summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/btf.c1
-rw-r--r--kernel/bpf/cgroup.c13
-rw-r--r--kernel/bpf/core.c17
-rw-r--r--kernel/bpf/local_storage.c28
-rw-r--r--kernel/bpf/tnum.c9
-rw-r--r--kernel/bpf/trampoline.c64
-rw-r--r--kernel/bpf/verifier.c89
-rw-r--r--kernel/cpu.c143
-rw-r--r--kernel/cred.c10
-rw-r--r--kernel/events/core.c6
-rw-r--r--kernel/exit.c12
-rw-r--r--kernel/fork.c10
-rw-r--r--kernel/futex.c1
-rw-r--r--kernel/locking/lockdep.c7
-rw-r--r--kernel/locking/mutex.c4
-rw-r--r--kernel/locking/rwsem.c4
-rw-r--r--kernel/locking/spinlock_debug.c32
-rw-r--r--kernel/module.c6
-rw-r--r--kernel/ptrace.c15
-rw-r--r--kernel/rseq.c2
-rw-r--r--kernel/sched/cpufreq.c18
-rw-r--r--kernel/sched/cpufreq_schedutil.c8
-rw-r--r--kernel/sched/fair.c13
-rw-r--r--kernel/sched/psi.c5
-rw-r--r--kernel/seccomp.c7
-rw-r--r--kernel/taskstats.c30
-rw-r--r--kernel/time/posix-clock.c31
-rw-r--r--kernel/time/posix-stubs.c3
-rw-r--r--kernel/time/tick-sched.c14
-rw-r--r--kernel/trace/fgraph.c23
-rw-r--r--kernel/trace/ftrace.c25
-rw-r--r--kernel/trace/ring_buffer.c2
-rw-r--r--kernel/trace/trace.c14
-rw-r--r--kernel/trace/trace_events.c8
-rw-r--r--kernel/trace/trace_events_filter.c2
-rw-r--r--kernel/trace/trace_events_hist.c21
-rw-r--r--kernel/trace/trace_events_inject.c4
-rw-r--r--kernel/trace/trace_sched_wakeup.c4
-rw-r--r--kernel/trace/trace_seq.c2
-rw-r--r--kernel/trace/trace_stack.c5
-rw-r--r--kernel/trace/tracing_map.c4
-rw-r--r--kernel/workqueue.c4
42 files changed, 455 insertions, 265 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 7d40da240891..ed2075884724 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3470,6 +3470,7 @@ static u8 bpf_ctx_convert_map[] = {
[_id] = __ctx_convert##_id,
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
+ 0, /* avoid empty array */
};
#undef BPF_MAP_TYPE
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 9f90d3c92bda..9e43b72eb619 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp)
*/
static void cgroup_bpf_release(struct work_struct *work)
{
- struct cgroup *cgrp = container_of(work, struct cgroup,
- bpf.release_work);
+ struct cgroup *p, *cgrp = container_of(work, struct cgroup,
+ bpf.release_work);
enum bpf_cgroup_storage_type stype;
struct bpf_prog_array *old_array;
unsigned int type;
@@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work)
mutex_unlock(&cgroup_mutex);
+ for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
+ cgroup_bpf_put(p);
+
percpu_ref_exit(&cgrp->bpf.refcnt);
cgroup_put(cgrp);
}
@@ -199,6 +202,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
*/
#define NR ARRAY_SIZE(cgrp->bpf.effective)
struct bpf_prog_array *arrays[NR] = {};
+ struct cgroup *p;
int ret, i;
ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0,
@@ -206,6 +210,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
if (ret)
return ret;
+ for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
+ cgroup_bpf_get(p);
+
for (i = 0; i < NR; i++)
INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
@@ -1341,7 +1348,7 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
*insn++ = BPF_LDX_MEM(
BPF_SIZE(si->code), si->dst_reg, si->src_reg,
bpf_target_off(struct bpf_sysctl_kern, write,
- FIELD_SIZEOF(struct bpf_sysctl_kern,
+ sizeof_field(struct bpf_sysctl_kern,
write),
target_size));
break;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 49e32acad7d8..af6b738cf435 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2043,23 +2043,28 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux)
for_each_cgroup_storage_type(stype) {
if (!aux->cgroup_storage[stype])
continue;
- bpf_cgroup_storage_release(aux->prog,
- aux->cgroup_storage[stype]);
+ bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]);
}
}
-static void bpf_free_used_maps(struct bpf_prog_aux *aux)
+void __bpf_free_used_maps(struct bpf_prog_aux *aux,
+ struct bpf_map **used_maps, u32 len)
{
struct bpf_map *map;
- int i;
+ u32 i;
bpf_free_cgroup_storage(aux);
- for (i = 0; i < aux->used_map_cnt; i++) {
- map = aux->used_maps[i];
+ for (i = 0; i < len; i++) {
+ map = used_maps[i];
if (map->ops->map_poke_untrack)
map->ops->map_poke_untrack(map, aux);
bpf_map_put(map);
}
+}
+
+static void bpf_free_used_maps(struct bpf_prog_aux *aux)
+{
+ __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt);
kfree(aux->used_maps);
}
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 2ba750725cb2..33d01866bcc2 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -20,7 +20,7 @@ struct bpf_cgroup_storage_map {
struct bpf_map map;
spinlock_t lock;
- struct bpf_prog *prog;
+ struct bpf_prog_aux *aux;
struct rb_root root;
struct list_head list;
};
@@ -357,7 +357,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
* The first field must be a 64 bit integer at 0 offset.
*/
m = (struct btf_member *)(key_type + 1);
- size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id);
+ size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id);
if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
return -EINVAL;
@@ -366,7 +366,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
*/
m++;
offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
- size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type);
+ size = sizeof_field(struct bpf_cgroup_storage_key, attach_type);
if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
return -EINVAL;
@@ -420,7 +420,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
.map_seq_show_elem = cgroup_storage_seq_show_elem,
};
-int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
+int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map)
{
enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
@@ -428,14 +428,14 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
spin_lock_bh(&map->lock);
- if (map->prog && map->prog != prog)
+ if (map->aux && map->aux != aux)
goto unlock;
- if (prog->aux->cgroup_storage[stype] &&
- prog->aux->cgroup_storage[stype] != _map)
+ if (aux->cgroup_storage[stype] &&
+ aux->cgroup_storage[stype] != _map)
goto unlock;
- map->prog = prog;
- prog->aux->cgroup_storage[stype] = _map;
+ map->aux = aux;
+ aux->cgroup_storage[stype] = _map;
ret = 0;
unlock:
spin_unlock_bh(&map->lock);
@@ -443,16 +443,16 @@ unlock:
return ret;
}
-void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map)
+void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map)
{
enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
spin_lock_bh(&map->lock);
- if (map->prog == prog) {
- WARN_ON(prog->aux->cgroup_storage[stype] != _map);
- map->prog = NULL;
- prog->aux->cgroup_storage[stype] = NULL;
+ if (map->aux == aux) {
+ WARN_ON(aux->cgroup_storage[stype] != _map);
+ map->aux = NULL;
+ aux->cgroup_storage[stype] = NULL;
}
spin_unlock_bh(&map->lock);
}
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index ca52b9642943..d4f335a9a899 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift)
return TNUM(a.value >> shift, a.mask >> shift);
}
-struct tnum tnum_arshift(struct tnum a, u8 min_shift)
+struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness)
{
/* if a.value is negative, arithmetic shifting by minimum shift
* will have larger negative offset compared to more shifting.
* If a.value is nonnegative, arithmetic shifting by minimum shift
* will have larger positive offset compare to more shifting.
*/
- return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift);
+ if (insn_bitness == 32)
+ return TNUM((u32)(((s32)a.value) >> min_shift),
+ (u32)(((s32)a.mask) >> min_shift));
+ else
+ return TNUM((s64)a.value >> min_shift,
+ (s64)a.mask >> min_shift);
}
struct tnum tnum_add(struct tnum a, struct tnum b)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 7e89f1f49d77..23b0d5cfd47e 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -3,6 +3,7 @@
#include <linux/hash.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/ftrace.h>
/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */
#define TRAMPOLINE_HASH_BITS 10
@@ -59,6 +60,60 @@ out:
return tr;
}
+static int is_ftrace_location(void *ip)
+{
+ long addr;
+
+ addr = ftrace_location((long)ip);
+ if (!addr)
+ return 0;
+ if (WARN_ON_ONCE(addr != (long)ip))
+ return -EFAULT;
+ return 1;
+}
+
+static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
+{
+ void *ip = tr->func.addr;
+ int ret;
+
+ if (tr->func.ftrace_managed)
+ ret = unregister_ftrace_direct((long)ip, (long)old_addr);
+ else
+ ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+ return ret;
+}
+
+static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr)
+{
+ void *ip = tr->func.addr;
+ int ret;
+
+ if (tr->func.ftrace_managed)
+ ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr);
+ else
+ ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
+ return ret;
+}
+
+/* first time registering */
+static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
+{
+ void *ip = tr->func.addr;
+ int ret;
+
+ ret = is_ftrace_location(ip);
+ if (ret < 0)
+ return ret;
+ tr->func.ftrace_managed = ret;
+
+ if (tr->func.ftrace_managed)
+ ret = register_ftrace_direct((long)ip, (long)new_addr);
+ else
+ ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+ return ret;
+}
+
/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
* bytes on x86. Pick a number to fit into PAGE_SIZE / 2
*/
@@ -77,8 +132,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
int err;
if (fentry_cnt + fexit_cnt == 0) {
- err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL,
- old_image, NULL);
+ err = unregister_fentry(tr, old_image);
tr->selector = 0;
goto out;
}
@@ -105,12 +159,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
if (tr->selector)
/* progs already running at this address */
- err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL,
- old_image, new_image);
+ err = modify_fentry(tr, old_image, new_image);
else
/* first time registering */
- err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, NULL,
- new_image);
+ err = register_fentry(tr, new_image);
if (err)
goto out;
tr->selector++;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 034ef81f935b..7d530ce8719d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -907,7 +907,8 @@ static const int caller_saved[CALLER_SAVED_REGS] = {
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
-static void __mark_reg_not_init(struct bpf_reg_state *reg);
+static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg);
/* Mark the unknown part of a register (variable offset or scalar value) as
* known to have the value @imm.
@@ -945,7 +946,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env,
verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
__mark_reg_known_zero(regs + regno);
@@ -1054,7 +1055,8 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg)
}
/* Mark a register as having a completely unknown (scalar) value. */
-static void __mark_reg_unknown(struct bpf_reg_state *reg)
+static void __mark_reg_unknown(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg)
{
/*
* Clear type, id, off, and union(map_ptr, range) and
@@ -1064,6 +1066,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg)
reg->type = SCALAR_VALUE;
reg->var_off = tnum_unknown;
reg->frameno = 0;
+ reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
+ true : false;
__mark_reg_unbounded(reg);
}
@@ -1074,19 +1078,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env,
verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
- regs += regno;
- __mark_reg_unknown(regs);
- /* constant backtracking is enabled for root without bpf2bpf calls */
- regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
- true : false;
+ __mark_reg_unknown(env, regs + regno);
}
-static void __mark_reg_not_init(struct bpf_reg_state *reg)
+static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg)
{
- __mark_reg_unknown(reg);
+ __mark_reg_unknown(env, reg);
reg->type = NOT_INIT;
}
@@ -1097,10 +1098,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env,
verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
}
#define DEF_NOT_SUBREG (0)
@@ -3234,7 +3235,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
}
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
state->stack[spi].spilled_ptr.type == SCALAR_VALUE) {
- __mark_reg_unknown(&state->stack[spi].spilled_ptr);
+ __mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
for (j = 0; j < BPF_REG_SIZE; j++)
state->stack[spi].slot_type[j] = STACK_MISC;
goto mark;
@@ -3892,7 +3893,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
if (!reg)
continue;
if (reg_is_pkt_pointer_any(reg))
- __mark_reg_unknown(reg);
+ __mark_reg_unknown(env, reg);
}
}
@@ -3920,7 +3921,7 @@ static void release_reg_references(struct bpf_verifier_env *env,
if (!reg)
continue;
if (reg->ref_obj_id == ref_obj_id)
- __mark_reg_unknown(reg);
+ __mark_reg_unknown(env, reg);
}
}
@@ -4134,6 +4135,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
struct bpf_map *map = meta->map_ptr;
struct tnum range;
u64 val;
+ int err;
if (func_id != BPF_FUNC_tail_call)
return 0;
@@ -4150,6 +4152,10 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
return 0;
}
+ err = mark_chain_precision(env, BPF_REG_3);
+ if (err)
+ return err;
+
val = reg->var_off.value;
if (bpf_map_key_unseen(aux))
bpf_map_key_store(aux, val);
@@ -4577,7 +4583,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
/* Taint dst register if offset had invalid bounds derived from
* e.g. dead branches.
*/
- __mark_reg_unknown(dst_reg);
+ __mark_reg_unknown(env, dst_reg);
return 0;
}
@@ -4829,13 +4835,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
/* Taint dst register if offset had invalid bounds derived from
* e.g. dead branches.
*/
- __mark_reg_unknown(dst_reg);
+ __mark_reg_unknown(env, dst_reg);
return 0;
}
if (!src_known &&
opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
- __mark_reg_unknown(dst_reg);
+ __mark_reg_unknown(env, dst_reg);
return 0;
}
@@ -5043,9 +5049,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
/* Upon reaching here, src_known is true and
* umax_val is equal to umin_val.
*/
- dst_reg->smin_value >>= umin_val;
- dst_reg->smax_value >>= umin_val;
- dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
+ if (insn_bitness == 32) {
+ dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val);
+ dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val);
+ } else {
+ dst_reg->smin_value >>= umin_val;
+ dst_reg->smax_value >>= umin_val;
+ }
+
+ dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val,
+ insn_bitness);
/* blow away the dst_reg umin_value/umax_value and rely on
* dst_reg var_off to refine the result.
@@ -6258,6 +6271,7 @@ static bool may_access_skb(enum bpf_prog_type type)
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = cur_regs(env);
+ static const int ctx_reg = BPF_REG_6;
u8 mode = BPF_MODE(insn->code);
int i, err;
@@ -6291,7 +6305,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
/* check whether implicit source operand (register R6) is readable */
- err = check_reg_arg(env, BPF_REG_6, SRC_OP);
+ err = check_reg_arg(env, ctx_reg, SRC_OP);
if (err)
return err;
@@ -6310,7 +6324,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return -EINVAL;
}
- if (regs[BPF_REG_6].type != PTR_TO_CTX) {
+ if (regs[ctx_reg].type != PTR_TO_CTX) {
verbose(env,
"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
return -EINVAL;
@@ -6323,6 +6337,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
}
+ err = check_ctx_reg(env, &regs[ctx_reg], ctx_reg);
+ if (err < 0)
+ return err;
+
/* reset caller saved regs to unreadable */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
@@ -6977,7 +6995,7 @@ static void clean_func_state(struct bpf_verifier_env *env,
/* since the register is unused, clear its state
* to make further comparison simpler
*/
- __mark_reg_not_init(&st->regs[i]);
+ __mark_reg_not_init(env, &st->regs[i]);
}
for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) {
@@ -6985,7 +7003,7 @@ static void clean_func_state(struct bpf_verifier_env *env,
/* liveness must not touch this stack slot anymore */
st->stack[i].spilled_ptr.live |= REG_LIVE_DONE;
if (!(live & REG_LIVE_READ)) {
- __mark_reg_not_init(&st->stack[i].spilled_ptr);
+ __mark_reg_not_init(env, &st->stack[i].spilled_ptr);
for (j = 0; j < BPF_REG_SIZE; j++)
st->stack[i].slot_type[j] = STACK_INVALID;
}
@@ -8268,7 +8286,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
env->used_maps[env->used_map_cnt++] = map;
if (bpf_map_is_cgroup_storage(map) &&
- bpf_cgroup_storage_assign(env->prog, map)) {
+ bpf_cgroup_storage_assign(env->prog->aux, map)) {
verbose(env, "only one cgroup storage of each type is allowed\n");
fdput(f);
return -EBUSY;
@@ -8298,18 +8316,8 @@ next_insn:
/* drop refcnt of maps used by the rejected program */
static void release_maps(struct bpf_verifier_env *env)
{
- enum bpf_cgroup_storage_type stype;
- int i;
-
- for_each_cgroup_storage_type(stype) {
- if (!env->prog->aux->cgroup_storage[stype])
- continue;
- bpf_cgroup_storage_release(env->prog,
- env->prog->aux->cgroup_storage[stype]);
- }
-
- for (i = 0; i < env->used_map_cnt; i++)
- bpf_map_put(env->used_maps[i]);
+ __bpf_free_used_maps(env->prog->aux, env->used_maps,
+ env->used_map_cnt);
}
/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
@@ -9282,7 +9290,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
insn->code = BPF_JMP | BPF_TAIL_CALL;
aux = &env->insn_aux_data[i + delta];
- if (prog->jit_requested && !expect_blinding &&
+ if (env->allow_ptr_leaks && !expect_blinding &&
+ prog->jit_requested &&
!bpf_map_key_poisoned(aux) &&
!bpf_map_ptr_poisoned(aux) &&
!bpf_map_ptr_unpriv(aux)) {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a59cc980adad..4dc279ed3b2d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1909,6 +1909,78 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
}
EXPORT_SYMBOL(__cpuhp_remove_state);
+#ifdef CONFIG_HOTPLUG_SMT
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = true;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = false;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ for_each_online_cpu(cpu) {
+ if (topology_is_primary_thread(cpu))
+ continue;
+ ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+ if (ret)
+ break;
+ /*
+ * As this needs to hold the cpu maps lock it's impossible
+ * to call device_offline() because that ends up calling
+ * cpu_down() which takes cpu maps lock. cpu maps lock
+ * needs to be held as this might race against in kernel
+ * abusers of the hotplug machinery (thermal management).
+ *
+ * So nothing would update device:offline state. That would
+ * leave the sysfs entry stale and prevent onlining after
+ * smt control has been changed to 'off' again. This is
+ * called under the sysfs hotplug lock, so it is properly
+ * serialized against the regular offline usage.
+ */
+ cpuhp_offline_cpu_device(cpu);
+ }
+ if (!ret)
+ cpu_smt_control = ctrlval;
+ cpu_maps_update_done();
+ return ret;
+}
+
+int cpuhp_smt_enable(void)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ cpu_smt_control = CPU_SMT_ENABLED;
+ for_each_present_cpu(cpu) {
+ /* Skip online CPUs and CPUs on offline nodes */
+ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+ continue;
+ ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+ if (ret)
+ break;
+ /* See comment in cpuhp_smt_disable() */
+ cpuhp_online_cpu_device(cpu);
+ }
+ cpu_maps_update_done();
+ return ret;
+}
+#endif
+
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t show_cpuhp_state(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -2063,77 +2135,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
#ifdef CONFIG_HOTPLUG_SMT
-static void cpuhp_offline_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = true;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
-}
-
-static void cpuhp_online_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = false;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_ONLINE);
-}
-
-int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- for_each_online_cpu(cpu) {
- if (topology_is_primary_thread(cpu))
- continue;
- ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
- if (ret)
- break;
- /*
- * As this needs to hold the cpu maps lock it's impossible
- * to call device_offline() because that ends up calling
- * cpu_down() which takes cpu maps lock. cpu maps lock
- * needs to be held as this might race against in kernel
- * abusers of the hotplug machinery (thermal management).
- *
- * So nothing would update device:offline state. That would
- * leave the sysfs entry stale and prevent onlining after
- * smt control has been changed to 'off' again. This is
- * called under the sysfs hotplug lock, so it is properly
- * serialized against the regular offline usage.
- */
- cpuhp_offline_cpu_device(cpu);
- }
- if (!ret)
- cpu_smt_control = ctrlval;
- cpu_maps_update_done();
- return ret;
-}
-
-int cpuhp_smt_enable(void)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- cpu_smt_control = CPU_SMT_ENABLED;
- for_each_present_cpu(cpu) {
- /* Skip online CPUs and CPUs on offline nodes */
- if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
- continue;
- ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
- if (ret)
- break;
- /* See comment in cpuhp_smt_disable() */
- cpuhp_online_cpu_device(cpu);
- }
- cpu_maps_update_done();
- return ret;
-}
-
-
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
diff --git a/kernel/cred.c b/kernel/cred.c
index c0a4c12d38b2..809a985b1793 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -175,8 +175,8 @@ void exit_creds(struct task_struct *tsk)
put_cred(cred);
#ifdef CONFIG_KEYS_REQUEST_CACHE
- key_put(current->cached_requested_key);
- current->cached_requested_key = NULL;
+ key_put(tsk->cached_requested_key);
+ tsk->cached_requested_key = NULL;
#endif
}
@@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void)
new->magic = CRED_MAGIC;
#endif
- if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+ if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
return new;
@@ -282,7 +282,7 @@ struct cred *prepare_creds(void)
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
validate_creds(new);
return new;
@@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
#ifdef CONFIG_SECURITY
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
put_cred(old);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4ff86d57f9e5..2173c23c25b4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10523,7 +10523,7 @@ again:
goto unlock;
}
- list_for_each_entry_rcu(pmu, &pmus, entry) {
+ list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) {
ret = perf_try_init_event(pmu, event);
if (!ret)
goto unlock;
@@ -11465,8 +11465,10 @@ SYSCALL_DEFINE5(perf_event_open,
}
}
- if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader))
+ if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) {
+ err = -EINVAL;
goto err_locked;
+ }
/*
* Must be under the same ctx::mutex as perf_install_in_context(),
diff --git a/kernel/exit.c b/kernel/exit.c
index bcbd59888e67..2833ffb0c211 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
}
write_unlock_irq(&tasklist_lock);
- if (unlikely(pid_ns == &init_pid_ns)) {
- panic("Attempted to kill init! exitcode=0x%08x\n",
- father->signal->group_exit_code ?: father->exit_code);
- }
list_for_each_entry_safe(p, n, dead, ptrace_entry) {
list_del_init(&p->ptrace_entry);
@@ -766,6 +762,14 @@ void __noreturn do_exit(long code)
acct_update_integrals(tsk);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
+ /*
+ * If the last thread of global init has exited, panic
+ * immediately to get a useable coredump.
+ */
+ if (unlikely(is_global_init(tsk)))
+ panic("Attempted to kill init! exitcode=0x%08x\n",
+ tsk->signal->group_exit_code ?: (int)code);
+
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2508a4f238a3..080809560072 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2578,6 +2578,16 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
#endif
#ifdef __ARCH_WANT_SYS_CLONE3
+
+/*
+ * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from
+ * the registers containing the syscall arguments for clone. This doesn't work
+ * with clone3 since the TLS value is passed in clone_args instead.
+ */
+#ifndef CONFIG_HAVE_COPY_THREAD_TLS
+#error clone3 requires copy_thread_tls support in arch
+#endif
+
noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
struct clone_args __user *uargs,
size_t usize)
diff --git a/kernel/futex.c b/kernel/futex.c
index 03c518e9747e..0cf84c8664f2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1178,6 +1178,7 @@ out_error:
/**
* wait_for_owner_exiting - Block until the owner has exited
+ * @ret: owner's current futex lock status
* @exiting: Pointer to the exiting task
*
* Caller must hold a refcount on @exiting.
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 32282e7112d3..32406ef0d6a2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -482,7 +482,7 @@ static struct lock_trace *save_trace(void)
struct lock_trace *trace, *t2;
struct hlist_head *hash_head;
u32 hash;
- unsigned int max_entries;
+ int max_entries;
BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE);
BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES);
@@ -490,10 +490,8 @@ static struct lock_trace *save_trace(void)
trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries);
max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries -
LOCK_TRACE_SIZE_IN_LONGS;
- trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
- if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES -
- LOCK_TRACE_SIZE_IN_LONGS - 1) {
+ if (max_entries <= 0) {
if (!debug_locks_off_graph_unlock())
return NULL;
@@ -502,6 +500,7 @@ static struct lock_trace *save_trace(void)
return NULL;
}
+ trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
hash = jhash(trace->entries, trace->nr_entries *
sizeof(trace->entries[0]), 0);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 54cc5f9286e9..5352ce50a97e 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -733,9 +733,6 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
*/
void __sched mutex_unlock(struct mutex *lock)
{
-#ifdef CONFIG_DEBUG_MUTEXES
- WARN_ON(in_interrupt());
-#endif
#ifndef CONFIG_DEBUG_LOCK_ALLOC
if (__mutex_unlock_fast(lock))
return;
@@ -1416,7 +1413,6 @@ int __sched mutex_trylock(struct mutex *lock)
#ifdef CONFIG_DEBUG_MUTEXES
DEBUG_LOCKS_WARN_ON(lock->magic != lock);
- WARN_ON(in_interrupt());
#endif
locked = __mutex_trylock(lock);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 44e68761f432..0d9b6be9ecc8 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1226,8 +1226,8 @@ wait:
* In this case, we attempt to acquire the lock again
* without sleeping.
*/
- if ((wstate == WRITER_HANDOFF) &&
- (rwsem_spin_on_owner(sem, 0) == OWNER_NULL))
+ if (wstate == WRITER_HANDOFF &&
+ rwsem_spin_on_owner(sem, RWSEM_NONSPINNABLE) == OWNER_NULL)
goto trylock_again;
/* Block until there are no active lockers. */
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 399669f7eba8..472dd462a40c 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -51,19 +51,19 @@ EXPORT_SYMBOL(__rwlock_init);
static void spin_dump(raw_spinlock_t *lock, const char *msg)
{
- struct task_struct *owner = NULL;
+ struct task_struct *owner = READ_ONCE(lock->owner);
- if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
- owner = lock->owner;
+ if (owner == SPINLOCK_OWNER_INIT)
+ owner = NULL;
printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
msg, raw_smp_processor_id(),
current->comm, task_pid_nr(current));
printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, "
".owner_cpu: %d\n",
- lock, lock->magic,
+ lock, READ_ONCE(lock->magic),
owner ? owner->comm : "<none>",
owner ? task_pid_nr(owner) : -1,
- lock->owner_cpu);
+ READ_ONCE(lock->owner_cpu));
dump_stack();
}
@@ -80,16 +80,16 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg)
static inline void
debug_spin_lock_before(raw_spinlock_t *lock)
{
- SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
- SPIN_BUG_ON(lock->owner == current, lock, "recursion");
- SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+ SPIN_BUG_ON(READ_ONCE(lock->magic) != SPINLOCK_MAGIC, lock, "bad magic");
+ SPIN_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion");
+ SPIN_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(),
lock, "cpu recursion");
}
static inline void debug_spin_lock_after(raw_spinlock_t *lock)
{
- lock->owner_cpu = raw_smp_processor_id();
- lock->owner = current;
+ WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id());
+ WRITE_ONCE(lock->owner, current);
}
static inline void debug_spin_unlock(raw_spinlock_t *lock)
@@ -99,8 +99,8 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock)
SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
lock, "wrong CPU");
- lock->owner = SPINLOCK_OWNER_INIT;
- lock->owner_cpu = -1;
+ WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT);
+ WRITE_ONCE(lock->owner_cpu, -1);
}
/*
@@ -187,8 +187,8 @@ static inline void debug_write_lock_before(rwlock_t *lock)
static inline void debug_write_lock_after(rwlock_t *lock)
{
- lock->owner_cpu = raw_smp_processor_id();
- lock->owner = current;
+ WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id());
+ WRITE_ONCE(lock->owner, current);
}
static inline void debug_write_unlock(rwlock_t *lock)
@@ -197,8 +197,8 @@ static inline void debug_write_unlock(rwlock_t *lock)
RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
lock, "wrong CPU");
- lock->owner = SPINLOCK_OWNER_INIT;
- lock->owner_cpu = -1;
+ WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT);
+ WRITE_ONCE(lock->owner_cpu, -1);
}
void do_raw_write_lock(rwlock_t *lock)
diff --git a/kernel/module.c b/kernel/module.c
index cb6250be6ee9..ac058a5ad1d1 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3687,6 +3687,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
module_enable_ro(mod, false);
module_enable_nx(mod);
+ module_enable_x(mod);
/* Mark state as coming so strong_try_module_get() ignores us,
* but kallsyms etc. can see us. */
@@ -3709,11 +3710,6 @@ static int prepare_coming_module(struct module *mod)
if (err)
return err;
- /* Make module executable after ftrace is enabled */
- mutex_lock(&module_mutex);
- module_enable_x(mod);
- mutex_unlock(&module_mutex);
-
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_COMING, mod);
return 0;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index cb9ddcc08119..43d6179508d6 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -264,12 +264,17 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
return ret;
}
-static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
+static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns,
+ unsigned int mode)
{
+ int ret;
+
if (mode & PTRACE_MODE_NOAUDIT)
- return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
+ ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT);
else
- return has_ns_capability(current, ns, CAP_SYS_PTRACE);
+ ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE);
+
+ return ret == 0;
}
/* Returns 0 on success, -errno on denial. */
@@ -321,7 +326,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
gid_eq(caller_gid, tcred->sgid) &&
gid_eq(caller_gid, tcred->gid))
goto ok;
- if (ptrace_has_cap(tcred->user_ns, mode))
+ if (ptrace_has_cap(cred, tcred->user_ns, mode))
goto ok;
rcu_read_unlock();
return -EPERM;
@@ -340,7 +345,7 @@ ok:
mm = task->mm;
if (mm &&
((get_dumpable(mm) != SUID_DUMP_USER) &&
- !ptrace_has_cap(mm->user_ns, mode)))
+ !ptrace_has_cap(cred, mm->user_ns, mode)))
return -EPERM;
return security_ptrace_access_check(task, mode);
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 27c48eb7de40..a4f86a9d6937 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -310,6 +310,8 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
int ret;
if (flags & RSEQ_FLAG_UNREGISTER) {
+ if (flags & ~RSEQ_FLAG_UNREGISTER)
+ return -EINVAL;
/* Unregister rseq for current thread. */
if (current->rseq != rseq || !current->rseq)
return -EINVAL;
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index b5dcd1d83c7f..7c2fe50fd76d 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -5,6 +5,8 @@
* Copyright (C) 2016, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
*/
+#include <linux/cpufreq.h>
+
#include "sched.h"
DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
@@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu)
rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL);
}
EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook);
+
+/**
+ * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated.
+ * @policy: cpufreq policy to check.
+ *
+ * Return 'true' if:
+ * - the local and remote CPUs share @policy,
+ * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going
+ * offline (in which case it is not expected to run cpufreq updates any more).
+ */
+bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy)
+{
+ return cpumask_test_cpu(smp_processor_id(), policy->cpus) ||
+ (policy->dvfs_possible_from_any_cpu &&
+ rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)));
+}
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 322ca8860f54..9b8916fd00a2 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
* by the hardware, as calculating the frequency is pointless if
* we cannot in fact act on it.
*
- * For the slow switching platforms, the kthread is always scheduled on
- * the right set of CPUs and any CPU can find the next frequency and
- * schedule the kthread.
+ * This is needed on the slow switching platforms too to prevent CPUs
+ * going offline from leaving stale IRQ work items behind.
*/
- if (sg_policy->policy->fast_switch_enabled &&
- !cpufreq_this_cpu_can_update(sg_policy->policy))
+ if (!cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
if (unlikely(sg_policy->limits_changed)) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 08a233e97a01..ba749f579714 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7328,7 +7328,14 @@ static int detach_tasks(struct lb_env *env)
load < 16 && !env->sd->nr_balance_failed)
goto next;
- if (load/2 > env->imbalance)
+ /*
+ * Make sure that we don't migrate too much load.
+ * Nevertheless, let relax the constraint if
+ * scheduler fails to find a good waiting task to
+ * migrate.
+ */
+ if (load/2 > env->imbalance &&
+ env->sd->nr_balance_failed <= env->sd->cache_nice_tries)
goto next;
env->imbalance -= load;
@@ -8417,6 +8424,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
if (!idlest)
return NULL;
+ /* The local group has been skipped because of CPU affinity */
+ if (!local)
+ return idlest;
+
/*
* If the local group is idler than the selected idlest group
* don't try and push the task.
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 517e3719027e..ce8f6748678a 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -185,7 +185,8 @@ static void group_init(struct psi_group *group)
for_each_possible_cpu(cpu)
seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
- group->avg_next_update = sched_clock() + psi_period;
+ group->avg_last_update = sched_clock();
+ group->avg_next_update = group->avg_last_update + psi_period;
INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
mutex_init(&group->avgs_lock);
/* Init trigger-related members */
@@ -481,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
u32 remaining;
remaining = win->size - elapsed;
- growth += div_u64(win->prev_growth * remaining, win->size);
+ growth += div64_u64(win->prev_growth * remaining, win->size);
}
return growth;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 12d2227e5786..b6ea3dcb57bf 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1026,6 +1026,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
struct seccomp_notif unotif;
ssize_t ret;
+ /* Verify that we're not given garbage to keep struct extensible. */
+ ret = check_zeroed_user(buf, sizeof(unotif));
+ if (ret < 0)
+ return ret;
+ if (!ret)
+ return -EINVAL;
+
memset(&unotif, 0, sizeof(unotif));
ret = down_interruptible(&filter->notif->request);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13a0f2e6ebc2..e2ac0e37c4ae 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
- struct taskstats *stats;
+ struct taskstats *stats_new, *stats;
- if (sig->stats || thread_group_empty(tsk))
- goto ret;
+ /* Pairs with smp_store_release() below. */
+ stats = smp_load_acquire(&sig->stats);
+ if (stats || thread_group_empty(tsk))
+ return stats;
/* No problem if kmem_cache_zalloc() fails */
- stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+ stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
spin_lock_irq(&tsk->sighand->siglock);
- if (!sig->stats) {
- sig->stats = stats;
- stats = NULL;
+ stats = sig->stats;
+ if (!stats) {
+ /*
+ * Pairs with smp_store_release() above and order the
+ * kmem_cache_zalloc().
+ */
+ smp_store_release(&sig->stats, stats_new);
+ stats = stats_new;
+ stats_new = NULL;
}
spin_unlock_irq(&tsk->sighand->siglock);
- if (stats)
- kmem_cache_free(taskstats_cache, stats);
-ret:
- return sig->stats;
+ if (stats_new)
+ kmem_cache_free(taskstats_cache, stats_new);
+
+ return stats;
}
/* Send pid data out on exit */
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index ec960bb939fd..200fb2d3be99 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -14,8 +14,6 @@
#include "posix-timers.h"
-static void delete_clock(struct kref *kref);
-
/*
* Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
*/
@@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
err = 0;
if (!err) {
- kref_get(&clk->kref);
+ get_device(clk->dev);
fp->private_data = clk;
}
out:
@@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp)
if (clk->ops.release)
err = clk->ops.release(clk);
- kref_put(&clk->kref, delete_clock);
+ put_device(clk->dev);
fp->private_data = NULL;
@@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = {
#endif
};
-int posix_clock_register(struct posix_clock *clk, dev_t devid)
+int posix_clock_register(struct posix_clock *clk, struct device *dev)
{
int err;
- kref_init(&clk->kref);
init_rwsem(&clk->rwsem);
cdev_init(&clk->cdev, &posix_clock_file_operations);
+ err = cdev_device_add(&clk->cdev, dev);
+ if (err) {
+ pr_err("%s unable to add device %d:%d\n",
+ dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
+ return err;
+ }
clk->cdev.owner = clk->ops.owner;
- err = cdev_add(&clk->cdev, devid, 1);
+ clk->dev = dev;
- return err;
+ return 0;
}
EXPORT_SYMBOL_GPL(posix_clock_register);
-static void delete_clock(struct kref *kref)
-{
- struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-
- if (clk->release)
- clk->release(clk);
-}
-
void posix_clock_unregister(struct posix_clock *clk)
{
- cdev_del(&clk->cdev);
+ cdev_device_del(&clk->cdev, clk->dev);
down_write(&clk->rwsem);
clk->zombie = true;
up_write(&clk->rwsem);
- kref_put(&clk->kref, delete_clock);
+ put_device(clk->dev);
}
EXPORT_SYMBOL_GPL(posix_clock_unregister);
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 67df65f887ac..20c65a7d4e3a 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -151,6 +151,9 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
#ifdef CONFIG_COMPAT
COMPAT_SYS_NI(timer_create);
+#endif
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
COMPAT_SYS_NI(getitimer);
COMPAT_SYS_NI(setitimer);
#endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 8b192e67aabc..a792d21cac64 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now)
/*
* Do a quick check without holding jiffies_lock:
+ * The READ_ONCE() pairs with two updates done later in this function.
*/
- delta = ktime_sub(now, last_jiffies_update);
+ delta = ktime_sub(now, READ_ONCE(last_jiffies_update));
if (delta < tick_period)
return;
@@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now)
if (delta >= tick_period) {
delta = ktime_sub(delta, tick_period);
- last_jiffies_update = ktime_add(last_jiffies_update,
- tick_period);
+ /* Pairs with the lockless read in this function. */
+ WRITE_ONCE(last_jiffies_update,
+ ktime_add(last_jiffies_update, tick_period));
/* Slow path for long timeouts */
if (unlikely(delta >= tick_period)) {
@@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now)
ticks = ktime_divns(delta, incr);
- last_jiffies_update = ktime_add_ns(last_jiffies_update,
- incr * ticks);
+ /* Pairs with the lockless read in this function. */
+ WRITE_ONCE(last_jiffies_update,
+ ktime_add_ns(last_jiffies_update,
+ incr * ticks));
}
do_timer(++ticks);
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 67e0c462b059..1af321dec0f1 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -96,11 +96,34 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
return 0;
}
+/*
+ * Not all archs define MCOUNT_INSN_SIZE which is used to look for direct
+ * functions. But those archs currently don't support direct functions
+ * anyway, and ftrace_find_rec_direct() is just a stub for them.
+ * Define MCOUNT_INSN_SIZE to keep those archs compiling.
+ */
+#ifndef MCOUNT_INSN_SIZE
+/* Make sure this only works without direct calls */
+# ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+# error MCOUNT_INSN_SIZE not defined with direct calls enabled
+# endif
+# define MCOUNT_INSN_SIZE 0
+#endif
+
int function_graph_enter(unsigned long ret, unsigned long func,
unsigned long frame_pointer, unsigned long *retp)
{
struct ftrace_graph_ent trace;
+ /*
+ * Skip graph tracing if the return location is served by direct trampoline,
+ * since call sequence and return addresses is unpredicatable anymore.
+ * Ex: BPF trampoline may call original function and may skip frame
+ * depending on type of BPF programs attached.
+ */
+ if (ftrace_direct_func_count &&
+ ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE))
+ return -EBUSY;
trace.func = func;
trace.depth = ++current->curr_ret_depth;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 74439ab5c2b6..9bf1f2cd515e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -526,8 +526,7 @@ static int function_stat_show(struct seq_file *m, void *v)
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- avg = rec->time;
- do_div(avg, rec->counter);
+ avg = div64_ul(rec->time, rec->counter);
if (tracing_thresh && (avg < tracing_thresh))
goto out;
#endif
@@ -553,7 +552,8 @@ static int function_stat_show(struct seq_file *m, void *v)
* Divide only 1000 for ns^2 -> us^2 conversion.
* trace_print_graph_duration will divide 1000 again.
*/
- do_div(stddev, rec->counter * (rec->counter - 1) * 1000);
+ stddev = div64_ul(stddev,
+ rec->counter * (rec->counter - 1) * 1000);
}
trace_seq_init(&s);
@@ -2364,7 +2364,7 @@ int ftrace_direct_func_count;
* Search the direct_functions hash to see if the given instruction pointer
* has a direct caller attached to it.
*/
-static unsigned long find_rec_direct(unsigned long ip)
+unsigned long ftrace_find_rec_direct(unsigned long ip)
{
struct ftrace_func_entry *entry;
@@ -2380,7 +2380,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip,
{
unsigned long addr;
- addr = find_rec_direct(ip);
+ addr = ftrace_find_rec_direct(ip);
if (!addr)
return;
@@ -2393,11 +2393,6 @@ struct ftrace_ops direct_ops = {
| FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
| FTRACE_OPS_FL_PERMANENT,
};
-#else
-static inline unsigned long find_rec_direct(unsigned long ip)
-{
- return 0;
-}
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
/**
@@ -2417,7 +2412,7 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec)
if ((rec->flags & FTRACE_FL_DIRECT) &&
(ftrace_rec_count(rec) == 1)) {
- addr = find_rec_direct(rec->ip);
+ addr = ftrace_find_rec_direct(rec->ip);
if (addr)
return addr;
WARN_ON_ONCE(1);
@@ -2458,7 +2453,7 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec)
/* Direct calls take precedence over trampolines */
if (rec->flags & FTRACE_FL_DIRECT_EN) {
- addr = find_rec_direct(rec->ip);
+ addr = ftrace_find_rec_direct(rec->ip);
if (addr)
return addr;
WARN_ON_ONCE(1);
@@ -3604,7 +3599,7 @@ static int t_show(struct seq_file *m, void *v)
if (rec->flags & FTRACE_FL_DIRECT) {
unsigned long direct;
- direct = find_rec_direct(rec->ip);
+ direct = ftrace_find_rec_direct(rec->ip);
if (direct)
seq_printf(m, "\n\tdirect-->%pS", (void *)direct);
}
@@ -5008,7 +5003,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
mutex_lock(&direct_mutex);
/* See if there's a direct function at @ip already */
- if (find_rec_direct(ip))
+ if (ftrace_find_rec_direct(ip))
goto out_unlock;
ret = -ENODEV;
@@ -5027,7 +5022,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
if (ip != rec->ip) {
ip = rec->ip;
/* Need to check this ip for a direct. */
- if (find_rec_direct(ip))
+ if (ftrace_find_rec_direct(ip))
goto out_unlock;
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 4bf050fcfe3b..3f655371eaf6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5070,7 +5070,7 @@ static __init int test_ringbuffer(void)
int ret = 0;
if (security_locked_down(LOCKDOWN_TRACEFS)) {
- pr_warning("Lockdown is enabled, skipping ring buffer tests\n");
+ pr_warn("Lockdown is enabled, skipping ring buffer tests\n");
return 0;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 23459d53d576..ddb7e7f5fe8d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1889,7 +1889,7 @@ int __init register_tracer(struct tracer *type)
}
if (security_locked_down(LOCKDOWN_TRACEFS)) {
- pr_warning("Can not register tracer %s due to lockdown\n",
+ pr_warn("Can not register tracer %s due to lockdown\n",
type->name);
return -EPERM;
}
@@ -4685,6 +4685,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
{
+ if ((mask == TRACE_ITER_RECORD_TGID) ||
+ (mask == TRACE_ITER_RECORD_CMD))
+ lockdep_assert_held(&event_mutex);
+
/* do nothing if flag is already set */
if (!!(tr->trace_flags & mask) == !!enabled)
return 0;
@@ -4752,6 +4756,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
cmp += len;
+ mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
ret = match_string(trace_options, -1, cmp);
@@ -4762,6 +4767,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
ret = set_tracer_flag(tr, 1 << ret, !neg);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
/*
* If the first trailing whitespace is replaced with '\0' by strstrip,
@@ -8076,9 +8082,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (val != 0 && val != 1)
return -EINVAL;
+ mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
ret = set_tracer_flag(tr, 1 << index, val);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
if (ret < 0)
return ret;
@@ -8796,7 +8804,7 @@ struct dentry *tracing_init_dentry(void)
struct trace_array *tr = &global_trace;
if (security_locked_down(LOCKDOWN_TRACEFS)) {
- pr_warning("Tracing disabled due to lockdown\n");
+ pr_warn("Tracing disabled due to lockdown\n");
return ERR_PTR(-EPERM);
}
@@ -9244,7 +9252,7 @@ __init static int tracer_alloc_buffers(void)
if (security_locked_down(LOCKDOWN_TRACEFS)) {
- pr_warning("Tracing disabled due to lockdown\n");
+ pr_warn("Tracing disabled due to lockdown\n");
return -EPERM;
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 974558156830..c8622a44d300 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -321,7 +321,8 @@ void trace_event_enable_cmd_record(bool enable)
struct trace_event_file *file;
struct trace_array *tr;
- mutex_lock(&event_mutex);
+ lockdep_assert_held(&event_mutex);
+
do_for_each_event_file(tr, file) {
if (!(file->flags & EVENT_FILE_FL_ENABLED))
@@ -335,7 +336,6 @@ void trace_event_enable_cmd_record(bool enable)
clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
}
} while_for_each_event_file();
- mutex_unlock(&event_mutex);
}
void trace_event_enable_tgid_record(bool enable)
@@ -343,7 +343,8 @@ void trace_event_enable_tgid_record(bool enable)
struct trace_event_file *file;
struct trace_array *tr;
- mutex_lock(&event_mutex);
+ lockdep_assert_held(&event_mutex);
+
do_for_each_event_file(tr, file) {
if (!(file->flags & EVENT_FILE_FL_ENABLED))
continue;
@@ -357,7 +358,6 @@ void trace_event_enable_tgid_record(bool enable)
&file->flags);
}
} while_for_each_event_file();
- mutex_unlock(&event_mutex);
}
static int __ftrace_event_enable_disable(struct trace_event_file *file,
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index c9a74f82b14a..bf44f6bbd0c3 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1662,7 +1662,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0);
return -EINVAL;
fail_mem:
- kfree(filter);
+ __free_filter(filter);
/* If any call succeeded, we still need to sync */
if (!fail)
tracepoint_synchronize_unregister();
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 23b0195ac977..ce376c78439f 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -911,7 +911,26 @@ static notrace void trace_event_raw_event_synth(void *__data,
strscpy(str_field, str_val, STR_VAR_LEN_MAX);
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
} else {
- entry->fields[n_u64] = var_ref_vals[var_ref_idx + i];
+ struct synth_field *field = event->fields[i];
+ u64 val = var_ref_vals[var_ref_idx + i];
+
+ switch (field->size) {
+ case 1:
+ *(u8 *)&entry->fields[n_u64] = (u8)val;
+ break;
+
+ case 2:
+ *(u16 *)&entry->fields[n_u64] = (u16)val;
+ break;
+
+ case 4:
+ *(u32 *)&entry->fields[n_u64] = (u32)val;
+ break;
+
+ default:
+ entry->fields[n_u64] = val;
+ break;
+ }
n_u64++;
}
}
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index d43710718ee5..22bcf7c51d1e 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -17,12 +17,10 @@ static int
trace_inject_entry(struct trace_event_file *file, void *rec, int len)
{
struct trace_event_buffer fbuffer;
- struct ring_buffer *buffer;
int written = 0;
void *entry;
rcu_read_lock_sched();
- buffer = file->tr->trace_buffer.buffer;
entry = trace_event_buffer_reserve(&fbuffer, file, len);
if (entry) {
memcpy(entry, rec, len);
@@ -197,7 +195,7 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry)
unsigned long irq_flags;
void *entry = NULL;
int entry_size;
- u64 val;
+ u64 val = 0;
int len;
entry = trace_alloc_entry(call, &entry_size);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 5e43b9664eca..617e297f46dc 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -630,7 +630,7 @@ static void start_wakeup_tracer(struct trace_array *tr)
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_migrate_task\n");
- return;
+ goto fail_deprobe_sched_switch;
}
wakeup_reset(tr);
@@ -648,6 +648,8 @@ static void start_wakeup_tracer(struct trace_array *tr)
printk(KERN_ERR "failed to start wakeup tracer\n");
return;
+fail_deprobe_sched_switch:
+ unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
fail_deprobe_wake_new:
unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
fail_deprobe:
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 344e4c1aa09c..87de6edafd14 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -381,7 +381,7 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
const void *buf, size_t len, bool ascii)
{
- unsigned int save_len = s->seq.len;
+ unsigned int save_len = s->seq.len;
if (s->full)
return 0;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 4df9a209f7ca..c557f42a9397 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -283,6 +283,11 @@ static void check_stack(unsigned long ip, unsigned long *stack)
local_irq_restore(flags);
}
+/* Some archs may not define MCOUNT_INSN_SIZE */
+#ifndef MCOUNT_INSN_SIZE
+# define MCOUNT_INSN_SIZE 0
+#endif
+
static void
stack_trace_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9a1c22310323..9e31bfc818ff 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b)
#define DEFINE_TRACING_MAP_CMP_FN(type) \
static int tracing_map_cmp_##type(void *val_a, void *val_b) \
{ \
- type a = *(type *)val_a; \
- type b = *(type *)val_b; \
+ type a = (type)(*(u64 *)val_a); \
+ type b = (type)(*(u64 *)val_b); \
\
return (a > b) ? 1 : ((a < b) ? -1 : 0); \
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bc88fd939f4e..cfc923558e04 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4374,8 +4374,8 @@ void destroy_workqueue(struct workqueue_struct *wq)
for_each_pwq(pwq, wq) {
spin_lock_irq(&pwq->pool->lock);
if (WARN_ON(pwq_busy(pwq))) {
- pr_warning("%s: %s has the following busy pwq\n",
- __func__, wq->name);
+ pr_warn("%s: %s has the following busy pwq\n",
+ __func__, wq->name);
show_pwq(pwq);
spin_unlock_irq(&pwq->pool->lock);
mutex_unlock(&wq->mutex);