summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c21
-rw-r--r--kernel/bpf/btf.c11
-rw-r--r--kernel/bpf/cgroup.c2
-rw-r--r--kernel/bpf/helpers.c2
-rw-r--r--kernel/bpf/syscall.c57
-rw-r--r--kernel/bpf/verifier.c82
-rw-r--r--kernel/cpu.c7
-rw-r--r--kernel/crash_core.c11
-rw-r--r--kernel/entry/syscall_user_dispatch.c4
-rw-r--r--kernel/events/core.c3
-rw-r--r--kernel/kprobes.c3
-rw-r--r--kernel/locking/rtmutex.c2
-rw-r--r--kernel/locking/rwsem.c182
-rw-r--r--kernel/power/hibernate.c6
-rw-r--r--kernel/power/user.c2
-rw-r--r--kernel/printk/printk.c5
-rw-r--r--kernel/sched/core.c10
-rw-r--r--kernel/sched/cputime.c12
-rw-r--r--kernel/sched/wait.c7
-rw-r--r--kernel/signal.c45
-rw-r--r--kernel/softirq.c3
-rw-r--r--kernel/time/tick-sched.c7
-rw-r--r--kernel/time/timekeeping.c3
-rw-r--r--kernel/time/timer.c16
-rw-r--r--kernel/trace/bpf_trace.c2
-rw-r--r--kernel/trace/ftrace.c8
-rw-r--r--kernel/trace/trace.c22
-rw-r--r--kernel/trace/trace.h24
-rw-r--r--kernel/trace/trace_events.c12
-rw-r--r--kernel/trace/trace_events_hist.c52
-rw-r--r--kernel/trace/trace_events_synth.c11
-rw-r--r--kernel/trace/trace_uprobe.c1
-rw-r--r--kernel/trace/tracing_map.c3
-rw-r--r--kernel/ucount.c15
34 files changed, 415 insertions, 238 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 121d37e700a6..4cebadb5f30d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -718,7 +718,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid,
{
int rc = 0;
struct sk_buff *skb;
- static unsigned int failed = 0;
+ unsigned int failed = 0;
/* NOTE: kauditd_thread takes care of all our locking, we just use
* the netlink info passed to us (e.g. sk and portid) */
@@ -735,32 +735,30 @@ static int kauditd_send_queue(struct sock *sk, u32 portid,
continue;
}
+retry:
/* grab an extra skb reference in case of error */
skb_get(skb);
rc = netlink_unicast(sk, skb, portid, 0);
if (rc < 0) {
- /* fatal failure for our queue flush attempt? */
+ /* send failed - try a few times unless fatal error */
if (++failed >= retry_limit ||
rc == -ECONNREFUSED || rc == -EPERM) {
- /* yes - error processing for the queue */
sk = NULL;
if (err_hook)
(*err_hook)(skb);
- if (!skb_hook)
- goto out;
- /* keep processing with the skb_hook */
+ if (rc == -EAGAIN)
+ rc = 0;
+ /* continue to drain the queue */
continue;
} else
- /* no - requeue to preserve ordering */
- skb_queue_head(queue, skb);
+ goto retry;
} else {
- /* it worked - drop the extra reference and continue */
+ /* skb sent - drop the extra reference and continue */
consume_skb(skb);
failed = 0;
}
}
-out:
return (rc >= 0 ? 0 : rc);
}
@@ -1609,7 +1607,8 @@ static int __net_init audit_net_init(struct net *net)
audit_panic("cannot initialize netlink socket in namespace");
return -ENOMEM;
}
- aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+ /* limit the timeout in case auditd is blocked/stopped */
+ aunet->sk->sk_sndtimeo = HZ / 10;
return 0;
}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index dbc3ad07e21b..9bdb03767db5 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6346,11 +6346,6 @@ BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct)
/* BTF ID set registration API for modules */
-struct kfunc_btf_id_list {
- struct list_head list;
- struct mutex mutex;
-};
-
#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
@@ -6376,8 +6371,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
{
struct kfunc_btf_id_set *s;
- if (!owner)
- return false;
mutex_lock(&klist->mutex);
list_for_each_entry(s, &klist->list, list) {
if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) {
@@ -6389,8 +6382,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
return false;
}
-#endif
-
#define DEFINE_KFUNC_BTF_ID_LIST(name) \
struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \
__MUTEX_INITIALIZER(name.mutex) }; \
@@ -6398,3 +6389,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list);
+
+#endif
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 2ca643af9a54..43eb3501721b 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sysctl_get_new_value_proto;
case BPF_FUNC_sysctl_set_new_value:
return &bpf_sysctl_set_new_value_proto;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
default:
return cgroup_base_func_proto(func_id, prog);
}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1ffd469c217f..649f07623df6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1364,8 +1364,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_ktime_get_boot_ns:
return &bpf_ktime_get_boot_ns_proto;
- case BPF_FUNC_ktime_get_coarse_ns:
- return &bpf_ktime_get_coarse_ns_proto;
case BPF_FUNC_ringbuf_output:
return &bpf_ringbuf_output_proto;
case BPF_FUNC_ringbuf_reserve:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 50f96ea4452a..1033ee8c0caf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
+static void bpf_map_write_active_inc(struct bpf_map *map)
+{
+ atomic64_inc(&map->writecnt);
+}
+
+static void bpf_map_write_active_dec(struct bpf_map *map)
+{
+ atomic64_dec(&map->writecnt);
+}
+
+bool bpf_map_write_active(const struct bpf_map *map)
+{
+ return atomic64_read(&map->writecnt) != 0;
+}
+
static u32 bpf_map_value_size(const struct bpf_map *map)
{
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_MAYWRITE) {
- mutex_lock(&map->freeze_mutex);
- map->writecnt++;
- mutex_unlock(&map->freeze_mutex);
- }
+ if (vma->vm_flags & VM_MAYWRITE)
+ bpf_map_write_active_inc(map);
}
/* called for all unmapped memory region (including initial) */
@@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_MAYWRITE) {
- mutex_lock(&map->freeze_mutex);
- map->writecnt--;
- mutex_unlock(&map->freeze_mutex);
- }
+ if (vma->vm_flags & VM_MAYWRITE)
+ bpf_map_write_active_dec(map);
}
static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
goto out;
if (vma->vm_flags & VM_MAYWRITE)
- map->writecnt++;
+ bpf_map_write_active_inc(map);
out:
mutex_unlock(&map->freeze_mutex);
return err;
@@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
@@ -1174,6 +1184,7 @@ free_value:
free_key:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
@@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr)
out:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
@@ -1597,6 +1611,7 @@ free_value:
free_key:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr)
}
mutex_lock(&map->freeze_mutex);
-
- if (map->writecnt) {
+ if (bpf_map_write_active(map)) {
err = -EBUSY;
goto err_put;
}
@@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
union bpf_attr __user *uattr,
int cmd)
{
+ bool has_read = cmd == BPF_MAP_LOOKUP_BATCH ||
+ cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH;
+ bool has_write = cmd != BPF_MAP_LOOKUP_BATCH;
struct bpf_map *map;
int err, ufd;
struct fd f;
@@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if ((cmd == BPF_MAP_LOOKUP_BATCH ||
- cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
- !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
+ if (has_write)
+ bpf_map_write_active_inc(map);
+ if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
err = -EPERM;
goto err_put;
}
-
- if (cmd != BPF_MAP_LOOKUP_BATCH &&
- !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+ if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
@@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
BPF_DO_BATCH(map->ops->map_update_batch);
else
BPF_DO_BATCH(map->ops->map_delete_batch);
-
err_put:
+ if (has_write)
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 890b3ec375a3..b532f1058d35 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1151,7 +1151,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
/* transfer reg's id which is unique for every map_lookup_elem
* as UID of the inner map.
*/
- reg->map_uid = reg->id;
+ if (map_value_has_timer(map->inner_map_meta))
+ reg->map_uid = reg->id;
} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
reg->type = PTR_TO_XDP_SOCK;
} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
@@ -1365,22 +1366,28 @@ static void __reg_bound_offset(struct bpf_reg_state *reg)
reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
}
+static bool __reg32_bound_s64(s32 a)
+{
+ return a >= 0 && a <= S32_MAX;
+}
+
static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
{
reg->umin_value = reg->u32_min_value;
reg->umax_value = reg->u32_max_value;
- /* Attempt to pull 32-bit signed bounds into 64-bit bounds
- * but must be positive otherwise set to worse case bounds
- * and refine later from tnum.
+
+ /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must
+ * be positive otherwise set to worse case bounds and refine later
+ * from tnum.
*/
- if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
- reg->smax_value = reg->s32_max_value;
- else
- reg->smax_value = U32_MAX;
- if (reg->s32_min_value >= 0)
+ if (__reg32_bound_s64(reg->s32_min_value) &&
+ __reg32_bound_s64(reg->s32_max_value)) {
reg->smin_value = reg->s32_min_value;
- else
+ reg->smax_value = reg->s32_max_value;
+ } else {
reg->smin_value = 0;
+ reg->smax_value = U32_MAX;
+ }
}
static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
@@ -2378,8 +2385,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
*/
if (insn->src_reg != BPF_REG_FP)
return 0;
- if (BPF_SIZE(insn->code) != BPF_DW)
- return 0;
/* dreg = *(u64 *)[fp - off] was a fill from the stack.
* that [fp - off] slot contains scalar that needs to be
@@ -2402,8 +2407,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
/* scalars can only be spilled into stack */
if (insn->dst_reg != BPF_REG_FP)
return 0;
- if (BPF_SIZE(insn->code) != BPF_DW)
- return 0;
spi = (-insn->off - 1) / BPF_REG_SIZE;
if (spi >= 64) {
verbose(env, "BUG spi %d\n", spi);
@@ -4055,7 +4058,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
static bool bpf_map_is_rdonly(const struct bpf_map *map)
{
- return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+ /* A map is considered read-only if the following condition are true:
+ *
+ * 1) BPF program side cannot change any of the map content. The
+ * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
+ * and was set at map creation time.
+ * 2) The map value(s) have been initialized from user space by a
+ * loader and then "frozen", such that no new map update/delete
+ * operations from syscall side are possible for the rest of
+ * the map's lifetime from that point onwards.
+ * 3) Any parallel/pending map update/delete operations from syscall
+ * side have been completed. Only after that point, it's safe to
+ * assume that map value(s) are immutable.
+ */
+ return (map->map_flags & BPF_F_RDONLY_PROG) &&
+ READ_ONCE(map->frozen) &&
+ !bpf_map_write_active(map);
}
static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
@@ -4535,9 +4553,16 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
if (insn->imm == BPF_CMPXCHG) {
/* Check comparison of R0 with memory location */
- err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ const u32 aux_reg = BPF_REG_0;
+
+ err = check_reg_arg(env, aux_reg, SRC_OP);
if (err)
return err;
+
+ if (is_pointer_value(env, aux_reg)) {
+ verbose(env, "R%d leaks addr into mem\n", aux_reg);
+ return -EACCES;
+ }
}
if (is_pointer_value(env, insn->src_reg)) {
@@ -4572,13 +4597,19 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
load_reg = -1;
}
- /* check whether we can read the memory */
+ /* Check whether we can read the memory, with second call for fetch
+ * case to simulate the register fill.
+ */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_READ, load_reg, true);
+ BPF_SIZE(insn->code), BPF_READ, -1, true);
+ if (!err && load_reg >= 0)
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+ BPF_SIZE(insn->code), BPF_READ, load_reg,
+ true);
if (err)
return err;
- /* check whether we can write into the same memory */
+ /* Check whether we can write into the same memory. */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1, true);
if (err)
@@ -8292,6 +8323,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
insn->dst_reg);
}
zext_32_to_64(dst_reg);
+
+ __update_reg_bounds(dst_reg);
+ __reg_deduce_bounds(dst_reg);
+ __reg_bound_offset(dst_reg);
}
} else {
/* case: R = imm
@@ -8406,7 +8441,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
new_range = dst_reg->off;
if (range_right_open)
- new_range--;
+ new_range++;
/* Examples for register markings:
*
@@ -11631,6 +11666,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
}
}
+ if (map_value_has_timer(map)) {
+ if (is_tracing_prog_type(prog_type)) {
+ verbose(env, "tracing progs cannot use bpf_timer yet\n");
+ return -EINVAL;
+ }
+ }
+
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
!bpf_offload_prog_map_match(prog, map)) {
verbose(env, "offload device mismatch between prog and map\n");
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 192e43a87407..407a2568f35e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -31,6 +31,7 @@
#include <linux/smpboot.h>
#include <linux/relay.h>
#include <linux/slab.h>
+#include <linux/scs.h>
#include <linux/percpu-rwsem.h>
#include <linux/cpuset.h>
@@ -588,6 +589,12 @@ static int bringup_cpu(unsigned int cpu)
int ret;
/*
+ * Reset stale stack state from the last time this CPU was online.
+ */
+ scs_task_reset(idle);
+ kasan_unpoison_task_stack(idle);
+
+ /*
* Some architectures have to walk the irq descriptors to
* setup the vector space for the cpu which comes online.
* Prevent irq alloc/free across the bringup.
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index eb53f5ec62c9..256cf6db573c 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -6,6 +6,7 @@
#include <linux/buildid.h>
#include <linux/crash_core.h>
+#include <linux/init.h>
#include <linux/utsname.h>
#include <linux/vmalloc.h>
@@ -295,6 +296,16 @@ int __init parse_crashkernel_low(char *cmdline,
"crashkernel=", suffix_tbl[SUFFIX_LOW]);
}
+/*
+ * Add a dummy early_param handler to mark crashkernel= as a known command line
+ * parameter and suppress incorrect warnings in init/main.c.
+ */
+static int __init parse_crashkernel_dummy(char *arg)
+{
+ return 0;
+}
+early_param("crashkernel", parse_crashkernel_dummy);
+
Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
void *data, size_t data_len)
{
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index 4508201847d2..0b6379adff6b 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -48,7 +48,7 @@ bool syscall_user_dispatch(struct pt_regs *regs)
* the selector is loaded by userspace.
*/
if (unlikely(__get_user(state, sd->selector))) {
- force_fatal_sig(SIGSEGV);
+ force_exit_sig(SIGSEGV);
return true;
}
@@ -56,7 +56,7 @@ bool syscall_user_dispatch(struct pt_regs *regs)
return false;
if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
- force_fatal_sig(SIGSYS);
+ force_exit_sig(SIGSYS);
return true;
}
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 523106a506ee..30d94f68c5bd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9759,6 +9759,9 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
continue;
if (event->attr.config != entry->type)
continue;
+ /* Cannot deliver synchronous signal to other task. */
+ if (event->attr.sigtrap)
+ continue;
if (perf_tp_event_match(event, &data, regs))
perf_swevent_event(event, count, &data, regs);
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e9db0c810554..21eccc961bba 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp)
}
}
+ if (rp->data_size > KRETPROBE_MAX_DATA_SIZE)
+ return -E2BIG;
+
rp->kp.pre_handler = pre_handler_kretprobe;
rp->kp.post_handler = NULL;
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0c6a48dfcecb..1f25a4d7de27 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1380,7 +1380,7 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock,
* - the VCPU on which owner runs is preempted
*/
if (!owner->on_cpu || need_resched() ||
- rt_mutex_waiter_is_top_waiter(lock, waiter) ||
+ !rt_mutex_waiter_is_top_waiter(lock, waiter) ||
vcpu_is_preempted(task_cpu(owner))) {
res = false;
break;
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index c51387a43265..04a74d040a6d 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -105,9 +105,9 @@
* atomic_long_cmpxchg() will be used to obtain writer lock.
*
* There are three places where the lock handoff bit may be set or cleared.
- * 1) rwsem_mark_wake() for readers.
- * 2) rwsem_try_write_lock() for writers.
- * 3) Error path of rwsem_down_write_slowpath().
+ * 1) rwsem_mark_wake() for readers -- set, clear
+ * 2) rwsem_try_write_lock() for writers -- set, clear
+ * 3) rwsem_del_waiter() -- clear
*
* For all the above cases, wait_lock will be held. A writer must also
* be the first one in the wait_list to be eligible for setting the handoff
@@ -334,6 +334,9 @@ struct rwsem_waiter {
struct task_struct *task;
enum rwsem_waiter_type type;
unsigned long timeout;
+
+ /* Writer only, not initialized in reader */
+ bool handoff_set;
};
#define rwsem_first_waiter(sem) \
list_first_entry(&sem->wait_list, struct rwsem_waiter, list)
@@ -344,12 +347,6 @@ enum rwsem_wake_type {
RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */
};
-enum writer_wait_state {
- WRITER_NOT_FIRST, /* Writer is not first in wait list */
- WRITER_FIRST, /* Writer is first in wait list */
- WRITER_HANDOFF /* Writer is first & handoff needed */
-};
-
/*
* The typical HZ value is either 250 or 1000. So set the minimum waiting
* time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait
@@ -365,6 +362,31 @@ enum writer_wait_state {
*/
#define MAX_READERS_WAKEUP 0x100
+static inline void
+rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
+{
+ lockdep_assert_held(&sem->wait_lock);
+ list_add_tail(&waiter->list, &sem->wait_list);
+ /* caller will set RWSEM_FLAG_WAITERS */
+}
+
+/*
+ * Remove a waiter from the wait_list and clear flags.
+ *
+ * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of
+ * this function. Modify with care.
+ */
+static inline void
+rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
+{
+ lockdep_assert_held(&sem->wait_lock);
+ list_del(&waiter->list);
+ if (likely(!list_empty(&sem->wait_list)))
+ return;
+
+ atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count);
+}
+
/*
* handle the lock release when processes blocked on it that can now run
* - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must
@@ -376,6 +398,8 @@ enum writer_wait_state {
* preferably when the wait_lock is released
* - woken process blocks are discarded from the list after having task zeroed
* - writers are only marked woken if downgrading is false
+ *
+ * Implies rwsem_del_waiter() for all woken readers.
*/
static void rwsem_mark_wake(struct rw_semaphore *sem,
enum rwsem_wake_type wake_type,
@@ -490,18 +514,25 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
adjustment = woken * RWSEM_READER_BIAS - adjustment;
lockevent_cond_inc(rwsem_wake_reader, woken);
+
+ oldcount = atomic_long_read(&sem->count);
if (list_empty(&sem->wait_list)) {
- /* hit end of list above */
+ /*
+ * Combined with list_move_tail() above, this implies
+ * rwsem_del_waiter().
+ */
adjustment -= RWSEM_FLAG_WAITERS;
+ if (oldcount & RWSEM_FLAG_HANDOFF)
+ adjustment -= RWSEM_FLAG_HANDOFF;
+ } else if (woken) {
+ /*
+ * When we've woken a reader, we no longer need to force
+ * writers to give up the lock and we can clear HANDOFF.
+ */
+ if (oldcount & RWSEM_FLAG_HANDOFF)
+ adjustment -= RWSEM_FLAG_HANDOFF;
}
- /*
- * When we've woken a reader, we no longer need to force writers
- * to give up the lock and we can clear HANDOFF.
- */
- if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF))
- adjustment -= RWSEM_FLAG_HANDOFF;
-
if (adjustment)
atomic_long_add(adjustment, &sem->count);
@@ -532,12 +563,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
* race conditions between checking the rwsem wait list and setting the
* sem->count accordingly.
*
- * If wstate is WRITER_HANDOFF, it will make sure that either the handoff
- * bit is set or the lock is acquired with handoff bit cleared.
+ * Implies rwsem_del_waiter() on success.
*/
static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
- enum writer_wait_state wstate)
+ struct rwsem_waiter *waiter)
{
+ bool first = rwsem_first_waiter(sem) == waiter;
long count, new;
lockdep_assert_held(&sem->wait_lock);
@@ -546,13 +577,19 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
do {
bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
- if (has_handoff && wstate == WRITER_NOT_FIRST)
- return false;
+ if (has_handoff) {
+ if (!first)
+ return false;
+
+ /* First waiter inherits a previously set handoff bit */
+ waiter->handoff_set = true;
+ }
new = count;
if (count & RWSEM_LOCK_MASK) {
- if (has_handoff || (wstate != WRITER_HANDOFF))
+ if (has_handoff || (!rt_task(waiter->task) &&
+ !time_after(jiffies, waiter->timeout)))
return false;
new |= RWSEM_FLAG_HANDOFF;
@@ -569,9 +606,17 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
* We have either acquired the lock with handoff bit cleared or
* set the handoff bit.
*/
- if (new & RWSEM_FLAG_HANDOFF)
+ if (new & RWSEM_FLAG_HANDOFF) {
+ waiter->handoff_set = true;
+ lockevent_inc(rwsem_wlock_handoff);
return false;
+ }
+ /*
+ * Have rwsem_try_write_lock() fully imply rwsem_del_waiter() on
+ * success.
+ */
+ list_del(&waiter->list);
rwsem_set_owner(sem);
return true;
}
@@ -956,7 +1001,7 @@ queue:
}
adjustment += RWSEM_FLAG_WAITERS;
}
- list_add_tail(&waiter.list, &sem->wait_list);
+ rwsem_add_waiter(sem, &waiter);
/* we're now waiting on the lock, but no longer actively locking */
count = atomic_long_add_return(adjustment, &sem->count);
@@ -1002,11 +1047,7 @@ queue:
return sem;
out_nolock:
- list_del(&waiter.list);
- if (list_empty(&sem->wait_list)) {
- atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF,
- &sem->count);
- }
+ rwsem_del_waiter(sem, &waiter);
raw_spin_unlock_irq(&sem->wait_lock);
__set_current_state(TASK_RUNNING);
lockevent_inc(rwsem_rlock_fail);
@@ -1020,9 +1061,7 @@ static struct rw_semaphore *
rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
{
long count;
- enum writer_wait_state wstate;
struct rwsem_waiter waiter;
- struct rw_semaphore *ret = sem;
DEFINE_WAKE_Q(wake_q);
/* do optimistic spinning and steal lock if possible */
@@ -1038,16 +1077,13 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
waiter.task = current;
waiter.type = RWSEM_WAITING_FOR_WRITE;
waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+ waiter.handoff_set = false;
raw_spin_lock_irq(&sem->wait_lock);
-
- /* account for this before adding a new element to the list */
- wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST;
-
- list_add_tail(&waiter.list, &sem->wait_list);
+ rwsem_add_waiter(sem, &waiter);
/* we're now waiting on the lock */
- if (wstate == WRITER_NOT_FIRST) {
+ if (rwsem_first_waiter(sem) != &waiter) {
count = atomic_long_read(&sem->count);
/*
@@ -1083,13 +1119,16 @@ wait:
/* wait until we successfully acquire the lock */
set_current_state(state);
for (;;) {
- if (rwsem_try_write_lock(sem, wstate)) {
+ if (rwsem_try_write_lock(sem, &waiter)) {
/* rwsem_try_write_lock() implies ACQUIRE on success */
break;
}
raw_spin_unlock_irq(&sem->wait_lock);
+ if (signal_pending_state(state, current))
+ goto out_nolock;
+
/*
* After setting the handoff bit and failing to acquire
* the lock, attempt to spin on owner to accelerate lock
@@ -1098,7 +1137,7 @@ wait:
* In this case, we attempt to acquire the lock again
* without sleeping.
*/
- if (wstate == WRITER_HANDOFF) {
+ if (waiter.handoff_set) {
enum owner_state owner_state;
preempt_disable();
@@ -1109,66 +1148,26 @@ wait:
goto trylock_again;
}
- /* Block until there are no active lockers. */
- for (;;) {
- if (signal_pending_state(state, current))
- goto out_nolock;
-
- schedule();
- lockevent_inc(rwsem_sleep_writer);
- set_current_state(state);
- /*
- * If HANDOFF bit is set, unconditionally do
- * a trylock.
- */
- if (wstate == WRITER_HANDOFF)
- break;
-
- if ((wstate == WRITER_NOT_FIRST) &&
- (rwsem_first_waiter(sem) == &waiter))
- wstate = WRITER_FIRST;
-
- count = atomic_long_read(&sem->count);
- if (!(count & RWSEM_LOCK_MASK))
- break;
-
- /*
- * The setting of the handoff bit is deferred
- * until rwsem_try_write_lock() is called.
- */
- if ((wstate == WRITER_FIRST) && (rt_task(current) ||
- time_after(jiffies, waiter.timeout))) {
- wstate = WRITER_HANDOFF;
- lockevent_inc(rwsem_wlock_handoff);
- break;
- }
- }
+ schedule();
+ lockevent_inc(rwsem_sleep_writer);
+ set_current_state(state);
trylock_again:
raw_spin_lock_irq(&sem->wait_lock);
}
__set_current_state(TASK_RUNNING);
- list_del(&waiter.list);
raw_spin_unlock_irq(&sem->wait_lock);
lockevent_inc(rwsem_wlock);
-
- return ret;
+ return sem;
out_nolock:
__set_current_state(TASK_RUNNING);
raw_spin_lock_irq(&sem->wait_lock);
- list_del(&waiter.list);
-
- if (unlikely(wstate == WRITER_HANDOFF))
- atomic_long_add(-RWSEM_FLAG_HANDOFF, &sem->count);
-
- if (list_empty(&sem->wait_list))
- atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count);
- else
+ rwsem_del_waiter(sem, &waiter);
+ if (!list_empty(&sem->wait_list))
rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
raw_spin_unlock_irq(&sem->wait_lock);
wake_up_q(&wake_q);
lockevent_inc(rwsem_wlock_fail);
-
return ERR_PTR(-EINTR);
}
@@ -1249,17 +1248,14 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
- /*
- * Optimize for the case when the rwsem is not locked at all.
- */
- tmp = RWSEM_UNLOCKED_VALUE;
- do {
+ tmp = atomic_long_read(&sem->count);
+ while (!(tmp & RWSEM_READ_FAILED_MASK)) {
if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
- tmp + RWSEM_READER_BIAS)) {
+ tmp + RWSEM_READER_BIAS)) {
rwsem_set_reader_owned(sem);
return 1;
}
- } while (!(tmp & RWSEM_READ_FAILED_MASK));
+ }
return 0;
}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 9ed9b744876c..e6af502c2fd7 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -693,7 +693,7 @@ static int load_image_and_restore(void)
goto Unlock;
error = swsusp_read(&flags);
- swsusp_close(FMODE_READ);
+ swsusp_close(FMODE_READ | FMODE_EXCL);
if (!error)
error = hibernation_restore(flags & SF_PLATFORM_MODE);
@@ -983,7 +983,7 @@ static int software_resume(void)
/* The snapshot device should not be opened while we're running */
if (!hibernate_acquire()) {
error = -EBUSY;
- swsusp_close(FMODE_READ);
+ swsusp_close(FMODE_READ | FMODE_EXCL);
goto Unlock;
}
@@ -1018,7 +1018,7 @@ static int software_resume(void)
pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
return error;
Close_Finish:
- swsusp_close(FMODE_READ);
+ swsusp_close(FMODE_READ | FMODE_EXCL);
goto Finish;
}
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 740723bb3885..ad241b4ff64c 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -177,7 +177,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
if (res <= 0)
goto unlock;
} else {
- res = PAGE_SIZE - pg_offp;
+ res = PAGE_SIZE;
}
if (!data_of(data->handle)) {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 013bfd6dcc34..57b132b658e1 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3253,6 +3253,11 @@ void defer_console_output(void)
preempt_enable();
}
+void printk_trigger_flush(void)
+{
+ defer_console_output();
+}
+
int vprintk_deferred(const char *fmt, va_list args)
{
int r;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3c9b0fda64ac..77563109c0ea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1918,7 +1918,7 @@ static void __init init_uclamp_rq(struct rq *rq)
};
}
- rq->uclamp_flags = 0;
+ rq->uclamp_flags = UCLAMP_FLAG_IDLE;
}
static void __init init_uclamp(void)
@@ -6617,11 +6617,11 @@ static int __init setup_preempt_mode(char *str)
int mode = sched_dynamic_mode(str);
if (mode < 0) {
pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
- return 1;
+ return 0;
}
sched_dynamic_update(mode);
- return 0;
+ return 1;
}
__setup("preempt=", setup_preempt_mode);
@@ -8619,9 +8619,6 @@ void __init init_idle(struct task_struct *idle, int cpu)
idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY;
kthread_set_per_cpu(idle, cpu);
- scs_task_reset(idle);
- kasan_unpoison_task_stack(idle);
-
#ifdef CONFIG_SMP
/*
* It's possible that init_idle() gets called multiple times on a task,
@@ -8777,7 +8774,6 @@ void idle_task_exit(void)
finish_arch_post_lock_switch();
}
- scs_task_reset(current);
/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
}
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 872e481d5098..9392aea1804e 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
.sum_exec_runtime = p->se.sum_exec_runtime,
};
- task_cputime(p, &cputime.utime, &cputime.stime);
+ if (task_cputime(p, &cputime.utime, &cputime.stime))
+ cputime.sum_exec_runtime = task_sched_runtime(p);
cputime_adjust(&cputime, &p->prev_cputime, ut, st);
}
EXPORT_SYMBOL_GPL(task_cputime_adjusted);
@@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t)
* add up the pending nohz execution time since the last
* cputime snapshot.
*/
-void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
+bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
{
struct vtime *vtime = &t->vtime;
unsigned int seq;
u64 delta;
+ int ret;
if (!vtime_accounting_enabled()) {
*utime = t->utime;
*stime = t->stime;
- return;
+ return false;
}
do {
+ ret = false;
seq = read_seqcount_begin(&vtime->seqcount);
*utime = t->utime;
@@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
if (vtime->state < VTIME_SYS)
continue;
+ ret = true;
delta = vtime_delta(vtime);
/*
@@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
else
*utime += vtime->utime + delta;
} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+ return ret;
}
static int vtime_state_fetch(struct vtime *vtime, int cpu)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 76577d1642a5..eca38107b32f 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -238,6 +238,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode)
}
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
+void __wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+ __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE));
+ /* POLLFREE must have cleared the queue. */
+ WARN_ON_ONCE(waitqueue_active(wq_head));
+}
+
/*
* Note: we use "set_current_state()" _after_ the wait-queue add,
* because we need a memory barrier there on SMP, so that any
diff --git a/kernel/signal.c b/kernel/signal.c
index 7c4b7ae714d4..dfcee3888b00 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1298,6 +1298,12 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p
return ret;
}
+enum sig_handler {
+ HANDLER_CURRENT, /* If reachable use the current handler */
+ HANDLER_SIG_DFL, /* Always use SIG_DFL handler semantics */
+ HANDLER_EXIT, /* Only visible as the process exit code */
+};
+
/*
* Force a signal that the process can't ignore: if necessary
* we unblock the signal and change any SIG_IGN to SIG_DFL.
@@ -1310,7 +1316,8 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p
* that is why we also clear SIGNAL_UNKILLABLE.
*/
static int
-force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool sigdfl)
+force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
+ enum sig_handler handler)
{
unsigned long int flags;
int ret, blocked, ignored;
@@ -1321,9 +1328,10 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool
action = &t->sighand->action[sig-1];
ignored = action->sa.sa_handler == SIG_IGN;
blocked = sigismember(&t->blocked, sig);
- if (blocked || ignored || sigdfl) {
+ if (blocked || ignored || (handler != HANDLER_CURRENT)) {
action->sa.sa_handler = SIG_DFL;
- action->sa.sa_flags |= SA_IMMUTABLE;
+ if (handler == HANDLER_EXIT)
+ action->sa.sa_flags |= SA_IMMUTABLE;
if (blocked) {
sigdelset(&t->blocked, sig);
recalc_sigpending_and_wake(t);
@@ -1343,7 +1351,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool
int force_sig_info(struct kernel_siginfo *info)
{
- return force_sig_info_to_task(info, current, false);
+ return force_sig_info_to_task(info, current, HANDLER_CURRENT);
}
/*
@@ -1660,7 +1668,20 @@ void force_fatal_sig(int sig)
info.si_code = SI_KERNEL;
info.si_pid = 0;
info.si_uid = 0;
- force_sig_info_to_task(&info, current, true);
+ force_sig_info_to_task(&info, current, HANDLER_SIG_DFL);
+}
+
+void force_exit_sig(int sig)
+{
+ struct kernel_siginfo info;
+
+ clear_siginfo(&info);
+ info.si_signo = sig;
+ info.si_errno = 0;
+ info.si_code = SI_KERNEL;
+ info.si_pid = 0;
+ info.si_uid = 0;
+ force_sig_info_to_task(&info, current, HANDLER_EXIT);
}
/*
@@ -1693,7 +1714,7 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr
info.si_flags = flags;
info.si_isr = isr;
#endif
- return force_sig_info_to_task(&info, t, false);
+ return force_sig_info_to_task(&info, t, HANDLER_CURRENT);
}
int force_sig_fault(int sig, int code, void __user *addr
@@ -1813,7 +1834,8 @@ int force_sig_seccomp(int syscall, int reason, bool force_coredump)
info.si_errno = reason;
info.si_arch = syscall_get_arch(current);
info.si_syscall = syscall;
- return force_sig_info_to_task(&info, current, force_coredump);
+ return force_sig_info_to_task(&info, current,
+ force_coredump ? HANDLER_EXIT : HANDLER_CURRENT);
}
/* For the crazy architectures that include trap information in
@@ -4163,6 +4185,15 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp,
ss_mode != 0))
return -EINVAL;
+ /*
+ * Return before taking any locks if no actual
+ * sigaltstack changes were requested.
+ */
+ if (t->sas_ss_sp == (unsigned long)ss_sp &&
+ t->sas_ss_size == ss_size &&
+ t->sas_ss_flags == ss_flags)
+ return 0;
+
sigaltstack_lock();
if (ss_mode == SS_DISABLE) {
ss_size = 0;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 322b65d45676..41f470929e99 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -595,7 +595,8 @@ void irq_enter_rcu(void)
{
__irq_enter_raw();
- if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))
+ if (tick_nohz_full_cpu(smp_processor_id()) ||
+ (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)))
tick_irq_enter();
account_hardirq_enter(current);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6bffe5af8cb1..17a283ce2b20 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void)
now = ktime_get();
if (ts->idle_active)
tick_nohz_stop_idle(ts, now);
+ /*
+ * If all CPUs are idle. We may need to update a stale jiffies value.
+ * Note nohz_full is a special case: a timekeeper is guaranteed to stay
+ * alive but it might be busy looping with interrupts disabled in some
+ * rare case (typically stop machine). So we must make sure we have a
+ * last resort.
+ */
if (ts->tick_stopped)
tick_nohz_update_jiffies(now);
}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index b348749a9fc6..dcdcb85121e4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1306,8 +1306,7 @@ int do_settimeofday64(const struct timespec64 *ts)
timekeeping_forward_now(tk);
xt = tk_xtime(tk);
- ts_delta.tv_sec = ts->tv_sec - xt.tv_sec;
- ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec;
+ ts_delta = timespec64_sub(*ts, xt);
if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) {
ret = -EINVAL;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index e3d2c23c413d..85f1021ad459 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs)
EXPORT_SYMBOL(msleep_interruptible);
/**
- * usleep_range - Sleep for an approximate time
- * @min: Minimum time in usecs to sleep
- * @max: Maximum time in usecs to sleep
+ * usleep_range_state - Sleep for an approximate time in a given state
+ * @min: Minimum time in usecs to sleep
+ * @max: Maximum time in usecs to sleep
+ * @state: State of the current task that will be while sleeping
*
* In non-atomic context where the exact wakeup time is flexible, use
- * usleep_range() instead of udelay(). The sleep improves responsiveness
+ * usleep_range_state() instead of udelay(). The sleep improves responsiveness
* by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces
* power usage by allowing hrtimers to take advantage of an already-
* scheduled interrupt instead of scheduling a new one just for this sleep.
*/
-void __sched usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range_state(unsigned long min, unsigned long max,
+ unsigned int state)
{
ktime_t exp = ktime_add_us(ktime_get(), min);
u64 delta = (u64)(max - min) * NSEC_PER_USEC;
for (;;) {
- __set_current_state(TASK_UNINTERRUPTIBLE);
+ __set_current_state(state);
/* Do not return before the requested sleep time has elapsed */
if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
break;
}
}
-EXPORT_SYMBOL(usleep_range);
+EXPORT_SYMBOL(usleep_range_state);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7396488793ff..ae9755037b7e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1111,8 +1111,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_ktime_get_boot_ns:
return &bpf_ktime_get_boot_ns_proto;
- case BPF_FUNC_ktime_get_coarse_ns:
- return &bpf_ktime_get_coarse_ns_proto;
case BPF_FUNC_tail_call:
return &bpf_tail_call_proto;
case BPF_FUNC_get_current_pid_tgid:
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 30bc880c3849..be5f6b32a012 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5217,6 +5217,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
{
struct ftrace_direct_func *direct;
struct ftrace_func_entry *entry;
+ struct ftrace_hash *hash;
int ret = -ENODEV;
mutex_lock(&direct_mutex);
@@ -5225,7 +5226,8 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
if (!entry)
goto out_unlock;
- if (direct_functions->count == 1)
+ hash = direct_ops.func_hash->filter_hash;
+ if (hash->count == 1)
unregister_ftrace_function(&direct_ops);
ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0);
@@ -5540,6 +5542,10 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
err = unregister_ftrace_function(ops);
remove_direct_functions_hash(hash, addr);
mutex_unlock(&direct_mutex);
+
+ /* cleanup for possible another register call */
+ ops->func = NULL;
+ ops->trampoline = 0;
return err;
}
EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f9139dc1262c..78ea542ce3bc 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3207,7 +3207,7 @@ struct trace_buffer_struct {
char buffer[4][TRACE_BUF_SIZE];
};
-static struct trace_buffer_struct *trace_percpu_buffer;
+static struct trace_buffer_struct __percpu *trace_percpu_buffer;
/*
* This allows for lockless recording. If we're nested too deeply, then
@@ -3217,7 +3217,7 @@ static char *get_trace_buf(void)
{
struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer);
- if (!buffer || buffer->nesting >= 4)
+ if (!trace_percpu_buffer || buffer->nesting >= 4)
return NULL;
buffer->nesting++;
@@ -3236,7 +3236,7 @@ static void put_trace_buf(void)
static int alloc_percpu_trace_buffer(void)
{
- struct trace_buffer_struct *buffers;
+ struct trace_buffer_struct __percpu *buffers;
if (trace_percpu_buffer)
return 0;
@@ -3812,6 +3812,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
iter->fmt[i] = '\0';
trace_seq_vprintf(&iter->seq, iter->fmt, ap);
+ /*
+ * If iter->seq is full, the above call no longer guarantees
+ * that ap is in sync with fmt processing, and further calls
+ * to va_arg() can return wrong positional arguments.
+ *
+ * Ensure that ap is no longer used in this case.
+ */
+ if (iter->seq.full) {
+ p = "";
+ break;
+ }
+
if (star)
len = va_arg(ap, int);
@@ -6706,9 +6718,7 @@ waitagain:
cnt = PAGE_SIZE - 1;
/* reset all but tr, trace, and overruns */
- memset(&iter->seq, 0,
- sizeof(struct trace_iterator) -
- offsetof(struct trace_iterator, seq));
+ memset_startat(iter, 0, seq);
cpumask_clear(iter->started);
trace_seq_init(&iter->seq);
iter->pos = -1;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6b60ab9475ed..38715aa6cfdf 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1366,14 +1366,26 @@ __event_trigger_test_discard(struct trace_event_file *file,
if (eflags & EVENT_FILE_FL_TRIGGER_COND)
*tt = event_triggers_call(file, buffer, entry, event);
- if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
- (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
- !filter_match_preds(file->filter, entry))) {
- __trace_event_discard_commit(buffer, event);
- return true;
- }
+ if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED |
+ EVENT_FILE_FL_FILTERED |
+ EVENT_FILE_FL_PID_FILTER))))
+ return false;
+
+ if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
+ goto discard;
+
+ if (file->flags & EVENT_FILE_FL_FILTERED &&
+ !filter_match_preds(file->filter, entry))
+ goto discard;
+
+ if ((file->flags & EVENT_FILE_FL_PID_FILTER) &&
+ trace_event_ignore_this_pid(file))
+ goto discard;
return false;
+ discard:
+ __trace_event_discard_commit(buffer, event);
+ return true;
}
/**
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4021b9a79f93..92be9cb1d7d4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2678,12 +2678,24 @@ static struct trace_event_file *
trace_create_new_event(struct trace_event_call *call,
struct trace_array *tr)
{
+ struct trace_pid_list *no_pid_list;
+ struct trace_pid_list *pid_list;
struct trace_event_file *file;
+ unsigned int first;
file = kmem_cache_alloc(file_cachep, GFP_TRACE);
if (!file)
return NULL;
+ pid_list = rcu_dereference_protected(tr->filtered_pids,
+ lockdep_is_held(&event_mutex));
+ no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+ lockdep_is_held(&event_mutex));
+
+ if (!trace_pid_list_first(pid_list, &first) ||
+ !trace_pid_list_first(no_pid_list, &first))
+ file->flags |= EVENT_FILE_FL_PID_FILTER;
+
file->event_call = call;
file->tr = tr;
atomic_set(&file->sm_ref, 0);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 8a10046c775f..319f9c8ca7e7 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2576,28 +2576,27 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
/* Split the expression string at the root operator */
if (!sep)
- goto free;
+ return ERR_PTR(-EINVAL);
+
*sep = '\0';
operand1_str = str;
str = sep+1;
/* Binary operator requires both operands */
if (*operand1_str == '\0' || *str == '\0')
- goto free;
+ return ERR_PTR(-EINVAL);
operand_flags = 0;
/* LHS of string is an expression e.g. a+b in a+b+c */
operand1 = parse_expr(hist_data, file, operand1_str, operand_flags, NULL, n_subexprs);
- if (IS_ERR(operand1)) {
- ret = PTR_ERR(operand1);
- operand1 = NULL;
- goto free;
- }
+ if (IS_ERR(operand1))
+ return ERR_CAST(operand1);
+
if (operand1->flags & HIST_FIELD_FL_STRING) {
hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str));
ret = -EINVAL;
- goto free;
+ goto free_op1;
}
/* RHS of string is another expression e.g. c in a+b+c */
@@ -2605,13 +2604,12 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, n_subexprs);
if (IS_ERR(operand2)) {
ret = PTR_ERR(operand2);
- operand2 = NULL;
- goto free;
+ goto free_op1;
}
if (operand2->flags & HIST_FIELD_FL_STRING) {
hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
ret = -EINVAL;
- goto free;
+ goto free_operands;
}
switch (field_op) {
@@ -2629,12 +2627,12 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
break;
default:
ret = -EINVAL;
- goto free;
+ goto free_operands;
}
ret = check_expr_operands(file->tr, operand1, operand2, &var1, &var2);
if (ret)
- goto free;
+ goto free_operands;
operand_flags = var1 ? var1->flags : operand1->flags;
operand2_flags = var2 ? var2->flags : operand2->flags;
@@ -2653,12 +2651,13 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
expr = create_hist_field(hist_data, NULL, flags, var_name);
if (!expr) {
ret = -ENOMEM;
- goto free;
+ goto free_operands;
}
operand1->read_once = true;
operand2->read_once = true;
+ /* The operands are now owned and free'd by 'expr' */
expr->operands[0] = operand1;
expr->operands[1] = operand2;
@@ -2669,7 +2668,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
if (!divisor) {
hist_err(file->tr, HIST_ERR_DIVISION_BY_ZERO, errpos(str));
ret = -EDOM;
- goto free;
+ goto free_expr;
}
/*
@@ -2709,18 +2708,22 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
if (!expr->type) {
ret = -ENOMEM;
- goto free;
+ goto free_expr;
}
expr->name = expr_str(expr, 0);
}
return expr;
-free:
- destroy_hist_field(operand1, 0);
+
+free_operands:
destroy_hist_field(operand2, 0);
- destroy_hist_field(expr, 0);
+free_op1:
+ destroy_hist_field(operand1, 0);
+ return ERR_PTR(ret);
+free_expr:
+ destroy_hist_field(expr, 0);
return ERR_PTR(ret);
}
@@ -3026,8 +3029,10 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,
if (val->flags & HIST_FIELD_FL_STRING) {
char *str = elt_data->field_var_str[j++];
char *val_str = (char *)(uintptr_t)var_val;
+ unsigned int size;
- strscpy(str, val_str, val->size);
+ size = min(val->size, STR_VAR_LEN_MAX);
+ strscpy(str, val_str, size);
var_val = (u64)(uintptr_t)str;
}
tracing_map_set_var(elt, var_idx, var_val);
@@ -3752,7 +3757,7 @@ static int check_synth_field(struct synth_event *event,
if (strcmp(field->type, hist_field->type) != 0) {
if (field->size != hist_field->size ||
- field->is_signed != hist_field->is_signed)
+ (!field->is_string && field->is_signed != hist_field->is_signed))
return -EINVAL;
}
@@ -4914,6 +4919,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
if (hist_field->flags & HIST_FIELD_FL_STRING) {
unsigned int str_start, var_str_idx, idx;
char *str, *val_str;
+ unsigned int size;
str_start = hist_data->n_field_var_str +
hist_data->n_save_var_str;
@@ -4922,7 +4928,9 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
str = elt_data->field_var_str[idx];
val_str = (char *)(uintptr_t)hist_val;
- strscpy(str, val_str, hist_field->size);
+
+ size = min(hist_field->size, STR_VAR_LEN_MAX);
+ strscpy(str, val_str, size);
hist_val = (u64)(uintptr_t)str;
}
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 22db3ce95e74..ca9c13b2ecf4 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1237,9 +1237,8 @@ static int __create_synth_event(const char *name, const char *raw_fields)
argv + consumed, &consumed,
&field_version);
if (IS_ERR(field)) {
- argv_free(argv);
ret = PTR_ERR(field);
- goto err;
+ goto err_free_arg;
}
/*
@@ -1262,18 +1261,19 @@ static int __create_synth_event(const char *name, const char *raw_fields)
if (cmd_version > 1 && n_fields_this_loop >= 1) {
synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str));
ret = -EINVAL;
- goto err;
+ goto err_free_arg;
}
fields[n_fields++] = field;
if (n_fields == SYNTH_FIELDS_MAX) {
synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0);
ret = -EINVAL;
- goto err;
+ goto err_free_arg;
}
n_fields_this_loop++;
}
+ argv_free(argv);
if (consumed < argc) {
synth_err(SYNTH_ERR_INVALID_CMD, 0);
@@ -1281,7 +1281,6 @@ static int __create_synth_event(const char *name, const char *raw_fields)
goto err;
}
- argv_free(argv);
}
if (n_fields == 0) {
@@ -1307,6 +1306,8 @@ static int __create_synth_event(const char *name, const char *raw_fields)
kfree(saved_fields);
return ret;
+ err_free_arg:
+ argv_free(argv);
err:
for (i = 0; i < n_fields; i++)
free_synth_field(fields[i]);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 0a5c0db3137e..f5f0039d31e5 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1313,6 +1313,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
return 0;
list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ tu = container_of(pos, struct trace_uprobe, tp);
err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
if (err) {
uprobe_perf_close(call, event);
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 39bb56d2dcbe..9628b5571846 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -15,6 +15,7 @@
#include <linux/jhash.h>
#include <linux/slab.h>
#include <linux/sort.h>
+#include <linux/kmemleak.h>
#include "tracing_map.h"
#include "trace.h"
@@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a)
for (i = 0; i < a->n_pages; i++) {
if (!a->pages[i])
break;
+ kmemleak_free(a->pages[i]);
free_page((unsigned long)a->pages[i]);
}
@@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
if (!a->pages[i])
goto free;
+ kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL);
}
out:
return a;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 4f5613dac227..7b32c356ebc5 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -264,15 +264,16 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
{
struct ucounts *iter;
+ long max = LONG_MAX;
long ret = 0;
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
- long max = READ_ONCE(iter->ns->ucount_max[type]);
long new = atomic_long_add_return(v, &iter->ucount[type]);
if (new < 0 || new > max)
ret = LONG_MAX;
else if (iter == ucounts)
ret = new;
+ max = READ_ONCE(iter->ns->ucount_max[type]);
}
return ret;
}
@@ -312,15 +313,16 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
{
/* Caller must hold a reference to ucounts */
struct ucounts *iter;
+ long max = LONG_MAX;
long dec, ret = 0;
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
- long max = READ_ONCE(iter->ns->ucount_max[type]);
long new = atomic_long_add_return(1, &iter->ucount[type]);
if (new < 0 || new > max)
goto unwind;
if (iter == ucounts)
ret = new;
+ max = READ_ONCE(iter->ns->ucount_max[type]);
/*
* Grab an extra ucount reference for the caller when
* the rlimit count was previously 0.
@@ -339,15 +341,16 @@ unwind:
return 0;
}
-bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max)
+bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long rlimit)
{
struct ucounts *iter;
- if (get_ucounts_value(ucounts, type) > max)
- return true;
+ long max = rlimit;
+ if (rlimit > LONG_MAX)
+ max = LONG_MAX;
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
- max = READ_ONCE(iter->ns->ucount_max[type]);
if (get_ucounts_value(iter, type) > max)
return true;
+ max = READ_ONCE(iter->ns->ucount_max[type]);
}
return false;
}
generated by cgit (git 2.34.1) at 2024-04-20 10:22:10 +0000