
+
+ get_task_comm(name, tsk);
+ audit_log_format(ab, " comm=");
+ audit_log_untrustedstring(ab, name);
+
+ if (mm) {
+ down_read(&mm->mmap_sem);
+ if (mm->exe_file)
+ audit_log_d_path(ab, " exe=", &mm->exe_file->f_path);
+ up_read(&mm->mmap_sem);
+ }
+ audit_log_task_context(ab);
+ }
+ EXPORT_SYMBOL(audit_log_task_info);
+
/**
* audit_log_link_denied - report a link restriction denial
* @operation: specific link opreation
void audit_log_link_denied(const char *operation, struct path *link)
{
struct audit_buffer *ab;
+ struct audit_names *name;
+
+ name = kzalloc(sizeof(*name), GFP_NOFS);
+ if (!name)
+ return;
+ /* Generate AUDIT_ANOM_LINK with subject, operation, outcome. */
ab = audit_log_start(current->audit_context, GFP_KERNEL,
AUDIT_ANOM_LINK);
if (!ab)
- return;
- audit_log_format(ab, "op=%s action=denied", operation);
- audit_log_format(ab, " pid=%d comm=", current->pid);
- audit_log_untrustedstring(ab, current->comm);
- audit_log_d_path(ab, " path=", link);
- audit_log_format(ab, " dev=");
- audit_log_untrustedstring(ab, link->dentry->d_inode->i_sb->s_id);
- audit_log_format(ab, " ino=%lu", link->dentry->d_inode->i_ino);
+ goto out;
+ audit_log_format(ab, "op=%s", operation);
+ audit_log_task_info(ab, current);
+ audit_log_format(ab, " res=0");
audit_log_end(ab);
+
+ /* Generate AUDIT_PATH record with object. */
+ name->type = AUDIT_TYPE_NORMAL;
+ audit_copy_inode(name, link->dentry, link->dentry->d_inode);
+ audit_log_name(current->audit_context, name, link, 0, NULL);
+ out:
+ kfree(name);
}
/**
audit_log_lost("rate limit exceeded");
} else {
struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
- nlh->nlmsg_len = ab->skb->len - NLMSG_SPACE(0);
+ nlh->nlmsg_len = ab->skb->len - NLMSG_HDRLEN;
if (audit_pid) {
skb_queue_tail(&audit_skb_queue, ab->skb);
#include <linux/fs.h>
#include <linux/audit.h>
#include <linux/skbuff.h>
+ #include <uapi/linux/mqueue.h>
/* 0 = no checking
1 = put_count checking
*/
#define AUDIT_DEBUG 0
+ /* AUDIT_NAMES is the number of slots we reserve in the audit_context
+ * for saving names from getname(). If we get more names we will allocate
+ * a name dynamically and also add those to the list anchored by names_list. */
+ #define AUDIT_NAMES 5
+
/* At task start time, the audit_state is set in the audit_context using
a per-task filter. At syscall entry, the audit_state is augmented by
the syscall filter. */
struct audit_krule rule;
};
-#ifdef CONFIG_AUDIT
-extern int audit_enabled;
+ struct audit_cap_data {
+ kernel_cap_t permitted;
+ kernel_cap_t inheritable;
+ union {
+ unsigned int fE; /* effective bit of file cap */
+ kernel_cap_t effective; /* effective set of process */
+ };
+ };
+
+ /* When fs/namei.c:getname() is called, we store the pointer in name and
+ * we don't let putname() free it (instead we free all of the saved
+ * pointers at syscall exit time).
+ *
+ * Further, in fs/namei.c:path_lookup() we store the inode and device.
+ */
+ struct audit_names {
+ struct list_head list; /* audit_context->names_list */
+
+ struct filename *name;
+ int name_len; /* number of chars to log */
+ bool name_put; /* call __putname()? */
+
+ unsigned long ino;
+ dev_t dev;
+ umode_t mode;
+ kuid_t uid;
+ kgid_t gid;
+ dev_t rdev;
+ u32 osid;
+ struct audit_cap_data fcap;
+ unsigned int fcap_ver;
+ unsigned char type; /* record type */
+ /*
+ * This was an allocated audit_names and not from the array of
+ * names allocated in the task audit context. Thus this name
+ * should be freed on syscall exit.
+ */
+ bool should_free;
+ };
+
+ /* The per-task audit context. */
+ struct audit_context {
+ int dummy; /* must be the first element */
+ int in_syscall; /* 1 if task is in a syscall */
+ enum audit_state state, current_state;
+ unsigned int serial; /* serial number for record */
+ int major; /* syscall number */
+ struct timespec ctime; /* time of syscall entry */
+ unsigned long argv[4]; /* syscall arguments */
+ long return_code;/* syscall return code */
+ u64 prio;
+ int return_valid; /* return code is valid */
+ /*
+ * The names_list is the list of all audit_names collected during this
+ * syscall. The first AUDIT_NAMES entries in the names_list will
+ * actually be from the preallocated_names array for performance
+ * reasons. Except during allocation they should never be referenced
+ * through the preallocated_names array and should only be found/used
+ * by running the names_list.
+ */
+ struct audit_names preallocated_names[AUDIT_NAMES];
+ int name_count; /* total records in names_list */
+ struct list_head names_list; /* struct audit_names->list anchor */
+ char *filterkey; /* key for rule that triggered record */
+ struct path pwd;
+ struct audit_aux_data *aux;
+ struct audit_aux_data *aux_pids;
+ struct sockaddr_storage *sockaddr;
+ size_t sockaddr_len;
+ /* Save things to print about task_struct */
+ pid_t pid, ppid;
+ kuid_t uid, euid, suid, fsuid;
+ kgid_t gid, egid, sgid, fsgid;
+ unsigned long personality;
+ int arch;
+
+ pid_t target_pid;
+ kuid_t target_auid;
+ kuid_t target_uid;
+ unsigned int target_sessionid;
+ u32 target_sid;
+ char target_comm[TASK_COMM_LEN];
+
+ struct audit_tree_refs *trees, *first_trees;
+ struct list_head killed_trees;
+ int tree_count;
+
+ int type;
+ union {
+ struct {
+ int nargs;
+ long args[6];
+ } socketcall;
+ struct {
+ kuid_t uid;
+ kgid_t gid;
+ umode_t mode;
+ u32 osid;
+ int has_perm;
+ uid_t perm_uid;
+ gid_t perm_gid;
+ umode_t perm_mode;
+ unsigned long qbytes;
+ } ipc;
+ struct {
+ mqd_t mqdes;
+ struct mq_attr mqstat;
+ } mq_getsetattr;
+ struct {
+ mqd_t mqdes;
+ int sigev_signo;
+ } mq_notify;
+ struct {
+ mqd_t mqdes;
+ size_t msg_len;
+ unsigned int msg_prio;
+ struct timespec abs_timeout;
+ } mq_sendrecv;
+ struct {
+ int oflag;
+ umode_t mode;
+ struct mq_attr attr;
+ } mq_open;
+ struct {
+ pid_t pid;
+ struct audit_cap_data cap;
+ } capset;
+ struct {
+ int fd;
+ int flags;
+ } mmap;
+ };
+ int fds[2];
+
+ #if AUDIT_DEBUG
+ int put_count;
+ int ino_count;
+ #endif
+ };
+
extern int audit_ever_enabled;
-#endif
+ extern void audit_copy_inode(struct audit_names *name,
+ const struct dentry *dentry,
+ const struct inode *inode);
+ extern void audit_log_cap(struct audit_buffer *ab, char *prefix,
+ kernel_cap_t *cap);
+ extern void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name);
+ extern void audit_log_name(struct audit_context *context,
+ struct audit_names *n, struct path *path,
+ int record_num, int *call_panic);
+
extern int audit_pid;
#define AUDIT_INODE_BUCKETS 32
return n;
}
-
- /* Translate struct audit_rule to kernel's rule respresentation.
- * Exists for backward compatibility with userspace. */
- static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
+ /* check if an audit field is valid */
+ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
{
- struct audit_entry *entry;
- int err = 0;
- int i;
-
- entry = audit_to_entry_common(rule);
- if (IS_ERR(entry))
- goto exit_nofree;
-
- for (i = 0; i < rule->field_count; i++) {
- struct audit_field *f = &entry->rule.fields[i];
- u32 n;
-
- n = rule->fields[i] & (AUDIT_NEGATE|AUDIT_OPERATORS);
-
- /* Support for legacy operators where
- * AUDIT_NEGATE bit signifies != and otherwise assumes == */
- if (n & AUDIT_NEGATE)
- f->op = Audit_not_equal;
- else if (!n)
- f->op = Audit_equal;
- else
- f->op = audit_to_op(n);
-
- entry->rule.vers_ops = (n & AUDIT_OPERATORS) ? 2 : 1;
-
- f->type = rule->fields[i] & ~(AUDIT_NEGATE|AUDIT_OPERATORS);
- f->val = rule->values[i];
- f->uid = INVALID_UID;
- f->gid = INVALID_GID;
-
- err = -EINVAL;
- if (f->op == Audit_bad)
- goto exit_free;
-
- switch(f->type) {
- default:
- goto exit_free;
- case AUDIT_UID:
- case AUDIT_EUID:
- case AUDIT_SUID:
- case AUDIT_FSUID:
- case AUDIT_LOGINUID:
- /* bit ops not implemented for uid comparisons */
- if (f->op == Audit_bitmask || f->op == Audit_bittest)
- goto exit_free;
-
- f->uid = make_kuid(current_user_ns(), f->val);
- if (!uid_valid(f->uid))
- goto exit_free;
- break;
- case AUDIT_GID:
- case AUDIT_EGID:
- case AUDIT_SGID:
- case AUDIT_FSGID:
- /* bit ops not implemented for gid comparisons */
- if (f->op == Audit_bitmask || f->op == Audit_bittest)
- goto exit_free;
-
- f->gid = make_kgid(current_user_ns(), f->val);
- if (!gid_valid(f->gid))
- goto exit_free;
- break;
- case AUDIT_PID:
- case AUDIT_PERS:
- case AUDIT_MSGTYPE:
- case AUDIT_PPID:
- case AUDIT_DEVMAJOR:
- case AUDIT_DEVMINOR:
- case AUDIT_EXIT:
- case AUDIT_SUCCESS:
- /* bit ops are only useful on syscall args */
- if (f->op == Audit_bitmask || f->op == Audit_bittest)
- goto exit_free;
- break;
- case AUDIT_ARG0:
- case AUDIT_ARG1:
- case AUDIT_ARG2:
- case AUDIT_ARG3:
- break;
- /* arch is only allowed to be = or != */
- case AUDIT_ARCH:
- if (f->op != Audit_not_equal && f->op != Audit_equal)
- goto exit_free;
- entry->rule.arch_f = f;
- break;
- case AUDIT_PERM:
- if (f->val & ~15)
- goto exit_free;
- break;
- case AUDIT_FILETYPE:
- if (f->val & ~S_IFMT)
- goto exit_free;
- break;
- case AUDIT_INODE:
- err = audit_to_inode(&entry->rule, f);
- if (err)
- goto exit_free;
- break;
- }
- }
-
- if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal)
- entry->rule.inode_f = NULL;
-
- exit_nofree:
- return entry;
+ switch(f->type) {
+ case AUDIT_MSGTYPE:
+ if (entry->rule.listnr != AUDIT_FILTER_TYPE &&
+ entry->rule.listnr != AUDIT_FILTER_USER)
+ return -EINVAL;
+ break;
+ };
- exit_free:
- audit_free_rule(entry);
- return ERR_PTR(err);
+ switch(f->type) {
+ default:
+ return -EINVAL;
+ case AUDIT_UID:
+ case AUDIT_EUID:
+ case AUDIT_SUID:
+ case AUDIT_FSUID:
+ case AUDIT_LOGINUID:
+ case AUDIT_OBJ_UID:
+ case AUDIT_GID:
+ case AUDIT_EGID:
+ case AUDIT_SGID:
+ case AUDIT_FSGID:
+ case AUDIT_OBJ_GID:
+ case AUDIT_PID:
+ case AUDIT_PERS:
+ case AUDIT_MSGTYPE:
+ case AUDIT_PPID:
+ case AUDIT_DEVMAJOR:
+ case AUDIT_DEVMINOR:
+ case AUDIT_EXIT:
+ case AUDIT_SUCCESS:
+ /* bit ops are only useful on syscall args */
+ if (f->op == Audit_bitmask || f->op == Audit_bittest)
+ return -EINVAL;
+ break;
+ case AUDIT_ARG0:
+ case AUDIT_ARG1:
+ case AUDIT_ARG2:
+ case AUDIT_ARG3:
+ case AUDIT_SUBJ_USER:
+ case AUDIT_SUBJ_ROLE:
+ case AUDIT_SUBJ_TYPE:
+ case AUDIT_SUBJ_SEN:
+ case AUDIT_SUBJ_CLR:
+ case AUDIT_OBJ_USER:
+ case AUDIT_OBJ_ROLE:
+ case AUDIT_OBJ_TYPE:
+ case AUDIT_OBJ_LEV_LOW:
+ case AUDIT_OBJ_LEV_HIGH:
+ case AUDIT_WATCH:
+ case AUDIT_DIR:
+ case AUDIT_FILTERKEY:
+ break;
+ case AUDIT_LOGINUID_SET:
+ if ((f->val != 0) && (f->val != 1))
+ return -EINVAL;
+ /* FALL THROUGH */
+ case AUDIT_ARCH:
+ if (f->op != Audit_not_equal && f->op != Audit_equal)
+ return -EINVAL;
+ break;
+ case AUDIT_PERM:
+ if (f->val & ~15)
+ return -EINVAL;
+ break;
+ case AUDIT_FILETYPE:
+ if (f->val & ~S_IFMT)
+ return -EINVAL;
+ break;
+ case AUDIT_FIELD_COMPARE:
+ if (f->val > AUDIT_MAX_FIELD_COMPARE)
+ return -EINVAL;
+ break;
+ };
+ return 0;
}
/* Translate struct audit_rule_data to kernel's rule respresentation. */
f->gid = INVALID_GID;
f->lsm_str = NULL;
f->lsm_rule = NULL;
- switch(f->type) {
+
+ /* Support legacy tests for a valid loginuid */
+ if ((f->type == AUDIT_LOGINUID) && (f->val == 4294967295)) {
+ f->type = AUDIT_LOGINUID_SET;
+ f->val = 0;
+ }
+
+ err = audit_field_valid(entry, f);
+ if (err)
+ goto exit_free;
+
+ err = -EINVAL;
+ switch (f->type) {
+ case AUDIT_LOGINUID:
case AUDIT_UID:
case AUDIT_EUID:
case AUDIT_SUID:
case AUDIT_FSUID:
- case AUDIT_LOGINUID:
case AUDIT_OBJ_UID:
- /* bit ops not implemented for uid comparisons */
- if (f->op == Audit_bitmask || f->op == Audit_bittest)
- goto exit_free;
-
f->uid = make_kuid(current_user_ns(), f->val);
if (!uid_valid(f->uid))
goto exit_free;
case AUDIT_SGID:
case AUDIT_FSGID:
case AUDIT_OBJ_GID:
- /* bit ops not implemented for gid comparisons */
- if (f->op == Audit_bitmask || f->op == Audit_bittest)
- goto exit_free;
-
f->gid = make_kgid(current_user_ns(), f->val);
if (!gid_valid(f->gid))
goto exit_free;
break;
- case AUDIT_PID:
- case AUDIT_PERS:
- case AUDIT_MSGTYPE:
- case AUDIT_PPID:
- case AUDIT_DEVMAJOR:
- case AUDIT_DEVMINOR:
- case AUDIT_EXIT:
- case AUDIT_SUCCESS:
- case AUDIT_ARG0:
- case AUDIT_ARG1:
- case AUDIT_ARG2:
- case AUDIT_ARG3:
- break;
case AUDIT_ARCH:
entry->rule.arch_f = f;
break;
entry->rule.buflen += f->val;
entry->rule.filterkey = str;
break;
- case AUDIT_PERM:
- if (f->val & ~15)
- goto exit_free;
- break;
- case AUDIT_FILETYPE:
- if (f->val & ~S_IFMT)
- goto exit_free;
- break;
- case AUDIT_FIELD_COMPARE:
- if (f->val > AUDIT_MAX_FIELD_COMPARE)
- goto exit_free;
- break;
- default:
- goto exit_free;
}
}
return entry;
exit_free:
+ if (entry->rule.watch)
+ audit_put_watch(entry->rule.watch); /* matches initial get */
+ if (entry->rule.tree)
+ audit_put_tree(entry->rule.tree); /* that's the temporary one */
audit_free_rule(entry);
return ERR_PTR(err);
}
return len;
}
- /* Translate kernel rule respresentation to struct audit_rule.
- * Exists for backward compatibility with userspace. */
- static struct audit_rule *audit_krule_to_rule(struct audit_krule *krule)
- {
- struct audit_rule *rule;
- int i;
-
- rule = kzalloc(sizeof(*rule), GFP_KERNEL);
- if (unlikely(!rule))
- return NULL;
-
- rule->flags = krule->flags | krule->listnr;
- rule->action = krule->action;
- rule->field_count = krule->field_count;
- for (i = 0; i < rule->field_count; i++) {
- rule->values[i] = krule->fields[i].val;
- rule->fields[i] = krule->fields[i].type;
-
- if (krule->vers_ops == 1) {
- if (krule->fields[i].op == Audit_not_equal)
- rule->fields[i] |= AUDIT_NEGATE;
- } else {
- rule->fields[i] |= audit_ops[krule->fields[i].op];
- }
- }
- for (i = 0; i < AUDIT_BITMASK_SIZE; i++) rule->mask[i] = krule->mask[i];
-
- return rule;
- }
-
/* Translate kernel rule respresentation to struct audit_rule_data. */
static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
{
return ret;
}
- /* List rules using struct audit_rule. Exists for backward
- * compatibility with userspace. */
- static void audit_list(int pid, int seq, struct sk_buff_head *q)
- {
- struct sk_buff *skb;
- struct audit_krule *r;
- int i;
-
- /* This is a blocking read, so use audit_filter_mutex instead of rcu
- * iterator to sync with list writers. */
- for (i=0; i<AUDIT_NR_FILTERS; i++) {
- list_for_each_entry(r, &audit_rules_list[i], list) {
- struct audit_rule *rule;
-
- rule = audit_krule_to_rule(r);
- if (unlikely(!rule))
- break;
- skb = audit_make_reply(pid, seq, AUDIT_LIST, 0, 1,
- rule, sizeof(*rule));
- if (skb)
- skb_queue_tail(q, skb);
- kfree(rule);
- }
- }
- skb = audit_make_reply(pid, seq, AUDIT_LIST, 1, 1, NULL, 0);
- if (skb)
- skb_queue_tail(q, skb);
- }
-
/* List rules using struct audit_rule_data. */
static void audit_list_rules(int pid, int seq, struct sk_buff_head *q)
{
}
/* Log rule additions and removals */
- static void audit_log_rule_change(kuid_t loginuid, u32 sessionid, u32 sid,
- char *action, struct audit_krule *rule,
- int res)
+ static void audit_log_rule_change(char *action, struct audit_krule *rule, int res)
{
struct audit_buffer *ab;
+ uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current));
+ u32 sessionid = audit_get_sessionid(current);
if (!audit_enabled)
return;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (!ab)
return;
- audit_log_format(ab, "auid=%u ses=%u",
- from_kuid(&init_user_ns, loginuid), sessionid);
- if (sid) {
- char *ctx = NULL;
- u32 len;
- if (security_secid_to_secctx(sid, &ctx, &len))
- audit_log_format(ab, " ssid=%u", sid);
- else {
- audit_log_format(ab, " subj=%s", ctx);
- security_release_secctx(ctx, len);
- }
- }
+ audit_log_format(ab, "auid=%u ses=%u" ,loginuid, sessionid);
+ audit_log_task_context(ab);
audit_log_format(ab, " op=");
audit_log_string(ab, action);
audit_log_key(ab, rule->filterkey);
* @sessionid: sessionid for netlink audit message
* @sid: SE Linux Security ID of sender
*/
- int audit_receive_filter(int type, int pid, int seq, void *data,
- size_t datasz, kuid_t loginuid, u32 sessionid, u32 sid)
+ int audit_receive_filter(int type, int pid, int seq, void *data, size_t datasz)
{
struct task_struct *tsk;
struct audit_netlink_list *dest;
struct audit_entry *entry;
switch (type) {
- case AUDIT_LIST:
case AUDIT_LIST_RULES:
/* We can't just spew out the rules here because we might fill
* the available socket buffer space and deadlock waiting for
skb_queue_head_init(&dest->q);
mutex_lock(&audit_filter_mutex);
- if (type == AUDIT_LIST)
- audit_list(pid, seq, &dest->q);
- else
- audit_list_rules(pid, seq, &dest->q);
+ audit_list_rules(pid, seq, &dest->q);
mutex_unlock(&audit_filter_mutex);
tsk = kthread_run(audit_send_list, dest, "audit_send_list");
err = PTR_ERR(tsk);
}
break;
- case AUDIT_ADD:
case AUDIT_ADD_RULE:
- if (type == AUDIT_ADD)
- entry = audit_rule_to_entry(data);
- else
- entry = audit_data_to_entry(data, datasz);
+ entry = audit_data_to_entry(data, datasz);
if (IS_ERR(entry))
return PTR_ERR(entry);
err = audit_add_rule(entry);
- audit_log_rule_change(loginuid, sessionid, sid, "add rule",
- &entry->rule, !err);
-
+ audit_log_rule_change("add rule", &entry->rule, !err);
if (err)
audit_free_rule(entry);
break;
- case AUDIT_DEL:
case AUDIT_DEL_RULE:
- if (type == AUDIT_DEL)
- entry = audit_rule_to_entry(data);
- else
- entry = audit_data_to_entry(data, datasz);
+ entry = audit_data_to_entry(data, datasz);
if (IS_ERR(entry))
return PTR_ERR(entry);
err = audit_del_rule(entry);
- audit_log_rule_change(loginuid, sessionid, sid, "remove rule",
- &entry->rule, !err);
-
+ audit_log_rule_change("remove rule", &entry->rule, !err);
audit_free_rule(entry);
break;
default:
return strncmp(p, dname, dlen);
}
- static int audit_filter_user_rules(struct audit_krule *rule,
+ static int audit_filter_user_rules(struct audit_krule *rule, int type,
enum audit_state *state)
{
int i;
result = audit_uid_comparator(audit_get_loginuid(current),
f->op, f->uid);
break;
+ case AUDIT_LOGINUID_SET:
+ result = audit_comparator(audit_loginuid_set(current),
+ f->op, f->val);
+ break;
+ case AUDIT_MSGTYPE:
+ result = audit_comparator(type, f->op, f->val);
+ break;
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
return 1;
}
- int audit_filter_user(void)
+ int audit_filter_user(int type)
{
enum audit_state state = AUDIT_DISABLED;
struct audit_entry *e;
rcu_read_lock();
list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) {
- if (audit_filter_user_rules(&e->rule, &state)) {
+ if (audit_filter_user_rules(&e->rule, type, &state)) {
if (state == AUDIT_DISABLED)
ret = 0;
break;
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/mutex.h>
-#include <linux/wanrouter.h>
#include <linux/if_bridge.h>
#include <linux/if_frad.h>
#include <linux/if_vlan.h>
file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
&socket_file_ops);
- if (unlikely(!file)) {
+ if (unlikely(IS_ERR(file))) {
/* drop dentry, keep inode */
ihold(path.dentry->d_inode);
path_put(&path);
- return ERR_PTR(-ENFILE);
+ return file;
}
sock->file = file;
file->f_flags = O_RDWR | (flags & O_NONBLOCK);
- file->f_pos = 0;
file->private_data = sock;
return file;
}
}
EXPORT_SYMBOL(sock_release);
-int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags)
+void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags)
{
*tx_flags = 0;
if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE))
*tx_flags |= SKBTX_SW_TSTAMP;
if (sock_flag(sk, SOCK_WIFI_STATUS))
*tx_flags |= SKBTX_WIFI_STATUS;
- return 0;
}
EXPORT_SYMBOL(sock_tx_timestamp);
}
EXPORT_SYMBOL(kernel_sendmsg);
-static int ktime2ts(ktime_t kt, struct timespec *ts)
-{
- if (kt.tv64) {
- *ts = ktime_to_timespec(kt);
- return 1;
- } else {
- return 0;
- }
-}
-
/*
* called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
*/
memset(ts, 0, sizeof(ts));
- if (skb->tstamp.tv64 &&
- sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) {
- skb_get_timestampns(skb, ts + 0);
+ if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE) &&
+ ktime_to_timespec_cond(skb->tstamp, ts + 0))
empty = 0;
- }
if (shhwtstamps) {
if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE) &&
- ktime2ts(shhwtstamps->syststamp, ts + 1))
+ ktime_to_timespec_cond(shhwtstamps->syststamp, ts + 1))
empty = 0;
if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE) &&
- ktime2ts(shhwtstamps->hwtstamp, ts + 2))
+ ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts + 2))
empty = 0;
}
if (!empty)
static int sock_close(struct inode *inode, struct file *filp)
{
- /*
- * It was possible the inode is NULL we were
- * closing an unfinished socket.
- */
-
- if (!inode) {
- printk(KERN_DEBUG "sock_close: NULL inode\n");
- return 0;
- }
sock_release(SOCKET_I(inode));
return 0;
}
SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
{
- unsigned long a[6];
+ unsigned long a[AUDITSC_ARGS];
unsigned long a0, a1;
int err;
unsigned int len;
if (copy_from_user(a, args, len))
return -EFAULT;
- audit_socketcall(nargs[call] / sizeof(unsigned long), a);
+ err = audit_socketcall(nargs[call] / sizeof(unsigned long), a);
+ if (err)
+ return err;
a0 = a[0];
a1 = a[1];
}
ifr = compat_alloc_user_space(buf_size);
- rxnfc = (void *)ifr + ALIGN(sizeof(struct ifreq), 8);
+ rxnfc = (void __user *)ifr + ALIGN(sizeof(struct ifreq), 8);
if (copy_in_user(&ifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ))
return -EFAULT;
offsetof(struct ethtool_rxnfc, fs.ring_cookie));
if (copy_in_user(rxnfc, compat_rxnfc,
- (void *)(&rxnfc->fs.m_ext + 1) -
- (void *)rxnfc) ||
+ (void __user *)(&rxnfc->fs.m_ext + 1) -
+ (void __user *)rxnfc) ||
copy_in_user(&rxnfc->fs.ring_cookie,
&compat_rxnfc->fs.ring_cookie,
- (void *)(&rxnfc->fs.location + 1) -
- (void *)&rxnfc->fs.ring_cookie) ||
+ (void __user *)(&rxnfc->fs.location + 1) -
+ (void __user *)&rxnfc->fs.ring_cookie) ||
copy_in_user(&rxnfc->rule_cnt, &compat_rxnfc->rule_cnt,
sizeof(rxnfc->rule_cnt)))
return -EFAULT;
if (convert_out) {
if (copy_in_user(compat_rxnfc, rxnfc,
- (const void *)(&rxnfc->fs.m_ext + 1) -
- (const void *)rxnfc) ||
+ (const void __user *)(&rxnfc->fs.m_ext + 1) -
+ (const void __user *)rxnfc) ||
copy_in_user(&compat_rxnfc->fs.ring_cookie,
&rxnfc->fs.ring_cookie,
- (const void *)(&rxnfc->fs.location + 1) -
- (const void *)&rxnfc->fs.ring_cookie) ||
+ (const void __user *)(&rxnfc->fs.location + 1) -
+ (const void __user *)&rxnfc->fs.ring_cookie) ||
copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt,
sizeof(rxnfc->rule_cnt)))
return -EFAULT;