summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.locks3
-rw-r--r--kernel/bpf/arraymap.c23
-rw-r--r--kernel/bpf/btf.c146
-rw-r--r--kernel/bpf/cgroup.c3
-rw-r--r--kernel/bpf/core.c315
-rw-r--r--kernel/bpf/disasm.c34
-rw-r--r--kernel/bpf/hashtab.c63
-rw-r--r--kernel/bpf/helpers.c96
-rw-r--r--kernel/bpf/local_storage.c16
-rw-r--r--kernel/bpf/map_in_map.c6
-rw-r--r--kernel/bpf/offload.c45
-rw-r--r--kernel/bpf/syscall.c90
-rw-r--r--kernel/bpf/verifier.c964
-rw-r--r--kernel/cgroup/cgroup-internal.h2
-rw-r--r--kernel/cgroup/cgroup-v1.c58
-rw-r--r--kernel/cgroup/cgroup.c27
-rw-r--r--kernel/compat.c64
-rw-r--r--kernel/cpu.c9
-rw-r--r--kernel/futex.c28
-rw-r--r--kernel/irq/affinity.c121
-rw-r--r--kernel/irq/chip.c66
-rw-r--r--kernel/irq/debugfs.c8
-rw-r--r--kernel/irq/handle.c2
-rw-r--r--kernel/irq/internals.h10
-rw-r--r--kernel/irq/irqdesc.c42
-rw-r--r--kernel/irq/irqdomain.c16
-rw-r--r--kernel/irq/manage.c406
-rw-r--r--kernel/kthread.c8
-rw-r--r--kernel/locking/lockdep.c966
-rw-r--r--kernel/locking/lockdep_internals.h7
-rw-r--r--kernel/locking/lockdep_proc.c12
-rw-r--r--kernel/locking/locktorture.c21
-rw-r--r--kernel/locking/qspinlock.c21
-rw-r--r--kernel/locking/qspinlock_stat.h21
-rw-r--r--kernel/locking/rwsem-xadd.c4
-rw-r--r--kernel/rcu/Kconfig30
-rw-r--r--kernel/rcu/rcu.h21
-rw-r--r--kernel/rcu/rcu_segcblist.c17
-rw-r--r--kernel/rcu/rcu_segcblist.h17
-rw-r--r--kernel/rcu/rcuperf.c27
-rw-r--r--kernel/rcu/rcutorture.c59
-rw-r--r--kernel/rcu/srcutiny.c17
-rw-r--r--kernel/rcu/srcutree.c72
-rw-r--r--kernel/rcu/sync.c15
-rw-r--r--kernel/rcu/tiny.c19
-rw-r--r--kernel/rcu/tree.c267
-rw-r--r--kernel/rcu/tree.h53
-rw-r--r--kernel/rcu/tree_exp.h201
-rw-r--r--kernel/rcu/tree_plugin.h238
-rw-r--r--kernel/rcu/update.c17
-rw-r--r--kernel/sched/core.c100
-rw-r--r--kernel/sched/cpufreq.c4
-rw-r--r--kernel/sched/cpufreq_schedutil.c2
-rw-r--r--kernel/sched/sched.h2
-rw-r--r--kernel/sched/topology.c4
-rw-r--r--kernel/seccomp.c2
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/softirq.c3
-rw-r--r--kernel/sys_ni.c22
-rw-r--r--kernel/sysctl.c37
-rw-r--r--kernel/time/Kconfig29
-rw-r--r--kernel/time/hrtimer.c4
-rw-r--r--kernel/time/ntp.c18
-rw-r--r--kernel/time/ntp_internal.h2
-rw-r--r--kernel/time/posix-clock.c2
-rw-r--r--kernel/time/posix-cpu-timers.c13
-rw-r--r--kernel/time/posix-stubs.c25
-rw-r--r--kernel/time/posix-timers.c72
-rw-r--r--kernel/time/posix-timers.h2
-rw-r--r--kernel/time/tick-broadcast.c1
-rw-r--r--kernel/time/time.c92
-rw-r--r--kernel/time/timekeeping.c4
-rw-r--r--kernel/time/timekeeping_debug.c11
-rw-r--r--kernel/time/timer.c4
-rw-r--r--kernel/torture.c25
-rw-r--r--kernel/workqueue.c59
76 files changed, 3719 insertions, 1615 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 84d882f3e299..fbba478ae522 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -242,6 +242,9 @@ config QUEUED_SPINLOCKS
def_bool y if ARCH_USE_QUEUED_SPINLOCKS
depends on SMP
+config BPF_ARCH_SPINLOCK
+ bool
+
config ARCH_USE_QUEUED_RWLOCKS
bool
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 25632a75d630..c72e0d8e1e65 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -253,8 +253,9 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
+ char *val;
- if (unlikely(map_flags > BPF_EXIST))
+ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST))
/* unknown flags */
return -EINVAL;
@@ -262,17 +263,25 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
- if (unlikely(map_flags == BPF_NOEXIST))
+ if (unlikely(map_flags & BPF_NOEXIST))
/* all elements already exist */
return -EEXIST;
- if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ if (unlikely((map_flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)))
+ return -EINVAL;
+
+ if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
value, map->value_size);
- else
- memcpy(array->value +
- array->elem_size * (index & array->index_mask),
- value, map->value_size);
+ } else {
+ val = array->value +
+ array->elem_size * (index & array->index_mask);
+ if (map_flags & BPF_F_LOCK)
+ copy_map_value_locked(map, val, value, false);
+ else
+ copy_map_value(map, val, value);
+ }
return 0;
}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index c57bd10340ed..bd3921b1514b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -157,7 +157,7 @@
*
*/
-#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE)
+#define BITS_PER_U128 (sizeof(u64) * BITS_PER_BYTE * 2)
#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
@@ -355,6 +355,11 @@ static bool btf_type_is_struct(const struct btf_type *t)
return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
}
+static bool __btf_type_is_struct(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT;
+}
+
static bool btf_type_is_array(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
@@ -525,7 +530,7 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
/*
* Regular int is not a bit field and it must be either
- * u8/u16/u32/u64.
+ * u8/u16/u32/u64 or __int128.
*/
static bool btf_type_int_is_regular(const struct btf_type *t)
{
@@ -538,7 +543,8 @@ static bool btf_type_int_is_regular(const struct btf_type *t)
if (BITS_PER_BYTE_MASKED(nr_bits) ||
BTF_INT_OFFSET(int_data) ||
(nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
- nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) {
+ nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64) &&
+ nr_bytes != (2 * sizeof(u64)))) {
return false;
}
@@ -1063,9 +1069,9 @@ static int btf_int_check_member(struct btf_verifier_env *env,
nr_copy_bits = BTF_INT_BITS(int_data) +
BITS_PER_BYTE_MASKED(struct_bits_off);
- if (nr_copy_bits > BITS_PER_U64) {
+ if (nr_copy_bits > BITS_PER_U128) {
btf_verifier_log_member(env, struct_type, member,
- "nr_copy_bits exceeds 64");
+ "nr_copy_bits exceeds 128");
return -EINVAL;
}
@@ -1119,9 +1125,9 @@ static int btf_int_check_kflag_member(struct btf_verifier_env *env,
bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
nr_copy_bits = nr_bits + BITS_PER_BYTE_MASKED(struct_bits_off);
- if (nr_copy_bits > BITS_PER_U64) {
+ if (nr_copy_bits > BITS_PER_U128) {
btf_verifier_log_member(env, struct_type, member,
- "nr_copy_bits exceeds 64");
+ "nr_copy_bits exceeds 128");
return -EINVAL;
}
@@ -1168,9 +1174,9 @@ static s32 btf_int_check_meta(struct btf_verifier_env *env,
nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data);
- if (nr_bits > BITS_PER_U64) {
+ if (nr_bits > BITS_PER_U128) {
btf_verifier_log_type(env, t, "nr_bits exceeds %zu",
- BITS_PER_U64);
+ BITS_PER_U128);
return -EINVAL;
}
@@ -1211,31 +1217,93 @@ static void btf_int_log(struct btf_verifier_env *env,
btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
}
+static void btf_int128_print(struct seq_file *m, void *data)
+{
+ /* data points to a __int128 number.
+ * Suppose
+ * int128_num = *(__int128 *)data;
+ * The below formulas shows what upper_num and lower_num represents:
+ * upper_num = int128_num >> 64;
+ * lower_num = int128_num & 0xffffffffFFFFFFFFULL;
+ */
+ u64 upper_num, lower_num;
+
+#ifdef __BIG_ENDIAN_BITFIELD
+ upper_num = *(u64 *)data;
+ lower_num = *(u64 *)(data + 8);
+#else
+ upper_num = *(u64 *)(data + 8);
+ lower_num = *(u64 *)data;
+#endif
+ if (upper_num == 0)
+ seq_printf(m, "0x%llx", lower_num);
+ else
+ seq_printf(m, "0x%llx%016llx", upper_num, lower_num);
+}
+
+static void btf_int128_shift(u64 *print_num, u16 left_shift_bits,
+ u16 right_shift_bits)
+{
+ u64 upper_num, lower_num;
+
+#ifdef __BIG_ENDIAN_BITFIELD
+ upper_num = print_num[0];
+ lower_num = print_num[1];
+#else
+ upper_num = print_num[1];
+ lower_num = print_num[0];
+#endif
+
+ /* shake out un-needed bits by shift/or operations */
+ if (left_shift_bits >= 64) {
+ upper_num = lower_num << (left_shift_bits - 64);
+ lower_num = 0;
+ } else {
+ upper_num = (upper_num << left_shift_bits) |
+ (lower_num >> (64 - left_shift_bits));
+ lower_num = lower_num << left_shift_bits;
+ }
+
+ if (right_shift_bits >= 64) {
+ lower_num = upper_num >> (right_shift_bits - 64);
+ upper_num = 0;
+ } else {
+ lower_num = (lower_num >> right_shift_bits) |
+ (upper_num << (64 - right_shift_bits));
+ upper_num = upper_num >> right_shift_bits;
+ }
+
+#ifdef __BIG_ENDIAN_BITFIELD
+ print_num[0] = upper_num;
+ print_num[1] = lower_num;
+#else
+ print_num[0] = lower_num;
+ print_num[1] = upper_num;
+#endif
+}
+
static void btf_bitfield_seq_show(void *data, u8 bits_offset,
u8 nr_bits, struct seq_file *m)
{
u16 left_shift_bits, right_shift_bits;
u8 nr_copy_bytes;
u8 nr_copy_bits;
- u64 print_num;
+ u64 print_num[2] = {};
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
- print_num = 0;
- memcpy(&print_num, data, nr_copy_bytes);
+ memcpy(print_num, data, nr_copy_bytes);
#ifdef __BIG_ENDIAN_BITFIELD
left_shift_bits = bits_offset;
#else
- left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+ left_shift_bits = BITS_PER_U128 - nr_copy_bits;
#endif
- right_shift_bits = BITS_PER_U64 - nr_bits;
+ right_shift_bits = BITS_PER_U128 - nr_bits;
- print_num <<= left_shift_bits;
- print_num >>= right_shift_bits;
-
- seq_printf(m, "0x%llx", print_num);
+ btf_int128_shift(print_num, left_shift_bits, right_shift_bits);
+ btf_int128_print(m, print_num);
}
@@ -1250,7 +1318,7 @@ static void btf_int_bits_seq_show(const struct btf *btf,
/*
* bits_offset is at most 7.
- * BTF_INT_OFFSET() cannot exceed 64 bits.
+ * BTF_INT_OFFSET() cannot exceed 128 bits.
*/
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
@@ -1274,6 +1342,9 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
}
switch (nr_bits) {
+ case 128:
+ btf_int128_print(m, data);
+ break;
case 64:
if (sign)
seq_printf(m, "%lld", *(s64 *)data);
@@ -1980,6 +2051,43 @@ static void btf_struct_log(struct btf_verifier_env *env,
btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
}
+/* find 'struct bpf_spin_lock' in map value.
+ * return >= 0 offset if found
+ * and < 0 in case of error
+ */
+int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
+{
+ const struct btf_member *member;
+ u32 i, off = -ENOENT;
+
+ if (!__btf_type_is_struct(t))
+ return -EINVAL;
+
+ for_each_member(i, t, member) {
+ const struct btf_type *member_type = btf_type_by_id(btf,
+ member->type);
+ if (!__btf_type_is_struct(member_type))
+ continue;
+ if (member_type->size != sizeof(struct bpf_spin_lock))
+ continue;
+ if (strcmp(__btf_name_by_offset(btf, member_type->name_off),
+ "bpf_spin_lock"))
+ continue;
+ if (off != -ENOENT)
+ /* only one 'struct bpf_spin_lock' is allowed */
+ return -E2BIG;
+ off = btf_member_bit_offset(t, member);
+ if (off % 8)
+ /* valid C code cannot generate such BTF */
+ return -EINVAL;
+ off /= 8;
+ if (off % __alignof__(struct bpf_spin_lock))
+ /* valid struct bpf_spin_lock will be 4 byte aligned */
+ return -EINVAL;
+ }
+ return off;
+}
+
static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index d17d05570a3f..4e807973aa80 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -230,6 +230,7 @@ cleanup:
* @cgrp: The cgroup which descendants to traverse
* @prog: A program to attach
* @type: Type of attach operation
+ * @flags: Option flags
*
* Must be called with cgroup_mutex held.
*/
@@ -363,7 +364,7 @@ cleanup:
* Must be called with cgroup_mutex held.
*/
int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
- enum bpf_attach_type type, u32 unused_flags)
+ enum bpf_attach_type type)
{
struct list_head *progs = &cgrp->bpf.progs[type];
enum bpf_cgroup_storage_type stype;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 19c49313c709..ff09d32a8a1b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -78,7 +78,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
return NULL;
}
-struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
+struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog_aux *aux;
@@ -104,6 +104,32 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
return fp;
}
+
+struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
+{
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+ struct bpf_prog *prog;
+ int cpu;
+
+ prog = bpf_prog_alloc_no_stats(size, gfp_extra_flags);
+ if (!prog)
+ return NULL;
+
+ prog->aux->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags);
+ if (!prog->aux->stats) {
+ kfree(prog->aux);
+ vfree(prog);
+ return NULL;
+ }
+
+ for_each_possible_cpu(cpu) {
+ struct bpf_prog_stats *pstats;
+
+ pstats = per_cpu_ptr(prog->aux->stats, cpu);
+ u64_stats_init(&pstats->syncp);
+ }
+ return prog;
+}
EXPORT_SYMBOL_GPL(bpf_prog_alloc);
int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog)
@@ -231,7 +257,10 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
void __bpf_prog_free(struct bpf_prog *fp)
{
- kfree(fp->aux);
+ if (fp->aux) {
+ free_percpu(fp->aux->stats);
+ kfree(fp->aux);
+ }
vfree(fp);
}
@@ -307,15 +336,16 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
return 0;
}
-static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
- u32 curr, const bool probe_pass)
+static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
+ s32 end_new, u32 curr, const bool probe_pass)
{
const s64 imm_min = S32_MIN, imm_max = S32_MAX;
+ s32 delta = end_new - end_old;
s64 imm = insn->imm;
- if (curr < pos && curr + imm + 1 > pos)
+ if (curr < pos && curr + imm + 1 >= end_old)
imm += delta;
- else if (curr > pos + delta && curr + imm + 1 <= pos + delta)
+ else if (curr >= end_new && curr + imm + 1 < end_new)
imm -= delta;
if (imm < imm_min || imm > imm_max)
return -ERANGE;
@@ -324,15 +354,16 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
return 0;
}
-static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
- u32 curr, const bool probe_pass)
+static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
+ s32 end_new, u32 curr, const bool probe_pass)
{
const s32 off_min = S16_MIN, off_max = S16_MAX;
+ s32 delta = end_new - end_old;
s32 off = insn->off;
- if (curr < pos && curr + off + 1 > pos)
+ if (curr < pos && curr + off + 1 >= end_old)
off += delta;
- else if (curr > pos + delta && curr + off + 1 <= pos + delta)
+ else if (curr >= end_new && curr + off + 1 < end_new)
off -= delta;
if (off < off_min || off > off_max)
return -ERANGE;
@@ -341,10 +372,10 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
return 0;
}
-static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
- const bool probe_pass)
+static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old,
+ s32 end_new, const bool probe_pass)
{
- u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0);
+ u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0);
struct bpf_insn *insn = prog->insnsi;
int ret = 0;
@@ -356,22 +387,23 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
* do any other adjustments. Therefore skip the patchlet.
*/
if (probe_pass && i == pos) {
- i += delta + 1;
- insn++;
+ i = end_new;
+ insn = prog->insnsi + end_old;
}
code = insn->code;
- if (BPF_CLASS(code) != BPF_JMP ||
+ if ((BPF_CLASS(code) != BPF_JMP &&
+ BPF_CLASS(code) != BPF_JMP32) ||
BPF_OP(code) == BPF_EXIT)
continue;
/* Adjust offset of jmps if we cross patch boundaries. */
if (BPF_OP(code) == BPF_CALL) {
if (insn->src_reg != BPF_PSEUDO_CALL)
continue;
- ret = bpf_adj_delta_to_imm(insn, pos, delta, i,
- probe_pass);
+ ret = bpf_adj_delta_to_imm(insn, pos, end_old,
+ end_new, i, probe_pass);
} else {
- ret = bpf_adj_delta_to_off(insn, pos, delta, i,
- probe_pass);
+ ret = bpf_adj_delta_to_off(insn, pos, end_old,
+ end_new, i, probe_pass);
}
if (ret)
break;
@@ -421,7 +453,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
* we afterwards may not fail anymore.
*/
if (insn_adj_cnt > cnt_max &&
- bpf_adj_branches(prog, off, insn_delta, true))
+ bpf_adj_branches(prog, off, off + 1, off + len, true))
return NULL;
/* Several new instructions need to be inserted. Make room
@@ -453,13 +485,25 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
* the ship has sailed to reverse to the original state. An
* overflow cannot happen at this point.
*/
- BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
+ BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false));
bpf_adj_linfo(prog_adj, off, insn_delta);
return prog_adj;
}
+int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
+{
+ /* Branch offsets can't overflow when program is shrinking, no need
+ * to call bpf_adj_branches(..., true) here
+ */
+ memmove(prog->insnsi + off, prog->insnsi + off + cnt,
+ sizeof(struct bpf_insn) * (prog->len - off - cnt));
+ prog->len -= cnt;
+
+ return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
+}
+
void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
{
int i;
@@ -934,6 +978,27 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
break;
+ case BPF_JMP32 | BPF_JEQ | BPF_K:
+ case BPF_JMP32 | BPF_JNE | BPF_K:
+ case BPF_JMP32 | BPF_JGT | BPF_K:
+ case BPF_JMP32 | BPF_JLT | BPF_K:
+ case BPF_JMP32 | BPF_JGE | BPF_K:
+ case BPF_JMP32 | BPF_JLE | BPF_K:
+ case BPF_JMP32 | BPF_JSGT | BPF_K:
+ case BPF_JMP32 | BPF_JSLT | BPF_K:
+ case BPF_JMP32 | BPF_JSGE | BPF_K:
+ case BPF_JMP32 | BPF_JSLE | BPF_K:
+ case BPF_JMP32 | BPF_JSET | BPF_K:
+ /* Accommodate for extra offset in case of a backjump. */
+ off = from->off;
+ if (off < 0)
+ off -= 2;
+ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+ *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ *to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX,
+ off);
+ break;
+
case BPF_LD | BPF_IMM | BPF_DW:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
@@ -1130,6 +1195,31 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_2(JMP, CALL), \
/* Exit instruction. */ \
INSN_2(JMP, EXIT), \
+ /* 32-bit Jump instructions. */ \
+ /* Register based. */ \
+ INSN_3(JMP32, JEQ, X), \
+ INSN_3(JMP32, JNE, X), \
+ INSN_3(JMP32, JGT, X), \
+ INSN_3(JMP32, JLT, X), \
+ INSN_3(JMP32, JGE, X), \
+ INSN_3(JMP32, JLE, X), \
+ INSN_3(JMP32, JSGT, X), \
+ INSN_3(JMP32, JSLT, X), \
+ INSN_3(JMP32, JSGE, X), \
+ INSN_3(JMP32, JSLE, X), \
+ INSN_3(JMP32, JSET, X), \
+ /* Immediate based. */ \
+ INSN_3(JMP32, JEQ, K), \
+ INSN_3(JMP32, JNE, K), \
+ INSN_3(JMP32, JGT, K), \
+ INSN_3(JMP32, JLT, K), \
+ INSN_3(JMP32, JGE, K), \
+ INSN_3(JMP32, JLE, K), \
+ INSN_3(JMP32, JSGT, K), \
+ INSN_3(JMP32, JSLT, K), \
+ INSN_3(JMP32, JSGE, K), \
+ INSN_3(JMP32, JSLE, K), \
+ INSN_3(JMP32, JSET, K), \
/* Jump instructions. */ \
/* Register based. */ \
INSN_3(JMP, JEQ, X), \
@@ -1202,8 +1292,9 @@ bool bpf_opcode_in_insntable(u8 code)
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
/**
* __bpf_prog_run - run eBPF program on a given context
- * @ctx: is the data we are operating on
+ * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
* @insn: is the array of eBPF instructions
+ * @stack: is the eBPF storage stack
*
* Decode and execute eBPF instructions.
*/
@@ -1390,145 +1481,49 @@ select_insn:
out:
CONT;
}
- /* JMP */
JMP_JA:
insn += insn->off;
CONT;
- JMP_JEQ_X:
- if (DST == SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JEQ_K:
- if (DST == IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JNE_X:
- if (DST != SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JNE_K:
- if (DST != IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGT_X:
- if (DST > SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGT_K:
- if (DST > IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JLT_X:
- if (DST < SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JLT_K:
- if (DST < IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGE_X:
- if (DST >= SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGE_K:
- if (DST >= IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JLE_X:
- if (DST <= SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JLE_K:
- if (DST <= IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSGT_X:
- if (((s64) DST) > ((s64) SRC)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSGT_K:
- if (((s64) DST) > ((s64) IMM)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSLT_X:
- if (((s64) DST) < ((s64) SRC)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSLT_K:
- if (((s64) DST) < ((s64) IMM)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSGE_X:
- if (((s64) DST) >= ((s64) SRC)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSGE_K:
- if (((s64) DST) >= ((s64) IMM)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSLE_X:
- if (((s64) DST) <= ((s64) SRC)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSLE_K:
- if (((s64) DST) <= ((s64) IMM)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSET_X:
- if (DST & SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSET_K:
- if (DST & IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
JMP_EXIT:
return BPF_R0;
-
+ /* JMP */
+#define COND_JMP(SIGN, OPCODE, CMP_OP) \
+ JMP_##OPCODE##_X: \
+ if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) { \
+ insn += insn->off; \
+ CONT_JMP; \
+ } \
+ CONT; \
+ JMP32_##OPCODE##_X: \
+ if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) { \
+ insn += insn->off; \
+ CONT_JMP; \
+ } \
+ CONT; \
+ JMP_##OPCODE##_K: \
+ if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) { \
+ insn += insn->off; \
+ CONT_JMP; \
+ } \
+ CONT; \
+ JMP32_##OPCODE##_K: \
+ if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) { \
+ insn += insn->off; \
+ CONT_JMP; \
+ } \
+ CONT;
+ COND_JMP(u, JEQ, ==)
+ COND_JMP(u, JNE, !=)
+ COND_JMP(u, JGT, >)
+ COND_JMP(u, JLT, <)
+ COND_JMP(u, JGE, >=)
+ COND_JMP(u, JLE, <=)
+ COND_JMP(u, JSET, &)
+ COND_JMP(s, JSGT, >)
+ COND_JMP(s, JSLT, <)
+ COND_JMP(s, JSGE, >=)
+ COND_JMP(s, JSLE, <=)
+#undef COND_JMP
/* STX and ST and LDX*/
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
@@ -2036,6 +2031,8 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
const struct bpf_func_proto bpf_map_push_elem_proto __weak;
const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
+const struct bpf_func_proto bpf_spin_lock_proto __weak;
+const struct bpf_func_proto bpf_spin_unlock_proto __weak;
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
@@ -2101,6 +2098,10 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
return -EFAULT;
}
+DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
+EXPORT_SYMBOL(bpf_stats_enabled_key);
+int sysctl_bpf_stats_enabled __read_mostly;
+
/* All definitions of tracepoints related to BPF. */
#define CREATE_TRACE_POINTS
#include <linux/bpf_trace.h>
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index d6b76377cb6e..de73f55e42fd 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -67,7 +67,7 @@ const char *const bpf_class_string[8] = {
[BPF_STX] = "stx",
[BPF_ALU] = "alu",
[BPF_JMP] = "jmp",
- [BPF_RET] = "BUG",
+ [BPF_JMP32] = "jmp32",
[BPF_ALU64] = "alu64",
};
@@ -136,23 +136,22 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
else
print_bpf_end_insn(verbose, cbs->private_data, insn);
} else if (BPF_OP(insn->code) == BPF_NEG) {
- verbose(cbs->private_data, "(%02x) r%d = %s-r%d\n",
- insn->code, insn->dst_reg,
- class == BPF_ALU ? "(u32) " : "",
+ verbose(cbs->private_data, "(%02x) %c%d = -%c%d\n",
+ insn->code, class == BPF_ALU ? 'w' : 'r',
+ insn->dst_reg, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg);
} else if (BPF_SRC(insn->code) == BPF_X) {
- verbose(cbs->private_data, "(%02x) %sr%d %s %sr%d\n",
- insn->code, class == BPF_ALU ? "(u32) " : "",
+ verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n",
+ insn->code, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg,
bpf_alu_string[BPF_OP(insn->code) >> 4],
- class == BPF_ALU ? "(u32) " : "",
+ class == BPF_ALU ? 'w' : 'r',
insn->src_reg);
} else {
- verbose(cbs->private_data, "(%02x) %sr%d %s %s%d\n",
- insn->code, class == BPF_ALU ? "(u32) " : "",
+ verbose(cbs->private_data, "(%02x) %c%d %s %d\n",
+ insn->code, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg,
bpf_alu_string[BPF_OP(insn->code) >> 4],
- class == BPF_ALU ? "(u32) " : "",
insn->imm);
}
} else if (class == BPF_STX) {
@@ -220,7 +219,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
verbose(cbs->private_data, "BUG_ld_%02x\n", insn->code);
return;
}
- } else if (class == BPF_JMP) {
+ } else if (class == BPF_JMP32 || class == BPF_JMP) {
u8 opcode = BPF_OP(insn->code);
if (opcode == BPF_CALL) {
@@ -244,13 +243,18 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
verbose(cbs->private_data, "(%02x) exit\n", insn->code);
} else if (BPF_SRC(insn->code) == BPF_X) {
- verbose(cbs->private_data, "(%02x) if r%d %s r%d goto pc%+d\n",
- insn->code, insn->dst_reg,
+ verbose(cbs->private_data,
+ "(%02x) if %c%d %s %c%d goto pc%+d\n",
+ insn->code, class == BPF_JMP32 ? 'w' : 'r',
+ insn->dst_reg,
bpf_jmp_string[BPF_OP(insn->code) >> 4],
+ class == BPF_JMP32 ? 'w' : 'r',
insn->src_reg, insn->off);
} else {
- verbose(cbs->private_data, "(%02x) if r%d %s 0x%x goto pc%+d\n",
- insn->code, insn->dst_reg,
+ verbose(cbs->private_data,
+ "(%02x) if %c%d %s 0x%x goto pc%+d\n",
+ insn->code, class == BPF_JMP32 ? 'w' : 'r',
+ insn->dst_reg,
bpf_jmp_string[BPF_OP(insn->code) >> 4],
insn->imm, insn->off);
}
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index f9274114c88d..fed15cf94dca 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -718,21 +718,12 @@ static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
BITS_PER_LONG == 64;
}
-static u32 htab_size_value(const struct bpf_htab *htab, bool percpu)
-{
- u32 size = htab->map.value_size;
-
- if (percpu || fd_htab_map_needs_adjust(htab))
- size = round_up(size, 8);
- return size;
-}
-
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
void *value, u32 key_size, u32 hash,
bool percpu, bool onallcpus,
struct htab_elem *old_elem)
{
- u32 size = htab_size_value(htab, percpu);
+ u32 size = htab->map.value_size;
bool prealloc = htab_is_prealloc(htab);
struct htab_elem *l_new, **pl_new;
void __percpu *pptr;
@@ -770,10 +761,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new = ERR_PTR(-ENOMEM);
goto dec_count;
}
+ check_and_init_map_lock(&htab->map,
+ l_new->key + round_up(key_size, 8));
}
memcpy(l_new->key, key, key_size);
if (percpu) {
+ size = round_up(size, 8);
if (prealloc) {
pptr = htab_elem_get_ptr(l_new, key_size);
} else {
@@ -791,8 +785,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
if (!prealloc)
htab_elem_set_ptr(l_new, key_size, pptr);
- } else {
+ } else if (fd_htab_map_needs_adjust(htab)) {
+ size = round_up(size, 8);
memcpy(l_new->key + round_up(key_size, 8), value, size);
+ } else {
+ copy_map_value(&htab->map,
+ l_new->key + round_up(key_size, 8),
+ value);
}
l_new->hash = hash;
@@ -805,11 +804,11 @@ dec_count:
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
u64 map_flags)
{
- if (l_old && map_flags == BPF_NOEXIST)
+ if (l_old && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
/* elem already exists */
return -EEXIST;
- if (!l_old && map_flags == BPF_EXIST)
+ if (!l_old && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
/* elem doesn't exist, cannot update it */
return -ENOENT;
@@ -828,7 +827,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
u32 key_size, hash;
int ret;
- if (unlikely(map_flags > BPF_EXIST))
+ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST))
/* unknown flags */
return -EINVAL;
@@ -841,6 +840,28 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
b = __select_bucket(htab, hash);
head = &b->head;
+ if (unlikely(map_flags & BPF_F_LOCK)) {
+ if (unlikely(!map_value_has_spin_lock(map)))
+ return -EINVAL;
+ /* find an element without taking the bucket lock */
+ l_old = lookup_nulls_elem_raw(head, hash, key, key_size,
+ htab->n_buckets);
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ return ret;
+ if (l_old) {
+ /* grab the element lock and update value in place */
+ copy_map_value_locked(map,
+ l_old->key + round_up(key_size, 8),
+ value, false);
+ return 0;
+ }
+ /* fall through, grab the bucket lock and lookup again.
+ * 99.9% chance that the element won't be found,
+ * but second lookup under lock has to be done.
+ */
+ }
+
/* bpf_map_update_elem() can be called in_irq() */
raw_spin_lock_irqsave(&b->lock, flags);
@@ -850,6 +871,20 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
if (ret)
goto err;
+ if (unlikely(l_old && (map_flags & BPF_F_LOCK))) {
+ /* first lookup without the bucket lock didn't find the element,
+ * but second lookup with the bucket lock found it.
+ * This case is highly unlikely, but has to be dealt with:
+ * grab the element lock in addition to the bucket lock
+ * and update element in place
+ */
+ copy_map_value_locked(map,
+ l_old->key + round_up(key_size, 8),
+ value, false);
+ ret = 0;
+ goto err;
+ }
+
l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
l_old);
if (IS_ERR(l_new)) {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a74972b07e74..a411fc17d265 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -221,6 +221,102 @@ const struct bpf_func_proto bpf_get_current_comm_proto = {
.arg2_type = ARG_CONST_SIZE,
};
+#if defined(CONFIG_QUEUED_SPINLOCKS) || defined(CONFIG_BPF_ARCH_SPINLOCK)
+
+static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
+{
+ arch_spinlock_t *l = (void *)lock;
+ union {
+ __u32 val;
+ arch_spinlock_t lock;
+ } u = { .lock = __ARCH_SPIN_LOCK_UNLOCKED };
+
+ compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0");
+ BUILD_BUG_ON(sizeof(*l) != sizeof(__u32));
+ BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32));
+ arch_spin_lock(l);
+}
+
+static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
+{
+ arch_spinlock_t *l = (void *)lock;
+
+ arch_spin_unlock(l);
+}
+
+#else
+
+static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
+{
+ atomic_t *l = (void *)lock;
+
+ BUILD_BUG_ON(sizeof(*l) != sizeof(*lock));
+ do {
+ atomic_cond_read_relaxed(l, !VAL);
+ } while (atomic_xchg(l, 1));
+}
+
+static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
+{
+ atomic_t *l = (void *)lock;
+
+ atomic_set_release(l, 0);
+}
+
+#endif
+
+static DEFINE_PER_CPU(unsigned long, irqsave_flags);
+
+notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __bpf_spin_lock(lock);
+ __this_cpu_write(irqsave_flags, flags);
+ return 0;
+}
+
+const struct bpf_func_proto bpf_spin_lock_proto = {
+ .func = bpf_spin_lock,
+ .gpl_only = false,
+ .ret_type = RET_VOID,
+ .arg1_type = ARG_PTR_TO_SPIN_LOCK,
+};
+
+notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock)
+{
+ unsigned long flags;
+
+ flags = __this_cpu_read(irqsave_flags);
+ __bpf_spin_unlock(lock);
+ local_irq_restore(flags);
+ return 0;
+}
+
+const struct bpf_func_proto bpf_spin_unlock_proto = {
+ .func = bpf_spin_unlock,
+ .gpl_only = false,
+ .ret_type = RET_VOID,
+ .arg1_type = ARG_PTR_TO_SPIN_LOCK,
+};
+
+void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
+ bool lock_src)
+{
+ struct bpf_spin_lock *lock;
+
+ if (lock_src)
+ lock = src + map->spin_lock_off;
+ else
+ lock = dst + map->spin_lock_off;
+ preempt_disable();
+ ____bpf_spin_lock(lock);
+ copy_map_value(map, dst, src);
+ ____bpf_spin_unlock(lock);
+ preempt_enable();
+}
+
#ifdef CONFIG_CGROUPS
BPF_CALL_0(bpf_get_current_cgroup_id)
{
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 07a34ef562a0..6b572e2de7fb 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -131,7 +131,14 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
struct bpf_cgroup_storage *storage;
struct bpf_storage_buffer *new;
- if (flags != BPF_ANY && flags != BPF_EXIST)
+ if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST | BPF_NOEXIST)))
+ return -EINVAL;
+
+ if (unlikely(flags & BPF_NOEXIST))
+ return -EINVAL;
+
+ if (unlikely((flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)))
return -EINVAL;
storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map,
@@ -139,6 +146,11 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
if (!storage)
return -ENOENT;
+ if (flags & BPF_F_LOCK) {
+ copy_map_value_locked(map, storage->buf->data, value, false);
+ return 0;
+ }
+
new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
map->value_size,
__GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
@@ -147,6 +159,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
return -ENOMEM;
memcpy(&new->data[0], value, map->value_size);
+ check_and_init_map_lock(map, new->data);
new = xchg(&storage->buf, new);
kfree_rcu(new, rcu);
@@ -483,6 +496,7 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
storage->buf = kmalloc_node(size, flags, map->numa_node);
if (!storage->buf)
goto enomem;
+ check_and_init_map_lock(map, storage->buf->data);
} else {
storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags);
if (!storage->percpu_buf)
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 52378d3e34b3..3dff41403583 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -37,6 +37,11 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
return ERR_PTR(-EINVAL);
}
+ if (map_value_has_spin_lock(inner_map)) {
+ fdput(f);
+ return ERR_PTR(-ENOTSUPP);
+ }
+
inner_map_meta_size = sizeof(*inner_map_meta);
/* In some cases verifier needs to access beyond just base map. */
if (inner_map->ops == &array_map_ops)
@@ -53,6 +58,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
inner_map_meta->value_size = inner_map->value_size;
inner_map_meta->map_flags = inner_map->map_flags;
inner_map_meta->max_entries = inner_map->max_entries;
+ inner_map_meta->spin_lock_off = inner_map->spin_lock_off;
/* Misc members not needed in bpf_map_meta_equal() check. */
inner_map_meta->ops = inner_map->ops;
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 54cf2b9c44a4..ba635209ae9a 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -35,6 +35,7 @@ static DECLARE_RWSEM(bpf_devs_lock);
struct bpf_offload_dev {
const struct bpf_prog_offload_ops *ops;
struct list_head netdevs;
+ void *priv;
};
struct bpf_offload_netdev {
@@ -173,6 +174,41 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
return ret;
}
+void
+bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
+ struct bpf_insn *insn)
+{
+ const struct bpf_prog_offload_ops *ops;
+ struct bpf_prog_offload *offload;
+ int ret = -EOPNOTSUPP;
+
+ down_read(&bpf_devs_lock);
+ offload = env->prog->aux->offload;
+ if (offload) {
+ ops = offload->offdev->ops;
+ if (!offload->opt_failed && ops->replace_insn)
+ ret = ops->replace_insn(env, off, insn);
+ offload->opt_failed |= ret;
+ }
+ up_read(&bpf_devs_lock);
+}
+
+void
+bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+ struct bpf_prog_offload *offload;
+ int ret = -EOPNOTSUPP;
+
+ down_read(&bpf_devs_lock);
+ offload = env->prog->aux->offload;
+ if (offload) {
+ if (!offload->opt_failed && offload->offdev->ops->remove_insns)
+ ret = offload->offdev->ops->remove_insns(env, off, cnt);
+ offload->opt_failed |= ret;
+ }
+ up_read(&bpf_devs_lock);
+}
+
static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
{
struct bpf_prog_offload *offload = prog->aux->offload;
@@ -634,7 +670,7 @@ unlock:
EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
struct bpf_offload_dev *
-bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops)
+bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv)
{
struct bpf_offload_dev *offdev;
int err;
@@ -653,6 +689,7 @@ bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops)
return ERR_PTR(-ENOMEM);
offdev->ops = ops;
+ offdev->priv = priv;
INIT_LIST_HEAD(&offdev->netdevs);
return offdev;
@@ -665,3 +702,9 @@ void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev)
kfree(offdev);
}
EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy);
+
+void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev)
+{
+ return offdev->priv;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_priv);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d7185c8f77bf..62f6bced3a3c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -463,7 +463,7 @@ int map_check_no_btf(const struct bpf_map *map,
return -ENOTSUPP;
}
-static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
+static int map_check_btf(struct bpf_map *map, const struct btf *btf,
u32 btf_key_id, u32 btf_value_id)
{
const struct btf_type *key_type, *value_type;
@@ -478,6 +478,22 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
if (!value_type || value_size != map->value_size)
return -EINVAL;
+ map->spin_lock_off = btf_find_spin_lock(btf, value_type);
+
+ if (map_value_has_spin_lock(map)) {
+ if (map->map_type != BPF_MAP_TYPE_HASH &&
+ map->map_type != BPF_MAP_TYPE_ARRAY &&
+ map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ return -ENOTSUPP;
+ if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
+ map->value_size) {
+ WARN_ONCE(1,
+ "verifier bug spin_lock_off %d value_size %d\n",
+ map->spin_lock_off, map->value_size);
+ return -EFAULT;
+ }
+ }
+
if (map->ops->map_check_btf)
ret = map->ops->map_check_btf(map, btf, key_type, value_type);
@@ -542,6 +558,8 @@ static int map_create(union bpf_attr *attr)
map->btf = btf;
map->btf_key_type_id = attr->btf_key_type_id;
map->btf_value_type_id = attr->btf_value_type_id;
+ } else {
+ map->spin_lock_off = -EINVAL;
}
err = security_bpf_map_alloc(map);
@@ -559,12 +577,12 @@ static int map_create(union bpf_attr *attr)
err = bpf_map_new_fd(map, f_flags);
if (err < 0) {
/* failed to allocate fd.
- * bpf_map_put() is needed because the above
+ * bpf_map_put_with_uref() is needed because the above
* bpf_map_alloc_id() has published the map
* to the userspace and the userspace may
* have refcnt-ed it through BPF_MAP_GET_FD_BY_ID.
*/
- bpf_map_put(map);
+ bpf_map_put_with_uref(map);
return err;
}
@@ -664,7 +682,7 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size)
}
/* last field in 'union bpf_attr' used by this command */
-#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
+#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags
static int map_lookup_elem(union bpf_attr *attr)
{
@@ -680,6 +698,9 @@ static int map_lookup_elem(union bpf_attr *attr)
if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
return -EINVAL;
+ if (attr->flags & ~BPF_F_LOCK)
+ return -EINVAL;
+
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
@@ -690,6 +711,12 @@ static int map_lookup_elem(union bpf_attr *attr)
goto err_put;
}
+ if ((attr->flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)) {
+ err = -EINVAL;
+ goto err_put;
+ }
+
key = __bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
@@ -745,7 +772,13 @@ static int map_lookup_elem(union bpf_attr *attr)
err = -ENOENT;
} else {
err = 0;
- memcpy(value, ptr, value_size);
+ if (attr->flags & BPF_F_LOCK)
+ /* lock 'ptr' and copy everything but lock */
+ copy_map_value_locked(map, value, ptr, true);
+ else
+ copy_map_value(map, value, ptr);
+ /* mask lock, since value wasn't zero inited */
+ check_and_init_map_lock(map, value);
}
rcu_read_unlock();
}
@@ -808,6 +841,12 @@ static int map_update_elem(union bpf_attr *attr)
goto err_put;
}
+ if ((attr->flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)) {
+ err = -EINVAL;
+ goto err_put;
+ }
+
key = __bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
@@ -1245,24 +1284,54 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
return 0;
}
+static void bpf_prog_get_stats(const struct bpf_prog *prog,
+ struct bpf_prog_stats *stats)
+{
+ u64 nsecs = 0, cnt = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ const struct bpf_prog_stats *st;
+ unsigned int start;
+ u64 tnsecs, tcnt;
+
+ st = per_cpu_ptr(prog->aux->stats, cpu);
+ do {
+ start = u64_stats_fetch_begin_irq(&st->syncp);
+ tnsecs = st->nsecs;
+ tcnt = st->cnt;
+ } while (u64_stats_fetch_retry_irq(&st->syncp, start));
+ nsecs += tnsecs;
+ cnt += tcnt;
+ }
+ stats->nsecs = nsecs;
+ stats->cnt = cnt;
+}
+
#ifdef CONFIG_PROC_FS
static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_prog *prog = filp->private_data;
char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
+ struct bpf_prog_stats stats;
+ bpf_prog_get_stats(prog, &stats);
bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
seq_printf(m,
"prog_type:\t%u\n"
"prog_jited:\t%u\n"
"prog_tag:\t%s\n"
"memlock:\t%llu\n"
- "prog_id:\t%u\n",
+ "prog_id:\t%u\n"
+ "run_time_ns:\t%llu\n"
+ "run_cnt:\t%llu\n",
prog->type,
prog->jited,
prog_tag,
prog->pages * 1ULL << PAGE_SHIFT,
- prog->aux->id);
+ prog->aux->id,
+ stats.nsecs,
+ stats.cnt);
}
#endif
@@ -1988,7 +2057,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
fd = bpf_map_new_fd(map, f_flags);
if (fd < 0)
- bpf_map_put(map);
+ bpf_map_put_with_uref(map);
return fd;
}
@@ -2085,6 +2154,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
struct bpf_prog_info info = {};
u32 info_len = attr->info.info_len;
+ struct bpf_prog_stats stats;
char __user *uinsns;
u32 ulen;
int err;
@@ -2124,6 +2194,10 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
if (err)
return err;
+ bpf_prog_get_stats(prog, &stats);
+ info.run_time_ns = stats.nsecs;
+ info.run_cnt = stats.cnt;
+
if (!capable(CAP_SYS_ADMIN)) {
info.jited_prog_len = 0;
info.xlated_prog_len = 0;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8f295b790297..a7b96bf0e654 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -213,6 +213,7 @@ struct bpf_call_arg_meta {
s64 msize_smax_value;
u64 msize_umax_value;
int ptr_id;
+ int func_id;
};
static DEFINE_MUTEX(bpf_verifier_lock);
@@ -330,10 +331,19 @@ static bool type_is_pkt_pointer(enum bpf_reg_type type)
type == PTR_TO_PACKET_META;
}
+static bool type_is_sk_pointer(enum bpf_reg_type type)
+{
+ return type == PTR_TO_SOCKET ||
+ type == PTR_TO_SOCK_COMMON ||
+ type == PTR_TO_TCP_SOCK;
+}
+
static bool reg_type_may_be_null(enum bpf_reg_type type)
{
return type == PTR_TO_MAP_VALUE_OR_NULL ||
- type == PTR_TO_SOCKET_OR_NULL;
+ type == PTR_TO_SOCKET_OR_NULL ||
+ type == PTR_TO_SOCK_COMMON_OR_NULL ||
+ type == PTR_TO_TCP_SOCK_OR_NULL;
}
static bool type_is_refcounted(enum bpf_reg_type type)
@@ -351,6 +361,12 @@ static bool reg_is_refcounted(const struct bpf_reg_state *reg)
return type_is_refcounted(reg->type);
}
+static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
+{
+ return reg->type == PTR_TO_MAP_VALUE &&
+ map_value_has_spin_lock(reg->map_ptr);
+}
+
static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg)
{
return type_is_refcounted_or_null(reg->type);
@@ -370,6 +386,12 @@ static bool is_release_function(enum bpf_func_id func_id)
return func_id == BPF_FUNC_sk_release;
}
+static bool is_acquire_function(enum bpf_func_id func_id)
+{
+ return func_id == BPF_FUNC_sk_lookup_tcp ||
+ func_id == BPF_FUNC_sk_lookup_udp;
+}
+
/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
[NOT_INIT] = "?",
@@ -385,6 +407,10 @@ static const char * const reg_type_str[] = {
[PTR_TO_FLOW_KEYS] = "flow_keys",
[PTR_TO_SOCKET] = "sock",
[PTR_TO_SOCKET_OR_NULL] = "sock_or_null",
+ [PTR_TO_SOCK_COMMON] = "sock_common",
+ [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
+ [PTR_TO_TCP_SOCK] = "tcp_sock",
+ [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
};
static char slot_type_char[] = {
@@ -611,13 +637,10 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
}
/* release function corresponding to acquire_reference_state(). Idempotent. */
-static int __release_reference_state(struct bpf_func_state *state, int ptr_id)
+static int release_reference_state(struct bpf_func_state *state, int ptr_id)
{
int i, last_idx;
- if (!ptr_id)
- return -EFAULT;
-
last_idx = state->acquired_refs - 1;
for (i = 0; i < state->acquired_refs; i++) {
if (state->refs[i].id == ptr_id) {
@@ -629,21 +652,7 @@ static int __release_reference_state(struct bpf_func_state *state, int ptr_id)
return 0;
}
}
- return -EFAULT;
-}
-
-/* variation on the above for cases where we expect that there must be an
- * outstanding reference for the specified ptr_id.
- */
-static int release_reference_state(struct bpf_verifier_env *env, int ptr_id)
-{
- struct bpf_func_state *state = cur_func(env);
- int err;
-
- err = __release_reference_state(state, ptr_id);
- if (WARN_ON_ONCE(err != 0))
- verbose(env, "verifier internal error: can't release reference\n");
- return err;
+ return -EINVAL;
}
static int transfer_reference_state(struct bpf_func_state *dst,
@@ -712,6 +721,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
}
dst_state->speculative = src->speculative;
dst_state->curframe = src->curframe;
+ dst_state->active_spin_lock = src->active_spin_lock;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
@@ -1095,7 +1105,7 @@ static int check_subprogs(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++) {
u8 code = insn[i].code;
- if (BPF_CLASS(code) != BPF_JMP)
+ if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
@@ -1201,6 +1211,10 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case CONST_PTR_TO_MAP:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
+ case PTR_TO_SOCK_COMMON:
+ case PTR_TO_SOCK_COMMON_OR_NULL:
+ case PTR_TO_TCP_SOCK:
+ case PTR_TO_TCP_SOCK_OR_NULL:
return true;
default:
return false;
@@ -1483,6 +1497,21 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
if (err)
verbose(env, "R%d max value is outside of the array range\n",
regno);
+
+ if (map_value_has_spin_lock(reg->map_ptr)) {
+ u32 lock = reg->map_ptr->spin_lock_off;
+
+ /* if any part of struct bpf_spin_lock can be touched by
+ * load/store reject this program.
+ * To check that [x1, x2) overlaps with [y1, y2)
+ * it is sufficient to check x1 < y2 && y1 < x2.
+ */
+ if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) &&
+ lock < reg->umax_value + off + size) {
+ verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n");
+ return -EACCES;
+ }
+ }
return err;
}
@@ -1624,6 +1653,7 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = &regs[regno];
struct bpf_insn_access_aux info = {};
+ bool valid;
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
@@ -1631,15 +1661,31 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
return -EACCES;
}
- if (!bpf_sock_is_valid_access(off, size, t, &info)) {
- verbose(env, "invalid bpf_sock access off=%d size=%d\n",
- off, size);
- return -EACCES;
+ switch (reg->type) {
+ case PTR_TO_SOCK_COMMON:
+ valid = bpf_sock_common_is_valid_access(off, size, t, &info);
+ break;
+ case PTR_TO_SOCKET:
+ valid = bpf_sock_is_valid_access(off, size, t, &info);
+ break;
+ case PTR_TO_TCP_SOCK:
+ valid = bpf_tcp_sock_is_valid_access(off, size, t, &info);
+ break;
+ default:
+ valid = false;
}
- env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
- return 0;
+ if (valid) {
+ env->insn_aux_data[insn_idx].ctx_field_size =
+ info.ctx_field_size;
+ return 0;
+ }
+
+ verbose(env, "R%d invalid %s access off=%d size=%d\n",
+ regno, reg_type_str[reg->type], off, size);
+
+ return -EACCES;
}
static bool __is_pointer_value(bool allow_ptr_leaks,
@@ -1665,8 +1711,14 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
- return reg->type == PTR_TO_CTX ||
- reg->type == PTR_TO_SOCKET;
+ return reg->type == PTR_TO_CTX;
+}
+
+static bool is_sk_reg(struct bpf_verifier_env *env, int regno)
+{
+ const struct bpf_reg_state *reg = reg_state(env, regno);
+
+ return type_is_sk_pointer(reg->type);
}
static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
@@ -1777,6 +1829,12 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
case PTR_TO_SOCKET:
pointer_desc = "sock ";
break;
+ case PTR_TO_SOCK_COMMON:
+ pointer_desc = "sock_common ";
+ break;
+ case PTR_TO_TCP_SOCK:
+ pointer_desc = "tcp_sock ";
+ break;
default:
break;
}
@@ -1980,11 +2038,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
* PTR_TO_PACKET[_META,_END]. In the latter
* case, we know the offset is zero.
*/
- if (reg_type == SCALAR_VALUE)
+ if (reg_type == SCALAR_VALUE) {
mark_reg_unknown(env, regs, value_regno);
- else
+ } else {
mark_reg_known_zero(env, regs,
value_regno);
+ if (reg_type_may_be_null(reg_type))
+ regs[value_regno].id = ++env->id_gen;
+ }
regs[value_regno].type = reg_type;
}
@@ -2030,9 +2091,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
err = check_flow_keys_access(env, off, size);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
- } else if (reg->type == PTR_TO_SOCKET) {
+ } else if (type_is_sk_pointer(reg->type)) {
if (t == BPF_WRITE) {
- verbose(env, "cannot write into socket\n");
+ verbose(env, "R%d cannot write into %s\n",
+ regno, reg_type_str[reg->type]);
return -EACCES;
}
err = check_sock_access(env, insn_idx, regno, off, size, t);
@@ -2079,7 +2141,8 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
if (is_ctx_reg(env, insn->dst_reg) ||
is_pkt_reg(env, insn->dst_reg) ||
- is_flow_key_reg(env, insn->dst_reg)) {
+ is_flow_key_reg(env, insn->dst_reg) ||
+ is_sk_reg(env, insn->dst_reg)) {
verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
insn->dst_reg,
reg_type_str[reg_state(env, insn->dst_reg)->type]);
@@ -2195,6 +2258,91 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
}
}
+/* Implementation details:
+ * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL
+ * Two bpf_map_lookups (even with the same key) will have different reg->id.
+ * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after
+ * value_or_null->value transition, since the verifier only cares about
+ * the range of access to valid map value pointer and doesn't care about actual
+ * address of the map element.
+ * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps
+ * reg->id > 0 after value_or_null->value transition. By doing so
+ * two bpf_map_lookups will be considered two different pointers that
+ * point to different bpf_spin_locks.
+ * The verifier allows taking only one bpf_spin_lock at a time to avoid
+ * dead-locks.
+ * Since only one bpf_spin_lock is allowed the checks are simpler than
+ * reg_is_refcounted() logic. The verifier needs to remember only
+ * one spin_lock instead of array of acquired_refs.
+ * cur_state->active_spin_lock remembers which map value element got locked
+ * and clears it after bpf_spin_unlock.
+ */
+static int process_spin_lock(struct bpf_verifier_env *env, int regno,
+ bool is_lock)
+{
+ struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+ struct bpf_verifier_state *cur = env->cur_state;
+ bool is_const = tnum_is_const(reg->var_off);
+ struct bpf_map *map = reg->map_ptr;
+ u64 val = reg->var_off.value;
+
+ if (reg->type != PTR_TO_MAP_VALUE) {
+ verbose(env, "R%d is not a pointer to map_value\n", regno);
+ return -EINVAL;
+ }
+ if (!is_const) {
+ verbose(env,
+ "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n",
+ regno);
+ return -EINVAL;
+ }
+ if (!map->btf) {
+ verbose(env,
+ "map '%s' has to have BTF in order to use bpf_spin_lock\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (!map_value_has_spin_lock(map)) {
+ if (map->spin_lock_off == -E2BIG)
+ verbose(env,
+ "map '%s' has more than one 'struct bpf_spin_lock'\n",
+ map->name);
+ else if (map->spin_lock_off == -ENOENT)
+ verbose(env,
+ "map '%s' doesn't have 'struct bpf_spin_lock'\n",
+ map->name);
+ else
+ verbose(env,
+ "map '%s' is not a struct type or bpf_spin_lock is mangled\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (map->spin_lock_off != val + reg->off) {
+ verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n",
+ val + reg->off);
+ return -EINVAL;
+ }
+ if (is_lock) {
+ if (cur->active_spin_lock) {
+ verbose(env,
+ "Locking two bpf_spin_locks are not allowed\n");
+ return -EINVAL;
+ }
+ cur->active_spin_lock = reg->id;
+ } else {
+ if (!cur->active_spin_lock) {
+ verbose(env, "bpf_spin_unlock without taking a lock\n");
+ return -EINVAL;
+ }
+ if (cur->active_spin_lock != reg->id) {
+ verbose(env, "bpf_spin_unlock of different lock\n");
+ return -EINVAL;
+ }
+ cur->active_spin_lock = 0;
+ }
+ return 0;
+}
+
static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_MEM ||
@@ -2261,6 +2409,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
err = check_ctx_reg(env, reg, regno);
if (err < 0)
return err;
+ } else if (arg_type == ARG_PTR_TO_SOCK_COMMON) {
+ expected_type = PTR_TO_SOCK_COMMON;
+ /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
+ if (!type_is_sk_pointer(type))
+ goto err_type;
} else if (arg_type == ARG_PTR_TO_SOCKET) {
expected_type = PTR_TO_SOCKET;
if (type != expected_type)
@@ -2271,6 +2424,17 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
return -EFAULT;
}
meta->ptr_id = reg->id;
+ } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
+ if (meta->func_id == BPF_FUNC_spin_lock) {
+ if (process_spin_lock(env, regno, true))
+ return -EACCES;
+ } else if (meta->func_id == BPF_FUNC_spin_unlock) {
+ if (process_spin_lock(env, regno, false))
+ return -EACCES;
+ } else {
+ verbose(env, "verifier internal error\n");
+ return -EFAULT;
+ }
} else if (arg_type_is_mem_ptr(arg_type)) {
expected_type = PTR_TO_STACK;
/* One exception here. In case function allows for NULL to be
@@ -2664,7 +2828,7 @@ static int release_reference(struct bpf_verifier_env *env,
for (i = 0; i <= vstate->curframe; i++)
release_reg_references(env, vstate->frame[i], meta->ptr_id);
- return release_reference_state(env, meta->ptr_id);
+ return release_reference_state(cur_func(env), meta->ptr_id);
}
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
@@ -2890,6 +3054,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return err;
}
+ meta.func_id = func_id;
/* check args */
err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
if (err)
@@ -2929,8 +3094,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
}
} else if (is_release_function(func_id)) {
err = release_reference(env, &meta);
- if (err)
+ if (err) {
+ verbose(env, "func %s#%d reference has not been acquired before\n",
+ func_id_name(func_id), func_id);
return err;
+ }
}
regs = cur_regs(env);
@@ -2972,17 +3140,30 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
regs[BPF_REG_0].map_ptr = meta.map_ptr;
if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ if (map_value_has_spin_lock(meta.map_ptr))
+ regs[BPF_REG_0].id = ++env->id_gen;
} else {
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
regs[BPF_REG_0].id = ++env->id_gen;
}
} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
- int id = acquire_reference_state(env, insn_idx);
- if (id < 0)
- return id;
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
- regs[BPF_REG_0].id = id;
+ if (is_acquire_function(func_id)) {
+ int id = acquire_reference_state(env, insn_idx);
+
+ if (id < 0)
+ return id;
+ /* For release_reference() */
+ regs[BPF_REG_0].id = id;
+ } else {
+ /* For mark_ptr_or_null_reg() */
+ regs[BPF_REG_0].id = ++env->id_gen;
+ }
+ } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
+ regs[BPF_REG_0].id = ++env->id_gen;
} else {
verbose(env, "unknown return type %d of func %s#%d\n",
fn->ret_type, func_id_name(func_id), func_id);
@@ -3242,6 +3423,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
case PTR_TO_PACKET_END:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
+ case PTR_TO_SOCK_COMMON:
+ case PTR_TO_SOCK_COMMON_OR_NULL:
+ case PTR_TO_TCP_SOCK:
+ case PTR_TO_TCP_SOCK_OR_NULL:
verbose(env, "R%d pointer arithmetic on %s prohibited\n",
dst, reg_type_str[ptr_reg->type]);
return -EACCES;
@@ -4034,11 +4219,50 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
* 0 - branch will not be taken and fall-through to next insn
* -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
*/
-static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
+ bool is_jmp32)
{
+ struct bpf_reg_state reg_lo;
+ s64 sval;
+
if (__is_pointer_value(false, reg))
return -1;
+ if (is_jmp32) {
+ reg_lo = *reg;
+ reg = &reg_lo;
+ /* For JMP32, only low 32 bits are compared, coerce_reg_to_size
+ * could truncate high bits and update umin/umax according to
+ * information of low bits.
+ */
+ coerce_reg_to_size(reg, 4);
+ /* smin/smax need special handling. For example, after coerce,
+ * if smin_value is 0x00000000ffffffffLL, the value is -1 when
+ * used as operand to JMP32. It is a negative number from s32's
+ * point of view, while it is a positive number when seen as
+ * s64. The smin/smax are kept as s64, therefore, when used with
+ * JMP32, they need to be transformed into s32, then sign
+ * extended back to s64.
+ *
+ * Also, smin/smax were copied from umin/umax. If umin/umax has
+ * different sign bit, then min/max relationship doesn't
+ * maintain after casting into s32, for this case, set smin/smax
+ * to safest range.
+ */
+ if ((reg->umax_value ^ reg->umin_value) &
+ (1ULL << 31)) {
+ reg->smin_value = S32_MIN;
+ reg->smax_value = S32_MAX;
+ }
+ reg->smin_value = (s64)(s32)reg->smin_value;
+ reg->smax_value = (s64)(s32)reg->smax_value;
+
+ val = (u32)val;
+ sval = (s64)(s32)val;
+ } else {
+ sval = (s64)val;
+ }
+
switch (opcode) {
case BPF_JEQ:
if (tnum_is_const(reg->var_off))
@@ -4061,9 +4285,9 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return 0;
break;
case BPF_JSGT:
- if (reg->smin_value > (s64)val)
+ if (reg->smin_value > sval)
return 1;
- else if (reg->smax_value < (s64)val)
+ else if (reg->smax_value < sval)
return 0;
break;
case BPF_JLT:
@@ -4073,9 +4297,9 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return 0;
break;
case BPF_JSLT:
- if (reg->smax_value < (s64)val)
+ if (reg->smax_value < sval)
return 1;
- else if (reg->smin_value >= (s64)val)
+ else if (reg->smin_value >= sval)
return 0;
break;
case BPF_JGE:
@@ -4085,9 +4309,9 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return 0;
break;
case BPF_JSGE:
- if (reg->smin_value >= (s64)val)
+ if (reg->smin_value >= sval)
return 1;
- else if (reg->smax_value < (s64)val)
+ else if (reg->smax_value < sval)
return 0;
break;
case BPF_JLE:
@@ -4097,9 +4321,9 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return 0;
break;
case BPF_JSLE:
- if (reg->smax_value <= (s64)val)
+ if (reg->smax_value <= sval)
return 1;
- else if (reg->smin_value > (s64)val)
+ else if (reg->smin_value > sval)
return 0;
break;
}
@@ -4107,6 +4331,29 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return -1;
}
+/* Generate min value of the high 32-bit from TNUM info. */
+static u64 gen_hi_min(struct tnum var)
+{
+ return var.value & ~0xffffffffULL;
+}
+
+/* Generate max value of the high 32-bit from TNUM info. */
+static u64 gen_hi_max(struct tnum var)
+{
+ return (var.value | var.mask) & ~0xffffffffULL;
+}
+
+/* Return true if VAL is compared with a s64 sign extended from s32, and they
+ * are with the same signedness.
+ */
+static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg)
+{
+ return ((s32)sval >= 0 &&
+ reg->smin_value >= 0 && reg->smax_value <= S32_MAX) ||
+ ((s32)sval < 0 &&
+ reg->smax_value <= 0 && reg->smin_value >= S32_MIN);
+}
+
/* Adjusts the register min/max values in the case that the dst_reg is the
* variable register that we are working on, and src_reg is a constant or we're
* simply doing a BPF_K check.
@@ -4114,8 +4361,10 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
*/
static void reg_set_min_max(struct bpf_reg_state *true_reg,
struct bpf_reg_state *false_reg, u64 val,
- u8 opcode)
+ u8 opcode, bool is_jmp32)
{
+ s64 sval;
+
/* If the dst_reg is a pointer, we can't learn anything about its
* variable offset from the compare (unless src_reg were a pointer into
* the same object, but we don't bother with that.
@@ -4125,19 +4374,31 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
if (__is_pointer_value(false, false_reg))
return;
+ val = is_jmp32 ? (u32)val : val;
+ sval = is_jmp32 ? (s64)(s32)val : (s64)val;
+
switch (opcode) {
case BPF_JEQ:
- /* If this is false then we know nothing Jon Snow, but if it is
- * true then we know for sure.
- */
- __mark_reg_known(true_reg, val);
- break;
case BPF_JNE:
- /* If this is true we know nothing Jon Snow, but if it is false
- * we know the value for sure;
+ {
+ struct bpf_reg_state *reg =
+ opcode == BPF_JEQ ? true_reg : false_reg;
+
+ /* For BPF_JEQ, if this is false we know nothing Jon Snow, but
+ * if it is true we know the value for sure. Likewise for
+ * BPF_JNE.
*/
- __mark_reg_known(false_reg, val);
+ if (is_jmp32) {
+ u64 old_v = reg->var_off.value;
+ u64 hi_mask = ~0xffffffffULL;
+
+ reg->var_off.value = (old_v & hi_mask) | val;
+ reg->var_off.mask &= hi_mask;
+ } else {
+ __mark_reg_known(reg, val);
+ }
break;
+ }
case BPF_JSET:
false_reg->var_off = tnum_and(false_reg->var_off,
tnum_const(~val));
@@ -4145,38 +4406,61 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
true_reg->var_off = tnum_or(true_reg->var_off,
tnum_const(val));
break;
- case BPF_JGT:
- false_reg->umax_value = min(false_reg->umax_value, val);
- true_reg->umin_value = max(true_reg->umin_value, val + 1);
- break;
- case BPF_JSGT:
- false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
- true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
- break;
- case BPF_JLT:
- false_reg->umin_value = max(false_reg->umin_value, val);
- true_reg->umax_value = min(true_reg->umax_value, val - 1);
- break;
- case BPF_JSLT:
- false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
- true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
- break;
case BPF_JGE:
- false_reg->umax_value = min(false_reg->umax_value, val - 1);
- true_reg->umin_value = max(true_reg->umin_value, val);
+ case BPF_JGT:
+ {
+ u64 false_umax = opcode == BPF_JGT ? val : val - 1;
+ u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
+
+ if (is_jmp32) {
+ false_umax += gen_hi_max(false_reg->var_off);
+ true_umin += gen_hi_min(true_reg->var_off);
+ }
+ false_reg->umax_value = min(false_reg->umax_value, false_umax);
+ true_reg->umin_value = max(true_reg->umin_value, true_umin);
break;
+ }
case BPF_JSGE:
- false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
- true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
+ case BPF_JSGT:
+ {
+ s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1;
+ s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
+
+ /* If the full s64 was not sign-extended from s32 then don't
+ * deduct further info.
+ */
+ if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
+ break;
+ false_reg->smax_value = min(false_reg->smax_value, false_smax);
+ true_reg->smin_value = max(true_reg->smin_value, true_smin);
break;
+ }
case BPF_JLE:
- false_reg->umin_value = max(false_reg->umin_value, val + 1);
- true_reg->umax_value = min(true_reg->umax_value, val);
+ case BPF_JLT:
+ {
+ u64 false_umin = opcode == BPF_JLT ? val : val + 1;
+ u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
+
+ if (is_jmp32) {
+ false_umin += gen_hi_min(false_reg->var_off);
+ true_umax += gen_hi_max(true_reg->var_off);
+ }
+ false_reg->umin_value = max(false_reg->umin_value, false_umin);
+ true_reg->umax_value = min(true_reg->umax_value, true_umax);
break;
+ }
case BPF_JSLE:
- false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
- true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
+ case BPF_JSLT:
+ {
+ s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1;
+ s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
+
+ if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
+ break;
+ false_reg->smin_value = max(false_reg->smin_value, false_smin);
+ true_reg->smax_value = min(true_reg->smax_value, true_smax);
break;
+ }
default:
break;
}
@@ -4199,24 +4483,34 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
*/
static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
struct bpf_reg_state *false_reg, u64 val,
- u8 opcode)
+ u8 opcode, bool is_jmp32)
{
+ s64 sval;
+
if (__is_pointer_value(false, false_reg))
return;
+ val = is_jmp32 ? (u32)val : val;
+ sval = is_jmp32 ? (s64)(s32)val : (s64)val;
+
switch (opcode) {
case BPF_JEQ:
- /* If this is false then we know nothing Jon Snow, but if it is
- * true then we know for sure.
- */
- __mark_reg_known(true_reg, val);
- break;
case BPF_JNE:
- /* If this is true we know nothing Jon Snow, but if it is false
- * we know the value for sure;
- */
- __mark_reg_known(false_reg, val);
+ {
+ struct bpf_reg_state *reg =
+ opcode == BPF_JEQ ? true_reg : false_reg;
+
+ if (is_jmp32) {
+ u64 old_v = reg->var_off.value;
+ u64 hi_mask = ~0xffffffffULL;
+
+ reg->var_off.value = (old_v & hi_mask) | val;
+ reg->var_off.mask &= hi_mask;
+ } else {
+ __mark_reg_known(reg, val);
+ }
break;
+ }
case BPF_JSET:
false_reg->var_off = tnum_and(false_reg->var_off,
tnum_const(~val));
@@ -4224,38 +4518,58 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
true_reg->var_off = tnum_or(true_reg->var_off,
tnum_const(val));
break;
- case BPF_JGT:
- true_reg->umax_value = min(true_reg->umax_value, val - 1);
- false_reg->umin_value = max(false_reg->umin_value, val);
- break;
- case BPF_JSGT:
- true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
- false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
- break;
- case BPF_JLT:
- true_reg->umin_value = max(true_reg->umin_value, val + 1);
- false_reg->umax_value = min(false_reg->umax_value, val);
- break;
- case BPF_JSLT:
- true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
- false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
- break;
case BPF_JGE:
- true_reg->umax_value = min(true_reg->umax_value, val);
- false_reg->umin_value = max(false_reg->umin_value, val + 1);
+ case BPF_JGT:
+ {
+ u64 false_umin = opcode == BPF_JGT ? val : val + 1;
+ u64 true_umax = opcode == BPF_JGT ? val - 1 : val;
+
+ if (is_jmp32) {
+ false_umin += gen_hi_min(false_reg->var_off);
+ true_umax += gen_hi_max(true_reg->var_off);
+ }
+ false_reg->umin_value = max(false_reg->umin_value, false_umin);
+ true_reg->umax_value = min(true_reg->umax_value, true_umax);
break;
+ }
case BPF_JSGE:
- true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
- false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
+ case BPF_JSGT:
+ {
+ s64 false_smin = opcode == BPF_JSGT ? sval : sval + 1;
+ s64 true_smax = opcode == BPF_JSGT ? sval - 1 : sval;
+
+ if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
+ break;
+ false_reg->smin_value = max(false_reg->smin_value, false_smin);
+ true_reg->smax_value = min(true_reg->smax_value, true_smax);
break;
+ }
case BPF_JLE:
- true_reg->umin_value = max(true_reg->umin_value, val);
- false_reg->umax_value = min(false_reg->umax_value, val - 1);
+ case BPF_JLT:
+ {
+ u64 false_umax = opcode == BPF_JLT ? val : val - 1;
+ u64 true_umin = opcode == BPF_JLT ? val + 1 : val;
+
+ if (is_jmp32) {
+ false_umax += gen_hi_max(false_reg->var_off);
+ true_umin += gen_hi_min(true_reg->var_off);
+ }
+ false_reg->umax_value = min(false_reg->umax_value, false_umax);
+ true_reg->umin_value = max(true_reg->umin_value, true_umin);
break;
+ }
case BPF_JSLE:
- true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
- false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
+ case BPF_JSLT:
+ {
+ s64 false_smax = opcode == BPF_JSLT ? sval : sval - 1;
+ s64 true_smin = opcode == BPF_JSLT ? sval + 1 : sval;
+
+ if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
+ break;
+ false_reg->smax_value = min(false_reg->smax_value, false_smax);
+ true_reg->smin_value = max(true_reg->smin_value, true_smin);
break;
+ }
default:
break;
}
@@ -4346,8 +4660,13 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
}
} else if (reg->type == PTR_TO_SOCKET_OR_NULL) {
reg->type = PTR_TO_SOCKET;
+ } else if (reg->type == PTR_TO_SOCK_COMMON_OR_NULL) {
+ reg->type = PTR_TO_SOCK_COMMON;
+ } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) {
+ reg->type = PTR_TO_TCP_SOCK;
}
- if (is_null || !reg_is_refcounted(reg)) {
+ if (is_null || !(reg_is_refcounted(reg) ||
+ reg_may_point_to_spin_lock(reg))) {
/* We don't need id from this point onwards anymore,
* thus we should better reset it, so that state
* pruning has chances to take effect.
@@ -4369,7 +4688,7 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
int i, j;
if (reg_is_refcounted_or_null(&regs[regno]) && is_null)
- __release_reference_state(state, id);
+ release_reference_state(state, id);
for (i = 0; i < MAX_BPF_REG; i++)
mark_ptr_or_null_reg(state, &regs[i], id, is_null);
@@ -4393,6 +4712,10 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
if (BPF_SRC(insn->code) != BPF_X)
return false;
+ /* Pointers are always 64-bit. */
+ if (BPF_CLASS(insn->code) == BPF_JMP32)
+ return false;
+
switch (BPF_OP(insn->code)) {
case BPF_JGT:
if ((dst_reg->type == PTR_TO_PACKET &&
@@ -4485,16 +4808,18 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
struct bpf_reg_state *dst_reg, *other_branch_regs;
u8 opcode = BPF_OP(insn->code);
+ bool is_jmp32;
int err;
- if (opcode > BPF_JSLE) {
- verbose(env, "invalid BPF_JMP opcode %x\n", opcode);
+ /* Only conditional jumps are expected to reach here. */
+ if (opcode == BPF_JA || opcode > BPF_JSLE) {
+ verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode);
return -EINVAL;
}
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0) {
- verbose(env, "BPF_JMP uses reserved fields\n");
+ verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
return -EINVAL;
}
@@ -4510,7 +4835,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
}
} else {
if (insn->src_reg != BPF_REG_0) {
- verbose(env, "BPF_JMP uses reserved fields\n");
+ verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
return -EINVAL;
}
}
@@ -4521,9 +4846,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return err;
dst_reg = &regs[insn->dst_reg];
+ is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
if (BPF_SRC(insn->code) == BPF_K) {
- int pred = is_branch_taken(dst_reg, insn->imm, opcode);
+ int pred = is_branch_taken(dst_reg, insn->imm, opcode,
+ is_jmp32);
if (pred == 1) {
/* only follow the goto, ignore fall-through */
@@ -4551,30 +4878,51 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
* comparable.
*/
if (BPF_SRC(insn->code) == BPF_X) {
+ struct bpf_reg_state *src_reg = &regs[insn->src_reg];
+ struct bpf_reg_state lo_reg0 = *dst_reg;
+ struct bpf_reg_state lo_reg1 = *src_reg;
+ struct bpf_reg_state *src_lo, *dst_lo;
+
+ dst_lo = &lo_reg0;
+ src_lo = &lo_reg1;
+ coerce_reg_to_size(dst_lo, 4);
+ coerce_reg_to_size(src_lo, 4);
+
if (dst_reg->type == SCALAR_VALUE &&
- regs[insn->src_reg].type == SCALAR_VALUE) {
- if (tnum_is_const(regs[insn->src_reg].var_off))
+ src_reg->type == SCALAR_VALUE) {
+ if (tnum_is_const(src_reg->var_off) ||
+ (is_jmp32 && tnum_is_const(src_lo->var_off)))
reg_set_min_max(&other_branch_regs[insn->dst_reg],
- dst_reg, regs[insn->src_reg].var_off.value,
- opcode);
- else if (tnum_is_const(dst_reg->var_off))
+ dst_reg,
+ is_jmp32
+ ? src_lo->var_off.value
+ : src_reg->var_off.value,
+ opcode, is_jmp32);
+ else if (tnum_is_const(dst_reg->var_off) ||
+ (is_jmp32 && tnum_is_const(dst_lo->var_off)))
reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
- &regs[insn->src_reg],
- dst_reg->var_off.value, opcode);
- else if (opcode == BPF_JEQ || opcode == BPF_JNE)
+ src_reg,
+ is_jmp32
+ ? dst_lo->var_off.value
+ : dst_reg->var_off.value,
+ opcode, is_jmp32);
+ else if (!is_jmp32 &&
+ (opcode == BPF_JEQ || opcode == BPF_JNE))
/* Comparing for equality, we can combine knowledge */
reg_combine_min_max(&other_branch_regs[insn->src_reg],
&other_branch_regs[insn->dst_reg],
- &regs[insn->src_reg],
- &regs[insn->dst_reg], opcode);
+ src_reg, dst_reg, opcode);
}
} else if (dst_reg->type == SCALAR_VALUE) {
reg_set_min_max(&other_branch_regs[insn->dst_reg],
- dst_reg, insn->imm, opcode);
+ dst_reg, insn->imm, opcode, is_jmp32);
}
- /* detect if R == 0 where R is returned from bpf_map_lookup_elem() */
- if (BPF_SRC(insn->code) == BPF_K &&
+ /* detect if R == 0 where R is returned from bpf_map_lookup_elem().
+ * NOTE: these optimizations below are related with pointer comparison
+ * which will never be JMP32.
+ */
+ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K &&
insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
reg_type_may_be_null(dst_reg->type)) {
/* Mark all identical registers in each branch as either
@@ -4716,6 +5064,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
}
+ if (env->cur_state->active_spin_lock) {
+ verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n");
+ return -EINVAL;
+ }
+
if (regs[BPF_REG_6].type != PTR_TO_CTX) {
verbose(env,
"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
@@ -4903,7 +5256,8 @@ peek_stack:
goto check_state;
t = insn_stack[cur_stack - 1];
- if (BPF_CLASS(insns[t].code) == BPF_JMP) {
+ if (BPF_CLASS(insns[t].code) == BPF_JMP ||
+ BPF_CLASS(insns[t].code) == BPF_JMP32) {
u8 opcode = BPF_OP(insns[t].code);
if (opcode == BPF_EXIT) {
@@ -5000,13 +5354,14 @@ static int check_btf_func(struct bpf_verifier_env *env,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- u32 i, nfuncs, urec_size, min_size, prev_offset;
+ u32 i, nfuncs, urec_size, min_size;
u32 krec_size = sizeof(struct bpf_func_info);
struct bpf_func_info *krecord;
const struct btf_type *type;
struct bpf_prog *prog;
const struct btf *btf;
void __user *urecord;
+ u32 prev_offset = 0;
int ret = 0;
nfuncs = attr->func_info_cnt;
@@ -5450,8 +5805,11 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
case PTR_TO_MAP_VALUE:
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
- * We don't care about the 'id' value, because nothing
- * uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL)
+ * 'id' is not compared, since it's only used for maps with
+ * bpf_spin_lock inside map element and in such cases if
+ * the rest of the prog is valid for one map element then
+ * it's valid for all map elements regardless of the key
+ * used in bpf_map_lookup()
*/
return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
range_within(rold, rcur) &&
@@ -5499,6 +5857,10 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
case PTR_TO_FLOW_KEYS:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
+ case PTR_TO_SOCK_COMMON:
+ case PTR_TO_SOCK_COMMON_OR_NULL:
+ case PTR_TO_TCP_SOCK:
+ case PTR_TO_TCP_SOCK_OR_NULL:
/* Only valid matches are exact, which memcmp() above
* would have accepted
*/
@@ -5654,6 +6016,9 @@ static bool states_equal(struct bpf_verifier_env *env,
if (old->speculative && !cur->speculative)
return false;
+ if (old->active_spin_lock != cur->active_spin_lock)
+ return false;
+
/* for states to be equal callsites have to be the same
* and all frame states need to be equivalent
*/
@@ -5816,6 +6181,10 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type)
case PTR_TO_CTX:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
+ case PTR_TO_SOCK_COMMON:
+ case PTR_TO_SOCK_COMMON_OR_NULL:
+ case PTR_TO_TCP_SOCK:
+ case PTR_TO_TCP_SOCK_OR_NULL:
return false;
default:
return true;
@@ -6058,7 +6427,7 @@ static int do_check(struct bpf_verifier_env *env)
if (err)
return err;
- } else if (class == BPF_JMP) {
+ } else if (class == BPF_JMP || class == BPF_JMP32) {
u8 opcode = BPF_OP(insn->code);
if (opcode == BPF_CALL) {
@@ -6066,11 +6435,18 @@ static int do_check(struct bpf_verifier_env *env)
insn->off != 0 ||
(insn->src_reg != BPF_REG_0 &&
insn->src_reg != BPF_PSEUDO_CALL) ||
- insn->dst_reg != BPF_REG_0) {
+ insn->dst_reg != BPF_REG_0 ||
+ class == BPF_JMP32) {
verbose(env, "BPF_CALL uses reserved fields\n");
return -EINVAL;
}
+ if (env->cur_state->active_spin_lock &&
+ (insn->src_reg == BPF_PSEUDO_CALL ||
+ insn->imm != BPF_FUNC_spin_unlock)) {
+ verbose(env, "function calls are not allowed while holding a lock\n");
+ return -EINVAL;
+ }
if (insn->src_reg == BPF_PSEUDO_CALL)
err = check_func_call(env, insn, &env->insn_idx);
else
@@ -6082,7 +6458,8 @@ static int do_check(struct bpf_verifier_env *env)
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
- insn->dst_reg != BPF_REG_0) {
+ insn->dst_reg != BPF_REG_0 ||
+ class == BPF_JMP32) {
verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
@@ -6094,11 +6471,17 @@ static int do_check(struct bpf_verifier_env *env)
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
- insn->dst_reg != BPF_REG_0) {
+ insn->dst_reg != BPF_REG_0 ||
+ class == BPF_JMP32) {
verbose(env, "BPF_EXIT uses reserved fields\n");
return -EINVAL;
}
+ if (env->cur_state->active_spin_lock) {
+ verbose(env, "bpf_spin_unlock is missing\n");
+ return -EINVAL;
+ }
+
if (state->curframe) {
/* exit from nested function */
env->prev_insn_idx = env->insn_idx;
@@ -6196,6 +6579,19 @@ static int check_map_prealloc(struct bpf_map *map)
!(map->map_flags & BPF_F_NO_PREALLOC);
}
+static bool is_tracing_prog_type(enum bpf_prog_type type)
+{
+ switch (type) {
+ case BPF_PROG_TYPE_KPROBE:
+ case BPF_PROG_TYPE_TRACEPOINT:
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ return true;
+ default:
+ return false;
+ }
+}
+
static int check_map_prog_compatibility(struct bpf_verifier_env *env,
struct bpf_map *map,
struct bpf_prog *prog)
@@ -6218,6 +6614,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
}
}
+ if ((is_tracing_prog_type(prog->type) ||
+ prog->type == BPF_PROG_TYPE_SOCKET_FILTER) &&
+ map_value_has_spin_lock(map)) {
+ verbose(env, "tracing progs cannot use bpf_spin_lock 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");
@@ -6434,6 +6837,153 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
return new_prog;
}
+static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env,
+ u32 off, u32 cnt)
+{
+ int i, j;
+
+ /* find first prog starting at or after off (first to remove) */
+ for (i = 0; i < env->subprog_cnt; i++)
+ if (env->subprog_info[i].start >= off)
+ break;
+ /* find first prog starting at or after off + cnt (first to stay) */
+ for (j = i; j < env->subprog_cnt; j++)
+ if (env->subprog_info[j].start >= off + cnt)
+ break;
+ /* if j doesn't start exactly at off + cnt, we are just removing
+ * the front of previous prog
+ */
+ if (env->subprog_info[j].start != off + cnt)
+ j--;
+
+ if (j > i) {
+ struct bpf_prog_aux *aux = env->prog->aux;
+ int move;
+
+ /* move fake 'exit' subprog as well */
+ move = env->subprog_cnt + 1 - j;
+
+ memmove(env->subprog_info + i,
+ env->subprog_info + j,
+ sizeof(*env->subprog_info) * move);
+ env->subprog_cnt -= j - i;
+
+ /* remove func_info */
+ if (aux->func_info) {
+ move = aux->func_info_cnt - j;
+
+ memmove(aux->func_info + i,
+ aux->func_info + j,
+ sizeof(*aux->func_info) * move);
+ aux->func_info_cnt -= j - i;
+ /* func_info->insn_off is set after all code rewrites,
+ * in adjust_btf_func() - no need to adjust
+ */
+ }
+ } else {
+ /* convert i from "first prog to remove" to "first to adjust" */
+ if (env->subprog_info[i].start == off)
+ i++;
+ }
+
+ /* update fake 'exit' subprog as well */
+ for (; i <= env->subprog_cnt; i++)
+ env->subprog_info[i].start -= cnt;
+
+ return 0;
+}
+
+static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off,
+ u32 cnt)
+{
+ struct bpf_prog *prog = env->prog;
+ u32 i, l_off, l_cnt, nr_linfo;
+ struct bpf_line_info *linfo;
+
+ nr_linfo = prog->aux->nr_linfo;
+ if (!nr_linfo)
+ return 0;
+
+ linfo = prog->aux->linfo;
+
+ /* find first line info to remove, count lines to be removed */
+ for (i = 0; i < nr_linfo; i++)
+ if (linfo[i].insn_off >= off)
+ break;
+
+ l_off = i;
+ l_cnt = 0;
+ for (; i < nr_linfo; i++)
+ if (linfo[i].insn_off < off + cnt)
+ l_cnt++;
+ else
+ break;
+
+ /* First live insn doesn't match first live linfo, it needs to "inherit"
+ * last removed linfo. prog is already modified, so prog->len == off
+ * means no live instructions after (tail of the program was removed).
+ */
+ if (prog->len != off && l_cnt &&
+ (i == nr_linfo || linfo[i].insn_off != off + cnt)) {
+ l_cnt--;
+ linfo[--i].insn_off = off + cnt;
+ }
+
+ /* remove the line info which refer to the removed instructions */
+ if (l_cnt) {
+ memmove(linfo + l_off, linfo + i,
+ sizeof(*linfo) * (nr_linfo - i));
+
+ prog->aux->nr_linfo -= l_cnt;
+ nr_linfo = prog->aux->nr_linfo;
+ }
+
+ /* pull all linfo[i].insn_off >= off + cnt in by cnt */
+ for (i = l_off; i < nr_linfo; i++)
+ linfo[i].insn_off -= cnt;
+
+ /* fix up all subprogs (incl. 'exit') which start >= off */
+ for (i = 0; i <= env->subprog_cnt; i++)
+ if (env->subprog_info[i].linfo_idx > l_off) {
+ /* program may have started in the removed region but
+ * may not be fully removed
+ */
+ if (env->subprog_info[i].linfo_idx >= l_off + l_cnt)
+ env->subprog_info[i].linfo_idx -= l_cnt;
+ else
+ env->subprog_info[i].linfo_idx = l_off;
+ }
+
+ return 0;
+}
+
+static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+ struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+ unsigned int orig_prog_len = env->prog->len;
+ int err;
+
+ if (bpf_prog_is_dev_bound(env->prog->aux))
+ bpf_prog_offload_remove_insns(env, off, cnt);
+
+ err = bpf_remove_insns(env->prog, off, cnt);
+ if (err)
+ return err;
+
+ err = adjust_subprog_starts_after_remove(env, off, cnt);
+ if (err)
+ return err;
+
+ err = bpf_adj_linfo_after_remove(env, off, cnt);
+ if (err)
+ return err;
+
+ memmove(aux_data + off, aux_data + off + cnt,
+ sizeof(*aux_data) * (orig_prog_len - off - cnt));
+
+ return 0;
+}
+
/* The verifier does more data flow analysis than llvm and will not
* explore branches that are dead at run time. Malicious programs can
* have dead code too. Therefore replace all dead at-run-time code
@@ -6460,6 +7010,91 @@ static void sanitize_dead_code(struct bpf_verifier_env *env)
}
}
+static bool insn_is_cond_jump(u8 code)
+{
+ u8 op;
+
+ if (BPF_CLASS(code) == BPF_JMP32)
+ return true;
+
+ if (BPF_CLASS(code) != BPF_JMP)
+ return false;
+
+ op = BPF_OP(code);
+ return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
+}
+
+static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env)
+{
+ struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+ struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
+ struct bpf_insn *insn = env->prog->insnsi;
+ const int insn_cnt = env->prog->len;
+ int i;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ if (!insn_is_cond_jump(insn->code))
+ continue;
+
+ if (!aux_data[i + 1].seen)
+ ja.off = insn->off;
+ else if (!aux_data[i + 1 + insn->off].seen)
+ ja.off = 0;
+ else
+ continue;
+
+ if (bpf_prog_is_dev_bound(env->prog->aux))
+ bpf_prog_offload_replace_insn(env, i, &ja);
+
+ memcpy(insn, &ja, sizeof(ja));
+ }
+}
+
+static int opt_remove_dead_code(struct bpf_verifier_env *env)
+{
+ struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+ int insn_cnt = env->prog->len;
+ int i, err;
+
+ for (i = 0; i < insn_cnt; i++) {
+ int j;
+
+ j = 0;
+ while (i + j < insn_cnt && !aux_data[i + j].seen)
+ j++;
+ if (!j)
+ continue;
+
+ err = verifier_remove_insns(env, i, j);
+ if (err)
+ return err;
+ insn_cnt = env->prog->len;
+ }
+
+ return 0;
+}
+
+static int opt_remove_nops(struct bpf_verifier_env *env)
+{
+ const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
+ struct bpf_insn *insn = env->prog->insnsi;
+ int insn_cnt = env->prog->len;
+ int i, err;
+
+ for (i = 0; i < insn_cnt; i++) {
+ if (memcmp(&insn[i], &ja, sizeof(ja)))
+ continue;
+
+ err = verifier_remove_insns(env, i, 1);
+ if (err)
+ return err;
+ insn_cnt--;
+ i--;
+ }
+
+ return 0;
+}
+
/* convert load instructions that access fields of a context type into a
* sequence of instructions that access fields of the underlying structure:
* struct __sk_buff -> struct sk_buff
@@ -6552,8 +7187,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
convert_ctx_access = ops->convert_ctx_access;
break;
case PTR_TO_SOCKET:
+ case PTR_TO_SOCK_COMMON:
convert_ctx_access = bpf_sock_convert_ctx_access;
break;
+ case PTR_TO_TCP_SOCK:
+ convert_ctx_access = bpf_tcp_sock_convert_ctx_access;
+ break;
default:
continue;
}
@@ -6681,7 +7320,12 @@ static int jit_subprogs(struct bpf_verifier_env *env)
subprog_end = env->subprog_info[i + 1].start;
len = subprog_end - subprog_start;
- func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
+ /* BPF_PROG_RUN doesn't call subprogs directly,
+ * hence main prog stats include the runtime of subprogs.
+ * subprogs don't have IDs and not reachable via prog_get_next_id
+ * func[i]->aux->stats will never be accessed and stays NULL
+ */
+ func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER);
if (!func[i])
goto out_free;
memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
@@ -6920,7 +7564,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
u32 off_reg;
aux = &env->insn_aux_data[i + delta];
- if (!aux->alu_state)
+ if (!aux->alu_state ||
+ aux->alu_state == BPF_ALU_NON_POINTER)
continue;
isneg = aux->alu_state & BPF_ALU_NEG_VALUE;
@@ -7150,7 +7795,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
{
struct bpf_verifier_env *env;
struct bpf_verifier_log *log;
- int ret = -EINVAL;
+ int i, len, ret = -EINVAL;
+ bool is_priv;
/* no program is valid */
if (ARRAY_SIZE(bpf_verifier_ops) == 0)
@@ -7164,12 +7810,14 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
return -ENOMEM;
log = &env->log;
+ len = (*prog)->len;
env->insn_aux_data =
- vzalloc(array_size(sizeof(struct bpf_insn_aux_data),
- (*prog)->len));
+ vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len));
ret = -ENOMEM;
if (!env->insn_aux_data)
goto err_free_env;
+ for (i = 0; i < len; i++)
+ env->insn_aux_data[i].orig_idx = i;
env->prog = *prog;
env->ops = bpf_verifier_ops[env->prog->type];
@@ -7197,6 +7845,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
env->strict_alignment = false;
+ is_priv = capable(CAP_SYS_ADMIN);
+ env->allow_ptr_leaks = is_priv;
+
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
goto skip_full_check;
@@ -7214,8 +7865,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
if (!env->explored_states)
goto skip_full_check;
- env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
-
ret = check_subprogs(env);
if (ret < 0)
goto skip_full_check;
@@ -7245,8 +7894,17 @@ skip_full_check:
ret = check_max_stack_depth(env);
/* instruction rewrites happen after this point */
- if (ret == 0)
- sanitize_dead_code(env);
+ if (is_priv) {
+ if (ret == 0)
+ opt_hard_wire_dead_code_branches(env);
+ if (ret == 0)
+ ret = opt_remove_dead_code(env);
+ if (ret == 0)
+ ret = opt_remove_nops(env);
+ } else {
+ if (ret == 0)
+ sanitize_dead_code(env);
+ }
if (ret == 0)
/* program is valid, convert *(u32*)(ctx + off) accesses */
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c950864016e2..c9a35f09e4b9 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -198,7 +198,7 @@ int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
void cgroup_free_root(struct cgroup_root *root);
void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts);
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags);
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask);
int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
struct cgroup_root *root, unsigned long magic,
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 583b969b0c0e..f94a7229974e 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1116,13 +1116,11 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
void *data, unsigned long magic,
struct cgroup_namespace *ns)
{
- struct super_block *pinned_sb = NULL;
struct cgroup_sb_opts opts;
struct cgroup_root *root;
struct cgroup_subsys *ss;
struct dentry *dentry;
int i, ret;
- bool new_root = false;
cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
@@ -1184,29 +1182,6 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
if (root->flags ^ opts.flags)
pr_warn("new mount options do not match the existing superblock, will be ignored\n");
- /*
- * We want to reuse @root whose lifetime is governed by its
- * ->cgrp. Let's check whether @root is alive and keep it
- * that way. As cgroup_kill_sb() can happen anytime, we
- * want to block it by pinning the sb so that @root doesn't
- * get killed before mount is complete.
- *
- * With the sb pinned, tryget_live can reliably indicate
- * whether @root can be reused. If it's being killed,
- * drain it. We can use wait_queue for the wait but this
- * path is super cold. Let's just sleep a bit and retry.
- */
- pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
- if (IS_ERR(pinned_sb) ||
- !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
- mutex_unlock(&cgroup_mutex);
- if (!IS_ERR_OR_NULL(pinned_sb))
- deactivate_super(pinned_sb);
- msleep(10);
- ret = restart_syscall();
- goto out_free;
- }
-
ret = 0;
goto out_unlock;
}
@@ -1232,15 +1207,20 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
ret = -ENOMEM;
goto out_unlock;
}
- new_root = true;
init_cgroup_root(root, &opts);
- ret = cgroup_setup_root(root, opts.subsys_mask, PERCPU_REF_INIT_DEAD);
+ ret = cgroup_setup_root(root, opts.subsys_mask);
if (ret)
cgroup_free_root(root);
out_unlock:
+ if (!ret && !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
+ mutex_unlock(&cgroup_mutex);
+ msleep(10);
+ ret = restart_syscall();
+ goto out_free;
+ }
mutex_unlock(&cgroup_mutex);
out_free:
kfree(opts.release_agent);
@@ -1252,25 +1232,13 @@ out_free:
dentry = cgroup_do_mount(&cgroup_fs_type, flags, root,
CGROUP_SUPER_MAGIC, ns);
- /*
- * There's a race window after we release cgroup_mutex and before
- * allocating a superblock. Make sure a concurrent process won't
- * be able to re-use the root during this window by delaying the
- * initialization of root refcnt.
- */
- if (new_root) {
- mutex_lock(&cgroup_mutex);
- percpu_ref_reinit(&root->cgrp.self.refcnt);
- mutex_unlock(&cgroup_mutex);
+ if (!IS_ERR(dentry) && percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
+ struct super_block *sb = dentry->d_sb;
+ dput(dentry);
+ deactivate_locked_super(sb);
+ msleep(10);
+ dentry = ERR_PTR(restart_syscall());
}
-
- /*
- * If @pinned_sb, we're reusing an existing root and holding an
- * extra ref on its sb. Mount is complete. Put the extra ref.
- */
- if (pinned_sb)
- deactivate_super(pinned_sb);
-
return dentry;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index f31bd61c9466..cef98502b124 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1927,7 +1927,7 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
}
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
{
LIST_HEAD(tmp_links);
struct cgroup *root_cgrp = &root->cgrp;
@@ -1944,7 +1944,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
root_cgrp->ancestor_ids[0] = ret;
ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
- ref_flags, GFP_KERNEL);
+ 0, GFP_KERNEL);
if (ret)
goto out;
@@ -2033,7 +2033,7 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
struct cgroup_namespace *ns)
{
struct dentry *dentry;
- bool new_sb;
+ bool new_sb = false;
dentry = kernfs_mount(fs_type, flags, root->kf_root, magic, &new_sb);
@@ -2043,6 +2043,7 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
*/
if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
struct dentry *nsdentry;
+ struct super_block *sb = dentry->d_sb;
struct cgroup *cgrp;
mutex_lock(&cgroup_mutex);
@@ -2053,12 +2054,14 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
- nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
+ nsdentry = kernfs_node_dentry(cgrp->kn, sb);
dput(dentry);
+ if (IS_ERR(nsdentry))
+ deactivate_locked_super(sb);
dentry = nsdentry;
}
- if (IS_ERR(dentry) || !new_sb)
+ if (!new_sb)
cgroup_put(&root->cgrp);
return dentry;
@@ -2118,18 +2121,16 @@ static void cgroup_kill_sb(struct super_block *sb)
struct cgroup_root *root = cgroup_root_from_kf(kf_root);
/*
- * If @root doesn't have any mounts or children, start killing it.
+ * If @root doesn't have any children, start killing it.
* This prevents new mounts by disabling percpu_ref_tryget_live().
* cgroup_mount() may wait for @root's release.
*
* And don't kill the default root.
*/
- if (!list_empty(&root->cgrp.self.children) ||
- root == &cgrp_dfl_root)
- cgroup_put(&root->cgrp);
- else
+ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
+ !percpu_ref_is_dying(&root->cgrp.self.refcnt))
percpu_ref_kill(&root->cgrp.self.refcnt);
-
+ cgroup_put(&root->cgrp);
kernfs_kill_sb(sb);
}
@@ -5399,7 +5400,7 @@ int __init cgroup_init(void)
hash_add(css_set_table, &init_css_set.hlist,
css_set_hash(init_css_set.subsys));
- BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0, 0));
+ BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
mutex_unlock(&cgroup_mutex);
@@ -5996,7 +5997,7 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
int ret;
mutex_lock(&cgroup_mutex);
- ret = __cgroup_bpf_detach(cgrp, prog, type, flags);
+ ret = __cgroup_bpf_detach(cgrp, prog, type);
mutex_unlock(&cgroup_mutex);
return ret;
}
diff --git a/kernel/compat.c b/kernel/compat.c
index f01affa17e22..d8a36c6ad7c9 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -20,7 +20,6 @@
#include <linux/syscalls.h>
#include <linux/unistd.h>
#include <linux/security.h>
-#include <linux/timex.h>
#include <linux/export.h>
#include <linux/migrate.h>
#include <linux/posix-timers.h>
@@ -30,69 +29,6 @@
#include <linux/uaccess.h>
-int compat_get_timex(struct timex *txc, const struct compat_timex __user *utp)
-{
- struct compat_timex tx32;
-
- memset(txc, 0, sizeof(struct timex));
- if (copy_from_user(&tx32, utp, sizeof(struct compat_timex)))
- return -EFAULT;
-
- txc->modes = tx32.modes;
- txc->offset = tx32.offset;
- txc->freq = tx32.freq;
- txc->maxerror = tx32.maxerror;
- txc->esterror = tx32.esterror;
- txc->status = tx32.status;
- txc->constant = tx32.constant;
- txc->precision = tx32.precision;
- txc->tolerance = tx32.tolerance;
- txc->time.tv_sec = tx32.time.tv_sec;
- txc->time.tv_usec = tx32.time.tv_usec;
- txc->tick = tx32.tick;
- txc->ppsfreq = tx32.ppsfreq;
- txc->jitter = tx32.jitter;
- txc->shift = tx32.shift;
- txc->stabil = tx32.stabil;
- txc->jitcnt = tx32.jitcnt;
- txc->calcnt = tx32.calcnt;
- txc->errcnt = tx32.errcnt;
- txc->stbcnt = tx32.stbcnt;
-
- return 0;
-}
-
-int compat_put_timex(struct compat_timex __user *utp, const struct timex *txc)
-{
- struct compat_timex tx32;
-
- memset(&tx32, 0, sizeof(struct compat_timex));
- tx32.modes = txc->modes;
- tx32.offset = txc->offset;
- tx32.freq = txc->freq;
- tx32.maxerror = txc->maxerror;
- tx32.esterror = txc->esterror;
- tx32.status = txc->status;
- tx32.constant = txc->constant;
- tx32.precision = txc->precision;
- tx32.tolerance = txc->tolerance;
- tx32.time.tv_sec = txc->time.tv_sec;
- tx32.time.tv_usec = txc->time.tv_usec;
- tx32.tick = txc->tick;
- tx32.ppsfreq = txc->ppsfreq;
- tx32.jitter = txc->jitter;
- tx32.shift = txc->shift;
- tx32.stabil = txc->stabil;
- tx32.jitcnt = txc->jitcnt;
- tx32.calcnt = txc->calcnt;
- tx32.errcnt = txc->errcnt;
- tx32.stbcnt = txc->stbcnt;
- tx32.tai = txc->tai;
- if (copy_to_user(utp, &tx32, sizeof(struct compat_timex)))
- return -EFAULT;
- return 0;
-}
-
static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv)
{
return (!access_ok(ctv, sizeof(*ctv)) ||
diff --git a/kernel/cpu.c b/kernel/cpu.c
index d1c6d152da89..025f419d16f6 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -313,6 +313,15 @@ void cpus_write_unlock(void)
void lockdep_assert_cpus_held(void)
{
+ /*
+ * We can't have hotplug operations before userspace starts running,
+ * and some init codepaths will knowingly not take the hotplug lock.
+ * This is all valid, so mute lockdep until it makes sense to report
+ * unheld locks.
+ */
+ if (system_state < SYSTEM_RUNNING)
+ return;
+
percpu_rwsem_assert_held(&cpu_hotplug_lock);
}
diff --git a/kernel/futex.c b/kernel/futex.c
index a0514e01c3eb..c3b73b0311bc 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -68,6 +68,7 @@
#include <linux/freezer.h>
#include <linux/memblock.h>
#include <linux/fault-inject.h>
+#include <linux/refcount.h>
#include <asm/futex.h>
@@ -212,7 +213,7 @@ struct futex_pi_state {
struct rt_mutex pi_mutex;
struct task_struct *owner;
- atomic_t refcount;
+ refcount_t refcount;
union futex_key key;
} __randomize_layout;
@@ -321,12 +322,8 @@ static int __init fail_futex_debugfs(void)
if (IS_ERR(dir))
return PTR_ERR(dir);
- if (!debugfs_create_bool("ignore-private", mode, dir,
- &fail_futex.ignore_private)) {
- debugfs_remove_recursive(dir);
- return -ENOMEM;
- }
-
+ debugfs_create_bool("ignore-private", mode, dir,
+ &fail_futex.ignore_private);
return 0;
}
@@ -803,7 +800,7 @@ static int refill_pi_state_cache(void)
INIT_LIST_HEAD(&pi_state->list);
/* pi_mutex gets initialized later */
pi_state->owner = NULL;
- atomic_set(&pi_state->refcount, 1);
+ refcount_set(&pi_state->refcount, 1);
pi_state->key = FUTEX_KEY_INIT;
current->pi_state_cache = pi_state;
@@ -823,7 +820,7 @@ static struct futex_pi_state *alloc_pi_state(void)
static void get_pi_state(struct futex_pi_state *pi_state)
{
- WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount));
+ WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount));
}
/*
@@ -835,7 +832,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
if (!pi_state)
return;
- if (!atomic_dec_and_test(&pi_state->refcount))
+ if (!refcount_dec_and_test(&pi_state->refcount))
return;
/*
@@ -865,7 +862,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
* refcount is at 0 - put it back to 1.
*/
pi_state->owner = NULL;
- atomic_set(&pi_state->refcount, 1);
+ refcount_set(&pi_state->refcount, 1);
current->pi_state_cache = pi_state;
}
}
@@ -908,7 +905,7 @@ void exit_pi_state_list(struct task_struct *curr)
* In that case; drop the locks to let put_pi_state() make
* progress and retry the loop.
*/
- if (!atomic_inc_not_zero(&pi_state->refcount)) {
+ if (!refcount_inc_not_zero(&pi_state->refcount)) {
raw_spin_unlock_irq(&curr->pi_lock);
cpu_relax();
raw_spin_lock_irq(&curr->pi_lock);
@@ -1064,7 +1061,7 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
* and futex_wait_requeue_pi() as it cannot go to 0 and consequently
* free pi_state before we can take a reference ourselves.
*/
- WARN_ON(!atomic_read(&pi_state->refcount));
+ WARN_ON(!refcount_read(&pi_state->refcount));
/*
* Now that we have a pi_state, we can acquire wait_lock
@@ -1467,8 +1464,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
* Queue the task for later wakeup for after we've released
* the hb->lock. wake_q_add() grabs reference to p.
*/
- wake_q_add(wake_q, p);
- put_task_struct(p);
+ wake_q_add_safe(wake_q, p);
}
/*
@@ -3823,7 +3819,7 @@ err_unlock:
#endif /* CONFIG_COMPAT */
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
+SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
u32, val3)
{
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 45b68b4ea48b..f18cd5aa33e8 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -9,7 +9,7 @@
#include <linux/cpu.h>
static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
- int cpus_per_vec)
+ unsigned int cpus_per_vec)
{
const struct cpumask *siblmsk;
int cpu, sibl;
@@ -95,15 +95,17 @@ static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask,
}
static int __irq_build_affinity_masks(const struct irq_affinity *affd,
- int startvec, int numvecs, int firstvec,
+ unsigned int startvec,
+ unsigned int numvecs,
+ unsigned int firstvec,
cpumask_var_t *node_to_cpumask,
const struct cpumask *cpu_mask,
struct cpumask *nmsk,
struct irq_affinity_desc *masks)
{
- int n, nodes, cpus_per_vec, extra_vecs, done = 0;
- int last_affv = firstvec + numvecs;
- int curvec = startvec;
+ unsigned int n, nodes, cpus_per_vec, extra_vecs, done = 0;
+ unsigned int last_affv = firstvec + numvecs;
+ unsigned int curvec = startvec;
nodemask_t nodemsk = NODE_MASK_NONE;
if (!cpumask_weight(cpu_mask))
@@ -117,18 +119,16 @@ static int __irq_build_affinity_masks(const struct irq_affinity *affd,
*/
if (numvecs <= nodes) {
for_each_node_mask(n, nodemsk) {
- cpumask_or(&masks[curvec].mask,
- &masks[curvec].mask,
- node_to_cpumask[n]);
+ cpumask_or(&masks[curvec].mask, &masks[curvec].mask,
+ node_to_cpumask[n]);
if (++curvec == last_affv)
curvec = firstvec;
}
- done = numvecs;
- goto out;
+ return numvecs;
}
for_each_node_mask(n, nodemsk) {
- int ncpus, v, vecs_to_assign, vecs_per_node;
+ unsigned int ncpus, v, vecs_to_assign, vecs_per_node;
/* Spread the vectors per node */
vecs_per_node = (numvecs - (curvec - firstvec)) / nodes;
@@ -163,8 +163,6 @@ static int __irq_build_affinity_masks(const struct irq_affinity *affd,
curvec = firstvec;
--nodes;
}
-
-out:
return done;
}
@@ -174,19 +172,24 @@ out:
* 2) spread other possible CPUs on these vectors
*/
static int irq_build_affinity_masks(const struct irq_affinity *affd,
- int startvec, int numvecs, int firstvec,
- cpumask_var_t *node_to_cpumask,
+ unsigned int startvec, unsigned int numvecs,
+ unsigned int firstvec,
struct irq_affinity_desc *masks)
{
- int curvec = startvec, nr_present, nr_others;
- int ret = -ENOMEM;
+ unsigned int curvec = startvec, nr_present, nr_others;
+ cpumask_var_t *node_to_cpumask;
cpumask_var_t nmsk, npresmsk;
+ int ret = -ENOMEM;
if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
return ret;
if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
- goto fail;
+ goto fail_nmsk;
+
+ node_to_cpumask = alloc_node_to_cpumask();
+ if (!node_to_cpumask)
+ goto fail_npresmsk;
ret = 0;
/* Stabilize the cpumasks */
@@ -217,13 +220,22 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
if (nr_present < numvecs)
WARN_ON(nr_present + nr_others < numvecs);
+ free_node_to_cpumask(node_to_cpumask);
+
+ fail_npresmsk:
free_cpumask_var(npresmsk);
- fail:
+ fail_nmsk:
free_cpumask_var(nmsk);
return ret;
}
+static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
+{
+ affd->nr_sets = 1;
+ affd->set_size[0] = affvecs;
+}
+
/**
* irq_create_affinity_masks - Create affinity masks for multiqueue spreading
* @nvecs: The total number of vectors
@@ -232,50 +244,62 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
* Returns the irq_affinity_desc pointer or NULL if allocation failed.
*/
struct irq_affinity_desc *
-irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
+irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
{
- int affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
- int curvec, usedvecs;
- cpumask_var_t *node_to_cpumask;
+ unsigned int affvecs, curvec, usedvecs, i;
struct irq_affinity_desc *masks = NULL;
- int i, nr_sets;
/*
- * If there aren't any vectors left after applying the pre/post
- * vectors don't bother with assigning affinity.
+ * Determine the number of vectors which need interrupt affinities
+ * assigned. If the pre/post request exhausts the available vectors
+ * then nothing to do here except for invoking the calc_sets()
+ * callback so the device driver can adjust to the situation. If there
+ * is only a single vector, then managing the queue is pointless as
+ * well.
*/
- if (nvecs == affd->pre_vectors + affd->post_vectors)
+ if (nvecs > 1 && nvecs > affd->pre_vectors + affd->post_vectors)
+ affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
+ else
+ affvecs = 0;
+
+ /*
+ * Simple invocations do not provide a calc_sets() callback. Install
+ * the generic one.
+ */
+ if (!affd->calc_sets)
+ affd->calc_sets = default_calc_sets;
+
+ /* Recalculate the sets */
+ affd->calc_sets(affd, affvecs);
+
+ if (WARN_ON_ONCE(affd->nr_sets > IRQ_AFFINITY_MAX_SETS))
return NULL;
- node_to_cpumask = alloc_node_to_cpumask();
- if (!node_to_cpumask)
+ /* Nothing to assign? */
+ if (!affvecs)
return NULL;
masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL);
if (!masks)
- goto outnodemsk;
+ return NULL;
/* Fill out vectors at the beginning that don't need affinity */
for (curvec = 0; curvec < affd->pre_vectors; curvec++)
cpumask_copy(&masks[curvec].mask, irq_default_affinity);
+
/*
* Spread on present CPUs starting from affd->pre_vectors. If we
* have multiple sets, build each sets affinity mask separately.
*/
- nr_sets = affd->nr_sets;
- if (!nr_sets)
- nr_sets = 1;
-
- for (i = 0, usedvecs = 0; i < nr_sets; i++) {
- int this_vecs = affd->sets ? affd->sets[i] : affvecs;
+ for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
+ unsigned int this_vecs = affd->set_size[i];
int ret;
ret = irq_build_affinity_masks(affd, curvec, this_vecs,
- curvec, node_to_cpumask, masks);
+ curvec, masks);
if (ret) {
kfree(masks);
- masks = NULL;
- goto outnodemsk;
+ return NULL;
}
curvec += this_vecs;
usedvecs += this_vecs;
@@ -293,8 +317,6 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
for (i = affd->pre_vectors; i < nvecs - affd->post_vectors; i++)
masks[i].is_managed = 1;
-outnodemsk:
- free_node_to_cpumask(node_to_cpumask);
return masks;
}
@@ -304,25 +326,22 @@ outnodemsk:
* @maxvec: The maximum number of vectors available
* @affd: Description of the affinity requirements
*/
-int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd)
+unsigned int irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec,
+ const struct irq_affinity *affd)
{
- int resv = affd->pre_vectors + affd->post_vectors;
- int vecs = maxvec - resv;
- int set_vecs;
+ unsigned int resv = affd->pre_vectors + affd->post_vectors;
+ unsigned int set_vecs;
if (resv > minvec)
return 0;
- if (affd->nr_sets) {
- int i;
-
- for (i = 0, set_vecs = 0; i < affd->nr_sets; i++)
- set_vecs += affd->sets[i];
+ if (affd->calc_sets) {
+ set_vecs = maxvec - resv;
} else {
get_online_cpus();
set_vecs = cpumask_weight(cpu_possible_mask);
put_online_cpus();
}
- return resv + min(set_vecs, vecs);
+ return resv + min(set_vecs, maxvec - resv);
}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 34e969069488..99b7dd6982a4 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -730,6 +730,37 @@ out:
EXPORT_SYMBOL_GPL(handle_fasteoi_irq);
/**
+ * handle_fasteoi_nmi - irq handler for NMI interrupt lines
+ * @desc: the interrupt description structure for this irq
+ *
+ * A simple NMI-safe handler, considering the restrictions
+ * from request_nmi.
+ *
+ * Only a single callback will be issued to the chip: an ->eoi()
+ * call when the interrupt has been serviced. This enables support
+ * for modern forms of interrupt handlers, which handle the flow
+ * details in hardware, transparently.
+ */
+void handle_fasteoi_nmi(struct irq_desc *desc)
+{
+ struct irq_chip *chip = irq_desc_get_chip(desc);
+ struct irqaction *action = desc->action;
+ unsigned int irq = irq_desc_get_irq(desc);
+ irqreturn_t res;
+
+ trace_irq_handler_entry(irq, action);
+ /*
+ * NMIs cannot be shared, there is only one action.
+ */
+ res = action->handler(irq, action->dev_id);
+ trace_irq_handler_exit(irq, action, res);
+
+ if (chip->irq_eoi)
+ chip->irq_eoi(&desc->irq_data);
+}
+EXPORT_SYMBOL_GPL(handle_fasteoi_nmi);
+
+/**
* handle_edge_irq - edge type IRQ handler
* @desc: the interrupt description structure for this irq
*
@@ -855,7 +886,11 @@ void handle_percpu_irq(struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
- kstat_incr_irqs_this_cpu(desc);
+ /*
+ * PER CPU interrupts are not serialized. Do not touch
+ * desc->tot_count.
+ */
+ __kstat_incr_irqs_this_cpu(desc);
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);
@@ -884,7 +919,11 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
unsigned int irq = irq_desc_get_irq(desc);
irqreturn_t res;
- kstat_incr_irqs_this_cpu(desc);
+ /*
+ * PER CPU interrupts are not serialized. Do not touch
+ * desc->tot_count.
+ */
+ __kstat_incr_irqs_this_cpu(desc);
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);
@@ -908,6 +947,29 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
chip->irq_eoi(&desc->irq_data);
}
+/**
+ * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
+ * dev ids
+ * @desc: the interrupt description structure for this irq
+ *
+ * Similar to handle_fasteoi_nmi, but handling the dev_id cookie
+ * as a percpu pointer.
+ */
+void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc)
+{
+ struct irq_chip *chip = irq_desc_get_chip(desc);
+ struct irqaction *action = desc->action;
+ unsigned int irq = irq_desc_get_irq(desc);
+ irqreturn_t res;
+
+ trace_irq_handler_entry(irq, action);
+ res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
+ trace_irq_handler_exit(irq, action, res);
+
+ if (chip->irq_eoi)
+ chip->irq_eoi(&desc->irq_data);
+}
+
static void
__irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
int is_chained, const char *name)
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index 6f636136cccc..516c00a5e867 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -56,6 +56,7 @@ static const struct irq_bit_descr irqchip_flags[] = {
BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE),
BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
+ BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI),
};
static void
@@ -140,6 +141,7 @@ static const struct irq_bit_descr irqdesc_istates[] = {
BIT_MASK_DESCR(IRQS_WAITING),
BIT_MASK_DESCR(IRQS_PENDING),
BIT_MASK_DESCR(IRQS_SUSPENDED),
+ BIT_MASK_DESCR(IRQS_NMI),
};
@@ -203,8 +205,8 @@ static ssize_t irq_debug_write(struct file *file, const char __user *user_buf,
chip_bus_lock(desc);
raw_spin_lock_irqsave(&desc->lock, flags);
- if (irq_settings_is_level(desc)) {
- /* Can't do level, sorry */
+ if (irq_settings_is_level(desc) || desc->istate & IRQS_NMI) {
+ /* Can't do level nor NMIs, sorry */
err = -EINVAL;
} else {
desc->istate |= IRQS_PENDING;
@@ -256,8 +258,6 @@ static int __init irq_debugfs_init(void)
int irq;
root_dir = debugfs_create_dir("irq", NULL);
- if (!root_dir)
- return -ENOMEM;
irq_domain_debugfs_init(root_dir);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 38554bc35375..6df5ddfdb0f8 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -166,7 +166,7 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags
__irq_wake_thread(desc, action);
- /* Fall through to add to randomness */
+ /* Fall through - to add to randomness */
case IRQ_HANDLED:
*flags |= action->flags;
break;
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index ca6afa267070..70c3053bc1f6 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -49,6 +49,7 @@ enum {
* IRQS_WAITING - irq is waiting
* IRQS_PENDING - irq is pending and replayed later
* IRQS_SUSPENDED - irq is suspended
+ * IRQS_NMI - irq line is used to deliver NMIs
*/
enum {
IRQS_AUTODETECT = 0x00000001,
@@ -60,6 +61,7 @@ enum {
IRQS_PENDING = 0x00000200,
IRQS_SUSPENDED = 0x00000800,
IRQS_TIMINGS = 0x00001000,
+ IRQS_NMI = 0x00002000,
};
#include "debug.h"
@@ -242,12 +244,18 @@ static inline void irq_state_set_masked(struct irq_desc *desc)
#undef __irqd_to_state
-static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
{
__this_cpu_inc(*desc->kstat_irqs);
__this_cpu_inc(kstat.irqs_sum);
}
+static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+{
+ __kstat_incr_irqs_this_cpu(desc);
+ desc->tot_count++;
+}
+
static inline int irq_desc_get_node(struct irq_desc *desc)
{
return irq_common_data_get_node(&desc->irq_common_data);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index ef8ad36cadcf..13539e12cd80 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -119,6 +119,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
desc->depth = 1;
desc->irq_count = 0;
desc->irqs_unhandled = 0;
+ desc->tot_count = 0;
desc->name = NULL;
desc->owner = owner;
for_each_possible_cpu(cpu)
@@ -669,6 +670,41 @@ int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
set_irq_regs(old_regs);
return ret;
}
+
+#ifdef CONFIG_IRQ_DOMAIN
+/**
+ * handle_domain_nmi - Invoke the handler for a HW irq belonging to a domain
+ * @domain: The domain where to perform the lookup
+ * @hwirq: The HW irq number to convert to a logical one
+ * @regs: Register file coming from the low-level handling code
+ *
+ * Returns: 0 on success, or -EINVAL if conversion has failed
+ */
+int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq,
+ struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ unsigned int irq;
+ int ret = 0;
+
+ nmi_enter();
+
+ irq = irq_find_mapping(domain, hwirq);
+
+ /*
+ * ack_bad_irq is not NMI-safe, just report
+ * an invalid interrupt.
+ */
+ if (likely(irq))
+ generic_handle_irq(irq);
+ else
+ ret = -EINVAL;
+
+ nmi_exit();
+ set_irq_regs(old_regs);
+ return ret;
+}
+#endif
#endif
/* Dynamic interrupt handling */
@@ -919,11 +955,15 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
unsigned int kstat_irqs(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
- int cpu;
unsigned int sum = 0;
+ int cpu;
if (!desc || !desc->kstat_irqs)
return 0;
+ if (!irq_settings_is_per_cpu_devid(desc) &&
+ !irq_settings_is_per_cpu(desc))
+ return desc->tot_count;
+
for_each_possible_cpu(cpu)
sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
return sum;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 8b0be4bd6565..3bf9793d8825 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -458,6 +458,20 @@ void irq_set_default_host(struct irq_domain *domain)
}
EXPORT_SYMBOL_GPL(irq_set_default_host);
+/**
+ * irq_get_default_host() - Retrieve the "default" irq domain
+ *
+ * Returns: the default domain, if any.
+ *
+ * Modern code should never use this. This should only be used on
+ * systems that cannot implement a firmware->fwnode mapping (which
+ * both DT and ACPI provide).
+ */
+struct irq_domain *irq_get_default_host(void)
+{
+ return irq_default_domain;
+}
+
static void irq_domain_clear_mapping(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
@@ -1749,8 +1763,6 @@ void __init irq_domain_debugfs_init(struct dentry *root)
struct irq_domain *d;
domain_dir = debugfs_create_dir("domains", root);
- if (!domain_dir)
- return;
debugfs_create_file("default", 0444, domain_dir, NULL,
&irq_domain_debug_fops);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 84b54a17b95d..9ec34a2a6638 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -341,7 +341,7 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
/* The release function is promised process context */
might_sleep();
- if (!desc)
+ if (!desc || desc->istate & IRQS_NMI)
return -EINVAL;
/* Complete initialisation of *notify */
@@ -553,6 +553,21 @@ bool disable_hardirq(unsigned int irq)
}
EXPORT_SYMBOL_GPL(disable_hardirq);
+/**
+ * disable_nmi_nosync - disable an nmi without waiting
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Disables and enables are
+ * nested.
+ * The interrupt to disable must have been requested through request_nmi.
+ * Unlike disable_nmi(), this function does not ensure existing
+ * instances of the IRQ handler have completed before returning.
+ */
+void disable_nmi_nosync(unsigned int irq)
+{
+ disable_irq_nosync(irq);
+}
+
void __enable_irq(struct irq_desc *desc)
{
switch (desc->depth) {
@@ -609,6 +624,20 @@ out:
}
EXPORT_SYMBOL(enable_irq);
+/**
+ * enable_nmi - enable handling of an nmi
+ * @irq: Interrupt to enable
+ *
+ * The interrupt to enable must have been requested through request_nmi.
+ * Undoes the effect of one call to disable_nmi(). If this
+ * matches the last disable, processing of interrupts on this
+ * IRQ line is re-enabled.
+ */
+void enable_nmi(unsigned int irq)
+{
+ enable_irq(irq);
+}
+
static int set_irq_wake_real(unsigned int irq, unsigned int on)
{
struct irq_desc *desc = irq_to_desc(irq);
@@ -644,6 +673,12 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on)
if (!desc)
return -EINVAL;
+ /* Don't use NMIs as wake up interrupts please */
+ if (desc->istate & IRQS_NMI) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
/* wakeup-capable irqs can be shared between drivers that
* don't need to have the same sleep mode behaviors.
*/
@@ -666,6 +701,8 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on)
irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
}
}
+
+out_unlock:
irq_put_desc_busunlock(desc, flags);
return ret;
}
@@ -726,6 +763,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
case IRQ_SET_MASK_OK_DONE:
irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
irqd_set(&desc->irq_data, flags);
+ /* fall through */
case IRQ_SET_MASK_OK_NOCOPY:
flags = irqd_get_trigger_type(&desc->irq_data);
@@ -1128,6 +1166,39 @@ static void irq_release_resources(struct irq_desc *desc)
c->irq_release_resources(d);
}
+static bool irq_supports_nmi(struct irq_desc *desc)
+{
+ struct irq_data *d = irq_desc_get_irq_data(desc);
+
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+ /* Only IRQs directly managed by the root irqchip can be set as NMI */
+ if (d->parent_data)
+ return false;
+#endif
+ /* Don't support NMIs for chips behind a slow bus */
+ if (d->chip->irq_bus_lock || d->chip->irq_bus_sync_unlock)
+ return false;
+
+ return d->chip->flags & IRQCHIP_SUPPORTS_NMI;
+}
+
+static int irq_nmi_setup(struct irq_desc *desc)
+{
+ struct irq_data *d = irq_desc_get_irq_data(desc);
+ struct irq_chip *c = d->chip;
+
+ return c->irq_nmi_setup ? c->irq_nmi_setup(d) : -EINVAL;
+}
+
+static void irq_nmi_teardown(struct irq_desc *desc)
+{
+ struct irq_data *d = irq_desc_get_irq_data(desc);
+ struct irq_chip *c = d->chip;
+
+ if (c->irq_nmi_teardown)
+ c->irq_nmi_teardown(d);
+}
+
static int
setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
{
@@ -1302,9 +1373,17 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
* fields must have IRQF_SHARED set and the bits which
* set the trigger type must match. Also all must
* agree on ONESHOT.
+ * Interrupt lines used for NMIs cannot be shared.
*/
unsigned int oldtype;
+ if (desc->istate & IRQS_NMI) {
+ pr_err("Invalid attempt to share NMI for %s (irq %d) on irqchip %s.\n",
+ new->name, irq, desc->irq_data.chip->name);
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
/*
* If nobody did set the configuration before, inherit
* the one provided by the requester.
@@ -1756,6 +1835,59 @@ const void *free_irq(unsigned int irq, void *dev_id)
}
EXPORT_SYMBOL(free_irq);
+/* This function must be called with desc->lock held */
+static const void *__cleanup_nmi(unsigned int irq, struct irq_desc *desc)
+{
+ const char *devname = NULL;
+
+ desc->istate &= ~IRQS_NMI;
+
+ if (!WARN_ON(desc->action == NULL)) {
+ irq_pm_remove_action(desc, desc->action);
+ devname = desc->action->name;
+ unregister_handler_proc(irq, desc->action);
+
+ kfree(desc->action);
+ desc->action = NULL;
+ }
+
+ irq_settings_clr_disable_unlazy(desc);
+ irq_shutdown(desc);
+
+ irq_release_resources(desc);
+
+ irq_chip_pm_put(&desc->irq_data);
+ module_put(desc->owner);
+
+ return devname;
+}
+
+const void *free_nmi(unsigned int irq, void *dev_id)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ unsigned long flags;
+ const void *devname;
+
+ if (!desc || WARN_ON(!(desc->istate & IRQS_NMI)))
+ return NULL;
+
+ if (WARN_ON(irq_settings_is_per_cpu_devid(desc)))
+ return NULL;
+
+ /* NMI still enabled */
+ if (WARN_ON(desc->depth == 0))
+ disable_nmi_nosync(irq);
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+
+ irq_nmi_teardown(desc);
+ devname = __cleanup_nmi(irq, desc);
+
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+ return devname;
+}
+
/**
* request_threaded_irq - allocate an interrupt line
* @irq: Interrupt line to allocate
@@ -1925,6 +2057,101 @@ int request_any_context_irq(unsigned int irq, irq_handler_t handler,
}
EXPORT_SYMBOL_GPL(request_any_context_irq);
+/**
+ * request_nmi - allocate an interrupt line for NMI delivery
+ * @irq: Interrupt line to allocate
+ * @handler: Function to be called when the IRQ occurs.
+ * Threaded handler for threaded interrupts.
+ * @irqflags: Interrupt type flags
+ * @name: An ascii name for the claiming device
+ * @dev_id: A cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the
+ * interrupt line and IRQ handling. It sets up the IRQ line
+ * to be handled as an NMI.
+ *
+ * An interrupt line delivering NMIs cannot be shared and IRQ handling
+ * cannot be threaded.
+ *
+ * Interrupt lines requested for NMI delivering must produce per cpu
+ * interrupts and have auto enabling setting disabled.
+ *
+ * Dev_id must be globally unique. Normally the address of the
+ * device data structure is used as the cookie. Since the handler
+ * receives this value it makes sense to use it.
+ *
+ * If the interrupt line cannot be used to deliver NMIs, function
+ * will fail and return a negative value.
+ */
+int request_nmi(unsigned int irq, irq_handler_t handler,
+ unsigned long irqflags, const char *name, void *dev_id)
+{
+ struct irqaction *action;
+ struct irq_desc *desc;
+ unsigned long flags;
+ int retval;
+
+ if (irq == IRQ_NOTCONNECTED)
+ return -ENOTCONN;
+
+ /* NMI cannot be shared, used for Polling */
+ if (irqflags & (IRQF_SHARED | IRQF_COND_SUSPEND | IRQF_IRQPOLL))
+ return -EINVAL;
+
+ if (!(irqflags & IRQF_PERCPU))
+ return -EINVAL;
+
+ if (!handler)
+ return -EINVAL;
+
+ desc = irq_to_desc(irq);
+
+ if (!desc || irq_settings_can_autoenable(desc) ||
+ !irq_settings_can_request(desc) ||
+ WARN_ON(irq_settings_is_per_cpu_devid(desc)) ||
+ !irq_supports_nmi(desc))
+ return -EINVAL;
+
+ action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+ if (!action)
+ return -ENOMEM;
+
+ action->handler = handler;
+ action->flags = irqflags | IRQF_NO_THREAD | IRQF_NOBALANCING;
+ action->name = name;
+ action->dev_id = dev_id;
+
+ retval = irq_chip_pm_get(&desc->irq_data);
+ if (retval < 0)
+ goto err_out;
+
+ retval = __setup_irq(irq, desc, action);
+ if (retval)
+ goto err_irq_setup;
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+
+ /* Setup NMI state */
+ desc->istate |= IRQS_NMI;
+ retval = irq_nmi_setup(desc);
+ if (retval) {
+ __cleanup_nmi(irq, desc);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+ return -EINVAL;
+ }
+
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+ return 0;
+
+err_irq_setup:
+ irq_chip_pm_put(&desc->irq_data);
+err_out:
+ kfree(action);
+
+ return retval;
+}
+
void enable_percpu_irq(unsigned int irq, unsigned int type)
{
unsigned int cpu = smp_processor_id();
@@ -1959,6 +2186,11 @@ out:
}
EXPORT_SYMBOL_GPL(enable_percpu_irq);
+void enable_percpu_nmi(unsigned int irq, unsigned int type)
+{
+ enable_percpu_irq(irq, type);
+}
+
/**
* irq_percpu_is_enabled - Check whether the per cpu irq is enabled
* @irq: Linux irq number to check for
@@ -1998,6 +2230,11 @@ void disable_percpu_irq(unsigned int irq)
}
EXPORT_SYMBOL_GPL(disable_percpu_irq);
+void disable_percpu_nmi(unsigned int irq)
+{
+ disable_percpu_irq(irq);
+}
+
/*
* Internal function to unregister a percpu irqaction.
*/
@@ -2029,6 +2266,8 @@ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_
/* Found it - now remove it from the list of entries: */
desc->action = NULL;
+ desc->istate &= ~IRQS_NMI;
+
raw_spin_unlock_irqrestore(&desc->lock, flags);
unregister_handler_proc(irq, action);
@@ -2082,6 +2321,19 @@ void free_percpu_irq(unsigned int irq, void __percpu *dev_id)
}
EXPORT_SYMBOL_GPL(free_percpu_irq);
+void free_percpu_nmi(unsigned int irq, void __percpu *dev_id)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ if (!desc || !irq_settings_is_per_cpu_devid(desc))
+ return;
+
+ if (WARN_ON(!(desc->istate & IRQS_NMI)))
+ return;
+
+ kfree(__free_percpu_irq(irq, dev_id));
+}
+
/**
* setup_percpu_irq - setup a per-cpu interrupt
* @irq: Interrupt line to setup
@@ -2172,6 +2424,158 @@ int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
EXPORT_SYMBOL_GPL(__request_percpu_irq);
/**
+ * request_percpu_nmi - allocate a percpu interrupt line for NMI delivery
+ * @irq: Interrupt line to allocate
+ * @handler: Function to be called when the IRQ occurs.
+ * @name: An ascii name for the claiming device
+ * @dev_id: A percpu cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs
+ * have to be setup on each CPU by calling prepare_percpu_nmi() before
+ * being enabled on the same CPU by using enable_percpu_nmi().
+ *
+ * Dev_id must be globally unique. It is a per-cpu variable, and
+ * the handler gets called with the interrupted CPU's instance of
+ * that variable.
+ *
+ * Interrupt lines requested for NMI delivering should have auto enabling
+ * setting disabled.
+ *
+ * If the interrupt line cannot be used to deliver NMIs, function
+ * will fail returning a negative value.
+ */
+int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
+ const char *name, void __percpu *dev_id)
+{
+ struct irqaction *action;
+ struct irq_desc *desc;
+ unsigned long flags;
+ int retval;
+
+ if (!handler)
+ return -EINVAL;
+
+ desc = irq_to_desc(irq);
+
+ if (!desc || !irq_settings_can_request(desc) ||
+ !irq_settings_is_per_cpu_devid(desc) ||
+ irq_settings_can_autoenable(desc) ||
+ !irq_supports_nmi(desc))
+ return -EINVAL;
+
+ /* The line cannot already be NMI */
+ if (desc->istate & IRQS_NMI)
+ return -EINVAL;
+
+ action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+ if (!action)
+ return -ENOMEM;
+
+ action->handler = handler;
+ action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND | IRQF_NO_THREAD
+ | IRQF_NOBALANCING;
+ action->name = name;
+ action->percpu_dev_id = dev_id;
+
+ retval = irq_chip_pm_get(&desc->irq_data);
+ if (retval < 0)
+ goto err_out;
+
+ retval = __setup_irq(irq, desc, action);
+ if (retval)
+ goto err_irq_setup;
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+ desc->istate |= IRQS_NMI;
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+ return 0;
+
+err_irq_setup:
+ irq_chip_pm_put(&desc->irq_data);
+err_out:
+ kfree(action);
+
+ return retval;
+}
+
+/**
+ * prepare_percpu_nmi - performs CPU local setup for NMI delivery
+ * @irq: Interrupt line to prepare for NMI delivery
+ *
+ * This call prepares an interrupt line to deliver NMI on the current CPU,
+ * before that interrupt line gets enabled with enable_percpu_nmi().
+ *
+ * As a CPU local operation, this should be called from non-preemptible
+ * context.
+ *
+ * If the interrupt line cannot be used to deliver NMIs, function
+ * will fail returning a negative value.
+ */
+int prepare_percpu_nmi(unsigned int irq)
+{
+ unsigned long flags;
+ struct irq_desc *desc;
+ int ret = 0;
+
+ WARN_ON(preemptible());
+
+ desc = irq_get_desc_lock(irq, &flags,
+ IRQ_GET_DESC_CHECK_PERCPU);
+ if (!desc)
+ return -EINVAL;
+
+ if (WARN(!(desc->istate & IRQS_NMI),
+ KERN_ERR "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n",
+ irq)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = irq_nmi_setup(desc);
+ if (ret) {
+ pr_err("Failed to setup NMI delivery: irq %u\n", irq);
+ goto out;
+ }
+
+out:
+ irq_put_desc_unlock(desc, flags);
+ return ret;
+}
+
+/**
+ * teardown_percpu_nmi - undoes NMI setup of IRQ line
+ * @irq: Interrupt line from which CPU local NMI configuration should be
+ * removed
+ *
+ * This call undoes the setup done by prepare_percpu_nmi().
+ *
+ * IRQ line should not be enabled for the current CPU.
+ *
+ * As a CPU local operation, this should be called from non-preemptible
+ * context.
+ */
+void teardown_percpu_nmi(unsigned int irq)
+{
+ unsigned long flags;
+ struct irq_desc *desc;
+
+ WARN_ON(preemptible());
+
+ desc = irq_get_desc_lock(irq, &flags,
+ IRQ_GET_DESC_CHECK_PERCPU);
+ if (!desc)
+ return;
+
+ if (WARN_ON(!(desc->istate & IRQS_NMI)))
+ goto out;
+
+ irq_nmi_teardown(desc);
+out:
+ irq_put_desc_unlock(desc, flags);
+}
+
+/**
* irq_get_irqchip_state - returns the irqchip state of a interrupt.
* @irq: Interrupt line that is forwarded to a VM
* @which: One of IRQCHIP_STATE_* the caller wants to know about
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 087d18d771b5..65234c89d85b 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -101,6 +101,12 @@ bool kthread_should_stop(void)
}
EXPORT_SYMBOL(kthread_should_stop);
+bool __kthread_should_park(struct task_struct *k)
+{
+ return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags);
+}
+EXPORT_SYMBOL_GPL(__kthread_should_park);
+
/**
* kthread_should_park - should this kthread park now?
*
@@ -114,7 +120,7 @@ EXPORT_SYMBOL(kthread_should_stop);
*/
bool kthread_should_park(void)
{
- return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
+ return __kthread_should_park(current);
}
EXPORT_SYMBOL_GPL(kthread_should_park);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index bc35a54ae3d4..21cb81fe6359 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -45,11 +45,13 @@
#include <linux/hash.h>
#include <linux/ftrace.h>
#include <linux/stringify.h>
+#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/gfp.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/nmi.h>
+#include <linux/rcupdate.h>
#include <linux/kprobes.h>
#include <asm/sections.h>
@@ -82,6 +84,7 @@ module_param(lock_stat, int, 0644);
* code to recurse back into the lockdep code...
*/
static arch_spinlock_t lockdep_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+static struct task_struct *lockdep_selftest_task_struct;
static int graph_lock(void)
{
@@ -131,13 +134,17 @@ static inline int debug_locks_off_graph_unlock(void)
unsigned long nr_list_entries;
static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
+static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES);
/*
* All data structures here are protected by the global debug_lock.
*
- * Mutex key structs only get allocated, once during bootup, and never
- * get freed - this significantly simplifies the debugging code.
+ * nr_lock_classes is the number of elements of lock_classes[] that is
+ * in use.
*/
+#define KEYHASH_BITS (MAX_LOCKDEP_KEYS_BITS - 1)
+#define KEYHASH_SIZE (1UL << KEYHASH_BITS)
+static struct hlist_head lock_keys_hash[KEYHASH_SIZE];
unsigned long nr_lock_classes;
#ifndef CONFIG_DEBUG_LOCKDEP
static
@@ -278,11 +285,42 @@ static inline void lock_release_holdtime(struct held_lock *hlock)
#endif
/*
- * We keep a global list of all lock classes. The list only grows,
- * never shrinks. The list is only accessed with the lockdep
- * spinlock lock held.
+ * We keep a global list of all lock classes. The list is only accessed with
+ * the lockdep spinlock lock held. free_lock_classes is a list with free
+ * elements. These elements are linked together by the lock_entry member in
+ * struct lock_class.
*/
LIST_HEAD(all_lock_classes);
+static LIST_HEAD(free_lock_classes);
+
+/**
+ * struct pending_free - information about data structures about to be freed
+ * @zapped: Head of a list with struct lock_class elements.
+ * @lock_chains_being_freed: Bitmap that indicates which lock_chains[] elements
+ * are about to be freed.
+ */
+struct pending_free {
+ struct list_head zapped;
+ DECLARE_BITMAP(lock_chains_being_freed, MAX_LOCKDEP_CHAINS);
+};
+
+/**
+ * struct delayed_free - data structures used for delayed freeing
+ *
+ * A data structure for delayed freeing of data structures that may be
+ * accessed by RCU readers at the time these were freed.
+ *
+ * @rcu_head: Used to schedule an RCU callback for freeing data structures.
+ * @index: Index of @pf to which freed data structures are added.
+ * @scheduled: Whether or not an RCU callback has been scheduled.
+ * @pf: Array with information about data structures about to be freed.
+ */
+static struct delayed_free {
+ struct rcu_head rcu_head;
+ int index;
+ int scheduled;
+ struct pending_free pf[2];
+} delayed_free;
/*
* The lockdep classes are in a hash-table as well, for fast lookup:
@@ -332,6 +370,11 @@ void lockdep_on(void)
}
EXPORT_SYMBOL(lockdep_on);
+void lockdep_set_selftest_task(struct task_struct *task)
+{
+ lockdep_selftest_task_struct = task;
+}
+
/*
* Debugging switches:
*/
@@ -600,7 +643,7 @@ static int very_verbose(struct lock_class *class)
* Is this the address of a static object:
*/
#ifdef __KERNEL__
-static int static_obj(void *obj)
+static int static_obj(const void *obj)
{
unsigned long start = (unsigned long) &_stext,
end = (unsigned long) &_end,
@@ -717,6 +760,17 @@ static bool assign_lock_key(struct lockdep_map *lock)
{
unsigned long can_addr, addr = (unsigned long)lock;
+#ifdef __KERNEL__
+ /*
+ * lockdep_free_key_range() assumes that struct lock_class_key
+ * objects do not overlap. Since we use the address of lock
+ * objects as class key for static objects, check whether the
+ * size of lock_class_key objects does not exceed the size of
+ * the smallest lock object.
+ */
+ BUILD_BUG_ON(sizeof(struct lock_class_key) > sizeof(raw_spinlock_t));
+#endif
+
if (__is_kernel_percpu_address(addr, &can_addr))
lock->key = (void *)can_addr;
else if (__is_module_percpu_address(addr, &can_addr))
@@ -736,6 +790,280 @@ static bool assign_lock_key(struct lockdep_map *lock)
return true;
}
+#ifdef CONFIG_DEBUG_LOCKDEP
+
+/* Check whether element @e occurs in list @h */
+static bool in_list(struct list_head *e, struct list_head *h)
+{
+ struct list_head *f;
+
+ list_for_each(f, h) {
+ if (e == f)
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Check whether entry @e occurs in any of the locks_after or locks_before
+ * lists.
+ */
+static bool in_any_class_list(struct list_head *e)
+{
+ struct lock_class *class;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(lock_classes); i++) {
+ class = &lock_classes[i];
+ if (in_list(e, &class->locks_after) ||
+ in_list(e, &class->locks_before))
+ return true;
+ }
+ return false;
+}
+
+static bool class_lock_list_valid(struct lock_class *c, struct list_head *h)
+{
+ struct lock_list *e;
+
+ list_for_each_entry(e, h, entry) {
+ if (e->links_to != c) {
+ printk(KERN_INFO "class %s: mismatch for lock entry %ld; class %s <> %s",
+ c->name ? : "(?)",
+ (unsigned long)(e - list_entries),
+ e->links_to && e->links_to->name ?
+ e->links_to->name : "(?)",
+ e->class && e->class->name ? e->class->name :
+ "(?)");
+ return false;
+ }
+ }
+ return true;
+}
+
+static u16 chain_hlocks[];
+
+static bool check_lock_chain_key(struct lock_chain *chain)
+{
+#ifdef CONFIG_PROVE_LOCKING
+ u64 chain_key = 0;
+ int i;
+
+ for (i = chain->base; i < chain->base + chain->depth; i++)
+ chain_key = iterate_chain_key(chain_key, chain_hlocks[i] + 1);
+ /*
+ * The 'unsigned long long' casts avoid that a compiler warning
+ * is reported when building tools/lib/lockdep.
+ */
+ if (chain->chain_key != chain_key) {
+ printk(KERN_INFO "chain %lld: key %#llx <> %#llx\n",
+ (unsigned long long)(chain - lock_chains),
+ (unsigned long long)chain->chain_key,
+ (unsigned long long)chain_key);
+ return false;
+ }
+#endif
+ return true;
+}
+
+static bool in_any_zapped_class_list(struct lock_class *class)
+{
+ struct pending_free *pf;
+ int i;
+
+ for (i = 0, pf = delayed_free.pf; i < ARRAY_SIZE(delayed_free.pf); i++, pf++) {
+ if (in_list(&class->lock_entry, &pf->zapped))
+ return true;
+ }
+
+ return false;
+}
+
+static bool __check_data_structures(void)
+{
+ struct lock_class *class;
+ struct lock_chain *chain;
+ struct hlist_head *head;
+ struct lock_list *e;
+ int i;
+
+ /* Check whether all classes occur in a lock list. */
+ for (i = 0; i < ARRAY_SIZE(lock_classes); i++) {
+ class = &lock_classes[i];
+ if (!in_list(&class->lock_entry, &all_lock_classes) &&
+ !in_list(&class->lock_entry, &free_lock_classes) &&
+ !in_any_zapped_class_list(class)) {
+ printk(KERN_INFO "class %px/%s is not in any class list\n",
+ class, class->name ? : "(?)");
+ return false;
+ }
+ }
+
+ /* Check whether all classes have valid lock lists. */
+ for (i = 0; i < ARRAY_SIZE(lock_classes); i++) {
+ class = &lock_classes[i];
+ if (!class_lock_list_valid(class, &class->locks_before))
+ return false;
+ if (!class_lock_list_valid(class, &class->locks_after))
+ return false;
+ }
+
+ /* Check the chain_key of all lock chains. */
+ for (i = 0; i < ARRAY_SIZE(chainhash_table); i++) {
+ head = chainhash_table + i;
+ hlist_for_each_entry_rcu(chain, head, entry) {
+ if (!check_lock_chain_key(chain))
+ return false;
+ }
+ }
+
+ /*
+ * Check whether all list entries that are in use occur in a class
+ * lock list.
+ */
+ for_each_set_bit(i, list_entries_in_use, ARRAY_SIZE(list_entries)) {
+ e = list_entries + i;
+ if (!in_any_class_list(&e->entry)) {
+ printk(KERN_INFO "list entry %d is not in any class list; class %s <> %s\n",
+ (unsigned int)(e - list_entries),
+ e->class->name ? : "(?)",
+ e->links_to->name ? : "(?)");
+ return false;
+ }
+ }
+
+ /*
+ * Check whether all list entries that are not in use do not occur in
+ * a class lock list.
+ */
+ for_each_clear_bit(i, list_entries_in_use, ARRAY_SIZE(list_entries)) {
+ e = list_entries + i;
+ if (in_any_class_list(&e->entry)) {
+ printk(KERN_INFO "list entry %d occurs in a class list; class %s <> %s\n",
+ (unsigned int)(e - list_entries),
+ e->class && e->class->name ? e->class->name :
+ "(?)",
+ e->links_to && e->links_to->name ?
+ e->links_to->name : "(?)");
+ return false;
+ }
+ }
+
+ return true;
+}
+
+int check_consistency = 0;
+module_param(check_consistency, int, 0644);
+
+static void check_data_structures(void)
+{
+ static bool once = false;
+
+ if (check_consistency && !once) {
+ if (!__check_data_structures()) {
+ once = true;
+ WARN_ON(once);
+ }
+ }
+}
+
+#else /* CONFIG_DEBUG_LOCKDEP */
+
+static inline void check_data_structures(void) { }
+
+#endif /* CONFIG_DEBUG_LOCKDEP */
+
+/*
+ * Initialize the lock_classes[] array elements, the free_lock_classes list
+ * and also the delayed_free structure.
+ */
+static void init_data_structures_once(void)
+{
+ static bool initialization_happened;
+ int i;
+
+ if (likely(initialization_happened))
+ return;
+
+ initialization_happened = true;
+
+ init_rcu_head(&delayed_free.rcu_head);
+ INIT_LIST_HEAD(&delayed_free.pf[0].zapped);
+ INIT_LIST_HEAD(&delayed_free.pf[1].zapped);
+
+ for (i = 0; i < ARRAY_SIZE(lock_classes); i++) {
+ list_add_tail(&lock_classes[i].lock_entry, &free_lock_classes);
+ INIT_LIST_HEAD(&lock_classes[i].locks_after);
+ INIT_LIST_HEAD(&lock_classes[i].locks_before);
+ }
+}
+
+static inline struct hlist_head *keyhashentry(const struct lock_class_key *key)
+{
+ unsigned long hash = hash_long((uintptr_t)key, KEYHASH_BITS);
+
+ return lock_keys_hash + hash;
+}
+
+/* Register a dynamically allocated key. */
+void lockdep_register_key(struct lock_class_key *key)
+{
+ struct hlist_head *hash_head;
+ struct lock_class_key *k;
+ unsigned long flags;
+
+ if (WARN_ON_ONCE(static_obj(key)))
+ return;
+ hash_head = keyhashentry(key);
+
+ raw_local_irq_save(flags);
+ if (!graph_lock())
+ goto restore_irqs;
+ hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
+ if (WARN_ON_ONCE(k == key))
+ goto out_unlock;
+ }
+ hlist_add_head_rcu(&key->hash_entry, hash_head);
+out_unlock:
+ graph_unlock();
+restore_irqs:
+ raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(lockdep_register_key);
+
+/* Check whether a key has been registered as a dynamic key. */
+static bool is_dynamic_key(const struct lock_class_key *key)
+{
+ struct hlist_head *hash_head;
+ struct lock_class_key *k;
+ bool found = false;
+
+ if (WARN_ON_ONCE(static_obj(key)))
+ return false;
+
+ /*
+ * If lock debugging is disabled lock_keys_hash[] may contain
+ * pointers to memory that has already been freed. Avoid triggering
+ * a use-after-free in that case by returning early.
+ */
+ if (!debug_locks)
+ return true;
+
+ hash_head = keyhashentry(key);
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
+ if (k == key) {
+ found = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return found;
+}
+
/*
* Register a lock's class in the hash-table, if the class is not present
* yet. Otherwise we look it up. We cache the result in the lock object
@@ -757,7 +1085,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
if (!lock->key) {
if (!assign_lock_key(lock))
return NULL;
- } else if (!static_obj(lock->key)) {
+ } else if (!static_obj(lock->key) && !is_dynamic_key(lock->key)) {
return NULL;
}
@@ -776,11 +1104,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
goto out_unlock_set;
}
- /*
- * Allocate a new key from the static array, and add it to
- * the hash:
- */
- if (nr_lock_classes >= MAX_LOCKDEP_KEYS) {
+ init_data_structures_once();
+
+ /* Allocate a new lock class and add it to the hash. */
+ class = list_first_entry_or_null(&free_lock_classes, typeof(*class),
+ lock_entry);
+ if (!class) {
if (!debug_locks_off_graph_unlock()) {
return NULL;
}
@@ -789,13 +1118,13 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
dump_stack();
return NULL;
}
- class = lock_classes + nr_lock_classes++;
+ nr_lock_classes++;
debug_atomic_inc(nr_unused_locks);
class->key = key;
class->name = lock->name;
class->subclass = subclass;
- INIT_LIST_HEAD(&class->locks_before);
- INIT_LIST_HEAD(&class->locks_after);
+ WARN_ON_ONCE(!list_empty(&class->locks_before));
+ WARN_ON_ONCE(!list_empty(&class->locks_after));
class->name_version = count_matching_names(class);
/*
* We use RCU's safe list-add method to make
@@ -803,9 +1132,10 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
*/
hlist_add_head_rcu(&class->hash_entry, hash_head);
/*
- * Add it to the global list of classes:
+ * Remove the class from the free list and add it to the global list
+ * of classes.
*/
- list_add_tail(&class->lock_entry, &all_lock_classes);
+ list_move_tail(&class->lock_entry, &all_lock_classes);
if (verbose(class)) {
graph_unlock();
@@ -846,7 +1176,10 @@ out_set_class_cache:
*/
static struct lock_list *alloc_list_entry(void)
{
- if (nr_list_entries >= MAX_LOCKDEP_ENTRIES) {
+ int idx = find_first_zero_bit(list_entries_in_use,
+ ARRAY_SIZE(list_entries));
+
+ if (idx >= ARRAY_SIZE(list_entries)) {
if (!debug_locks_off_graph_unlock())
return NULL;
@@ -854,13 +1187,16 @@ static struct lock_list *alloc_list_entry(void)
dump_stack();
return NULL;
}
- return list_entries + nr_list_entries++;
+ nr_list_entries++;
+ __set_bit(idx, list_entries_in_use);
+ return list_entries + idx;
}
/*
* Add a new dependency to the head of the list:
*/
-static int add_lock_to_list(struct lock_class *this, struct list_head *head,
+static int add_lock_to_list(struct lock_class *this,
+ struct lock_class *links_to, struct list_head *head,
unsigned long ip, int distance,
struct stack_trace *trace)
{
@@ -874,6 +1210,7 @@ static int add_lock_to_list(struct lock_class *this, struct list_head *head,
return 0;
entry->class = this;
+ entry->links_to = links_to;
entry->distance = distance;
entry->trace = *trace;
/*
@@ -956,7 +1293,7 @@ static inline void mark_lock_accessed(struct lock_list *lock,
unsigned long nr;
nr = lock - list_entries;
- WARN_ON(nr >= nr_list_entries); /* Out-of-bounds, input fail */
+ WARN_ON(nr >= ARRAY_SIZE(list_entries)); /* Out-of-bounds, input fail */
lock->parent = parent;
lock->class->dep_gen_id = lockdep_dependency_gen_id;
}
@@ -966,7 +1303,7 @@ static inline unsigned long lock_accessed(struct lock_list *lock)
unsigned long nr;
nr = lock - list_entries;
- WARN_ON(nr >= nr_list_entries); /* Out-of-bounds, input fail */
+ WARN_ON(nr >= ARRAY_SIZE(list_entries)); /* Out-of-bounds, input fail */
return lock->class->dep_gen_id == lockdep_dependency_gen_id;
}
@@ -1625,29 +1962,18 @@ static const char *state_rnames[] = {
static inline const char *state_name(enum lock_usage_bit bit)
{
- return (bit & 1) ? state_rnames[bit >> 2] : state_names[bit >> 2];
+ return (bit & LOCK_USAGE_READ_MASK) ? state_rnames[bit >> 2] : state_names[bit >> 2];
}
static int exclusive_bit(int new_bit)
{
- /*
- * USED_IN
- * USED_IN_READ
- * ENABLED
- * ENABLED_READ
- *
- * bit 0 - write/read
- * bit 1 - used_in/enabled
- * bit 2+ state
- */
-
- int state = new_bit & ~3;
- int dir = new_bit & 2;
+ int state = new_bit & LOCK_USAGE_STATE_MASK;
+ int dir = new_bit & LOCK_USAGE_DIR_MASK;
/*
* keep state, bit flip the direction and strip read.
*/
- return state | (dir ^ 2);
+ return state | (dir ^ LOCK_USAGE_DIR_MASK);
}
static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
@@ -1843,6 +2169,24 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
struct lock_list this;
int ret;
+ if (!hlock_class(prev)->key || !hlock_class(next)->key) {
+ /*
+ * The warning statements below may trigger a use-after-free
+ * of the class name. It is better to trigger a use-after free
+ * and to have the class name most of the time instead of not
+ * having the class name available.
+ */
+ WARN_ONCE(!debug_locks_silent && !hlock_class(prev)->key,
+ "Detected use-after-free of lock class %px/%s\n",
+ hlock_class(prev),
+ hlock_class(prev)->name);
+ WARN_ONCE(!debug_locks_silent && !hlock_class(next)->key,
+ "Detected use-after-free of lock class %px/%s\n",
+ hlock_class(next),
+ hlock_class(next)->name);
+ return 2;
+ }
+
/*
* Prove that the new <prev> -> <next> dependency would not
* create a circular dependency in the graph. (We do this by
@@ -1919,14 +2263,14 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
* Ok, all validations passed, add the new lock
* to the previous lock's dependency list:
*/
- ret = add_lock_to_list(hlock_class(next),
+ ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
&hlock_class(prev)->locks_after,
next->acquire_ip, distance, trace);
if (!ret)
return 0;
- ret = add_lock_to_list(hlock_class(prev),
+ ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
&hlock_class(next)->locks_before,
next->acquire_ip, distance, trace);
if (!ret)
@@ -2019,8 +2363,8 @@ out_bug:
return 0;
}
-unsigned long nr_lock_chains;
struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS];
+static DECLARE_BITMAP(lock_chains_in_use, MAX_LOCKDEP_CHAINS);
int nr_chain_hlocks;
static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS];
@@ -2154,6 +2498,33 @@ static int check_no_collision(struct task_struct *curr,
}
/*
+ * Given an index that is >= -1, return the index of the next lock chain.
+ * Return -2 if there is no next lock chain.
+ */
+long lockdep_next_lockchain(long i)
+{
+ i = find_next_bit(lock_chains_in_use, ARRAY_SIZE(lock_chains), i + 1);
+ return i < ARRAY_SIZE(lock_chains) ? i : -2;
+}
+
+unsigned long lock_chain_count(void)
+{
+ return bitmap_weight(lock_chains_in_use, ARRAY_SIZE(lock_chains));
+}
+
+/* Must be called with the graph lock held. */
+static struct lock_chain *alloc_lock_chain(void)
+{
+ int idx = find_first_zero_bit(lock_chains_in_use,
+ ARRAY_SIZE(lock_chains));
+
+ if (unlikely(idx >= ARRAY_SIZE(lock_chains)))
+ return NULL;
+ __set_bit(idx, lock_chains_in_use);
+ return lock_chains + idx;
+}
+
+/*
* Adds a dependency chain into chain hashtable. And must be called with
* graph_lock held.
*
@@ -2170,19 +2541,15 @@ static inline int add_chain_cache(struct task_struct *curr,
int i, j;
/*
- * Allocate a new chain entry from the static array, and add
- * it to the hash:
- */
-
- /*
- * We might need to take the graph lock, ensure we've got IRQs
+ * The caller must hold the graph lock, ensure we've got IRQs
* disabled to make this an IRQ-safe lock.. for recursion reasons
* lockdep won't complain about its own locking errors.
*/
if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
return 0;
- if (unlikely(nr_lock_chains >= MAX_LOCKDEP_CHAINS)) {
+ chain = alloc_lock_chain();
+ if (!chain) {
if (!debug_locks_off_graph_unlock())
return 0;
@@ -2190,7 +2557,6 @@ static inline int add_chain_cache(struct task_struct *curr,
dump_stack();
return 0;
}
- chain = lock_chains + nr_lock_chains++;
chain->chain_key = chain_key;
chain->irq_context = hlock->irq_context;
i = get_first_held_lock(curr, hlock);
@@ -2207,16 +2573,8 @@ static inline int add_chain_cache(struct task_struct *curr,
chain_hlocks[chain->base + j] = lock_id;
}
chain_hlocks[chain->base + j] = class - lock_classes;
- }
-
- if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS)
nr_chain_hlocks += chain->depth;
-
-#ifdef CONFIG_DEBUG_LOCKDEP
- /*
- * Important for check_no_collision().
- */
- if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) {
+ } else {
if (!debug_locks_off_graph_unlock())
return 0;
@@ -2224,7 +2582,6 @@ static inline int add_chain_cache(struct task_struct *curr,
dump_stack();
return 0;
}
-#endif
hlist_add_head_rcu(&chain->entry, hash_head);
debug_atomic_inc(chain_lookup_misses);
@@ -2234,19 +2591,16 @@ static inline int add_chain_cache(struct task_struct *curr,
}
/*
- * Look up a dependency chain.
+ * Look up a dependency chain. Must be called with either the graph lock or
+ * the RCU read lock held.
*/
static inline struct lock_chain *lookup_chain_cache(u64 chain_key)
{
struct hlist_head *hash_head = chainhashentry(chain_key);
struct lock_chain *chain;
- /*
- * We can walk it lock-free, because entries only get added
- * to the hash:
- */
hlist_for_each_entry_rcu(chain, hash_head, entry) {
- if (chain->chain_key == chain_key) {
+ if (READ_ONCE(chain->chain_key) == chain_key) {
debug_atomic_inc(chain_lookup_hits);
return chain;
}
@@ -2663,8 +3017,8 @@ mark_lock_irq(struct task_struct *curr, struct held_lock *this,
enum lock_usage_bit new_bit)
{
int excl_bit = exclusive_bit(new_bit);
- int read = new_bit & 1;
- int dir = new_bit & 2;
+ int read = new_bit & LOCK_USAGE_READ_MASK;
+ int dir = new_bit & LOCK_USAGE_DIR_MASK;
/*
* mark USED_IN has to look forwards -- to ensure no dependency
@@ -2688,19 +3042,19 @@ mark_lock_irq(struct task_struct *curr, struct held_lock *this,
* states.
*/
if ((!read || !dir || STRICT_READ_CHECKS) &&
- !usage(curr, this, excl_bit, state_name(new_bit & ~1)))
+ !usage(curr, this, excl_bit, state_name(new_bit & ~LOCK_USAGE_READ_MASK)))
return 0;
/*
* Check for read in write conflicts
*/
if (!read) {
- if (!valid_state(curr, this, new_bit, excl_bit + 1))
+ if (!valid_state(curr, this, new_bit, excl_bit + LOCK_USAGE_READ_MASK))
return 0;
if (STRICT_READ_CHECKS &&
- !usage(curr, this, excl_bit + 1,
- state_name(new_bit + 1)))
+ !usage(curr, this, excl_bit + LOCK_USAGE_READ_MASK,
+ state_name(new_bit + LOCK_USAGE_READ_MASK)))
return 0;
}
@@ -2710,35 +3064,28 @@ mark_lock_irq(struct task_struct *curr, struct held_lock *this,
return 1;
}
-enum mark_type {
-#define LOCKDEP_STATE(__STATE) __STATE,
-#include "lockdep_states.h"
-#undef LOCKDEP_STATE
-};
-
/*
* Mark all held locks with a usage bit:
*/
static int
-mark_held_locks(struct task_struct *curr, enum mark_type mark)
+mark_held_locks(struct task_struct *curr, enum lock_usage_bit base_bit)
{
- enum lock_usage_bit usage_bit;
struct held_lock *hlock;
int i;
for (i = 0; i < curr->lockdep_depth; i++) {
+ enum lock_usage_bit hlock_bit = base_bit;
hlock = curr->held_locks + i;
- usage_bit = 2 + (mark << 2); /* ENABLED */
if (hlock->read)
- usage_bit += 1; /* READ */
+ hlock_bit += LOCK_USAGE_READ_MASK;
- BUG_ON(usage_bit >= LOCK_USAGE_STATES);
+ BUG_ON(hlock_bit >= LOCK_USAGE_STATES);
if (!hlock->check)
continue;
- if (!mark_lock(curr, hlock, usage_bit))
+ if (!mark_lock(curr, hlock, hlock_bit))
return 0;
}
@@ -2759,7 +3106,7 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
* We are going to turn hardirqs on, so set the
* usage bit for all held locks:
*/
- if (!mark_held_locks(curr, HARDIRQ))
+ if (!mark_held_locks(curr, LOCK_ENABLED_HARDIRQ))
return;
/*
* If we have softirqs enabled, then set the usage
@@ -2767,7 +3114,7 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
* this bit from being set before)
*/
if (curr->softirqs_enabled)
- if (!mark_held_locks(curr, SOFTIRQ))
+ if (!mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ))
return;
curr->hardirq_enable_ip = ip;
@@ -2883,7 +3230,7 @@ void trace_softirqs_on(unsigned long ip)
* enabled too:
*/
if (curr->hardirqs_enabled)
- mark_held_locks(curr, SOFTIRQ);
+ mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
current->lockdep_recursion = 0;
}
@@ -3122,13 +3469,12 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
if (DEBUG_LOCKS_WARN_ON(!key))
return;
/*
- * Sanity check, the lock-class key must be persistent:
+ * Sanity check, the lock-class key must either have been allocated
+ * statically or must have been registered as a dynamic key.
*/
- if (!static_obj(key)) {
- printk("BUG: key %px not in .data!\n", key);
- /*
- * What it says above ^^^^^, I suggest you read it.
- */
+ if (!static_obj(key) && !is_dynamic_key(key)) {
+ if (debug_locks)
+ printk(KERN_ERR "BUG: key %px has not been registered!\n", key);
DEBUG_LOCKS_WARN_ON(1);
return;
}
@@ -3338,6 +3684,11 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
if (nest_lock && !__lock_is_held(nest_lock, -1))
return print_lock_nested_lock_not_held(curr, hlock, ip);
+ if (!debug_locks_silent) {
+ WARN_ON_ONCE(depth && !hlock_class(hlock - 1)->key);
+ WARN_ON_ONCE(!hlock_class(hlock)->key);
+ }
+
if (!validate_chain(curr, lock, hlock, chain_head, chain_key))
return 0;
@@ -3500,6 +3851,9 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
unsigned int depth;
int i;
+ if (unlikely(!debug_locks))
+ return 0;
+
depth = curr->lockdep_depth;
/*
* This function is about (re)setting the class of a held lock,
@@ -3538,6 +3892,9 @@ static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
unsigned int depth;
int i;
+ if (unlikely(!debug_locks))
+ return 0;
+
depth = curr->lockdep_depth;
/*
* This function is about (re)setting the class of a held lock,
@@ -4128,29 +4485,131 @@ void lockdep_reset(void)
raw_local_irq_restore(flags);
}
+/* Remove a class from a lock chain. Must be called with the graph lock held. */
+static void remove_class_from_lock_chain(struct pending_free *pf,
+ struct lock_chain *chain,
+ struct lock_class *class)
+{
+#ifdef CONFIG_PROVE_LOCKING
+ struct lock_chain *new_chain;
+ u64 chain_key;
+ int i;
+
+ for (i = chain->base; i < chain->base + chain->depth; i++) {
+ if (chain_hlocks[i] != class - lock_classes)
+ continue;
+ /* The code below leaks one chain_hlock[] entry. */
+ if (--chain->depth > 0) {
+ memmove(&chain_hlocks[i], &chain_hlocks[i + 1],
+ (chain->base + chain->depth - i) *
+ sizeof(chain_hlocks[0]));
+ }
+ /*
+ * Each lock class occurs at most once in a lock chain so once
+ * we found a match we can break out of this loop.
+ */
+ goto recalc;
+ }
+ /* Since the chain has not been modified, return. */
+ return;
+
+recalc:
+ chain_key = 0;
+ for (i = chain->base; i < chain->base + chain->depth; i++)
+ chain_key = iterate_chain_key(chain_key, chain_hlocks[i] + 1);
+ if (chain->depth && chain->chain_key == chain_key)
+ return;
+ /* Overwrite the chain key for concurrent RCU readers. */
+ WRITE_ONCE(chain->chain_key, chain_key);
+ /*
+ * Note: calling hlist_del_rcu() from inside a
+ * hlist_for_each_entry_rcu() loop is safe.
+ */
+ hlist_del_rcu(&chain->entry);
+ __set_bit(chain - lock_chains, pf->lock_chains_being_freed);
+ if (chain->depth == 0)
+ return;
+ /*
+ * If the modified lock chain matches an existing lock chain, drop
+ * the modified lock chain.
+ */
+ if (lookup_chain_cache(chain_key))
+ return;
+ new_chain = alloc_lock_chain();
+ if (WARN_ON_ONCE(!new_chain)) {
+ debug_locks_off();
+ return;
+ }
+ *new_chain = *chain;
+ hlist_add_head_rcu(&new_chain->entry, chainhashentry(chain_key));
+#endif
+}
+
+/* Must be called with the graph lock held. */
+static void remove_class_from_lock_chains(struct pending_free *pf,
+ struct lock_class *class)
+{
+ struct lock_chain *chain;
+ struct hlist_head *head;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(chainhash_table); i++) {
+ head = chainhash_table + i;
+ hlist_for_each_entry_rcu(chain, head, entry) {
+ remove_class_from_lock_chain(pf, chain, class);
+ }
+ }
+}
+
/*
* Remove all references to a lock class. The caller must hold the graph lock.
*/
-static void zap_class(struct lock_class *class)
+static void zap_class(struct pending_free *pf, struct lock_class *class)
{
+ struct lock_list *entry;
int i;
+ WARN_ON_ONCE(!class->key);
+
/*
* Remove all dependencies this lock is
* involved in:
*/
- for (i = 0; i < nr_list_entries; i++) {
- if (list_entries[i].class == class)
- list_del_rcu(&list_entries[i].entry);
+ for_each_set_bit(i, list_entries_in_use, ARRAY_SIZE(list_entries)) {
+ entry = list_entries + i;
+ if (entry->class != class && entry->links_to != class)
+ continue;
+ __clear_bit(i, list_entries_in_use);
+ nr_list_entries--;
+ list_del_rcu(&entry->entry);
+ }
+ if (list_empty(&class->locks_after) &&
+ list_empty(&class->locks_before)) {
+ list_move_tail(&class->lock_entry, &pf->zapped);
+ hlist_del_rcu(&class->hash_entry);
+ WRITE_ONCE(class->key, NULL);
+ WRITE_ONCE(class->name, NULL);
+ nr_lock_classes--;
+ } else {
+ WARN_ONCE(true, "%s() failed for class %s\n", __func__,
+ class->name);
}
- /*
- * Unhash the class and remove it from the all_lock_classes list:
- */
- hlist_del_rcu(&class->hash_entry);
- list_del(&class->lock_entry);
- RCU_INIT_POINTER(class->key, NULL);
- RCU_INIT_POINTER(class->name, NULL);
+ remove_class_from_lock_chains(pf, class);
+}
+
+static void reinit_class(struct lock_class *class)
+{
+ void *const p = class;
+ const unsigned int offset = offsetof(struct lock_class, key);
+
+ WARN_ON_ONCE(!class->lock_entry.next);
+ WARN_ON_ONCE(!list_empty(&class->locks_after));
+ WARN_ON_ONCE(!list_empty(&class->locks_before));
+ memset(p + offset, 0, sizeof(*class) - offset);
+ WARN_ON_ONCE(!class->lock_entry.next);
+ WARN_ON_ONCE(!list_empty(&class->locks_after));
+ WARN_ON_ONCE(!list_empty(&class->locks_before));
}
static inline int within(const void *addr, void *start, unsigned long size)
@@ -4158,55 +4617,175 @@ static inline int within(const void *addr, void *start, unsigned long size)
return addr >= start && addr < start + size;
}
+static bool inside_selftest(void)
+{
+ return current == lockdep_selftest_task_struct;
+}
+
+/* The caller must hold the graph lock. */
+static struct pending_free *get_pending_free(void)
+{
+ return delayed_free.pf + delayed_free.index;
+}
+
+static void free_zapped_rcu(struct rcu_head *cb);
+
/*
- * Used in module.c to remove lock classes from memory that is going to be
- * freed; and possibly re-used by other modules.
- *
- * We will have had one sync_sched() before getting here, so we're guaranteed
- * nobody will look up these exact classes -- they're properly dead but still
- * allocated.
+ * Schedule an RCU callback if no RCU callback is pending. Must be called with
+ * the graph lock held.
*/
-void lockdep_free_key_range(void *start, unsigned long size)
+static void call_rcu_zapped(struct pending_free *pf)
+{
+ WARN_ON_ONCE(inside_selftest());
+
+ if (list_empty(&pf->zapped))
+ return;
+
+ if (delayed_free.scheduled)
+ return;
+
+ delayed_free.scheduled = true;
+
+ WARN_ON_ONCE(delayed_free.pf + delayed_free.index != pf);
+ delayed_free.index ^= 1;
+
+ call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+}
+
+/* The caller must hold the graph lock. May be called from RCU context. */
+static void __free_zapped_classes(struct pending_free *pf)
{
struct lock_class *class;
- struct hlist_head *head;
+
+ check_data_structures();
+
+ list_for_each_entry(class, &pf->zapped, lock_entry)
+ reinit_class(class);
+
+ list_splice_init(&pf->zapped, &free_lock_classes);
+
+#ifdef CONFIG_PROVE_LOCKING
+ bitmap_andnot(lock_chains_in_use, lock_chains_in_use,
+ pf->lock_chains_being_freed, ARRAY_SIZE(lock_chains));
+ bitmap_clear(pf->lock_chains_being_freed, 0, ARRAY_SIZE(lock_chains));
+#endif
+}
+
+static void free_zapped_rcu(struct rcu_head *ch)
+{
+ struct pending_free *pf;
unsigned long flags;
- int i;
- int locked;
+
+ if (WARN_ON_ONCE(ch != &delayed_free.rcu_head))
+ return;
raw_local_irq_save(flags);
- locked = graph_lock();
+ if (!graph_lock())
+ goto out_irq;
+
+ /* closed head */
+ pf = delayed_free.pf + (delayed_free.index ^ 1);
+ __free_zapped_classes(pf);
+ delayed_free.scheduled = false;
/*
- * Unhash all classes that were created by this module:
+ * If there's anything on the open list, close and start a new callback.
*/
+ call_rcu_zapped(delayed_free.pf + delayed_free.index);
+
+ graph_unlock();
+out_irq:
+ raw_local_irq_restore(flags);
+}
+
+/*
+ * Remove all lock classes from the class hash table and from the
+ * all_lock_classes list whose key or name is in the address range [start,
+ * start + size). Move these lock classes to the zapped_classes list. Must
+ * be called with the graph lock held.
+ */
+static void __lockdep_free_key_range(struct pending_free *pf, void *start,
+ unsigned long size)
+{
+ struct lock_class *class;
+ struct hlist_head *head;
+ int i;
+
+ /* Unhash all classes that were created by a module. */
for (i = 0; i < CLASSHASH_SIZE; i++) {
head = classhash_table + i;
hlist_for_each_entry_rcu(class, head, hash_entry) {
- if (within(class->key, start, size))
- zap_class(class);
- else if (within(class->name, start, size))
- zap_class(class);
+ if (!within(class->key, start, size) &&
+ !within(class->name, start, size))
+ continue;
+ zap_class(pf, class);
}
}
+}
- if (locked)
- graph_unlock();
+/*
+ * Used in module.c to remove lock classes from memory that is going to be
+ * freed; and possibly re-used by other modules.
+ *
+ * We will have had one synchronize_rcu() before getting here, so we're
+ * guaranteed nobody will look up these exact classes -- they're properly dead
+ * but still allocated.
+ */
+static void lockdep_free_key_range_reg(void *start, unsigned long size)
+{
+ struct pending_free *pf;
+ unsigned long flags;
+ int locked;
+
+ init_data_structures_once();
+
+ raw_local_irq_save(flags);
+ locked = graph_lock();
+ if (!locked)
+ goto out_irq;
+
+ pf = get_pending_free();
+ __lockdep_free_key_range(pf, start, size);
+ call_rcu_zapped(pf);
+
+ graph_unlock();
+out_irq:
raw_local_irq_restore(flags);
/*
* Wait for any possible iterators from look_up_lock_class() to pass
* before continuing to free the memory they refer to.
- *
- * sync_sched() is sufficient because the read-side is IRQ disable.
*/
synchronize_rcu();
+}
- /*
- * XXX at this point we could return the resources to the pool;
- * instead we leak them. We would need to change to bitmap allocators
- * instead of the linear allocators we have now.
- */
+/*
+ * Free all lockdep keys in the range [start, start+size). Does not sleep.
+ * Ignores debug_locks. Must only be used by the lockdep selftests.
+ */
+static void lockdep_free_key_range_imm(void *start, unsigned long size)
+{
+ struct pending_free *pf = delayed_free.pf;
+ unsigned long flags;
+
+ init_data_structures_once();
+
+ raw_local_irq_save(flags);
+ arch_spin_lock(&lockdep_lock);
+ __lockdep_free_key_range(pf, start, size);
+ __free_zapped_classes(pf);
+ arch_spin_unlock(&lockdep_lock);
+ raw_local_irq_restore(flags);
+}
+
+void lockdep_free_key_range(void *start, unsigned long size)
+{
+ init_data_structures_once();
+
+ if (inside_selftest())
+ lockdep_free_key_range_imm(start, size);
+ else
+ lockdep_free_key_range_reg(start, size);
}
/*
@@ -4231,14 +4810,12 @@ static bool lock_class_cache_is_registered(struct lockdep_map *lock)
return false;
}
-void lockdep_reset_lock(struct lockdep_map *lock)
+/* The caller must hold the graph lock. Does not sleep. */
+static void __lockdep_reset_lock(struct pending_free *pf,
+ struct lockdep_map *lock)
{
struct lock_class *class;
- unsigned long flags;
- int j, locked;
-
- raw_local_irq_save(flags);
- locked = graph_lock();
+ int j;
/*
* Remove all classes this lock might have:
@@ -4249,27 +4826,104 @@ void lockdep_reset_lock(struct lockdep_map *lock)
*/
class = look_up_lock_class(lock, j);
if (class)
- zap_class(class);
+ zap_class(pf, class);
}
/*
* Debug check: in the end all mapped classes should
* be gone.
*/
- if (unlikely(lock_class_cache_is_registered(lock))) {
- if (debug_locks_off_graph_unlock()) {
- /*
- * We all just reset everything, how did it match?
- */
- WARN_ON(1);
+ if (WARN_ON_ONCE(lock_class_cache_is_registered(lock)))
+ debug_locks_off();
+}
+
+/*
+ * Remove all information lockdep has about a lock if debug_locks == 1. Free
+ * released data structures from RCU context.
+ */
+static void lockdep_reset_lock_reg(struct lockdep_map *lock)
+{
+ struct pending_free *pf;
+ unsigned long flags;
+ int locked;
+
+ raw_local_irq_save(flags);
+ locked = graph_lock();
+ if (!locked)
+ goto out_irq;
+
+ pf = get_pending_free();
+ __lockdep_reset_lock(pf, lock);
+ call_rcu_zapped(pf);
+
+ graph_unlock();
+out_irq:
+ raw_local_irq_restore(flags);
+}
+
+/*
+ * Reset a lock. Does not sleep. Ignores debug_locks. Must only be used by the
+ * lockdep selftests.
+ */
+static void lockdep_reset_lock_imm(struct lockdep_map *lock)
+{
+ struct pending_free *pf = delayed_free.pf;
+ unsigned long flags;
+
+ raw_local_irq_save(flags);
+ arch_spin_lock(&lockdep_lock);
+ __lockdep_reset_lock(pf, lock);
+ __free_zapped_classes(pf);
+ arch_spin_unlock(&lockdep_lock);
+ raw_local_irq_restore(flags);
+}
+
+void lockdep_reset_lock(struct lockdep_map *lock)
+{
+ init_data_structures_once();
+
+ if (inside_selftest())
+ lockdep_reset_lock_imm(lock);
+ else
+ lockdep_reset_lock_reg(lock);
+}
+
+/* Unregister a dynamically allocated key. */
+void lockdep_unregister_key(struct lock_class_key *key)
+{
+ struct hlist_head *hash_head = keyhashentry(key);
+ struct lock_class_key *k;
+ struct pending_free *pf;
+ unsigned long flags;
+ bool found = false;
+
+ might_sleep();
+
+ if (WARN_ON_ONCE(static_obj(key)))
+ return;
+
+ raw_local_irq_save(flags);
+ if (!graph_lock())
+ goto out_irq;
+
+ pf = get_pending_free();
+ hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
+ if (k == key) {
+ hlist_del_rcu(&k->hash_entry);
+ found = true;
+ break;
}
- goto out_restore;
}
- if (locked)
- graph_unlock();
-
-out_restore:
+ WARN_ON_ONCE(!found);
+ __lockdep_free_key_range(pf, key, 1);
+ call_rcu_zapped(pf);
+ graph_unlock();
+out_irq:
raw_local_irq_restore(flags);
+
+ /* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
+ synchronize_rcu();
}
+EXPORT_SYMBOL_GPL(lockdep_unregister_key);
void __init lockdep_init(void)
{
@@ -4283,20 +4937,24 @@ void __init lockdep_init(void)
printk("... MAX_LOCKDEP_CHAINS: %lu\n", MAX_LOCKDEP_CHAINS);
printk("... CHAINHASH_SIZE: %lu\n", CHAINHASH_SIZE);
- printk(" memory used by lock dependency info: %lu kB\n",
- (sizeof(struct lock_class) * MAX_LOCKDEP_KEYS +
- sizeof(struct list_head) * CLASSHASH_SIZE +
- sizeof(struct lock_list) * MAX_LOCKDEP_ENTRIES +
- sizeof(struct lock_chain) * MAX_LOCKDEP_CHAINS +
- sizeof(struct list_head) * CHAINHASH_SIZE
+ printk(" memory used by lock dependency info: %zu kB\n",
+ (sizeof(lock_classes) +
+ sizeof(classhash_table) +
+ sizeof(list_entries) +
+ sizeof(list_entries_in_use) +
+ sizeof(chainhash_table) +
+ sizeof(delayed_free)
#ifdef CONFIG_PROVE_LOCKING
- + sizeof(struct circular_queue)
+ + sizeof(lock_cq)
+ + sizeof(lock_chains)
+ + sizeof(lock_chains_in_use)
+ + sizeof(chain_hlocks)
#endif
) / 1024
);
- printk(" per task-struct memory footprint: %lu bytes\n",
- sizeof(struct held_lock) * MAX_LOCK_DEPTH);
+ printk(" per task-struct memory footprint: %zu bytes\n",
+ sizeof(((struct task_struct *)NULL)->held_locks));
}
static void
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 88c847a41c8a..d4c197425f68 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -22,6 +22,10 @@ enum lock_usage_bit {
LOCK_USAGE_STATES
};
+#define LOCK_USAGE_READ_MASK 1
+#define LOCK_USAGE_DIR_MASK 2
+#define LOCK_USAGE_STATE_MASK (~(LOCK_USAGE_READ_MASK | LOCK_USAGE_DIR_MASK))
+
/*
* Usage-state bitmasks:
*/
@@ -96,7 +100,8 @@ struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i);
extern unsigned long nr_lock_classes;
extern unsigned long nr_list_entries;
-extern unsigned long nr_lock_chains;
+long lockdep_next_lockchain(long i);
+unsigned long lock_chain_count(void);
extern int nr_chain_hlocks;
extern unsigned long nr_stack_trace_entries;
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 3d31f9b0059e..9c49ec645d8b 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -104,18 +104,18 @@ static const struct seq_operations lockdep_ops = {
#ifdef CONFIG_PROVE_LOCKING
static void *lc_start(struct seq_file *m, loff_t *pos)
{
+ if (*pos < 0)
+ return NULL;
+
if (*pos == 0)
return SEQ_START_TOKEN;
- if (*pos - 1 < nr_lock_chains)
- return lock_chains + (*pos - 1);
-
- return NULL;
+ return lock_chains + (*pos - 1);
}
static void *lc_next(struct seq_file *m, void *v, loff_t *pos)
{
- (*pos)++;
+ *pos = lockdep_next_lockchain(*pos - 1) + 1;
return lc_start(m, pos);
}
@@ -268,7 +268,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
#ifdef CONFIG_PROVE_LOCKING
seq_printf(m, " dependency chains: %11lu [max: %lu]\n",
- nr_lock_chains, MAX_LOCKDEP_CHAINS);
+ lock_chain_count(), MAX_LOCKDEP_CHAINS);
seq_printf(m, " dependency chain hlocks: %11d [max: %lu]\n",
nr_chain_hlocks, MAX_LOCKDEP_CHAIN_HLOCKS);
#endif
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 7d0b0ed74404..ad40a2617063 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Module-based torture test facility for locking
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright (C) IBM Corporation, 2014
*
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
* Davidlohr Bueso <dave@stgolabs.net>
* Based on kernel/rcu/torture.c.
*/
@@ -45,7 +32,7 @@
#include <linux/torture.h>
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
torture_param(int, nwriters_stress, -1,
"Number of write-locking stress-test threads");
@@ -970,7 +957,7 @@ static int __init lock_torture_init(void)
/* Prepare torture context. */
if (onoff_interval > 0) {
firsterr = torture_onoff_init(onoff_holdoff * HZ,
- onoff_interval * HZ);
+ onoff_interval * HZ, NULL);
if (firsterr)
goto unwind;
}
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 8a8c3c208c5e..5e9247dc2515 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -124,9 +124,6 @@ static inline __pure u32 encode_tail(int cpu, int idx)
{
u32 tail;
-#ifdef CONFIG_DEBUG_SPINLOCK
- BUG_ON(idx > 3);
-#endif
tail = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
@@ -412,12 +409,28 @@ pv_queue:
idx = node->count++;
tail = encode_tail(smp_processor_id(), idx);
+ /*
+ * 4 nodes are allocated based on the assumption that there will
+ * not be nested NMIs taking spinlocks. That may not be true in
+ * some architectures even though the chance of needing more than
+ * 4 nodes will still be extremely unlikely. When that happens,
+ * we fall back to spinning on the lock directly without using
+ * any MCS node. This is not the most elegant solution, but is
+ * simple enough.
+ */
+ if (unlikely(idx >= MAX_NODES)) {
+ qstat_inc(qstat_lock_no_node, true);
+ while (!queued_spin_trylock(lock))
+ cpu_relax();
+ goto release;
+ }
+
node = grab_mcs_node(node, idx);
/*
* Keep counts of non-zero index values:
*/
- qstat_inc(qstat_lock_idx1 + idx - 1, idx);
+ qstat_inc(qstat_lock_use_node2 + idx - 1, idx);
/*
* Ensure that we increment the head node->count before initialising
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 42d3d8dc8f49..d73f85388d5c 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -30,6 +30,13 @@
* pv_wait_node - # of vCPU wait's at a non-head queue node
* lock_pending - # of locking operations via pending code
* lock_slowpath - # of locking operations via MCS lock queue
+ * lock_use_node2 - # of locking operations that use 2nd per-CPU node
+ * lock_use_node3 - # of locking operations that use 3rd per-CPU node
+ * lock_use_node4 - # of locking operations that use 4th per-CPU node
+ * lock_no_node - # of locking operations without using per-CPU node
+ *
+ * Subtracting lock_use_node[234] from lock_slowpath will give you
+ * lock_use_node1.
*
* Writing to the "reset_counters" file will reset all the above counter
* values.
@@ -55,9 +62,10 @@ enum qlock_stats {
qstat_pv_wait_node,
qstat_lock_pending,
qstat_lock_slowpath,
- qstat_lock_idx1,
- qstat_lock_idx2,
- qstat_lock_idx3,
+ qstat_lock_use_node2,
+ qstat_lock_use_node3,
+ qstat_lock_use_node4,
+ qstat_lock_no_node,
qstat_num, /* Total number of statistical counters */
qstat_reset_cnts = qstat_num,
};
@@ -85,9 +93,10 @@ static const char * const qstat_names[qstat_num + 1] = {
[qstat_pv_wait_node] = "pv_wait_node",
[qstat_lock_pending] = "lock_pending",
[qstat_lock_slowpath] = "lock_slowpath",
- [qstat_lock_idx1] = "lock_index1",
- [qstat_lock_idx2] = "lock_index2",
- [qstat_lock_idx3] = "lock_index3",
+ [qstat_lock_use_node2] = "lock_use_node2",
+ [qstat_lock_use_node3] = "lock_use_node3",
+ [qstat_lock_use_node4] = "lock_use_node4",
+ [qstat_lock_no_node] = "lock_no_node",
[qstat_reset_cnts] = "reset_counters",
};
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 50d9af615dc4..fbe96341beee 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -211,9 +211,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
* Ensure issuing the wakeup (either by us or someone else)
* after setting the reader waiter to nil.
*/
- wake_q_add(wake_q, tsk);
- /* wake_q_add() already take the task ref */
- put_task_struct(tsk);
+ wake_q_add_safe(wake_q, tsk);
}
adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 939a2056c87a..37301430970e 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -87,36 +87,6 @@ config RCU_STALL_COMMON
config RCU_NEED_SEGCBLIST
def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU )
-config CONTEXT_TRACKING
- bool
-
-config CONTEXT_TRACKING_FORCE
- bool "Force context tracking"
- depends on CONTEXT_TRACKING
- default y if !NO_HZ_FULL
- help
- The major pre-requirement for full dynticks to work is to
- support the context tracking subsystem. But there are also
- other dependencies to provide in order to make the full
- dynticks working.
-
- This option stands for testing when an arch implements the
- context tracking backend but doesn't yet fullfill all the
- requirements to make the full dynticks feature working.
- Without the full dynticks, there is no way to test the support
- for context tracking and the subsystems that rely on it: RCU
- userspace extended quiescent state and tickless cputime
- accounting. This option copes with the absence of the full
- dynticks subsystem by forcing the context tracking on all
- CPUs in the system.
-
- Say Y only if you're working on the development of an
- architecture backend for the context tracking.
-
- Say N otherwise, this option brings an overhead that you
- don't want in production.
-
-
config RCU_FANOUT
int "Tree-based hierarchical RCU fanout value"
range 2 64 if 64BIT
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index a393e24a9195..acee72c0b24b 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update definitions shared among RCU implementations.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright IBM Corporation, 2011
*
- * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#ifndef __LINUX_RCU_H
@@ -30,7 +17,7 @@
#define RCU_TRACE(stmt)
#endif /* #else #ifdef CONFIG_RCU_TRACE */
-/* Offset to allow for unmatched rcu_irq_{enter,exit}(). */
+/* Offset to allow distinguishing irq vs. task-based idle entry/exit. */
#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1)
@@ -462,8 +449,6 @@ void rcu_request_urgent_qs_task(struct task_struct *t);
enum rcutorture_type {
RCU_FLAVOR,
- RCU_BH_FLAVOR,
- RCU_SCHED_FLAVOR,
RCU_TASKS_FLAVOR,
SRCU_FLAVOR,
INVALID_RCU_FLAVOR
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 5aff271adf1e..9bd5f6023c21 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* RCU segmented callback lists, function definitions
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright IBM Corporation, 2017
*
- * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/types.h>
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 948470cef385..71b64648464e 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* RCU segmented callback lists, internal-to-rcu header file
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright IBM Corporation, 2017
*
- * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/rcu_segcblist.h>
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index b459da70b4fc..c29761152874 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update module-based performance-test facility
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright (C) IBM Corporation, 2015
*
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#define pr_fmt(fmt) fmt
@@ -54,7 +41,7 @@
#include "rcu.h"
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
#define PERF_FLAG "-perf:"
#define PERFOUT_STRING(s) \
@@ -83,13 +70,19 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
* Various other use cases may of course be specified.
*/
+#ifdef MODULE
+# define RCUPERF_SHUTDOWN 0
+#else
+# define RCUPERF_SHUTDOWN 1
+#endif
+
torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
torture_param(int, nreaders, -1, "Number of RCU reader threads");
torture_param(int, nwriters, -1, "Number of RCU updater threads");
-torture_param(bool, shutdown, !IS_ENABLED(MODULE),
+torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
"Shutdown at end of performance tests.");
torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index f6e85faa4ff4..f14d1b18a74f 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update module-based torture test facility
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright (C) IBM Corporation, 2005, 2006
*
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
* Josh Triplett <josh@joshtriplett.org>
*
* See also: Documentation/RCU/torture.txt
@@ -61,7 +48,7 @@
#include "rcu.h"
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
/* Bits for ->extendables field, extendables param, and related definitions. */
@@ -1630,21 +1617,34 @@ static bool rcu_fwd_emergency_stop;
#define MIN_FWD_CB_LAUNDERS 3 /* This many CB invocations to count. */
#define MIN_FWD_CBS_LAUNDERED 100 /* Number of counted CBs. */
#define FWD_CBS_HIST_DIV 10 /* Histogram buckets/second. */
-static long n_launders_hist[2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)];
+struct rcu_launder_hist {
+ long n_launders;
+ unsigned long launder_gp_seq;
+};
+#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV))
+static struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
+static unsigned long rcu_launder_gp_seq_start;
static void rcu_torture_fwd_cb_hist(void)
{
+ unsigned long gps;
+ unsigned long gps_old;
int i;
int j;
for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
- if (n_launders_hist[i] > 0)
+ if (n_launders_hist[i].n_launders > 0)
break;
pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
__func__, jiffies - rcu_fwd_startat);
- for (j = 0; j <= i; j++)
- pr_cont(" %ds/%d: %ld",
- j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j]);
+ gps_old = rcu_launder_gp_seq_start;
+ for (j = 0; j <= i; j++) {
+ gps = n_launders_hist[j].launder_gp_seq;
+ pr_cont(" %ds/%d: %ld:%ld",
+ j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j].n_launders,
+ rcutorture_seq_diff(gps, gps_old));
+ gps_old = gps;
+ }
pr_cont("\n");
}
@@ -1666,7 +1666,8 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
if (i >= ARRAY_SIZE(n_launders_hist))
i = ARRAY_SIZE(n_launders_hist) - 1;
- n_launders_hist[i]++;
+ n_launders_hist[i].n_launders++;
+ n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq();
spin_unlock_irqrestore(&rcu_fwd_lock, flags);
}
@@ -1786,9 +1787,10 @@ static void rcu_torture_fwd_prog_cr(void)
n_max_cbs = 0;
n_max_gps = 0;
for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++)
- n_launders_hist[i] = 0;
+ n_launders_hist[i].n_launders = 0;
cver = READ_ONCE(rcu_torture_current_version);
gps = cur_ops->get_gp_seq();
+ rcu_launder_gp_seq_start = gps;
while (time_before(jiffies, stopat) &&
!READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
rfcp = READ_ONCE(rcu_fwd_cb_head);
@@ -2228,6 +2230,14 @@ static void rcu_test_debug_objects(void)
#endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
}
+static void rcutorture_sync(void)
+{
+ static unsigned long n;
+
+ if (cur_ops->sync && !(++n & 0xfff))
+ cur_ops->sync();
+}
+
static int __init
rcu_torture_init(void)
{
@@ -2389,7 +2399,8 @@ rcu_torture_init(void)
firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
if (firsterr)
goto unwind;
- firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval);
+ firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval,
+ rcutorture_sync);
if (firsterr)
goto unwind;
firsterr = rcu_torture_stall_init();
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 32dfd6522548..5d4a39a6505a 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -1,24 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion,
* tiny version for non-preemptible single-CPU use.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright (C) IBM Corporation, 2017
*
- * Author: Paul McKenney <paulmck@us.ibm.com>
+ * Author: Paul McKenney <paulmck@linux.ibm.com>
*/
#include <linux/export.h>
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 3600d88d8956..a60b8ba9e1ac 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1,24 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright (C) IBM Corporation, 2006
* Copyright (C) Fujitsu, 2012
*
- * Author: Paul McKenney <paulmck@us.ibm.com>
+ * Author: Paul McKenney <paulmck@linux.ibm.com>
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
@@ -58,6 +45,7 @@ static bool __read_mostly srcu_init_done;
static void srcu_invoke_callbacks(struct work_struct *work);
static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
static void process_srcu(struct work_struct *work);
+static void srcu_delay_timer(struct timer_list *t);
/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
#define spin_lock_rcu_node(p) \
@@ -156,7 +144,8 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp, bool is_static)
snp->grphi = cpu;
}
sdp->cpu = cpu;
- INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
+ INIT_WORK(&sdp->work, srcu_invoke_callbacks);
+ timer_setup(&sdp->delay_work, srcu_delay_timer, 0);
sdp->ssp = ssp;
sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
if (is_static)
@@ -386,13 +375,19 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
} else {
flush_delayed_work(&ssp->work);
}
- for_each_possible_cpu(cpu)
+ for_each_possible_cpu(cpu) {
+ struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
+
if (quiesced) {
- if (WARN_ON(delayed_work_pending(&per_cpu_ptr(ssp->sda, cpu)->work)))
+ if (WARN_ON(timer_pending(&sdp->delay_work)))
+ return; /* Just leak it! */
+ if (WARN_ON(work_pending(&sdp->work)))
return; /* Just leak it! */
} else {
- flush_delayed_work(&per_cpu_ptr(ssp->sda, cpu)->work);
+ del_timer_sync(&sdp->delay_work);
+ flush_work(&sdp->work);
}
+ }
if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(ssp))) {
pr_info("%s: Active srcu_struct %p state: %d\n",
@@ -463,39 +458,23 @@ static void srcu_gp_start(struct srcu_struct *ssp)
WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
}
-/*
- * Track online CPUs to guide callback workqueue placement.
- */
-DEFINE_PER_CPU(bool, srcu_online);
-void srcu_online_cpu(unsigned int cpu)
+static void srcu_delay_timer(struct timer_list *t)
{
- WRITE_ONCE(per_cpu(srcu_online, cpu), true);
-}
+ struct srcu_data *sdp = container_of(t, struct srcu_data, delay_work);
-void srcu_offline_cpu(unsigned int cpu)
-{
- WRITE_ONCE(per_cpu(srcu_online, cpu), false);
+ queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work);
}
-/*
- * Place the workqueue handler on the specified CPU if online, otherwise
- * just run it whereever. This is useful for placing workqueue handlers
- * that are to invoke the specified CPU's callbacks.
- */
-static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
- struct delayed_work *dwork,
+static void srcu_queue_delayed_work_on(struct srcu_data *sdp,
unsigned long delay)
{
- bool ret;
+ if (!delay) {
+ queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work);
+ return;
+ }
- preempt_disable();
- if (READ_ONCE(per_cpu(srcu_online, cpu)))
- ret = queue_delayed_work_on(cpu, wq, dwork, delay);
- else
- ret = queue_delayed_work(wq, dwork, delay);
- preempt_enable();
- return ret;
+ timer_reduce(&sdp->delay_work, jiffies + delay);
}
/*
@@ -504,7 +483,7 @@ static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
*/
static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
{
- srcu_queue_delayed_work_on(sdp->cpu, rcu_gp_wq, &sdp->work, delay);
+ srcu_queue_delayed_work_on(sdp, delay);
}
/*
@@ -1186,7 +1165,8 @@ static void srcu_invoke_callbacks(struct work_struct *work)
struct srcu_data *sdp;
struct srcu_struct *ssp;
- sdp = container_of(work, struct srcu_data, work.work);
+ sdp = container_of(work, struct srcu_data, work);
+
ssp = sdp->ssp;
rcu_cblist_init(&ready_cbs);
spin_lock_irq_rcu_node(sdp);
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index be10036fa621..a8304d90573f 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* RCU-based infrastructure for lightweight reader-writer locking
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright (c) 2015, Red Hat, Inc.
*
* Author: Oleg Nesterov <oleg@redhat.com>
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 5f5963ba313e..911bd9076d43 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright IBM Corporation, 2008
*
- * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
@@ -76,7 +63,7 @@ void rcu_qs(void)
* be called from hardirq context. It is normally called from the
* scheduling-clock interrupt.
*/
-void rcu_check_callbacks(int user)
+void rcu_sched_clock_irq(int user)
{
if (user) {
rcu_qs();
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 74db52a0a466..acd6ccf56faf 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1,27 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright IBM Corporation, 2008
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.com>
- * Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version
+ * Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical version
*
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
*
* For detailed explanation of Read-Copy Update mechanism see -
@@ -62,6 +49,7 @@
#include <linux/suspend.h>
#include <linux/ftrace.h>
#include <linux/tick.h>
+#include <linux/sysrq.h>
#include <linux/kprobes.h>
#include "tree.h"
@@ -116,6 +104,9 @@ int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
/* panic() on RCU Stall sysctl. */
int sysctl_panic_on_rcu_stall __read_mostly;
+/* Commandeer a sysrq key to dump RCU's tree. */
+static bool sysrq_rcu;
+module_param(sysrq_rcu, bool, 0444);
/*
* The rcu_scheduler_active variable is initialized to the value
@@ -480,7 +471,6 @@ module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next
module_param(rcu_kick_kthreads, bool, 0644);
static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
-static void force_quiescent_state(void);
static int rcu_pending(void);
/*
@@ -505,13 +495,12 @@ unsigned long rcu_exp_batches_completed(void)
EXPORT_SYMBOL_GPL(rcu_exp_batches_completed);
/*
- * Force a quiescent state.
+ * Return the root node of the rcu_state structure.
*/
-void rcu_force_quiescent_state(void)
+static struct rcu_node *rcu_get_root(void)
{
- force_quiescent_state();
+ return &rcu_state.node[0];
}
-EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
* Convert a ->gp_state value to a character string.
@@ -530,19 +519,30 @@ void show_rcu_gp_kthreads(void)
{
int cpu;
unsigned long j;
+ unsigned long ja;
+ unsigned long jr;
+ unsigned long jw;
struct rcu_data *rdp;
struct rcu_node *rnp;
- j = jiffies - READ_ONCE(rcu_state.gp_activity);
- pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %ld\n",
+ j = jiffies;
+ ja = j - READ_ONCE(rcu_state.gp_activity);
+ jr = j - READ_ONCE(rcu_state.gp_req_activity);
+ jw = j - READ_ONCE(rcu_state.gp_wake_time);
+ pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
rcu_state.name, gp_state_getname(rcu_state.gp_state),
- rcu_state.gp_state, rcu_state.gp_kthread->state, j);
+ rcu_state.gp_state,
+ rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
+ ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
+ (long)READ_ONCE(rcu_state.gp_seq),
+ (long)READ_ONCE(rcu_get_root()->gp_seq_needed),
+ READ_ONCE(rcu_state.gp_flags));
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
continue;
- pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
- rnp->grplo, rnp->grphi, rnp->gp_seq,
- rnp->gp_seq_needed);
+ pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
+ rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
+ (long)rnp->gp_seq_needed);
if (!rcu_is_leaf_node(rnp))
continue;
for_each_leaf_node_possible_cpu(rnp, cpu) {
@@ -551,14 +551,35 @@ void show_rcu_gp_kthreads(void)
ULONG_CMP_GE(rcu_state.gp_seq,
rdp->gp_seq_needed))
continue;
- pr_info("\tcpu %d ->gp_seq_needed %lu\n",
- cpu, rdp->gp_seq_needed);
+ pr_info("\tcpu %d ->gp_seq_needed %ld\n",
+ cpu, (long)rdp->gp_seq_needed);
}
}
/* sched_show_task(rcu_state.gp_kthread); */
}
EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
+/* Dump grace-period-request information due to commandeered sysrq. */
+static void sysrq_show_rcu(int key)
+{
+ show_rcu_gp_kthreads();
+}
+
+static struct sysrq_key_op sysrq_rcudump_op = {
+ .handler = sysrq_show_rcu,
+ .help_msg = "show-rcu(y)",
+ .action_msg = "Show RCU tree",
+ .enable_mask = SYSRQ_ENABLE_DUMP,
+};
+
+static int __init rcu_sysrq_init(void)
+{
+ if (sysrq_rcu)
+ return register_sysrq_key('y', &sysrq_rcudump_op);
+ return 0;
+}
+early_initcall(rcu_sysrq_init);
+
/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
@@ -567,8 +588,6 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
{
switch (test_type) {
case RCU_FLAVOR:
- case RCU_BH_FLAVOR:
- case RCU_SCHED_FLAVOR:
*flags = READ_ONCE(rcu_state.gp_flags);
*gp_seq = rcu_seq_current(&rcu_state.gp_seq);
break;
@@ -579,14 +598,6 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
/*
- * Return the root node of the rcu_state structure.
- */
-static struct rcu_node *rcu_get_root(void)
-{
- return &rcu_state.node[0];
-}
-
-/*
* Enter an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*
@@ -702,7 +713,6 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
/**
* rcu_nmi_exit - inform RCU of exit from NMI context
- * @irq: Is this call from rcu_irq_exit?
*
* If you add or remove a call to rcu_nmi_exit(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
@@ -1117,7 +1127,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
}
/*
- * NO_HZ_FULL CPUs can run in-kernel without rcu_check_callbacks!
+ * NO_HZ_FULL CPUs can run in-kernel without rcu_sched_clock_irq!
* The above code handles this, but only for straight cond_resched().
* And some in-kernel loops check need_resched() before calling
* cond_resched(), which defeats the above code for CPUs that are
@@ -1183,7 +1193,7 @@ static void rcu_check_gp_kthread_starvation(void)
pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
rcu_state.name, j,
(long)rcu_seq_current(&rcu_state.gp_seq),
- rcu_state.gp_flags,
+ READ_ONCE(rcu_state.gp_flags),
gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
if (gpk) {
@@ -1312,7 +1322,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
panic_on_rcu_stall();
- force_quiescent_state(); /* Kick them all. */
+ rcu_force_quiescent_state(); /* Kick them all. */
}
static void print_cpu_stall(void)
@@ -1559,17 +1569,28 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
}
/*
- * Awaken the grace-period kthread. Don't do a self-awaken, and don't
- * bother awakening when there is nothing for the grace-period kthread
- * to do (as in several CPUs raced to awaken, and we lost), and finally
- * don't try to awaken a kthread that has not yet been created.
+ * Awaken the grace-period kthread. Don't do a self-awaken (unless in
+ * an interrupt or softirq handler), and don't bother awakening when there
+ * is nothing for the grace-period kthread to do (as in several CPUs raced
+ * to awaken, and we lost), and finally don't try to awaken a kthread that
+ * has not yet been created. If all those checks are passed, track some
+ * debug information and awaken.
+ *
+ * So why do the self-wakeup when in an interrupt or softirq handler
+ * in the grace-period kthread's context? Because the kthread might have
+ * been interrupted just as it was going to sleep, and just after the final
+ * pre-sleep check of the awaken condition. In this case, a wakeup really
+ * is required, and is therefore supplied.
*/
static void rcu_gp_kthread_wake(void)
{
- if (current == rcu_state.gp_kthread ||
+ if ((current == rcu_state.gp_kthread &&
+ !in_interrupt() && !in_serving_softirq()) ||
!READ_ONCE(rcu_state.gp_flags) ||
!rcu_state.gp_kthread)
return;
+ WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
+ WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
swake_up_one(&rcu_state.gp_wq);
}
@@ -1713,7 +1734,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
zero_cpu_stall_ticks(rdp);
}
rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */
- if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap)
+ if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
rdp->gp_seq_needed = rnp->gp_seq_needed;
WRITE_ONCE(rdp->gpwrap, false);
rcu_gpnum_ovf(rnp, rdp);
@@ -1941,7 +1962,7 @@ static void rcu_gp_fqs_loop(void)
if (!ret) {
rcu_state.jiffies_force_qs = jiffies + j;
WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
- jiffies + 3 * j);
+ jiffies + (j ? 3 * j : 2));
}
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
@@ -2499,14 +2520,14 @@ static void rcu_do_batch(struct rcu_data *rdp)
}
/*
- * Check to see if this CPU is in a non-context-switch quiescent state
- * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
- * Also schedule RCU core processing.
- *
- * This function must be called from hardirq context. It is normally
- * invoked from the scheduling-clock interrupt.
+ * This function is invoked from each scheduling-clock interrupt,
+ * and checks to see if this CPU is in a non-context-switch quiescent
+ * state, for example, user mode or idle loop. It also schedules RCU
+ * core processing. If the current grace period has gone on too long,
+ * it will ask the scheduler to manufacture a context switch for the sole
+ * purpose of providing a providing the needed quiescent state.
*/
-void rcu_check_callbacks(int user)
+void rcu_sched_clock_irq(int user)
{
trace_rcu_utilization(TPS("Start scheduler-tick"));
raw_cpu_inc(rcu_data.ticks_this_gp);
@@ -2519,7 +2540,7 @@ void rcu_check_callbacks(int user)
}
__this_cpu_write(rcu_data.rcu_urgent_qs, false);
}
- rcu_flavor_check_callbacks(user);
+ rcu_flavor_sched_clock_irq(user);
if (rcu_pending())
invoke_rcu_core();
@@ -2580,7 +2601,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
* Force quiescent states on reluctant CPUs, and also detect which
* CPUs are in dyntick-idle mode.
*/
-static void force_quiescent_state(void)
+void rcu_force_quiescent_state(void)
{
unsigned long flags;
bool ret;
@@ -2612,6 +2633,7 @@ static void force_quiescent_state(void)
raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
rcu_gp_kthread_wake();
}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
* This function checks for grace-period requests that fail to motivate
@@ -2659,16 +2681,11 @@ rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
- pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
- __func__, (long)READ_ONCE(rcu_state.gp_seq),
- (long)READ_ONCE(rnp_root->gp_seq_needed),
- j - rcu_state.gp_req_activity, j - rcu_state.gp_activity,
- rcu_state.gp_flags, rcu_state.gp_state, rcu_state.name,
- rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL);
WARN_ON(1);
if (rnp_root != rnp)
raw_spin_unlock_rcu_node(rnp_root);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ show_rcu_gp_kthreads();
}
/*
@@ -2713,12 +2730,8 @@ void rcu_fwd_progress_check(unsigned long j)
}
EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
-/*
- * This does the RCU core processing work for the specified rcu_data
- * structures. This may be called only from the CPU to whom the rdp
- * belongs.
- */
-static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
+/* Perform RCU core processing work for the current CPU. */
+static __latent_entropy void rcu_core(struct softirq_action *unused)
{
unsigned long flags;
struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
@@ -2803,9 +2816,9 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
/*
* Force the grace period if too many callbacks or too long waiting.
- * Enforce hysteresis, and don't invoke force_quiescent_state()
+ * Enforce hysteresis, and don't invoke rcu_force_quiescent_state()
* if some other CPU has recently done so. Also, don't bother
- * invoking force_quiescent_state() if the newly enqueued callback
+ * invoking rcu_force_quiescent_state() if the newly enqueued callback
* is the only one waiting for a grace period to complete.
*/
if (unlikely(rcu_segcblist_n_cbs(&rdp->cblist) >
@@ -2822,7 +2835,7 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
rdp->blimit = LONG_MAX;
if (rcu_state.n_force_qs == rdp->n_force_qs_snap &&
rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
- force_quiescent_state();
+ rcu_force_quiescent_state();
rdp->n_force_qs_snap = rcu_state.n_force_qs;
rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
}
@@ -2891,9 +2904,6 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy)
rcu_segcblist_init(&rdp->cblist);
}
rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
- if (!lazy)
- rcu_idle_count_callbacks_posted();
-
if (__is_kfree_rcu_offset((unsigned long)func))
trace_rcu_kfree_callback(rcu_state.name, head,
(unsigned long)func,
@@ -2963,6 +2973,79 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
}
EXPORT_SYMBOL_GPL(kfree_call_rcu);
+/*
+ * During early boot, any blocking grace-period wait automatically
+ * implies a grace period. Later on, this is never the case for PREEMPT.
+ *
+ * Howevr, because a context switch is a grace period for !PREEMPT, any
+ * blocking grace-period wait automatically implies a grace period if
+ * there is only one CPU online at any point time during execution of
+ * either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to
+ * occasionally incorrectly indicate that there are multiple CPUs online
+ * when there was in fact only one the whole time, as this just adds some
+ * overhead: RCU still operates correctly.
+ */
+static int rcu_blocking_is_gp(void)
+{
+ int ret;
+
+ if (IS_ENABLED(CONFIG_PREEMPT))
+ return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
+ might_sleep(); /* Check for RCU read-side critical section. */
+ preempt_disable();
+ ret = num_online_cpus() <= 1;
+ preempt_enable();
+ return ret;
+}
+
+/**
+ * synchronize_rcu - wait until a grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full grace
+ * period has elapsed, in other words after all currently executing RCU
+ * read-side critical sections have completed. Note, however, that
+ * upon return from synchronize_rcu(), the caller might well be executing
+ * concurrently with new RCU read-side critical sections that began while
+ * synchronize_rcu() was waiting. RCU read-side critical sections are
+ * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
+ * In addition, regions of code across which interrupts, preemption, or
+ * softirqs have been disabled also serve as RCU read-side critical
+ * sections. This includes hardware interrupt handlers, softirq handlers,
+ * and NMI handlers.
+ *
+ * Note that this guarantee implies further memory-ordering guarantees.
+ * On systems with more than one CPU, when synchronize_rcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last RCU read-side critical section whose beginning
+ * preceded the call to synchronize_rcu(). In addition, each CPU having
+ * an RCU read-side critical section that extends beyond the return from
+ * synchronize_rcu() is guaranteed to have executed a full memory barrier
+ * after the beginning of synchronize_rcu() and before the beginning of
+ * that RCU read-side critical section. Note that these guarantees include
+ * CPUs that are offline, idle, or executing in user mode, as well as CPUs
+ * that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_rcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_rcu() -- even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ */
+void synchronize_rcu(void)
+{
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+ lock_is_held(&rcu_lock_map) ||
+ lock_is_held(&rcu_sched_lock_map),
+ "Illegal synchronize_rcu() in RCU read-side critical section");
+ if (rcu_blocking_is_gp())
+ return;
+ if (rcu_gp_is_expedited())
+ synchronize_rcu_expedited();
+ else
+ wait_rcu_gp(call_rcu);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu);
+
/**
* get_state_synchronize_rcu - Snapshot current RCU state
*
@@ -3051,28 +3134,6 @@ static int rcu_pending(void)
}
/*
- * Return true if the specified CPU has any callback. If all_lazy is
- * non-NULL, store an indication of whether all callbacks are lazy.
- * (If there are no callbacks, all of them are deemed to be lazy.)
- */
-static bool rcu_cpu_has_callbacks(bool *all_lazy)
-{
- bool al = true;
- bool hc = false;
- struct rcu_data *rdp;
-
- rdp = this_cpu_ptr(&rcu_data);
- if (!rcu_segcblist_empty(&rdp->cblist)) {
- hc = true;
- if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist))
- al = false;
- }
- if (all_lazy)
- *all_lazy = al;
- return hc;
-}
-
-/*
* Helper function for rcu_barrier() tracing. If tracing is disabled,
* the compiler is expected to optimize this away.
*/
@@ -3301,7 +3362,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcu_prepare_kthreads(cpu);
- rcu_spawn_all_nocb_kthreads(cpu);
+ rcu_spawn_cpu_nocb_kthread(cpu);
return 0;
}
@@ -3331,8 +3392,6 @@ int rcutree_online_cpu(unsigned int cpu)
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rnp->ffmask |= rdp->grpmask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- if (IS_ENABLED(CONFIG_TREE_SRCU))
- srcu_online_cpu(cpu);
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return 0; /* Too early in boot for scheduler work. */
sync_sched_exp_online_cleanup(cpu);
@@ -3357,8 +3416,6 @@ int rcutree_offline_cpu(unsigned int cpu)
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcutree_affinity_setting(cpu, cpu);
- if (IS_ENABLED(CONFIG_TREE_SRCU))
- srcu_offline_cpu(cpu);
return 0;
}
@@ -3779,7 +3836,7 @@ void __init rcu_init(void)
rcu_init_one();
if (dump_tree)
rcu_dump_rcu_node_tree();
- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+ open_softirq(RCU_SOFTIRQ, rcu_core);
/*
* We don't need protection against CPU-hotplug here because
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index d90b02b53c0e..bb4f995f2d3f 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -1,25 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
* Internal non-public definitions.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright IBM Corporation, 2008
*
* Author: Ingo Molnar <mingo@elte.hu>
- * Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/cache.h>
@@ -36,7 +23,6 @@
/* Communicate arguments to a workqueue handler. */
struct rcu_exp_work {
- smp_call_func_t rew_func;
unsigned long rew_s;
struct work_struct rew_work;
};
@@ -194,10 +180,7 @@ struct rcu_data {
bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */
bool rcu_urgent_qs; /* GP old need light quiescent state. */
#ifdef CONFIG_RCU_FAST_NO_HZ
- bool all_lazy; /* Are all CPU's CBs lazy? */
- unsigned long nonlazy_posted; /* # times non-lazy CB posted to CPU. */
- unsigned long nonlazy_posted_snap;
- /* Nonlazy_posted snapshot. */
+ bool all_lazy; /* All CPU's CBs lazy at idle start? */
unsigned long last_accelerate; /* Last jiffy CBs were accelerated. */
unsigned long last_advance_all; /* Last jiffy CBs were all advanced. */
int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
@@ -234,7 +217,13 @@ struct rcu_data {
/* Leader CPU takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- /* 6) Diagnostic data, including RCU CPU stall warnings. */
+ /* 6) RCU priority boosting. */
+ struct task_struct *rcu_cpu_kthread_task;
+ /* rcuc per-CPU kthread or NULL. */
+ unsigned int rcu_cpu_kthread_status;
+ char rcu_cpu_has_work;
+
+ /* 7) Diagnostic data, including RCU CPU stall warnings. */
unsigned int softirq_snap; /* Snapshot of softirq activity. */
/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
struct irq_work rcu_iw; /* Check for non-irq activity. */
@@ -303,6 +292,8 @@ struct rcu_state {
struct swait_queue_head gp_wq; /* Where GP task waits. */
short gp_flags; /* Commands for GP task. */
short gp_state; /* GP kthread sleep state. */
+ unsigned long gp_wake_time; /* Last GP kthread wake. */
+ unsigned long gp_wake_seq; /* ->gp_seq at ^^^. */
/* End of fields guarded by root rcu_node's lock. */
@@ -402,13 +393,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
int rcu_dynticks_snap(struct rcu_data *rdp);
-#ifdef CONFIG_RCU_BOOST
-DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
-DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
-DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-DECLARE_PER_CPU(char, rcu_cpu_has_work);
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
/* Forward declarations for rcutree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_qs(void);
@@ -420,7 +404,7 @@ static void rcu_print_detail_task_stall(void);
static int rcu_print_task_stall(struct rcu_node *rnp);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
-static void rcu_flavor_check_callbacks(int user);
+static void rcu_flavor_sched_clock_irq(int user);
void call_rcu(struct rcu_head *head, rcu_callback_t func);
static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
@@ -431,7 +415,6 @@ static void __init rcu_spawn_boost_kthreads(void);
static void rcu_prepare_kthreads(int cpu);
static void rcu_cleanup_after_idle(void);
static void rcu_prepare_for_idle(void);
-static void rcu_idle_count_callbacks_posted(void);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
static void rcu_preempt_deferred_qs(struct task_struct *t);
@@ -451,7 +434,7 @@ static bool rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
-static void rcu_spawn_all_nocb_kthreads(int cpu);
+static void rcu_spawn_cpu_nocb_kthread(int cpu);
static void __init rcu_spawn_nocb_kthreads(void);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(void);
@@ -462,11 +445,3 @@ static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(void);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
-
-#ifdef CONFIG_SRCU
-void srcu_online_cpu(unsigned int cpu);
-void srcu_offline_cpu(unsigned int cpu);
-#else /* #ifdef CONFIG_SRCU */
-void srcu_online_cpu(unsigned int cpu) { }
-void srcu_offline_cpu(unsigned int cpu) { }
-#endif /* #else #ifdef CONFIG_SRCU */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 928fe5893a57..4c2a0189e748 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -1,27 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* RCU expedited grace periods
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright IBM Corporation, 2016
*
- * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/lockdep.h>
+static void rcu_exp_handler(void *unused);
+
/*
* Record the start of an expedited grace period.
*/
@@ -344,7 +333,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
{
int cpu;
unsigned long flags;
- smp_call_func_t func;
unsigned long mask_ofl_test;
unsigned long mask_ofl_ipi;
int ret;
@@ -352,7 +340,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
container_of(wp, struct rcu_exp_work, rew_work);
struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
- func = rewp->rew_func;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
/* Each pass checks a CPU for identity, offline, and idle. */
@@ -396,7 +383,7 @@ retry_ipi:
mask_ofl_test |= mask;
continue;
}
- ret = smp_call_function_single(cpu, func, NULL, 0);
+ ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
if (!ret) {
mask_ofl_ipi &= ~mask;
continue;
@@ -426,7 +413,7 @@ retry_ipi:
* Select the nodes that the upcoming expedited grace period needs
* to wait for.
*/
-static void sync_rcu_exp_select_cpus(smp_call_func_t func)
+static void sync_rcu_exp_select_cpus(void)
{
int cpu;
struct rcu_node *rnp;
@@ -440,7 +427,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
rnp->exp_need_flush = false;
if (!READ_ONCE(rnp->expmask))
continue; /* Avoid early boot non-existent wq. */
- rnp->rew.rew_func = func;
if (!READ_ONCE(rcu_par_gp_wq) ||
rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
rcu_is_last_leaf_node(rnp)) {
@@ -449,7 +435,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
continue;
}
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
- preempt_disable();
cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
/* If all offline, queue the work on an unbound CPU. */
if (unlikely(cpu > rnp->grphi - rnp->grplo))
@@ -457,7 +442,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
else
cpu += rnp->grplo;
queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
- preempt_enable();
rnp->exp_need_flush = true;
}
@@ -580,10 +564,10 @@ static void rcu_exp_wait_wake(unsigned long s)
* Common code to drive an expedited grace period forward, used by
* workqueues and mid-boot-time tasks.
*/
-static void rcu_exp_sel_wait_wake(smp_call_func_t func, unsigned long s)
+static void rcu_exp_sel_wait_wake(unsigned long s)
{
/* Initialize the rcu_node tree in preparation for the wait. */
- sync_rcu_exp_select_cpus(func);
+ sync_rcu_exp_select_cpus();
/* Wait and clean up, including waking everyone. */
rcu_exp_wait_wake(s);
@@ -597,52 +581,7 @@ static void wait_rcu_exp_gp(struct work_struct *wp)
struct rcu_exp_work *rewp;
rewp = container_of(wp, struct rcu_exp_work, rew_work);
- rcu_exp_sel_wait_wake(rewp->rew_func, rewp->rew_s);
-}
-
-/*
- * Given a smp_call_function() handler, kick off the specified
- * implementation of expedited grace period.
- */
-static void _synchronize_rcu_expedited(smp_call_func_t func)
-{
- struct rcu_data *rdp;
- struct rcu_exp_work rew;
- struct rcu_node *rnp;
- unsigned long s;
-
- /* If expedited grace periods are prohibited, fall back to normal. */
- if (rcu_gp_is_normal()) {
- wait_rcu_gp(call_rcu);
- return;
- }
-
- /* Take a snapshot of the sequence number. */
- s = rcu_exp_gp_seq_snap();
- if (exp_funnel_lock(s))
- return; /* Someone else did our work for us. */
-
- /* Ensure that load happens before action based on it. */
- if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
- /* Direct call during scheduler init and early_initcalls(). */
- rcu_exp_sel_wait_wake(func, s);
- } else {
- /* Marshall arguments & schedule the expedited grace period. */
- rew.rew_func = func;
- rew.rew_s = s;
- INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
- queue_work(rcu_gp_wq, &rew.rew_work);
- }
-
- /* Wait for expedited grace period to complete. */
- rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
- rnp = rcu_get_root();
- wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
- sync_exp_work_done(s));
- smp_mb(); /* Workqueue actions happen before return. */
-
- /* Let the next expedited grace period start. */
- mutex_unlock(&rcu_state.exp_mutex);
+ rcu_exp_sel_wait_wake(rewp->rew_s);
}
#ifdef CONFIG_PREEMPT_RCU
@@ -654,7 +593,7 @@ static void _synchronize_rcu_expedited(smp_call_func_t func)
* ->expmask fields in the rcu_node tree. Otherwise, immediately
* report the quiescent state.
*/
-static void sync_rcu_exp_handler(void *unused)
+static void rcu_exp_handler(void *unused)
{
unsigned long flags;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -697,6 +636,7 @@ static void sync_rcu_exp_handler(void *unused)
WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ return;
}
/*
@@ -730,43 +670,10 @@ static void sync_sched_exp_online_cleanup(int cpu)
{
}
-/**
- * synchronize_rcu_expedited - Brute-force RCU grace period
- *
- * Wait for an RCU-preempt grace period, but expedite it. The basic
- * idea is to IPI all non-idle non-nohz online CPUs. The IPI handler
- * checks whether the CPU is in an RCU-preempt critical section, and
- * if so, it sets a flag that causes the outermost rcu_read_unlock()
- * to report the quiescent state. On the other hand, if the CPU is
- * not in an RCU read-side critical section, the IPI handler reports
- * the quiescent state immediately.
- *
- * Although this is a greate improvement over previous expedited
- * implementations, it is still unfriendly to real-time workloads, so is
- * thus not recommended for any sort of common-case code. In fact, if
- * you are using synchronize_rcu_expedited() in a loop, please restructure
- * your code to batch your updates, and then Use a single synchronize_rcu()
- * instead.
- *
- * This has the same semantics as (but is more brutal than) synchronize_rcu().
- */
-void synchronize_rcu_expedited(void)
-{
- RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
- lock_is_held(&rcu_lock_map) ||
- lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
-
- if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
- return;
- _synchronize_rcu_expedited(sync_rcu_exp_handler);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
-
#else /* #ifdef CONFIG_PREEMPT_RCU */
/* Invoked on each online non-idle CPU for expedited quiescent state. */
-static void sync_sched_exp_handler(void *unused)
+static void rcu_exp_handler(void *unused)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
@@ -798,44 +705,78 @@ static void sync_sched_exp_online_cleanup(int cpu)
rnp = rdp->mynode;
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
return;
- ret = smp_call_function_single(cpu, sync_sched_exp_handler, NULL, 0);
+ ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
WARN_ON_ONCE(ret);
}
-/*
- * Because a context switch is a grace period for !PREEMPT, any
- * blocking grace-period wait automatically implies a grace period if
- * there is only one CPU online at any point time during execution of
- * either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to
- * occasionally incorrectly indicate that there are multiple CPUs online
- * when there was in fact only one the whole time, as this just adds some
- * overhead: RCU still operates correctly.
- */
-static int rcu_blocking_is_gp(void)
-{
- int ret;
-
- might_sleep(); /* Check for RCU read-side critical section. */
- preempt_disable();
- ret = num_online_cpus() <= 1;
- preempt_enable();
- return ret;
-}
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-/* PREEMPT=n implementation of synchronize_rcu_expedited(). */
+/**
+ * synchronize_rcu_expedited - Brute-force RCU grace period
+ *
+ * Wait for an RCU grace period, but expedite it. The basic idea is to
+ * IPI all non-idle non-nohz online CPUs. The IPI handler checks whether
+ * the CPU is in an RCU critical section, and if so, it sets a flag that
+ * causes the outermost rcu_read_unlock() to report the quiescent state
+ * for RCU-preempt or asks the scheduler for help for RCU-sched. On the
+ * other hand, if the CPU is not in an RCU read-side critical section,
+ * the IPI handler reports the quiescent state immediately.
+ *
+ * Although this is a greate improvement over previous expedited
+ * implementations, it is still unfriendly to real-time workloads, so is
+ * thus not recommended for any sort of common-case code. In fact, if
+ * you are using synchronize_rcu_expedited() in a loop, please restructure
+ * your code to batch your updates, and then Use a single synchronize_rcu()
+ * instead.
+ *
+ * This has the same semantics as (but is more brutal than) synchronize_rcu().
+ */
void synchronize_rcu_expedited(void)
{
+ struct rcu_data *rdp;
+ struct rcu_exp_work rew;
+ struct rcu_node *rnp;
+ unsigned long s;
+
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu_expedited() in RCU read-side critical section");
- /* If only one CPU, this is automatically a grace period. */
+ /* Is the state is such that the call is a grace period? */
if (rcu_blocking_is_gp())
return;
- _synchronize_rcu_expedited(sync_sched_exp_handler);
+ /* If expedited grace periods are prohibited, fall back to normal. */
+ if (rcu_gp_is_normal()) {
+ wait_rcu_gp(call_rcu);
+ return;
+ }
+
+ /* Take a snapshot of the sequence number. */
+ s = rcu_exp_gp_seq_snap();
+ if (exp_funnel_lock(s))
+ return; /* Someone else did our work for us. */
+
+ /* Ensure that load happens before action based on it. */
+ if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
+ /* Direct call during scheduler init and early_initcalls(). */
+ rcu_exp_sel_wait_wake(s);
+ } else {
+ /* Marshall arguments & schedule the expedited grace period. */
+ rew.rew_s = s;
+ INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
+ queue_work(rcu_gp_wq, &rew.rew_work);
+ }
+
+ /* Wait for expedited grace period to complete. */
+ rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
+ rnp = rcu_get_root();
+ wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
+ sync_exp_work_done(s));
+ smp_mb(); /* Workqueue actions happen before return. */
+
+ /* Let the next expedited grace period start. */
+ mutex_unlock(&rcu_state.exp_mutex);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
-
-#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 1b3dd2fc0cd6..97dba50f6fb2 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1,27 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
* Internal non-public definitions that provide either classic
* or preemptible semantics.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright Red Hat, 2009
* Copyright IBM Corporation, 2009
*
* Author: Ingo Molnar <mingo@elte.hu>
- * Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/delay.h>
@@ -34,17 +21,7 @@
#include "../time/tick-internal.h"
#ifdef CONFIG_RCU_BOOST
-
#include "../locking/rtmutex_common.h"
-
-/*
- * Control variables for per-CPU and per-rcu_node kthreads.
- */
-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-DEFINE_PER_CPU(char, rcu_cpu_has_work);
-
#else /* #ifdef CONFIG_RCU_BOOST */
/*
@@ -307,7 +284,7 @@ static void rcu_qs(void)
__this_cpu_read(rcu_data.gp_seq),
TPS("cpuqs"));
__this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
- barrier(); /* Coordinate with rcu_flavor_check_callbacks(). */
+ barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */
current->rcu_read_unlock_special.b.need_qs = false;
}
}
@@ -788,13 +765,13 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
}
/*
- * Check for a quiescent state from the current CPU. When a task blocks,
- * the task is recorded in the corresponding CPU's rcu_node structure,
- * which is checked elsewhere.
- *
- * Caller must disable hard irqs.
+ * Check for a quiescent state from the current CPU, including voluntary
+ * context switches for Tasks RCU. When a task blocks, the task is
+ * recorded in the corresponding CPU's rcu_node structure, which is checked
+ * elsewhere, hence this function need only check for quiescent states
+ * related to the current CPU, not to those related to tasks.
*/
-static void rcu_flavor_check_callbacks(int user)
+static void rcu_flavor_sched_clock_irq(int user)
{
struct task_struct *t = current;
@@ -825,54 +802,6 @@ static void rcu_flavor_check_callbacks(int user)
t->rcu_read_unlock_special.b.need_qs = true;
}
-/**
- * synchronize_rcu - wait until a grace period has elapsed.
- *
- * Control will return to the caller some time after a full grace
- * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed. Note, however, that
- * upon return from synchronize_rcu(), the caller might well be executing
- * concurrently with new RCU read-side critical sections that began while
- * synchronize_rcu() was waiting. RCU read-side critical sections are
- * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
- * In addition, regions of code across which interrupts, preemption, or
- * softirqs have been disabled also serve as RCU read-side critical
- * sections. This includes hardware interrupt handlers, softirq handlers,
- * and NMI handlers.
- *
- * Note that this guarantee implies further memory-ordering guarantees.
- * On systems with more than one CPU, when synchronize_rcu() returns,
- * each CPU is guaranteed to have executed a full memory barrier since
- * the end of its last RCU read-side critical section whose beginning
- * preceded the call to synchronize_rcu(). In addition, each CPU having
- * an RCU read-side critical section that extends beyond the return from
- * synchronize_rcu() is guaranteed to have executed a full memory barrier
- * after the beginning of synchronize_rcu() and before the beginning of
- * that RCU read-side critical section. Note that these guarantees include
- * CPUs that are offline, idle, or executing in user mode, as well as CPUs
- * that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked synchronize_rcu(), which returned
- * to its caller on CPU B, then both CPU A and CPU B are guaranteed
- * to have executed a full memory barrier during the execution of
- * synchronize_rcu() -- even if CPU A and CPU B are the same CPU (but
- * again only if the system has more than one CPU).
- */
-void synchronize_rcu(void)
-{
- RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
- lock_is_held(&rcu_lock_map) ||
- lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_rcu() in RCU read-side critical section");
- if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
- return;
- if (rcu_gp_is_expedited())
- synchronize_rcu_expedited();
- else
- wait_rcu_gp(call_rcu);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu);
-
/*
* Check for a task exiting while in a preemptible-RCU read-side
* critical section, clean up if so. No need to issue warnings,
@@ -1088,14 +1017,10 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
}
/*
- * Check to see if this CPU is in a non-context-switch quiescent state
- * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
- * Also schedule RCU core processing.
- *
- * This function must be called from hardirq context. It is normally
- * invoked from the scheduling-clock interrupt.
+ * Check to see if this CPU is in a non-context-switch quiescent state,
+ * namely user mode and idle loop.
*/
-static void rcu_flavor_check_callbacks(int user)
+static void rcu_flavor_sched_clock_irq(int user)
{
if (user || rcu_is_cpu_rrupt_from_idle()) {
@@ -1115,22 +1040,6 @@ static void rcu_flavor_check_callbacks(int user)
}
}
-/* PREEMPT=n implementation of synchronize_rcu(). */
-void synchronize_rcu(void)
-{
- RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
- lock_is_held(&rcu_lock_map) ||
- lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_rcu() in RCU read-side critical section");
- if (rcu_blocking_is_gp())
- return;
- if (rcu_gp_is_expedited())
- synchronize_rcu_expedited();
- else
- wait_rcu_gp(call_rcu);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu);
-
/*
* Because preemptible RCU does not exist, tasks cannot possibly exit
* while in preemptible RCU read-side critical sections.
@@ -1307,11 +1216,11 @@ static void invoke_rcu_callbacks_kthread(void)
unsigned long flags;
local_irq_save(flags);
- __this_cpu_write(rcu_cpu_has_work, 1);
- if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
- current != __this_cpu_read(rcu_cpu_kthread_task)) {
- rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task),
- __this_cpu_read(rcu_cpu_kthread_status));
+ __this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
+ if (__this_cpu_read(rcu_data.rcu_cpu_kthread_task) != NULL &&
+ current != __this_cpu_read(rcu_data.rcu_cpu_kthread_task)) {
+ rcu_wake_cond(__this_cpu_read(rcu_data.rcu_cpu_kthread_task),
+ __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
}
local_irq_restore(flags);
}
@@ -1322,7 +1231,7 @@ static void invoke_rcu_callbacks_kthread(void)
*/
static bool rcu_is_callbacks_kthread(void)
{
- return __this_cpu_read(rcu_cpu_kthread_task) == current;
+ return __this_cpu_read(rcu_data.rcu_cpu_kthread_task) == current;
}
#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
@@ -1369,11 +1278,6 @@ static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
return 0;
}
-static void rcu_kthread_do_work(void)
-{
- rcu_do_batch(this_cpu_ptr(&rcu_data));
-}
-
static void rcu_cpu_kthread_setup(unsigned int cpu)
{
struct sched_param sp;
@@ -1384,12 +1288,12 @@ static void rcu_cpu_kthread_setup(unsigned int cpu)
static void rcu_cpu_kthread_park(unsigned int cpu)
{
- per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+ per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
}
static int rcu_cpu_kthread_should_run(unsigned int cpu)
{
- return __this_cpu_read(rcu_cpu_has_work);
+ return __this_cpu_read(rcu_data.rcu_cpu_has_work);
}
/*
@@ -1399,21 +1303,20 @@ static int rcu_cpu_kthread_should_run(unsigned int cpu)
*/
static void rcu_cpu_kthread(unsigned int cpu)
{
- unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
- char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
+ unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
+ char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
int spincnt;
for (spincnt = 0; spincnt < 10; spincnt++) {
trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
local_bh_disable();
*statusp = RCU_KTHREAD_RUNNING;
- this_cpu_inc(rcu_cpu_kthread_loops);
local_irq_disable();
work = *workp;
*workp = 0;
local_irq_enable();
if (work)
- rcu_kthread_do_work();
+ rcu_do_batch(this_cpu_ptr(&rcu_data));
local_bh_enable();
if (*workp == 0) {
trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
@@ -1459,7 +1362,7 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
}
static struct smp_hotplug_thread rcu_cpu_thread_spec = {
- .store = &rcu_cpu_kthread_task,
+ .store = &rcu_data.rcu_cpu_kthread_task,
.thread_should_run = rcu_cpu_kthread_should_run,
.thread_fn = rcu_cpu_kthread,
.thread_comm = "rcuc/%u",
@@ -1476,7 +1379,7 @@ static void __init rcu_spawn_boost_kthreads(void)
int cpu;
for_each_possible_cpu(cpu)
- per_cpu(rcu_cpu_has_work, cpu) = 0;
+ per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0;
if (WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcub kthread, OOM is now expected behavior\n", __func__))
return;
rcu_for_each_leaf_node(rnp)
@@ -1543,7 +1446,7 @@ static void rcu_prepare_kthreads(int cpu)
int rcu_needs_cpu(u64 basemono, u64 *nextevt)
{
*nextevt = KTIME_MAX;
- return rcu_cpu_has_callbacks(NULL);
+ return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist);
}
/*
@@ -1562,14 +1465,6 @@ static void rcu_prepare_for_idle(void)
{
}
-/*
- * Don't bother keeping a running count of the number of RCU callbacks
- * posted because CONFIG_RCU_FAST_NO_HZ=n.
- */
-static void rcu_idle_count_callbacks_posted(void)
-{
-}
-
#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
/*
@@ -1652,11 +1547,8 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
lockdep_assert_irqs_disabled();
- /* Snapshot to detect later posting of non-lazy callback. */
- rdp->nonlazy_posted_snap = rdp->nonlazy_posted;
-
/* If no callbacks, RCU doesn't need the CPU. */
- if (!rcu_cpu_has_callbacks(&rdp->all_lazy)) {
+ if (rcu_segcblist_empty(&rdp->cblist)) {
*nextevt = KTIME_MAX;
return 0;
}
@@ -1670,11 +1562,12 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
rdp->last_accelerate = jiffies;
/* Request timer delay depending on laziness, and round. */
- if (!rdp->all_lazy) {
+ rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist);
+ if (rdp->all_lazy) {
+ dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
+ } else {
dj = round_up(rcu_idle_gp_delay + jiffies,
rcu_idle_gp_delay) - jiffies;
- } else {
- dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
}
*nextevt = basemono + dj * TICK_NSEC;
return 0;
@@ -1704,7 +1597,7 @@ static void rcu_prepare_for_idle(void)
/* Handle nohz enablement switches conservatively. */
tne = READ_ONCE(tick_nohz_active);
if (tne != rdp->tick_nohz_enabled_snap) {
- if (rcu_cpu_has_callbacks(NULL))
+ if (!rcu_segcblist_empty(&rdp->cblist))
invoke_rcu_core(); /* force nohz to see update. */
rdp->tick_nohz_enabled_snap = tne;
return;
@@ -1717,10 +1610,8 @@ static void rcu_prepare_for_idle(void)
* callbacks, invoke RCU core for the side-effect of recalculating
* idle duration on re-entry to idle.
*/
- if (rdp->all_lazy &&
- rdp->nonlazy_posted != rdp->nonlazy_posted_snap) {
+ if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) {
rdp->all_lazy = false;
- rdp->nonlazy_posted_snap = rdp->nonlazy_posted;
invoke_rcu_core();
return;
}
@@ -1756,19 +1647,6 @@ static void rcu_cleanup_after_idle(void)
invoke_rcu_core();
}
-/*
- * Keep a running count of the number of non-lazy callbacks posted
- * on this CPU. This running counter (which is never decremented) allows
- * rcu_prepare_for_idle() to detect when something out of the idle loop
- * posts a callback, even if an equal number of callbacks are invoked.
- * Of course, callbacks should only be posted from within a trace event
- * designed to be called from idle or from within RCU_NONIDLE().
- */
-static void rcu_idle_count_callbacks_posted(void)
-{
- __this_cpu_add(rcu_data.nonlazy_posted, 1);
-}
-
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
#ifdef CONFIG_RCU_FAST_NO_HZ
@@ -1776,13 +1654,12 @@ static void rcu_idle_count_callbacks_posted(void)
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
- unsigned long nlpd = rdp->nonlazy_posted - rdp->nonlazy_posted_snap;
- sprintf(cp, "last_accelerate: %04lx/%04lx, nonlazy_posted: %ld, %c%c",
+ sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
rdp->last_accelerate & 0xffff, jiffies & 0xffff,
- ulong2long(nlpd),
- rdp->all_lazy ? 'L' : '.',
- rdp->tick_nohz_enabled_snap ? '.' : 'D');
+ ".l"[rdp->all_lazy],
+ ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
+ ".D"[!rdp->tick_nohz_enabled_snap]);
}
#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
@@ -1868,22 +1745,24 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp)
/*
* Offload callback processing from the boot-time-specified set of CPUs
- * specified by rcu_nocb_mask. For each CPU in the set, there is a
- * kthread created that pulls the callbacks from the corresponding CPU,
- * waits for a grace period to elapse, and invokes the callbacks.
- * The no-CBs CPUs do a wake_up() on their kthread when they insert
- * a callback into any empty list, unless the rcu_nocb_poll boot parameter
- * has been specified, in which case each kthread actively polls its
- * CPU. (Which isn't so great for energy efficiency, but which does
- * reduce RCU's overhead on that CPU.)
+ * specified by rcu_nocb_mask. For the CPUs in the set, there are kthreads
+ * created that pull the callbacks from the corresponding CPU, wait for
+ * a grace period to elapse, and invoke the callbacks. These kthreads
+ * are organized into leaders, which manage incoming callbacks, wait for
+ * grace periods, and awaken followers, and the followers, which only
+ * invoke callbacks. Each leader is its own follower. The no-CBs CPUs
+ * do a wake_up() on their kthread when they insert a callback into any
+ * empty list, unless the rcu_nocb_poll boot parameter has been specified,
+ * in which case each kthread actively polls its CPU. (Which isn't so great
+ * for energy efficiency, but which does reduce RCU's overhead on that CPU.)
*
* This is intended to be used in conjunction with Frederic Weisbecker's
* adaptive-idle work, which would seriously reduce OS jitter on CPUs
* running CPU-bound user-mode computations.
*
- * Offloading of callback processing could also in theory be used as
- * an energy-efficiency measure because CPUs with no RCU callbacks
- * queued are more aggressive about entering dyntick-idle mode.
+ * Offloading of callbacks can also be used as an energy-efficiency
+ * measure because CPUs with no RCU callbacks queued are more aggressive
+ * about entering dyntick-idle mode.
*/
@@ -1987,10 +1866,7 @@ static void wake_nocb_leader_defer(struct rcu_data *rdp, int waketype,
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
}
-/*
- * Does the specified CPU need an RCU callback for this invocation
- * of rcu_barrier()?
- */
+/* Does rcu_barrier need to queue an RCU callback on the specified CPU? */
static bool rcu_nocb_cpu_needs_barrier(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
@@ -2006,8 +1882,8 @@ static bool rcu_nocb_cpu_needs_barrier(int cpu)
* callbacks would be posted. In the worst case, the first
* barrier in rcu_barrier() suffices (but the caller cannot
* necessarily rely on this, not a substitute for the caller
- * getting the concurrency design right!). There must also be
- * a barrier between the following load an posting of a callback
+ * getting the concurrency design right!). There must also be a
+ * barrier between the following load and posting of a callback
* (if a callback is in fact needed). This is associated with an
* atomic_inc() in the caller.
*/
@@ -2517,9 +2393,9 @@ static void rcu_spawn_one_nocb_kthread(int cpu)
/*
* If the specified CPU is a no-CBs CPU that does not already have its
- * rcuo kthreads, spawn them.
+ * rcuo kthread, spawn it.
*/
-static void rcu_spawn_all_nocb_kthreads(int cpu)
+static void rcu_spawn_cpu_nocb_kthread(int cpu)
{
if (rcu_scheduler_fully_active)
rcu_spawn_one_nocb_kthread(cpu);
@@ -2536,7 +2412,7 @@ static void __init rcu_spawn_nocb_kthreads(void)
int cpu;
for_each_online_cpu(cpu)
- rcu_spawn_all_nocb_kthreads(cpu);
+ rcu_spawn_cpu_nocb_kthread(cpu);
}
/* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */
@@ -2670,7 +2546,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
{
}
-static void rcu_spawn_all_nocb_kthreads(int cpu)
+static void rcu_spawn_cpu_nocb_kthread(int cpu)
{
}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index f4ca36d92138..cbaa976c5945 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -1,26 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright IBM Corporation, 2001
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.com>
*
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
* Papers:
* http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d8d76a65cfdd..0002995570db 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -396,19 +396,7 @@ static bool set_nr_if_polling(struct task_struct *p)
#endif
#endif
-/**
- * wake_q_add() - queue a wakeup for 'later' waking.
- * @head: the wake_q_head to add @task to
- * @task: the task to queue for 'later' wakeup
- *
- * Queue a task for later wakeup, most likely by the wake_up_q() call in the
- * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
- * instantly.
- *
- * This function must be used as-if it were wake_up_process(); IOW the task
- * must be ready to be woken at this location.
- */
-void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
struct wake_q_node *node = &task->wake_q;
@@ -421,16 +409,56 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
* state, even in the failed case, an explicit smp_mb() must be used.
*/
smp_mb__before_atomic();
- if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))
- return;
-
- get_task_struct(task);
+ if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
+ return false;
/*
* The head is context local, there can be no concurrency.
*/
*head->lastp = node;
head->lastp = &node->next;
+ return true;
+}
+
+/**
+ * wake_q_add() - queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+ if (__wake_q_add(head, task))
+ get_task_struct(task);
+}
+
+/**
+ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ *
+ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
+ * that already hold reference to @task can call the 'safe' version and trust
+ * wake_q to do the right thing depending whether or not the @task is already
+ * queued for wakeup.
+ */
+void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
+{
+ if (!__wake_q_add(head, task))
+ put_task_struct(task);
}
void wake_up_q(struct wake_q_head *head)
@@ -5265,9 +5293,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
}
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval,
- compat_pid_t, pid,
- struct old_timespec32 __user *, interval)
+SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
+ struct old_timespec32 __user *, interval)
{
struct timespec64 t;
int retval = sched_rr_get_interval(pid, &t);
@@ -5867,14 +5894,11 @@ void __init sched_init_smp(void)
/*
* There's no userspace yet to cause hotplug operations; hence all the
* CPU masks are stable and all blatant races in the below code cannot
- * happen. The hotplug lock is nevertheless taken to satisfy lockdep,
- * but there won't be any contention on it.
+ * happen.
*/
- cpus_read_lock();
mutex_lock(&sched_domains_mutex);
sched_init_domains(cpu_active_mask);
mutex_unlock(&sched_domains_mutex);
- cpus_read_unlock();
/* Move init over to a non-isolated CPU */
if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
@@ -6162,6 +6186,34 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
EXPORT_SYMBOL(___might_sleep);
+
+void __cant_sleep(const char *file, int line, int preempt_offset)
+{
+ static unsigned long prev_jiffy;
+
+ if (irqs_disabled())
+ return;
+
+ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
+ return;
+
+ if (preempt_count() > preempt_offset)
+ return;
+
+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+ return;
+ prev_jiffy = jiffies;
+
+ printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
+ printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
+ in_atomic(), irqs_disabled(),
+ current->pid, current->comm);
+
+ debug_show_held_locks(current);
+ dump_stack();
+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+}
+EXPORT_SYMBOL_GPL(__cant_sleep);
#endif
#ifdef CONFIG_MAGIC_SYSRQ
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 22bd8980f32f..835671f0f917 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -48,8 +48,8 @@ EXPORT_SYMBOL_GPL(cpufreq_add_update_util_hook);
*
* Clear the update_util_data pointer for the given CPU.
*
- * Callers must use RCU-sched callbacks to free any memory that might be
- * accessed via the old update_util_data pointer or invoke synchronize_sched()
+ * Callers must use RCU callbacks to free any memory that might be
+ * accessed via the old update_util_data pointer or invoke synchronize_rcu()
* right after this function to avoid use-after-free.
*/
void cpufreq_remove_update_util_hook(int cpu)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 033ec7c45f13..2efe629425be 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -859,7 +859,7 @@ static void sugov_stop(struct cpufreq_policy *policy)
for_each_cpu(cpu, policy->cpus)
cpufreq_remove_update_util_hook(cpu);
- synchronize_sched();
+ synchronize_rcu();
if (!policy->fast_switch_enabled) {
irq_work_sync(&sg_policy->irq_work);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d04530bf251f..6665b9c02e2f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1260,7 +1260,7 @@ extern void sched_ttwu_pending(void);
/*
* The domain tree (rq->sd) is protected by RCU's quiescent state transition.
- * See detach_destroy_domains: synchronize_sched for details.
+ * See destroy_sched_domains: call_rcu for details.
*
* The domain tree of any CPU may only be accessed from within
* preempt-disabled sections.
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 3f35ba1d8fde..7d905f55e7fa 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -442,7 +442,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
raw_spin_unlock_irqrestore(&rq->lock, flags);
if (old_rd)
- call_rcu_sched(&old_rd->rcu, free_rootdomain);
+ call_rcu(&old_rd->rcu, free_rootdomain);
}
void sched_get_rd(struct root_domain *rd)
@@ -455,7 +455,7 @@ void sched_put_rd(struct root_domain *rd)
if (!atomic_dec_and_test(&rd->refcount))
return;
- call_rcu_sched(&rd->rcu, free_rootdomain);
+ call_rcu(&rd->rcu, free_rootdomain);
}
static int init_rootdomain(struct root_domain *rd)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index e815781ed751..a43c601ac252 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -267,6 +267,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
* All filters in the list are evaluated and the lowest BPF return
* value always takes priority (ignoring the DATA).
*/
+ preempt_disable();
for (; f; f = f->prev) {
u32 cur_ret = BPF_PROG_RUN(f->prog, sd);
@@ -275,6 +276,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
*match = f;
}
}
+ preempt_enable();
return ret;
}
#endif /* CONFIG_SECCOMP_FILTER */
diff --git a/kernel/signal.c b/kernel/signal.c
index 57b7771e20d7..5d53183e2705 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3455,7 +3455,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time64, compat_sigset_t __user *, uthese,
}
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese,
+COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese,
struct compat_siginfo __user *, uinfo,
struct old_timespec32 __user *, uts, compat_size_t, sigsetsize)
{
diff --git a/kernel/softirq.c b/kernel/softirq.c
index d28813306b2c..10277429ed84 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -89,7 +89,8 @@ static bool ksoftirqd_running(unsigned long pending)
if (pending & SOFTIRQ_NOW_MASK)
return false;
- return tsk && (tsk->state == TASK_RUNNING);
+ return tsk && (tsk->state == TASK_RUNNING) &&
+ !__kthread_should_park(tsk);
}
/*
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index ab9d0e3c6d50..85e5ccec0955 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -42,9 +42,11 @@ COND_SYSCALL(io_destroy);
COND_SYSCALL(io_submit);
COND_SYSCALL_COMPAT(io_submit);
COND_SYSCALL(io_cancel);
+COND_SYSCALL(io_getevents_time32);
COND_SYSCALL(io_getevents);
+COND_SYSCALL(io_pgetevents_time32);
COND_SYSCALL(io_pgetevents);
-COND_SYSCALL_COMPAT(io_getevents);
+COND_SYSCALL_COMPAT(io_pgetevents_time32);
COND_SYSCALL_COMPAT(io_pgetevents);
/* fs/xattr.c */
@@ -114,9 +116,9 @@ COND_SYSCALL_COMPAT(signalfd4);
/* fs/timerfd.c */
COND_SYSCALL(timerfd_create);
COND_SYSCALL(timerfd_settime);
-COND_SYSCALL_COMPAT(timerfd_settime);
+COND_SYSCALL(timerfd_settime32);
COND_SYSCALL(timerfd_gettime);
-COND_SYSCALL_COMPAT(timerfd_gettime);
+COND_SYSCALL(timerfd_gettime32);
/* fs/utimes.c */
@@ -135,7 +137,7 @@ COND_SYSCALL(capset);
/* kernel/futex.c */
COND_SYSCALL(futex);
-COND_SYSCALL_COMPAT(futex);
+COND_SYSCALL(futex_time32);
COND_SYSCALL(set_robust_list);
COND_SYSCALL_COMPAT(set_robust_list);
COND_SYSCALL(get_robust_list);
@@ -187,9 +189,9 @@ COND_SYSCALL(mq_open);
COND_SYSCALL_COMPAT(mq_open);
COND_SYSCALL(mq_unlink);
COND_SYSCALL(mq_timedsend);
-COND_SYSCALL_COMPAT(mq_timedsend);
+COND_SYSCALL(mq_timedsend_time32);
COND_SYSCALL(mq_timedreceive);
-COND_SYSCALL_COMPAT(mq_timedreceive);
+COND_SYSCALL(mq_timedreceive_time32);
COND_SYSCALL(mq_notify);
COND_SYSCALL_COMPAT(mq_notify);
COND_SYSCALL(mq_getsetattr);
@@ -197,6 +199,7 @@ COND_SYSCALL_COMPAT(mq_getsetattr);
/* ipc/msg.c */
COND_SYSCALL(msgget);
+COND_SYSCALL(old_msgctl);
COND_SYSCALL(msgctl);
COND_SYSCALL_COMPAT(msgctl);
COND_SYSCALL(msgrcv);
@@ -206,14 +209,16 @@ COND_SYSCALL_COMPAT(msgsnd);
/* ipc/sem.c */
COND_SYSCALL(semget);
+COND_SYSCALL(old_semctl);
COND_SYSCALL(semctl);
COND_SYSCALL_COMPAT(semctl);
COND_SYSCALL(semtimedop);
-COND_SYSCALL_COMPAT(semtimedop);
+COND_SYSCALL(semtimedop_time32);
COND_SYSCALL(semop);
/* ipc/shm.c */
COND_SYSCALL(shmget);
+COND_SYSCALL(old_shmctl);
COND_SYSCALL(shmctl);
COND_SYSCALL_COMPAT(shmctl);
COND_SYSCALL(shmat);
@@ -285,7 +290,7 @@ COND_SYSCALL(perf_event_open);
COND_SYSCALL(accept4);
COND_SYSCALL(recvmmsg);
COND_SYSCALL(recvmmsg_time32);
-COND_SYSCALL_COMPAT(recvmmsg);
+COND_SYSCALL_COMPAT(recvmmsg_time32);
COND_SYSCALL_COMPAT(recvmmsg_time64);
/*
@@ -366,6 +371,7 @@ COND_SYSCALL(kexec_file_load);
/* s390 */
COND_SYSCALL(s390_pci_mmio_read);
COND_SYSCALL(s390_pci_mmio_write);
+COND_SYSCALL(s390_ipc);
COND_SYSCALL_COMPAT(s390_ipc);
/* powerpc */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ba4d9e85feb8..7578e21a711b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -224,6 +224,11 @@ static int proc_dostring_coredump(struct ctl_table *table, int write,
#endif
static int proc_dopipe_max_size(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
+#ifdef CONFIG_BPF_SYSCALL
+static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
+#endif
#ifdef CONFIG_MAGIC_SYSRQ
/* Note: sysrq code uses its own private copy */
@@ -1229,6 +1234,15 @@ static struct ctl_table kern_table[] = {
.extra1 = &one,
.extra2 = &one,
},
+ {
+ .procname = "bpf_stats_enabled",
+ .data = &sysctl_bpf_stats_enabled,
+ .maxlen = sizeof(sysctl_bpf_stats_enabled),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax_bpf_stats,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
#endif
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
{
@@ -3260,6 +3274,29 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
#endif /* CONFIG_PROC_SYSCTL */
+#ifdef CONFIG_BPF_SYSCALL
+static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret, bpf_stats = *(int *)table->data;
+ struct ctl_table tmp = *table;
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ tmp.data = &bpf_stats;
+ ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ if (write && !ret) {
+ *(int *)table->data = bpf_stats;
+ if (bpf_stats)
+ static_branch_enable(&bpf_stats_enabled_key);
+ else
+ static_branch_disable(&bpf_stats_enabled_key);
+ }
+ return ret;
+}
+#endif
/*
* No sense putting this after each symbol definition, twice,
* exception granted :-)
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 58b981f4bb5d..e2c038d6c13c 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -117,6 +117,35 @@ config NO_HZ_FULL
endchoice
+config CONTEXT_TRACKING
+ bool
+
+config CONTEXT_TRACKING_FORCE
+ bool "Force context tracking"
+ depends on CONTEXT_TRACKING
+ default y if !NO_HZ_FULL
+ help
+ The major pre-requirement for full dynticks to work is to
+ support the context tracking subsystem. But there are also
+ other dependencies to provide in order to make the full
+ dynticks working.
+
+ This option stands for testing when an arch implements the
+ context tracking backend but doesn't yet fullfill all the
+ requirements to make the full dynticks feature working.
+ Without the full dynticks, there is no way to test the support
+ for context tracking and the subsystems that rely on it: RCU
+ userspace extended quiescent state and tickless cputime
+ accounting. This option copes with the absence of the full
+ dynticks subsystem by forcing the context tracking on all
+ CPUs in the system.
+
+ Say Y only if you're working on the development of an
+ architecture backend for the context tracking.
+
+ Say N otherwise, this option brings an overhead that you
+ don't want in production.
+
config NO_HZ
bool "Old Idle dynticks config"
depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index f5cfa1b73d6f..41dfff23c1f9 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -364,7 +364,7 @@ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
switch (state) {
case ODEBUG_STATE_ACTIVE:
WARN_ON(1);
-
+ /* fall through */
default:
return false;
}
@@ -1771,7 +1771,7 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp,
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE2(nanosleep, struct old_timespec32 __user *, rqtp,
+SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp,
struct old_timespec32 __user *, rmtp)
{
struct timespec64 tu;
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 36a2bef00125..92a90014a925 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -188,13 +188,13 @@ static inline int is_error_status(int status)
&& (status & (STA_PPSWANDER|STA_PPSERROR)));
}
-static inline void pps_fill_timex(struct timex *txc)
+static inline void pps_fill_timex(struct __kernel_timex *txc)
{
txc->ppsfreq = shift_right((pps_freq >> PPM_SCALE_INV_SHIFT) *
PPM_SCALE_INV, NTP_SCALE_SHIFT);
txc->jitter = pps_jitter;
if (!(time_status & STA_NANO))
- txc->jitter /= NSEC_PER_USEC;
+ txc->jitter = pps_jitter / NSEC_PER_USEC;
txc->shift = pps_shift;
txc->stabil = pps_stabil;
txc->jitcnt = pps_jitcnt;
@@ -220,7 +220,7 @@ static inline int is_error_status(int status)
return status & (STA_UNSYNC|STA_CLOCKERR);
}
-static inline void pps_fill_timex(struct timex *txc)
+static inline void pps_fill_timex(struct __kernel_timex *txc)
{
/* PPS is not implemented, so these are zero */
txc->ppsfreq = 0;
@@ -633,7 +633,7 @@ void ntp_notify_cmos_timer(void)
/*
* Propagate a new txc->status value into the NTP state:
*/
-static inline void process_adj_status(const struct timex *txc)
+static inline void process_adj_status(const struct __kernel_timex *txc)
{
if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
time_state = TIME_OK;
@@ -656,7 +656,8 @@ static inline void process_adj_status(const struct timex *txc)
}
-static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai)
+static inline void process_adjtimex_modes(const struct __kernel_timex *txc,
+ s32 *time_tai)
{
if (txc->modes & ADJ_STATUS)
process_adj_status(txc);
@@ -707,7 +708,8 @@ static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai
* adjtimex mainly allows reading (and writing, if superuser) of
* kernel time-keeping variables. used by xntpd.
*/
-int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai)
+int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts,
+ s32 *time_tai)
{
int result;
@@ -729,7 +731,7 @@ int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai)
txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
NTP_SCALE_SHIFT);
if (!(time_status & STA_NANO))
- txc->offset /= NSEC_PER_USEC;
+ txc->offset = (u32)txc->offset / NSEC_PER_USEC;
}
result = time_state; /* mostly `TIME_OK' */
@@ -754,7 +756,7 @@ int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai)
txc->time.tv_sec = (time_t)ts->tv_sec;
txc->time.tv_usec = ts->tv_nsec;
if (!(time_status & STA_NANO))
- txc->time.tv_usec /= NSEC_PER_USEC;
+ txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC;
/* Handle leapsec adjustments */
if (unlikely(ts->tv_sec >= ntp_next_leap_sec)) {
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index c24b0e13f011..40e6122e634e 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -8,6 +8,6 @@ extern void ntp_clear(void);
extern u64 ntp_tick_length(void);
extern ktime_t ntp_get_next_leap(void);
extern int second_overflow(time64_t secs);
-extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai);
+extern int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, s32 *time_tai);
extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
#endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 425bbfce6819..ec960bb939fd 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -228,7 +228,7 @@ static void put_clock_desc(struct posix_clock_desc *cd)
fput(cd->fp);
}
-static int pc_clock_adjtime(clockid_t id, struct timex *tx)
+static int pc_clock_adjtime(clockid_t id, struct __kernel_timex *tx)
{
struct posix_clock_desc cd;
int err;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 80f955210861..0a426f4e3125 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -67,13 +67,13 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now)
int i;
u64 delta, incr;
- if (timer->it.cpu.incr == 0)
+ if (!timer->it_interval)
return;
if (now < timer->it.cpu.expires)
return;
- incr = timer->it.cpu.incr;
+ incr = timer->it_interval;
delta = now + incr - timer->it.cpu.expires;
/* Don't use (incr*2 < delta), incr*2 might overflow. */
@@ -520,7 +520,7 @@ static void cpu_timer_fire(struct k_itimer *timer)
*/
wake_up_process(timer->it_process);
timer->it.cpu.expires = 0;
- } else if (timer->it.cpu.incr == 0) {
+ } else if (!timer->it_interval) {
/*
* One-shot timer. Clear it as soon as it's fired.
*/
@@ -606,7 +606,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
*/
ret = 0;
- old_incr = timer->it.cpu.incr;
+ old_incr = timer->it_interval;
old_expires = timer->it.cpu.expires;
if (unlikely(timer->it.cpu.firing)) {
timer->it.cpu.firing = -1;
@@ -684,8 +684,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
* Install the new reload setting, and
* set up the signal and overrun bookkeeping.
*/
- timer->it.cpu.incr = timespec64_to_ns(&new->it_interval);
- timer->it_interval = ns_to_ktime(timer->it.cpu.incr);
+ timer->it_interval = timespec64_to_ktime(new->it_interval);
/*
* This acts as a modification timestamp for the timer,
@@ -724,7 +723,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
/*
* Easy part: convert the reload time.
*/
- itp->it_interval = ns_to_timespec64(timer->it.cpu.incr);
+ itp->it_interval = ktime_to_timespec64(timer->it_interval);
if (!timer->it.cpu.expires)
return;
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index a51895486e5e..67df65f887ac 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -45,6 +45,7 @@ SYS_NI(timer_delete);
SYS_NI(clock_adjtime);
SYS_NI(getitimer);
SYS_NI(setitimer);
+SYS_NI(clock_adjtime32);
#ifdef __ARCH_WANT_SYS_ALARM
SYS_NI(alarm);
#endif
@@ -150,16 +151,16 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
#ifdef CONFIG_COMPAT
COMPAT_SYS_NI(timer_create);
-COMPAT_SYS_NI(clock_adjtime);
-COMPAT_SYS_NI(timer_settime);
-COMPAT_SYS_NI(timer_gettime);
COMPAT_SYS_NI(getitimer);
COMPAT_SYS_NI(setitimer);
#endif
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
- struct old_timespec32 __user *, tp)
+SYS_NI(timer_settime32);
+SYS_NI(timer_gettime32);
+
+SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock,
+ struct old_timespec32 __user *, tp)
{
struct timespec64 new_tp;
@@ -171,8 +172,8 @@ COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
return do_sys_settimeofday64(&new_tp, NULL);
}
-COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
- struct old_timespec32 __user *, tp)
+SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock,
+ struct old_timespec32 __user *, tp)
{
int ret;
struct timespec64 kernel_tp;
@@ -186,8 +187,8 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
return 0;
}
-COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
- struct old_timespec32 __user *, tp)
+SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock,
+ struct old_timespec32 __user *, tp)
{
struct timespec64 rtn_tp = {
.tv_sec = 0,
@@ -206,9 +207,9 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
}
}
-COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
- struct old_timespec32 __user *, rqtp,
- struct old_timespec32 __user *, rmtp)
+SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
+ struct old_timespec32 __user *, rqtp,
+ struct old_timespec32 __user *, rmtp)
{
struct timespec64 t;
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 0e84bb72a3da..29176635991f 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -179,7 +179,7 @@ static int posix_clock_realtime_set(const clockid_t which_clock,
}
static int posix_clock_realtime_adj(const clockid_t which_clock,
- struct timex *t)
+ struct __kernel_timex *t)
{
return do_adjtimex(t);
}
@@ -730,8 +730,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
- struct old_itimerspec32 __user *, setting)
+SYSCALL_DEFINE2(timer_gettime32, timer_t, timer_id,
+ struct old_itimerspec32 __user *, setting)
{
struct itimerspec64 cur_setting;
@@ -903,9 +903,9 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
}
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
- struct old_itimerspec32 __user *, new,
- struct old_itimerspec32 __user *, old)
+SYSCALL_DEFINE4(timer_settime32, timer_t, timer_id, int, flags,
+ struct old_itimerspec32 __user *, new,
+ struct old_itimerspec32 __user *, old)
{
struct itimerspec64 new_spec, old_spec;
struct itimerspec64 *rtn = old ? &old_spec : NULL;
@@ -1047,22 +1047,28 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
return error;
}
-SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
- struct timex __user *, utx)
+int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * ktx)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
- struct timex ktx;
- int err;
if (!kc)
return -EINVAL;
if (!kc->clock_adj)
return -EOPNOTSUPP;
+ return kc->clock_adj(which_clock, ktx);
+}
+
+SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
+ struct __kernel_timex __user *, utx)
+{
+ struct __kernel_timex ktx;
+ int err;
+
if (copy_from_user(&ktx, utx, sizeof(ktx)))
return -EFAULT;
- err = kc->clock_adj(which_clock, &ktx);
+ err = do_clock_adjtime(which_clock, &ktx);
if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx)))
return -EFAULT;
@@ -1090,8 +1096,8 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock,
- struct old_timespec32 __user *, tp)
+SYSCALL_DEFINE2(clock_settime32, clockid_t, which_clock,
+ struct old_timespec32 __user *, tp)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec64 ts;
@@ -1105,8 +1111,8 @@ COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock,
return kc->clock_set(which_clock, &ts);
}
-COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
- struct old_timespec32 __user *, tp)
+SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock,
+ struct old_timespec32 __user *, tp)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec64 ts;
@@ -1123,40 +1129,26 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
return err;
}
-#endif
-
-#ifdef CONFIG_COMPAT
-
-COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock,
- struct compat_timex __user *, utp)
+SYSCALL_DEFINE2(clock_adjtime32, clockid_t, which_clock,
+ struct old_timex32 __user *, utp)
{
- const struct k_clock *kc = clockid_to_kclock(which_clock);
- struct timex ktx;
+ struct __kernel_timex ktx;
int err;
- if (!kc)
- return -EINVAL;
- if (!kc->clock_adj)
- return -EOPNOTSUPP;
-
- err = compat_get_timex(&ktx, utp);
+ err = get_old_timex32(&ktx, utp);
if (err)
return err;
- err = kc->clock_adj(which_clock, &ktx);
+ err = do_clock_adjtime(which_clock, &ktx);
if (err >= 0)
- err = compat_put_timex(utp, &ktx);
+ err = put_old_timex32(utp, &ktx);
return err;
}
-#endif
-
-#ifdef CONFIG_COMPAT_32BIT_TIME
-
-COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
- struct old_timespec32 __user *, tp)
+SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock,
+ struct old_timespec32 __user *, tp)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec64 ts;
@@ -1212,9 +1204,9 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
- struct old_timespec32 __user *, rqtp,
- struct old_timespec32 __user *, rmtp)
+SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
+ struct old_timespec32 __user *, rqtp,
+ struct old_timespec32 __user *, rmtp)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec64 t;
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index ddb21145211a..de5daa6d975a 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -8,7 +8,7 @@ struct k_clock {
const struct timespec64 *tp);
int (*clock_get)(const clockid_t which_clock,
struct timespec64 *tp);
- int (*clock_adj)(const clockid_t which_clock, struct timex *tx);
+ int (*clock_adj)(const clockid_t which_clock, struct __kernel_timex *tx);
int (*timer_create)(struct k_itimer *timer);
int (*nsleep)(const clockid_t which_clock, int flags,
const struct timespec64 *);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 803fa67aace9..ee834d4fb814 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -375,6 +375,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
switch (mode) {
case TICK_BROADCAST_FORCE:
tick_broadcast_forced = 1;
+ /* fall through */
case TICK_BROADCAST_ON:
cpumask_set_cpu(cpu, tick_broadcast_on);
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 2edb5088a70b..c3f756f8534b 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -98,11 +98,11 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr)
#endif /* __ARCH_WANT_SYS_TIME */
-#ifdef CONFIG_COMPAT
-#ifdef __ARCH_WANT_COMPAT_SYS_TIME
+#ifdef CONFIG_COMPAT_32BIT_TIME
+#ifdef __ARCH_WANT_SYS_TIME32
/* old_time32_t is a 32 bit "long" and needs to get converted. */
-COMPAT_SYSCALL_DEFINE1(time, old_time32_t __user *, tloc)
+SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc)
{
old_time32_t i;
@@ -116,7 +116,7 @@ COMPAT_SYSCALL_DEFINE1(time, old_time32_t __user *, tloc)
return i;
}
-COMPAT_SYSCALL_DEFINE1(stime, old_time32_t __user *, tptr)
+SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr)
{
struct timespec64 tv;
int err;
@@ -134,7 +134,7 @@ COMPAT_SYSCALL_DEFINE1(stime, old_time32_t __user *, tptr)
return 0;
}
-#endif /* __ARCH_WANT_COMPAT_SYS_TIME */
+#endif /* __ARCH_WANT_SYS_TIME32 */
#endif
SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
@@ -263,35 +263,99 @@ COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv,
}
#endif
-SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
+#if !defined(CONFIG_64BIT_TIME) || defined(CONFIG_64BIT)
+SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p)
{
- struct timex txc; /* Local copy of parameter */
+ struct __kernel_timex txc; /* Local copy of parameter */
int ret;
/* Copy the user data space into the kernel copy
* structure. But bear in mind that the structures
* may change
*/
- if (copy_from_user(&txc, txc_p, sizeof(struct timex)))
+ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex)))
return -EFAULT;
ret = do_adjtimex(&txc);
- return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret;
+ return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret;
}
+#endif
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
+int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp)
+{
+ struct old_timex32 tx32;
+
+ memset(txc, 0, sizeof(struct __kernel_timex));
+ if (copy_from_user(&tx32, utp, sizeof(struct old_timex32)))
+ return -EFAULT;
+
+ txc->modes = tx32.modes;
+ txc->offset = tx32.offset;
+ txc->freq = tx32.freq;
+ txc->maxerror = tx32.maxerror;
+ txc->esterror = tx32.esterror;
+ txc->status = tx32.status;
+ txc->constant = tx32.constant;
+ txc->precision = tx32.precision;
+ txc->tolerance = tx32.tolerance;
+ txc->time.tv_sec = tx32.time.tv_sec;
+ txc->time.tv_usec = tx32.time.tv_usec;
+ txc->tick = tx32.tick;
+ txc->ppsfreq = tx32.ppsfreq;
+ txc->jitter = tx32.jitter;
+ txc->shift = tx32.shift;
+ txc->stabil = tx32.stabil;
+ txc->jitcnt = tx32.jitcnt;
+ txc->calcnt = tx32.calcnt;
+ txc->errcnt = tx32.errcnt;
+ txc->stbcnt = tx32.stbcnt;
+
+ return 0;
+}
+
+int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc)
+{
+ struct old_timex32 tx32;
+
+ memset(&tx32, 0, sizeof(struct old_timex32));
+ tx32.modes = txc->modes;
+ tx32.offset = txc->offset;
+ tx32.freq = txc->freq;
+ tx32.maxerror = txc->maxerror;
+ tx32.esterror = txc->esterror;
+ tx32.status = txc->status;
+ tx32.constant = txc->constant;
+ tx32.precision = txc->precision;
+ tx32.tolerance = txc->tolerance;
+ tx32.time.tv_sec = txc->time.tv_sec;
+ tx32.time.tv_usec = txc->time.tv_usec;
+ tx32.tick = txc->tick;
+ tx32.ppsfreq = txc->ppsfreq;
+ tx32.jitter = txc->jitter;
+ tx32.shift = txc->shift;
+ tx32.stabil = txc->stabil;
+ tx32.jitcnt = txc->jitcnt;
+ tx32.calcnt = txc->calcnt;
+ tx32.errcnt = txc->errcnt;
+ tx32.stbcnt = txc->stbcnt;
+ tx32.tai = txc->tai;
+ if (copy_to_user(utp, &tx32, sizeof(struct old_timex32)))
+ return -EFAULT;
+ return 0;
+}
-COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp)
+SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp)
{
- struct timex txc;
+ struct __kernel_timex txc;
int err, ret;
- err = compat_get_timex(&txc, utp);
+ err = get_old_timex32(&txc, utp);
if (err)
return err;
ret = do_adjtimex(&txc);
- err = compat_put_timex(utp, &txc);
+ err = put_old_timex32(utp, &txc);
if (err)
return err;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ac5dbf2cd4a2..f986e1918d12 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2234,7 +2234,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
/**
* timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
*/
-static int timekeeping_validate_timex(const struct timex *txc)
+static int timekeeping_validate_timex(const struct __kernel_timex *txc)
{
if (txc->modes & ADJ_ADJTIME) {
/* singleshot must not be used with any other mode bits */
@@ -2300,7 +2300,7 @@ static int timekeeping_validate_timex(const struct timex *txc)
/**
* do_adjtimex() - Accessor function to NTP __do_adjtimex function
*/
-int do_adjtimex(struct timex *txc)
+int do_adjtimex(struct __kernel_timex *txc)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned long flags;
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 86489950d690..b73e8850e58d 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -37,15 +37,8 @@ DEFINE_SHOW_ATTRIBUTE(tk_debug_sleep_time);
static int __init tk_debug_sleep_time_init(void)
{
- struct dentry *d;
-
- d = debugfs_create_file("sleep_time", 0444, NULL, NULL,
- &tk_debug_sleep_time_fops);
- if (!d) {
- pr_err("Failed to create sleep_time debug file\n");
- return -ENOMEM;
- }
-
+ debugfs_create_file("sleep_time", 0444, NULL, NULL,
+ &tk_debug_sleep_time_fops);
return 0;
}
late_initcall(tk_debug_sleep_time_init);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 444156debfa0..2fce056f8a49 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -647,7 +647,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
case ODEBUG_STATE_ACTIVE:
WARN_ON(1);
-
+ /* fall through */
default:
return false;
}
@@ -1632,7 +1632,7 @@ void update_process_times(int user_tick)
/* Note: this timer irq context must be accounted for as well. */
account_process_tick(p, user_tick);
run_local_timers();
- rcu_check_callbacks(user_tick);
+ rcu_sched_clock_irq(user_tick);
#ifdef CONFIG_IRQ_WORK
if (in_irq())
irq_work_tick();
diff --git a/kernel/torture.c b/kernel/torture.c
index bbf6d473e50c..8faa1a9aaeb9 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Common functions for in-kernel torture tests.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
* Copyright (C) IBM Corporation, 2014
*
- * Author: Paul E. McKenney <paulmck@us.ibm.com>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
* Based on kernel/rcu/torture.c.
*/
@@ -53,7 +40,7 @@
#include "rcu/rcu.h"
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
static char *torture_type;
static int verbose;
@@ -75,6 +62,7 @@ static DEFINE_MUTEX(fullstop_mutex);
static struct task_struct *onoff_task;
static long onoff_holdoff;
static long onoff_interval;
+static torture_ofl_func *onoff_f;
static long n_offline_attempts;
static long n_offline_successes;
static unsigned long sum_offline;
@@ -118,6 +106,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: offlined %d\n",
torture_type, cpu);
+ if (onoff_f)
+ onoff_f();
(*n_offl_successes)++;
delta = jiffies - starttime;
*sum_offl += delta;
@@ -243,11 +233,12 @@ stop:
/*
* Initiate online-offline handling.
*/
-int torture_onoff_init(long ooholdoff, long oointerval)
+int torture_onoff_init(long ooholdoff, long oointerval, torture_ofl_func *f)
{
#ifdef CONFIG_HOTPLUG_CPU
onoff_holdoff = ooholdoff;
onoff_interval = oointerval;
+ onoff_f = f;
if (onoff_interval <= 0)
return 0;
return torture_create_kthread(torture_onoff, NULL, onoff_task);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index fc5d23d752a5..e163e7a7f5e5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -259,6 +259,8 @@ struct workqueue_struct {
struct wq_device *wq_dev; /* I: for sysfs interface */
#endif
#ifdef CONFIG_LOCKDEP
+ char *lock_name;
+ struct lock_class_key key;
struct lockdep_map lockdep_map;
#endif
char name[WQ_NAME_LEN]; /* I: workqueue name */
@@ -3337,11 +3339,49 @@ static int init_worker_pool(struct worker_pool *pool)
return 0;
}
+#ifdef CONFIG_LOCKDEP
+static void wq_init_lockdep(struct workqueue_struct *wq)
+{
+ char *lock_name;
+
+ lockdep_register_key(&wq->key);
+ lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name);
+ if (!lock_name)
+ lock_name = wq->name;
+ lockdep_init_map(&wq->lockdep_map, lock_name, &wq->key, 0);
+}
+
+static void wq_unregister_lockdep(struct workqueue_struct *wq)
+{
+ lockdep_unregister_key(&wq->key);
+}
+
+static void wq_free_lockdep(struct workqueue_struct *wq)
+{
+ if (wq->lock_name != wq->name)
+ kfree(wq->lock_name);
+}
+#else
+static void wq_init_lockdep(struct workqueue_struct *wq)
+{
+}
+
+static void wq_unregister_lockdep(struct workqueue_struct *wq)
+{
+}
+
+static void wq_free_lockdep(struct workqueue_struct *wq)
+{
+}
+#endif
+
static void rcu_free_wq(struct rcu_head *rcu)
{
struct workqueue_struct *wq =
container_of(rcu, struct workqueue_struct, rcu);
+ wq_free_lockdep(wq);
+
if (!(wq->flags & WQ_UNBOUND))
free_percpu(wq->cpu_pwqs);
else
@@ -3532,8 +3572,10 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
* If we're the last pwq going away, @wq is already dead and no one
* is gonna access it anymore. Schedule RCU free.
*/
- if (is_last)
+ if (is_last) {
+ wq_unregister_lockdep(wq);
call_rcu(&wq->rcu, rcu_free_wq);
+ }
}
/**
@@ -4067,11 +4109,9 @@ static int init_rescuer(struct workqueue_struct *wq)
return 0;
}
-struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
- unsigned int flags,
- int max_active,
- struct lock_class_key *key,
- const char *lock_name, ...)
+struct workqueue_struct *alloc_workqueue(const char *fmt,
+ unsigned int flags,
+ int max_active, ...)
{
size_t tbl_size = 0;
va_list args;
@@ -4106,7 +4146,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
goto err_free_wq;
}
- va_start(args, lock_name);
+ va_start(args, max_active);
vsnprintf(wq->name, sizeof(wq->name), fmt, args);
va_end(args);
@@ -4123,7 +4163,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
INIT_LIST_HEAD(&wq->flusher_overflow);
INIT_LIST_HEAD(&wq->maydays);
- lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
+ wq_init_lockdep(wq);
INIT_LIST_HEAD(&wq->list);
if (alloc_and_link_pwqs(wq) < 0)
@@ -4161,7 +4201,7 @@ err_destroy:
destroy_workqueue(wq);
return NULL;
}
-EXPORT_SYMBOL_GPL(__alloc_workqueue_key);
+EXPORT_SYMBOL_GPL(alloc_workqueue);
/**
* destroy_workqueue - safely terminate a workqueue
@@ -4214,6 +4254,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
kthread_stop(wq->rescuer->task);
if (!(wq->flags & WQ_UNBOUND)) {
+ wq_unregister_lockdep(wq);
/*
* The base ref is never dropped on per-cpu pwqs. Directly
* schedule RCU free.