summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/syscall.c5
-rw-r--r--kernel/bpf/verifier.c29
-rw-r--r--kernel/cgroup/cpuset.c2
-rw-r--r--kernel/cpu.c14
-rw-r--r--kernel/rcu/tasks.h2
-rw-r--r--kernel/rcu/tree_stall.h3
-rw-r--r--kernel/sched/core.c2
-rw-r--r--kernel/sched/fair.c53
-rw-r--r--kernel/sched/isolation.c7
-rw-r--r--kernel/sched/topology.c2
-rw-r--r--kernel/softirq.c12
-rw-r--r--kernel/trace/ftrace.c39
-rw-r--r--kernel/trace/ring_buffer.c9
-rw-r--r--kernel/trace/trace_events_user.c181
14 files changed, 256 insertions, 104 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0f90b6b274..1860ba3437 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3852,6 +3852,11 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
* check permissions at attach time.
*/
return -EPERM;
+
+ ptype = attach_type_to_prog_type(attach_type);
+ if (prog->type != ptype)
+ return -EINVAL;
+
return prog->enforce_expected_attach_type &&
prog->expected_attach_type != attach_type ?
-EINVAL : 0;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 11bc3af33f..6edfcc3375 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2328,6 +2328,8 @@ static void mark_btf_ld_reg(struct bpf_verifier_env *env,
regs[regno].type = PTR_TO_BTF_ID | flag;
regs[regno].btf = btf;
regs[regno].btf_id = btf_id;
+ if (type_may_be_null(flag))
+ regs[regno].id = ++env->id_gen;
}
#define DEF_NOT_SUBREG (0)
@@ -3584,7 +3586,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
* sreg needs precision before this insn
*/
bt_clear_reg(bt, dreg);
- bt_set_reg(bt, sreg);
+ if (sreg != BPF_REG_FP)
+ bt_set_reg(bt, sreg);
} else {
/* dreg = K
* dreg needs precision after this insn.
@@ -3600,7 +3603,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
* both dreg and sreg need precision
* before this insn
*/
- bt_set_reg(bt, sreg);
+ if (sreg != BPF_REG_FP)
+ bt_set_reg(bt, sreg);
} /* else dreg += K
* dreg still needs precision before this insn
*/
@@ -5320,8 +5324,6 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
*/
mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf,
kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field));
- /* For mark_ptr_or_null_reg */
- val_reg->id = ++env->id_gen;
} else if (class == BPF_STX) {
val_reg = reg_state(env, value_regno);
if (!register_is_null(val_reg) &&
@@ -5632,7 +5634,8 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg)
return true;
/* Types listed in the reg2btf_ids are always trusted */
- if (reg2btf_ids[base_type(reg->type)])
+ if (reg2btf_ids[base_type(reg->type)] &&
+ !bpf_type_has_unsafe_modifiers(reg->type))
return true;
/* If a register is not referenced, it is trusted if it has the
@@ -6242,6 +6245,7 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val,
#define BTF_TYPE_SAFE_RCU(__type) __PASTE(__type, __safe_rcu)
#define BTF_TYPE_SAFE_RCU_OR_NULL(__type) __PASTE(__type, __safe_rcu_or_null)
#define BTF_TYPE_SAFE_TRUSTED(__type) __PASTE(__type, __safe_trusted)
+#define BTF_TYPE_SAFE_TRUSTED_OR_NULL(__type) __PASTE(__type, __safe_trusted_or_null)
/*
* Allow list few fields as RCU trusted or full trusted.
@@ -6305,7 +6309,7 @@ BTF_TYPE_SAFE_TRUSTED(struct dentry) {
struct inode *d_inode;
};
-BTF_TYPE_SAFE_TRUSTED(struct socket) {
+BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) {
struct sock *sk;
};
@@ -6340,11 +6344,20 @@ static bool type_is_trusted(struct bpf_verifier_env *env,
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm));
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file));
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry));
- BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct socket));
return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted");
}
+static bool type_is_trusted_or_null(struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg,
+ const char *field_name, u32 btf_id)
+{
+ BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket));
+
+ return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id,
+ "__safe_trusted_or_null");
+}
+
static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
struct bpf_reg_state *regs,
int regno, int off, int size,
@@ -6453,6 +6466,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
*/
if (type_is_trusted(env, reg, field_name, btf_id)) {
flag |= PTR_TRUSTED;
+ } else if (type_is_trusted_or_null(env, reg, field_name, btf_id)) {
+ flag |= PTR_TRUSTED | PTR_MAYBE_NULL;
} else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) {
if (type_is_rcu(env, reg, field_name, btf_id)) {
/* ignore __rcu tag and mark it MEM_RCU */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 927bef3a59..6d6e540bac 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2948,7 +2948,7 @@ bool current_cpuset_is_being_rebound(void)
static int update_relax_domain_level(struct cpuset *cs, s64 val)
{
#ifdef CONFIG_SMP
- if (val < -1 || val >= sched_domain_level_max)
+ if (val < -1 || val > sched_domain_level_max + 1)
return -EINVAL;
#endif
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f8a0406ce8..bac70ea54e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3196,6 +3196,7 @@ void __init boot_cpu_hotplug_init(void)
this_cpu_write(cpuhp_state.target, CPUHP_ONLINE);
}
+#ifdef CONFIG_CPU_MITIGATIONS
/*
* These are used for a global "mitigations=" cmdline option for toggling
* optional CPU mitigations.
@@ -3206,9 +3207,7 @@ enum cpu_mitigations {
CPU_MITIGATIONS_AUTO_NOSMT,
};
-static enum cpu_mitigations cpu_mitigations __ro_after_init =
- IS_ENABLED(CONFIG_CPU_MITIGATIONS) ? CPU_MITIGATIONS_AUTO :
- CPU_MITIGATIONS_OFF;
+static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
static int __init mitigations_parse_cmdline(char *arg)
{
@@ -3224,7 +3223,6 @@ static int __init mitigations_parse_cmdline(char *arg)
return 0;
}
-early_param("mitigations", mitigations_parse_cmdline);
/* mitigations=off */
bool cpu_mitigations_off(void)
@@ -3239,3 +3237,11 @@ bool cpu_mitigations_auto_nosmt(void)
return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
+#else
+static int __init mitigations_parse_cmdline(char *arg)
+{
+ pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n");
+ return 0;
+}
+#endif
+early_param("mitigations", mitigations_parse_cmdline);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 732ad5b399..3f64268fe9 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -1941,7 +1941,7 @@ void show_rcu_tasks_trace_gp_kthread(void)
{
char buf[64];
- sprintf(buf, "N%lu h:%lu/%lu/%lu",
+ snprintf(buf, sizeof(buf), "N%lu h:%lu/%lu/%lu",
data_race(n_trc_holdouts),
data_race(n_heavy_reader_ofl_updates),
data_race(n_heavy_reader_updates),
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 5d66642854..b5ec62b2d8 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -504,7 +504,8 @@ static void print_cpu_stall_info(int cpu)
rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu));
rcuc_starved = rcu_is_rcuc_kthread_starving(rdp, &j);
if (rcuc_starved)
- sprintf(buf, " rcuc=%ld jiffies(starved)", j);
+ // Print signed value, as negative values indicate a probable bug.
+ snprintf(buf, sizeof(buf), " rcuc=%ld jiffies(starved)", j);
pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%04x/%ld/%#lx softirq=%u/%u fqs=%ld%s%s\n",
cpu,
"O."[!!cpu_online(cpu)],
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9116bcc903..d3aef62839 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11381,7 +11381,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
{
struct task_group *tg = css_tg(of_css(of));
u64 period = tg_get_cfs_period(tg);
- u64 burst = tg_get_cfs_burst(tg);
+ u64 burst = tg->cfs_bandwidth.burst;
u64 quota;
int ret;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aee5e7a701..a01269ed96 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6669,22 +6669,42 @@ static inline void hrtick_update(struct rq *rq)
#ifdef CONFIG_SMP
static inline bool cpu_overutilized(int cpu)
{
- unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
- unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
+ unsigned long rq_util_min, rq_util_max;
+
+ if (!sched_energy_enabled())
+ return false;
+
+ rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
+ rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
/* Return true only if the utilization doesn't fit CPU's capacity */
return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu);
}
-static inline void update_overutilized_status(struct rq *rq)
+static inline void set_rd_overutilized_status(struct root_domain *rd,
+ unsigned int status)
{
- if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) {
- WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
- trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED);
- }
+ if (!sched_energy_enabled())
+ return;
+
+ WRITE_ONCE(rd->overutilized, status);
+ trace_sched_overutilized_tp(rd, !!status);
+}
+
+static inline void check_update_overutilized_status(struct rq *rq)
+{
+ /*
+ * overutilized field is used for load balancing decisions only
+ * if energy aware scheduler is being used
+ */
+ if (!sched_energy_enabled())
+ return;
+
+ if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
+ set_rd_overutilized_status(rq->rd, SG_OVERUTILIZED);
}
#else
-static inline void update_overutilized_status(struct rq *rq) { }
+static inline void check_update_overutilized_status(struct rq *rq) { }
#endif
/* Runqueue only has SCHED_IDLE tasks enqueued */
@@ -6785,7 +6805,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
* and the following generally works well enough in practice.
*/
if (!task_new)
- update_overutilized_status(rq);
+ check_update_overutilized_status(rq);
enqueue_throttle:
assert_list_leaf_cfs_rq(rq);
@@ -10621,19 +10641,14 @@ next_group:
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
if (!env->sd->parent) {
- struct root_domain *rd = env->dst_rq->rd;
-
/* update overload indicator if we are at root domain */
- WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD);
+ WRITE_ONCE(env->dst_rq->rd->overload, sg_status & SG_OVERLOAD);
/* Update over-utilization (tipping point, U >= 0) indicator */
- WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);
- trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED);
+ set_rd_overutilized_status(env->dst_rq->rd,
+ sg_status & SG_OVERUTILIZED);
} else if (sg_status & SG_OVERUTILIZED) {
- struct root_domain *rd = env->dst_rq->rd;
-
- WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED);
- trace_sched_overutilized_tp(rd, SG_OVERUTILIZED);
+ set_rd_overutilized_status(env->dst_rq->rd, SG_OVERUTILIZED);
}
update_idle_cpu_scan(env, sum_util);
@@ -12639,7 +12654,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
task_tick_numa(rq, curr);
update_misfit_status(curr, rq);
- update_overutilized_status(task_rq(curr));
+ check_update_overutilized_status(task_rq(curr));
task_tick_core(rq, curr);
}
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 373d42c707..82e2f7fc7c 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -109,6 +109,7 @@ static void __init housekeeping_setup_type(enum hk_type type,
static int __init housekeeping_setup(char *str, unsigned long flags)
{
cpumask_var_t non_housekeeping_mask, housekeeping_staging;
+ unsigned int first_cpu;
int err = 0;
if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) {
@@ -129,7 +130,8 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
cpumask_andnot(housekeeping_staging,
cpu_possible_mask, non_housekeeping_mask);
- if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) {
+ first_cpu = cpumask_first_and(cpu_present_mask, housekeeping_staging);
+ if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) {
__cpumask_set_cpu(smp_processor_id(), housekeeping_staging);
__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
if (!housekeeping.flags) {
@@ -138,6 +140,9 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
}
}
+ if (cpumask_empty(non_housekeeping_mask))
+ goto free_housekeeping_staging;
+
if (!housekeeping.flags) {
/* First setup call ("nohz_full=" or "isolcpus=") */
enum hk_type type;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 10d1391e74..4fdab14953 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1468,7 +1468,7 @@ static void set_domain_attribute(struct sched_domain *sd,
} else
request = attr->relax_domain_level;
- if (sd->level > request) {
+ if (sd->level >= request) {
/* Turn off idle balance on this domain: */
sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 210cf5f8d9..bd9716d7bb 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -507,7 +507,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
static inline void lockdep_softirq_end(bool in_hardirq) { }
#endif
-asmlinkage __visible void __softirq_entry __do_softirq(void)
+static void handle_softirqs(bool ksirqd)
{
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
unsigned long old_flags = current->flags;
@@ -562,8 +562,7 @@ restart:
pending >>= softirq_bit;
}
- if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
- __this_cpu_read(ksoftirqd) == current)
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd)
rcu_softirq_qs();
local_irq_disable();
@@ -583,6 +582,11 @@ restart:
current_restore_flags(old_flags, PF_MEMALLOC);
}
+asmlinkage __visible void __softirq_entry __do_softirq(void)
+{
+ handle_softirqs(false);
+}
+
/**
* irq_enter_rcu - Enter an interrupt context with RCU watching
*/
@@ -918,7 +922,7 @@ static void run_ksoftirqd(unsigned int cpu)
* We can safely run softirq on inline stack, as we are not deep
* in the task stack here.
*/
- __do_softirq();
+ handle_softirqs(true);
ksoftirqd_run_end();
cond_resched();
return;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 83ba342aef..2f80239348 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1595,12 +1595,15 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end)
unsigned long ftrace_location_range(unsigned long start, unsigned long end)
{
struct dyn_ftrace *rec;
+ unsigned long ip = 0;
+ rcu_read_lock();
rec = lookup_rec(start, end);
if (rec)
- return rec->ip;
+ ip = rec->ip;
+ rcu_read_unlock();
- return 0;
+ return ip;
}
/**
@@ -1613,25 +1616,22 @@ unsigned long ftrace_location_range(unsigned long start, unsigned long end)
*/
unsigned long ftrace_location(unsigned long ip)
{
- struct dyn_ftrace *rec;
+ unsigned long loc;
unsigned long offset;
unsigned long size;
- rec = lookup_rec(ip, ip);
- if (!rec) {
+ loc = ftrace_location_range(ip, ip);
+ if (!loc) {
if (!kallsyms_lookup_size_offset(ip, &size, &offset))
goto out;
/* map sym+0 to __fentry__ */
if (!offset)
- rec = lookup_rec(ip, ip + size - 1);
+ loc = ftrace_location_range(ip, ip + size - 1);
}
- if (rec)
- return rec->ip;
-
out:
- return 0;
+ return loc;
}
/**
@@ -6593,6 +6593,8 @@ static int ftrace_process_locs(struct module *mod,
/* We should have used all pages unless we skipped some */
if (pg_unuse) {
WARN_ON(!skipped);
+ /* Need to synchronize with ftrace_location_range() */
+ synchronize_rcu();
ftrace_free_pages(pg_unuse);
}
return ret;
@@ -6806,6 +6808,9 @@ void ftrace_release_mod(struct module *mod)
out_unlock:
mutex_unlock(&ftrace_lock);
+ /* Need to synchronize with ftrace_location_range() */
+ if (tmp_page)
+ synchronize_rcu();
for (pg = tmp_page; pg; pg = tmp_page) {
/* Needs to be called outside of ftrace_lock */
@@ -7139,6 +7144,7 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
unsigned long start = (unsigned long)(start_ptr);
unsigned long end = (unsigned long)(end_ptr);
struct ftrace_page **last_pg = &ftrace_pages_start;
+ struct ftrace_page *tmp_page = NULL;
struct ftrace_page *pg;
struct dyn_ftrace *rec;
struct dyn_ftrace key;
@@ -7180,12 +7186,8 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
ftrace_update_tot_cnt--;
if (!pg->index) {
*last_pg = pg->next;
- if (pg->records) {
- free_pages((unsigned long)pg->records, pg->order);
- ftrace_number_of_pages -= 1 << pg->order;
- }
- ftrace_number_of_groups--;
- kfree(pg);
+ pg->next = tmp_page;
+ tmp_page = pg;
pg = container_of(last_pg, struct ftrace_page, next);
if (!(*last_pg))
ftrace_pages = pg;
@@ -7202,6 +7204,11 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
clear_func_from_hashes(func);
kfree(func);
}
+ /* Need to synchronize with ftrace_location_range() */
+ if (tmp_page) {
+ synchronize_rcu();
+ ftrace_free_pages(tmp_page);
+ }
}
void __init ftrace_free_init_mem(void)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index faf56d9a9e..943850b25f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1456,6 +1456,11 @@ static void rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
*
* As a safety measure we check to make sure the data pages have not
* been corrupted.
+ *
+ * Callers of this function need to guarantee that the list of pages doesn't get
+ * modified during the check. In particular, if it's possible that the function
+ * is invoked with concurrent readers which can swap in a new reader page then
+ * the caller should take cpu_buffer->reader_lock.
*/
static void rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
@@ -2205,8 +2210,12 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
*/
synchronize_rcu();
for_each_buffer_cpu(buffer, cpu) {
+ unsigned long flags;
+
cpu_buffer = buffer->buffers[cpu];
+ raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
rb_check_pages(cpu_buffer);
+ raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
}
atomic_dec(&buffer->record_disabled);
}
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index e76f5e1efd..704de62f7a 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -202,6 +202,8 @@ static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm);
static struct user_event_mm *user_event_mm_get_all(struct user_event *user);
static void user_event_mm_put(struct user_event_mm *mm);
static int destroy_user_event(struct user_event *user);
+static bool user_fields_match(struct user_event *user, int argc,
+ const char **argv);
static u32 user_event_key(char *name)
{
@@ -1493,17 +1495,24 @@ static int destroy_user_event(struct user_event *user)
}
static struct user_event *find_user_event(struct user_event_group *group,
- char *name, u32 *outkey)
+ char *name, int argc, const char **argv,
+ u32 flags, u32 *outkey)
{
struct user_event *user;
u32 key = user_event_key(name);
*outkey = key;
- hash_for_each_possible(group->register_table, user, node, key)
- if (!strcmp(EVENT_NAME(user), name))
+ hash_for_each_possible(group->register_table, user, node, key) {
+ if (strcmp(EVENT_NAME(user), name))
+ continue;
+
+ if (user_fields_match(user, argc, argv))
return user_event_get(user);
+ return ERR_PTR(-EADDRINUSE);
+ }
+
return NULL;
}
@@ -1860,6 +1869,9 @@ static bool user_fields_match(struct user_event *user, int argc,
struct list_head *head = &user->fields;
int i = 0;
+ if (argc == 0)
+ return list_empty(head);
+
list_for_each_entry_reverse(field, head, link) {
if (!user_field_match(field, argc, argv, &i))
return false;
@@ -1880,10 +1892,8 @@ static bool user_event_match(const char *system, const char *event,
match = strcmp(EVENT_NAME(user), event) == 0 &&
(!system || strcmp(system, USER_EVENTS_SYSTEM) == 0);
- if (match && argc > 0)
+ if (match)
match = user_fields_match(user, argc, argv);
- else if (match && argc == 0)
- match = list_empty(&user->fields);
return match;
}
@@ -1914,6 +1924,80 @@ static int user_event_trace_register(struct user_event *user)
}
/*
+ * Counts how many ';' without a trailing space are in the args.
+ */
+static int count_semis_no_space(char *args)
+{
+ int count = 0;
+
+ while ((args = strchr(args, ';'))) {
+ args++;
+
+ if (!isspace(*args))
+ count++;
+ }
+
+ return count;
+}
+
+/*
+ * Copies the arguments while ensuring all ';' have a trailing space.
+ */
+static char *insert_space_after_semis(char *args, int count)
+{
+ char *fixed, *pos;
+ int len;
+
+ len = strlen(args) + count;
+ fixed = kmalloc(len + 1, GFP_KERNEL);
+
+ if (!fixed)
+ return NULL;
+
+ pos = fixed;
+
+ /* Insert a space after ';' if there is no trailing space. */
+ while (*args) {
+ *pos = *args++;
+
+ if (*pos++ == ';' && !isspace(*args))
+ *pos++ = ' ';
+ }
+
+ *pos = '\0';
+
+ return fixed;
+}
+
+static char **user_event_argv_split(char *args, int *argc)
+{
+ char **split;
+ char *fixed;
+ int count;
+
+ /* Count how many ';' without a trailing space */
+ count = count_semis_no_space(args);
+
+ /* No fixup is required */
+ if (!count)
+ return argv_split(GFP_KERNEL, args, argc);
+
+ /* We must fixup 'field;field' to 'field; field' */
+ fixed = insert_space_after_semis(args, count);
+
+ if (!fixed)
+ return NULL;
+
+ /* We do a normal split afterwards */
+ split = argv_split(GFP_KERNEL, fixed, argc);
+
+ /* We can free since argv_split makes a copy */
+ kfree(fixed);
+
+ return split;
+}
+
+/*
* Parses the event name, arguments and flags then registers if successful.
* The name buffer lifetime is owned by this method for success cases only.
* Upon success the returned user_event has its ref count increased by 1.
@@ -1922,11 +2006,11 @@ static int user_event_parse(struct user_event_group *group, char *name,
char *args, char *flags,
struct user_event **newuser, int reg_flags)
{
- int ret;
- u32 key;
struct user_event *user;
+ char **argv = NULL;
int argc = 0;
- char **argv;
+ int ret;
+ u32 key;
/* Currently don't support any text based flags */
if (flags != NULL)
@@ -1935,41 +2019,34 @@ static int user_event_parse(struct user_event_group *group, char *name,
if (!user_event_capable(reg_flags))
return -EPERM;
+ if (args) {
+ argv = user_event_argv_split(args, &argc);
+
+ if (!argv)
+ return -ENOMEM;
+ }
+
/* Prevent dyn_event from racing */
mutex_lock(&event_mutex);
- user = find_user_event(group, name, &key);
+ user = find_user_event(group, name, argc, (const char **)argv,
+ reg_flags, &key);
mutex_unlock(&event_mutex);
- if (user) {
- if (args) {
- argv = argv_split(GFP_KERNEL, args, &argc);
- if (!argv) {
- ret = -ENOMEM;
- goto error;
- }
+ if (argv)
+ argv_free(argv);
- ret = user_fields_match(user, argc, (const char **)argv);
- argv_free(argv);
-
- } else
- ret = list_empty(&user->fields);
-
- if (ret) {
- *newuser = user;
- /*
- * Name is allocated by caller, free it since it already exists.
- * Caller only worries about failure cases for freeing.
- */
- kfree(name);
- } else {
- ret = -EADDRINUSE;
- goto error;
- }
+ if (IS_ERR(user))
+ return PTR_ERR(user);
+
+ if (user) {
+ *newuser = user;
+ /*
+ * Name is allocated by caller, free it since it already exists.
+ * Caller only worries about failure cases for freeing.
+ */
+ kfree(name);
return 0;
-error:
- user_event_put(user, false);
- return ret;
}
user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT);
@@ -2052,25 +2129,33 @@ put_user:
}
/*
- * Deletes a previously created event if it is no longer being used.
+ * Deletes previously created events if they are no longer being used.
*/
static int delete_user_event(struct user_event_group *group, char *name)
{
- u32 key;
- struct user_event *user = find_user_event(group, name, &key);
+ struct user_event *user;
+ struct hlist_node *tmp;
+ u32 key = user_event_key(name);
+ int ret = -ENOENT;
- if (!user)
- return -ENOENT;
+ /* Attempt to delete all event(s) with the name passed in */
+ hash_for_each_possible_safe(group->register_table, user, tmp, node, key) {
+ if (strcmp(EVENT_NAME(user), name))
+ continue;
- user_event_put(user, true);
+ if (!user_event_last_ref(user))
+ return -EBUSY;
- if (!user_event_last_ref(user))
- return -EBUSY;
+ if (!user_event_capable(user->reg_flags))
+ return -EPERM;
- if (!user_event_capable(user->reg_flags))
- return -EPERM;
+ ret = destroy_user_event(user);
- return destroy_user_event(user);
+ if (ret)
+ goto out;
+ }
+out:
+ return ret;
}
/*
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-15 23:43:22 +0000