summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/bpf/core.c9
-rw-r--r--kernel/bpf/inode.c2
-rw-r--r--kernel/bpf/syscall.c8
-rw-r--r--kernel/bpf/verifier.c166
-rw-r--r--kernel/crash_core.c439
-rw-r--r--kernel/events/callchain.c6
-rw-r--r--kernel/fork.c39
-rw-r--r--kernel/gcov/base.c6
-rw-r--r--kernel/gcov/gcc_4_7.c4
-rw-r--r--kernel/groups.c2
-rw-r--r--kernel/hung_task.c8
-rw-r--r--kernel/irq/manage.c15
-rw-r--r--kernel/kcov.c9
-rw-r--r--kernel/kexec_core.c431
-rw-r--r--kernel/ksysfs.c8
-rw-r--r--kernel/locking/lockdep.c86
-rw-r--r--kernel/locking/rtmutex-debug.c9
-rw-r--r--kernel/module.c5
-rw-r--r--kernel/pid.c4
-rw-r--r--kernel/pid_namespace.c36
-rw-r--r--kernel/power/process.c2
-rw-r--r--kernel/power/snapshot.c3
-rw-r--r--kernel/power/suspend.c29
-rw-r--r--kernel/printk/braille.c15
-rw-r--r--kernel/printk/braille.h13
-rw-r--r--kernel/printk/printk.c30
-rw-r--r--kernel/rcu/Makefile5
-rw-r--r--kernel/rcu/rcu.h153
-rw-r--r--kernel/rcu/rcu_segcblist.c505
-rw-r--r--kernel/rcu/rcu_segcblist.h164
-rw-r--r--kernel/rcu/rcutorture.c43
-rw-r--r--kernel/rcu/srcu.c12
-rw-r--r--kernel/rcu/srcutiny.c216
-rw-r--r--kernel/rcu/srcutree.c1155
-rw-r--r--kernel/rcu/tiny.c20
-rw-r--r--kernel/rcu/tiny_plugin.h13
-rw-r--r--kernel/rcu/tree.c710
-rw-r--r--kernel/rcu/tree.h163
-rw-r--r--kernel/rcu/tree_exp.h25
-rw-r--r--kernel/rcu/tree_plugin.h64
-rw-r--r--kernel/rcu/tree_trace.c26
-rw-r--r--kernel/rcu/update.c53
-rw-r--r--kernel/sched/core.c2
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/sysctl.c2
-rw-r--r--kernel/taskstats.c14
-rw-r--r--kernel/time/time.c14
-rw-r--r--kernel/trace/ftrace.c20
-rw-r--r--kernel/trace/trace.c7
-rw-r--r--kernel/trace/trace_entries.h6
-rw-r--r--kernel/trace/trace_hwlat.c14
-rw-r--r--kernel/trace/trace_output.c9
53 files changed, 3526 insertions, 1276 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index b302b4731d16..72aa080f91f0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_MODULE_SIG) += module_signing.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
+obj-$(CONFIG_CRASH_CORE) += crash_core.o
obj-$(CONFIG_KEXEC_CORE) += kexec_core.o
obj-$(CONFIG_KEXEC) += kexec.o
obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 6f81e0f5a0fa..dedf367f59bb 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -76,8 +76,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
- gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog_aux *aux;
struct bpf_prog *fp;
@@ -107,8 +106,7 @@ EXPORT_SYMBOL_GPL(bpf_prog_alloc);
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
- gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
u32 pages, delta;
int ret;
@@ -655,8 +653,7 @@ out:
static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,
gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
- gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index fddcae801724..9bbd33497d3d 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -429,7 +429,7 @@ static int bpf_parse_options(char *data, struct bpf_mount_opts *opts)
static int bpf_fill_super(struct super_block *sb, void *data, int silent)
{
- static struct tree_descr bpf_rfiles[] = { { "" } };
+ static const struct tree_descr bpf_rfiles[] = { { "" } };
struct bpf_mount_opts opts;
struct inode *inode;
int ret;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 13642c73dca0..265a0d854e33 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -67,8 +67,7 @@ void *bpf_map_area_alloc(size_t size)
return area;
}
- return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags,
- PAGE_KERNEL);
+ return __vmalloc(size, GFP_KERNEL | flags, PAGE_KERNEL);
}
void bpf_map_area_free(void *area)
@@ -784,7 +783,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
EXPORT_SYMBOL_GPL(bpf_prog_get_type);
/* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD kern_version
+#define BPF_PROG_LOAD_LAST_FIELD prog_flags
static int bpf_prog_load(union bpf_attr *attr)
{
@@ -797,6 +796,9 @@ static int bpf_prog_load(union bpf_attr *attr)
if (CHECK_ATTR(BPF_PROG_LOAD))
return -EINVAL;
+ if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT)
+ return -EINVAL;
+
/* copy eBPF program license from user space */
if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
sizeof(license) - 1) < 0)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c2ff608c1984..1eddb713b815 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -140,7 +140,7 @@ struct bpf_verifier_stack_elem {
struct bpf_verifier_stack_elem *next;
};
-#define BPF_COMPLEXITY_LIMIT_INSNS 65536
+#define BPF_COMPLEXITY_LIMIT_INSNS 98304
#define BPF_COMPLEXITY_LIMIT_STACK 1024
#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
@@ -241,6 +241,12 @@ static void print_verifier_state(struct bpf_verifier_state *state)
if (reg->max_value != BPF_REGISTER_MAX_RANGE)
verbose(",max_value=%llu",
(unsigned long long)reg->max_value);
+ if (reg->min_align)
+ verbose(",min_align=%u", reg->min_align);
+ if (reg->aux_off)
+ verbose(",aux_off=%u", reg->aux_off);
+ if (reg->aux_off_align)
+ verbose(",aux_off_align=%u", reg->aux_off_align);
}
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
if (state->stack_slot_type[i] == STACK_SPILL)
@@ -298,7 +304,8 @@ static const char *const bpf_jmp_string[16] = {
[BPF_EXIT >> 4] = "exit",
};
-static void print_bpf_insn(struct bpf_insn *insn)
+static void print_bpf_insn(const struct bpf_verifier_env *env,
+ const struct bpf_insn *insn)
{
u8 class = BPF_CLASS(insn->code);
@@ -362,9 +369,19 @@ static void print_bpf_insn(struct bpf_insn *insn)
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->src_reg, insn->imm);
- } else if (BPF_MODE(insn->code) == BPF_IMM) {
- verbose("(%02x) r%d = 0x%x\n",
- insn->code, insn->dst_reg, insn->imm);
+ } else if (BPF_MODE(insn->code) == BPF_IMM &&
+ BPF_SIZE(insn->code) == BPF_DW) {
+ /* At this point, we already made sure that the second
+ * part of the ldimm64 insn is accessible.
+ */
+ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+ bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+
+ if (map_ptr && !env->allow_ptr_leaks)
+ imm = 0;
+
+ verbose("(%02x) r%d = 0x%llx\n", insn->code,
+ insn->dst_reg, (unsigned long long)imm);
} else {
verbose("BUG_ld_%02x\n", insn->code);
return;
@@ -455,6 +472,9 @@ static void init_reg_state(struct bpf_reg_state *regs)
regs[i].imm = 0;
regs[i].min_value = BPF_REGISTER_MIN_RANGE;
regs[i].max_value = BPF_REGISTER_MAX_RANGE;
+ regs[i].min_align = 0;
+ regs[i].aux_off = 0;
+ regs[i].aux_off_align = 0;
}
/* frame pointer */
@@ -481,6 +501,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
{
regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+ regs[regno].min_align = 0;
}
static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs,
@@ -768,17 +789,33 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
}
static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
- int off, int size)
+ int off, int size, bool strict)
{
- if (reg->id && size != 1) {
- verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
- return -EACCES;
+ int ip_align;
+ int reg_off;
+
+ /* Byte size accesses are always allowed. */
+ if (!strict || size == 1)
+ return 0;
+
+ reg_off = reg->off;
+ if (reg->id) {
+ if (reg->aux_off_align % size) {
+ verbose("Packet access is only %u byte aligned, %d byte access not allowed\n",
+ reg->aux_off_align, size);
+ return -EACCES;
+ }
+ reg_off += reg->aux_off;
}
- /* skb->data is NET_IP_ALIGN-ed */
- if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
+ /* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking
+ * we force this to 2 which is universally what architectures use
+ * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ */
+ ip_align = strict ? 2 : NET_IP_ALIGN;
+ if ((ip_align + reg_off + off) % size != 0) {
verbose("misaligned packet access off %d+%d+%d size %d\n",
- NET_IP_ALIGN, reg->off, off, size);
+ ip_align, reg_off, off, size);
return -EACCES;
}
@@ -786,9 +823,9 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
}
static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
- int size)
+ int size, bool strict)
{
- if (size != 1) {
+ if (strict && size != 1) {
verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
return -EACCES;
}
@@ -796,16 +833,20 @@ static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
return 0;
}
-static int check_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_ptr_alignment(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
int off, int size)
{
+ bool strict = env->strict_alignment;
+
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ strict = true;
+
switch (reg->type) {
case PTR_TO_PACKET:
- return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
- check_pkt_ptr_alignment(reg, off, size);
+ return check_pkt_ptr_alignment(reg, off, size, strict);
case PTR_TO_MAP_VALUE_ADJ:
- return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
- check_val_ptr_alignment(reg, size);
+ return check_val_ptr_alignment(reg, size, strict);
default:
if (off % size != 0) {
verbose("misaligned access off %d size %d\n",
@@ -838,7 +879,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
if (size < 0)
return size;
- err = check_ptr_alignment(reg, off, size);
+ err = check_ptr_alignment(env, reg, off, size);
if (err)
return err;
@@ -872,6 +913,8 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
value_regno);
/* note that reg.[id|off|range] == 0 */
state->regs[value_regno].type = reg_type;
+ state->regs[value_regno].aux_off = 0;
+ state->regs[value_regno].aux_off_align = 0;
}
} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
@@ -1444,6 +1487,8 @@ add_imm:
*/
dst_reg->off += imm;
} else {
+ bool had_id;
+
if (src_reg->type == PTR_TO_PACKET) {
/* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */
tmp_reg = *dst_reg; /* save r7 state */
@@ -1477,14 +1522,23 @@ add_imm:
src_reg->imm);
return -EACCES;
}
+
+ had_id = (dst_reg->id != 0);
+
/* dst_reg stays as pkt_ptr type and since some positive
* integer value was added to the pointer, increment its 'id'
*/
dst_reg->id = ++env->id_gen;
- /* something was added to pkt_ptr, set range and off to zero */
+ /* something was added to pkt_ptr, set range to zero */
+ dst_reg->aux_off += dst_reg->off;
dst_reg->off = 0;
dst_reg->range = 0;
+ if (had_id)
+ dst_reg->aux_off_align = min(dst_reg->aux_off_align,
+ src_reg->min_align);
+ else
+ dst_reg->aux_off_align = src_reg->min_align;
}
return 0;
}
@@ -1658,6 +1712,13 @@ static void check_reg_overflow(struct bpf_reg_state *reg)
reg->min_value = BPF_REGISTER_MIN_RANGE;
}
+static u32 calc_align(u32 imm)
+{
+ if (!imm)
+ return 1U << 31;
+ return imm - ((imm - 1) & imm);
+}
+
static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
@@ -1665,8 +1726,10 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
s64 min_val = BPF_REGISTER_MIN_RANGE;
u64 max_val = BPF_REGISTER_MAX_RANGE;
u8 opcode = BPF_OP(insn->code);
+ u32 dst_align, src_align;
dst_reg = &regs[insn->dst_reg];
+ src_align = 0;
if (BPF_SRC(insn->code) == BPF_X) {
check_reg_overflow(&regs[insn->src_reg]);
min_val = regs[insn->src_reg].min_value;
@@ -1682,12 +1745,18 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
regs[insn->src_reg].type != UNKNOWN_VALUE) {
min_val = BPF_REGISTER_MIN_RANGE;
max_val = BPF_REGISTER_MAX_RANGE;
+ src_align = 0;
+ } else {
+ src_align = regs[insn->src_reg].min_align;
}
} else if (insn->imm < BPF_REGISTER_MAX_RANGE &&
(s64)insn->imm > BPF_REGISTER_MIN_RANGE) {
min_val = max_val = insn->imm;
+ src_align = calc_align(insn->imm);
}
+ dst_align = dst_reg->min_align;
+
/* We don't know anything about what was done to this register, mark it
* as unknown.
*/
@@ -1712,18 +1781,21 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
dst_reg->min_value += min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value += max_val;
+ dst_reg->min_align = min(src_align, dst_align);
break;
case BPF_SUB:
if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
dst_reg->min_value -= min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value -= max_val;
+ dst_reg->min_align = min(src_align, dst_align);
break;
case BPF_MUL:
if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
dst_reg->min_value *= min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value *= max_val;
+ dst_reg->min_align = max(src_align, dst_align);
break;
case BPF_AND:
/* Disallow AND'ing of negative numbers, ain't nobody got time
@@ -1735,17 +1807,23 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
else
dst_reg->min_value = 0;
dst_reg->max_value = max_val;
+ dst_reg->min_align = max(src_align, dst_align);
break;
case BPF_LSH:
/* Gotta have special overflow logic here, if we're shifting
* more than MAX_RANGE then just assume we have an invalid
* range.
*/
- if (min_val > ilog2(BPF_REGISTER_MAX_RANGE))
+ if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) {
dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
- else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
- dst_reg->min_value <<= min_val;
-
+ dst_reg->min_align = 1;
+ } else {
+ if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+ dst_reg->min_value <<= min_val;
+ if (!dst_reg->min_align)
+ dst_reg->min_align = 1;
+ dst_reg->min_align <<= min_val;
+ }
if (max_val > ilog2(BPF_REGISTER_MAX_RANGE))
dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
@@ -1755,11 +1833,19 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
/* RSH by a negative number is undefined, and the BPF_RSH is an
* unsigned shift, so make the appropriate casts.
*/
- if (min_val < 0 || dst_reg->min_value < 0)
+ if (min_val < 0 || dst_reg->min_value < 0) {
dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
- else
+ } else {
dst_reg->min_value =
(u64)(dst_reg->min_value) >> min_val;
+ }
+ if (min_val < 0) {
+ dst_reg->min_align = 1;
+ } else {
+ dst_reg->min_align >>= (u64) min_val;
+ if (!dst_reg->min_align)
+ dst_reg->min_align = 1;
+ }
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value >>= max_val;
break;
@@ -1861,6 +1947,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
regs[insn->dst_reg].imm = insn->imm;
regs[insn->dst_reg].max_value = insn->imm;
regs[insn->dst_reg].min_value = insn->imm;
+ regs[insn->dst_reg].min_align = calc_align(insn->imm);
}
} else if (opcode > BPF_END) {
@@ -2553,6 +2640,7 @@ peek_stack:
env->explored_states[t + 1] = STATE_LIST_MARK;
} else {
/* conditional jump with two edges */
+ env->explored_states[t] = STATE_LIST_MARK;
ret = push_insn(t, t + 1, FALLTHROUGH, env);
if (ret == 1)
goto peek_stack;
@@ -2711,6 +2799,12 @@ static bool states_equal(struct bpf_verifier_env *env,
rcur->type != NOT_INIT))
continue;
+ /* Don't care about the reg->id in this case. */
+ if (rold->type == PTR_TO_MAP_VALUE_OR_NULL &&
+ rcur->type == PTR_TO_MAP_VALUE_OR_NULL &&
+ rold->map_ptr == rcur->map_ptr)
+ continue;
+
if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
compare_ptrs_to_packet(rold, rcur))
continue;
@@ -2845,15 +2939,22 @@ static int do_check(struct bpf_verifier_env *env)
goto process_bpf_exit;
}
- if (log_level && do_print_state) {
- verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
+ if (need_resched())
+ cond_resched();
+
+ if (log_level > 1 || (log_level && do_print_state)) {
+ if (log_level > 1)
+ verbose("%d:", insn_idx);
+ else
+ verbose("\nfrom %d to %d:",
+ prev_insn_idx, insn_idx);
print_verifier_state(&env->cur_state);
do_print_state = false;
}
if (log_level) {
verbose("%d: ", insn_idx);
- print_bpf_insn(insn);
+ print_bpf_insn(env, insn);
}
err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
@@ -3483,6 +3584,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
} else {
log_level = 0;
}
+ if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT)
+ env->strict_alignment = true;
+ else
+ env->strict_alignment = false;
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
@@ -3588,6 +3693,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
mutex_lock(&bpf_verifier_lock);
log_level = 0;
+ env->strict_alignment = false;
env->explored_states = kcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
new file mode 100644
index 000000000000..fcbd568f1e95
--- /dev/null
+++ b/kernel/crash_core.c
@@ -0,0 +1,439 @@
+/*
+ * crash.c - kernel crash support code.
+ * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com>
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ */
+
+#include <linux/crash_core.h>
+#include <linux/utsname.h>
+#include <linux/vmalloc.h>
+
+#include <asm/page.h>
+#include <asm/sections.h>
+
+/* vmcoreinfo stuff */
+static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
+u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+size_t vmcoreinfo_size;
+size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+
+/*
+ * parsing the "crashkernel" commandline
+ *
+ * this code is intended to be called from architecture specific code
+ */
+
+
+/*
+ * This function parses command lines in the format
+ *
+ * crashkernel=ramsize-range:size[,...][@offset]
+ *
+ * The function returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_mem(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ char *cur = cmdline, *tmp;
+
+ /* for each entry of the comma-separated list */
+ do {
+ unsigned long long start, end = ULLONG_MAX, size;
+
+ /* get the start of the range */
+ start = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("crashkernel: Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (*cur != '-') {
+ pr_warn("crashkernel: '-' expected\n");
+ return -EINVAL;
+ }
+ cur++;
+
+ /* if no ':' is here, than we read the end */
+ if (*cur != ':') {
+ end = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("crashkernel: Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (end <= start) {
+ pr_warn("crashkernel: end <= start\n");
+ return -EINVAL;
+ }
+ }
+
+ if (*cur != ':') {
+ pr_warn("crashkernel: ':' expected\n");
+ return -EINVAL;
+ }
+ cur++;
+
+ size = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (size >= system_ram) {
+ pr_warn("crashkernel: invalid size\n");
+ return -EINVAL;
+ }
+
+ /* match ? */
+ if (system_ram >= start && system_ram < end) {
+ *crash_size = size;
+ break;
+ }
+ } while (*cur++ == ',');
+
+ if (*crash_size > 0) {
+ while (*cur && *cur != ' ' && *cur != '@')
+ cur++;
+ if (*cur == '@') {
+ cur++;
+ *crash_base = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("Memory value expected after '@'\n");
+ return -EINVAL;
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * That function parses "simple" (old) crashkernel command lines like
+ *
+ * crashkernel=size[@offset]
+ *
+ * It returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_simple(char *cmdline,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ char *cur = cmdline;
+
+ *crash_size = memparse(cmdline, &cur);
+ if (cmdline == cur) {
+ pr_warn("crashkernel: memory value expected\n");
+ return -EINVAL;
+ }
+
+ if (*cur == '@')
+ *crash_base = memparse(cur+1, &cur);
+ else if (*cur != ' ' && *cur != '\0') {
+ pr_warn("crashkernel: unrecognized char: %c\n", *cur);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+#define SUFFIX_HIGH 0
+#define SUFFIX_LOW 1
+#define SUFFIX_NULL 2
+static __initdata char *suffix_tbl[] = {
+ [SUFFIX_HIGH] = ",high",
+ [SUFFIX_LOW] = ",low",
+ [SUFFIX_NULL] = NULL,
+};
+
+/*
+ * That function parses "suffix" crashkernel command lines like
+ *
+ * crashkernel=size,[high|low]
+ *
+ * It returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_suffix(char *cmdline,
+ unsigned long long *crash_size,
+ const char *suffix)
+{
+ char *cur = cmdline;
+
+ *crash_size = memparse(cmdline, &cur);
+ if (cmdline == cur) {
+ pr_warn("crashkernel: memory value expected\n");
+ return -EINVAL;
+ }
+
+ /* check with suffix */
+ if (strncmp(cur, suffix, strlen(suffix))) {
+ pr_warn("crashkernel: unrecognized char: %c\n", *cur);
+ return -EINVAL;
+ }
+ cur += strlen(suffix);
+ if (*cur != ' ' && *cur != '\0') {
+ pr_warn("crashkernel: unrecognized char: %c\n", *cur);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static __init char *get_last_crashkernel(char *cmdline,
+ const char *name,
+ const char *suffix)
+{
+ char *p = cmdline, *ck_cmdline = NULL;
+
+ /* find crashkernel and use the last one if there are more */
+ p = strstr(p, name);
+ while (p) {
+ char *end_p = strchr(p, ' ');
+ char *q;
+
+ if (!end_p)
+ end_p = p + strlen(p);
+
+ if (!suffix) {
+ int i;
+
+ /* skip the one with any known suffix */
+ for (i = 0; suffix_tbl[i]; i++) {
+ q = end_p - strlen(suffix_tbl[i]);
+ if (!strncmp(q, suffix_tbl[i],
+ strlen(suffix_tbl[i])))
+ goto next;
+ }
+ ck_cmdline = p;
+ } else {
+ q = end_p - strlen(suffix);
+ if (!strncmp(q, suffix, strlen(suffix)))
+ ck_cmdline = p;
+ }
+next:
+ p = strstr(p+1, name);
+ }
+
+ if (!ck_cmdline)
+ return NULL;
+
+ return ck_cmdline;
+}
+
+static int __init __parse_crashkernel(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base,
+ const char *name,
+ const char *suffix)
+{
+ char *first_colon, *first_space;
+ char *ck_cmdline;
+
+ BUG_ON(!crash_size || !crash_base);
+ *crash_size = 0;
+ *crash_base = 0;
+
+ ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
+
+ if (!ck_cmdline)
+ return -EINVAL;
+
+ ck_cmdline += strlen(name);
+
+ if (suffix)
+ return parse_crashkernel_suffix(ck_cmdline, crash_size,
+ suffix);
+ /*
+ * if the commandline contains a ':', then that's the extended
+ * syntax -- if not, it must be the classic syntax
+ */
+ first_colon = strchr(ck_cmdline, ':');
+ first_space = strchr(ck_cmdline, ' ');
+ if (first_colon && (!first_space || first_colon < first_space))
+ return parse_crashkernel_mem(ck_cmdline, system_ram,
+ crash_size, crash_base);
+
+ return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
+}
+
+/*
+ * That function is the entry point for command line parsing and should be
+ * called from the arch-specific code.
+ */
+int __init parse_crashkernel(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", NULL);
+}
+
+int __init parse_crashkernel_high(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", suffix_tbl[SUFFIX_HIGH]);
+}
+
+int __init parse_crashkernel_low(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", suffix_tbl[SUFFIX_LOW]);
+}
+
+Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
+ void *data, size_t data_len)
+{
+ struct elf_note *note = (struct elf_note *)buf;
+
+ note->n_namesz = strlen(name) + 1;
+ note->n_descsz = data_len;
+ note->n_type = type;
+ buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word));
+ memcpy(buf, name, note->n_namesz);
+ buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word));
+ memcpy(buf, data, data_len);
+ buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word));
+
+ return buf;
+}
+
+void final_note(Elf_Word *buf)
+{
+ memset(buf, 0, sizeof(struct elf_note));
+}
+
+static void update_vmcoreinfo_note(void)
+{
+ u32 *buf = vmcoreinfo_note;
+
+ if (!vmcoreinfo_size)
+ return;
+ buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
+ vmcoreinfo_size);
+ final_note(buf);
+}
+
+void crash_save_vmcoreinfo(void)
+{
+ vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
+ update_vmcoreinfo_note();
+}
+
+void vmcoreinfo_append_str(const char *fmt, ...)
+{
+ va_list args;
+ char buf[0x50];
+ size_t r;
+
+ va_start(args, fmt);
+ r = vscnprintf(buf, sizeof(buf), fmt, args);
+ va_end(args);
+
+ r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+
+ memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
+
+ vmcoreinfo_size += r;
+}
+
+/*
+ * provide an empty default implementation here -- architecture
+ * code may override this
+ */
+void __weak arch_crash_save_vmcoreinfo(void)
+{}
+
+phys_addr_t __weak paddr_vmcoreinfo_note(void)
+{
+ return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+}
+
+static int __init crash_save_vmcoreinfo_init(void)
+{
+ VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+ VMCOREINFO_PAGESIZE(PAGE_SIZE);
+
+ VMCOREINFO_SYMBOL(init_uts_ns);
+ VMCOREINFO_SYMBOL(node_online_map);
+#ifdef CONFIG_MMU
+ VMCOREINFO_SYMBOL(swapper_pg_dir);
+#endif
+ VMCOREINFO_SYMBOL(_stext);
+ VMCOREINFO_SYMBOL(vmap_area_list);
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+ VMCOREINFO_SYMBOL(mem_map);
+ VMCOREINFO_SYMBOL(contig_page_data);
+#endif
+#ifdef CONFIG_SPARSEMEM
+ VMCOREINFO_SYMBOL(mem_section);
+ VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
+ VMCOREINFO_STRUCT_SIZE(mem_section);
+ VMCOREINFO_OFFSET(mem_section, section_mem_map);
+#endif
+ VMCOREINFO_STRUCT_SIZE(page);
+ VMCOREINFO_STRUCT_SIZE(pglist_data);
+ VMCOREINFO_STRUCT_SIZE(zone);
+ VMCOREINFO_STRUCT_SIZE(free_area);
+ VMCOREINFO_STRUCT_SIZE(list_head);
+ VMCOREINFO_SIZE(nodemask_t);
+ VMCOREINFO_OFFSET(page, flags);
+ VMCOREINFO_OFFSET(page, _refcount);
+ VMCOREINFO_OFFSET(page, mapping);
+ VMCOREINFO_OFFSET(page, lru);
+ VMCOREINFO_OFFSET(page, _mapcount);
+ VMCOREINFO_OFFSET(page, private);
+ VMCOREINFO_OFFSET(page, compound_dtor);
+ VMCOREINFO_OFFSET(page, compound_order);
+ VMCOREINFO_OFFSET(page, compound_head);
+ VMCOREINFO_OFFSET(pglist_data, node_zones);
+ VMCOREINFO_OFFSET(pglist_data, nr_zones);
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+ VMCOREINFO_OFFSET(pglist_data, node_mem_map);
+#endif
+ VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
+ VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
+ VMCOREINFO_OFFSET(pglist_data, node_id);
+ VMCOREINFO_OFFSET(zone, free_area);
+ VMCOREINFO_OFFSET(zone, vm_stat);
+ VMCOREINFO_OFFSET(zone, spanned_pages);
+ VMCOREINFO_OFFSET(free_area, free_list);
+ VMCOREINFO_OFFSET(list_head, next);
+ VMCOREINFO_OFFSET(list_head, prev);
+ VMCOREINFO_OFFSET(vmap_area, va_start);
+ VMCOREINFO_OFFSET(vmap_area, list);
+ VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
+ log_buf_vmcoreinfo_setup();
+ VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
+ VMCOREINFO_NUMBER(NR_FREE_PAGES);
+ VMCOREINFO_NUMBER(PG_lru);
+ VMCOREINFO_NUMBER(PG_private);
+ VMCOREINFO_NUMBER(PG_swapcache);
+ VMCOREINFO_NUMBER(PG_slab);
+#ifdef CONFIG_MEMORY_FAILURE
+ VMCOREINFO_NUMBER(PG_hwpoison);
+#endif
+ VMCOREINFO_NUMBER(PG_head_mask);
+ VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
+#ifdef CONFIG_HUGETLB_PAGE
+ VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
+#endif
+
+ arch_crash_save_vmcoreinfo();
+ update_vmcoreinfo_note();
+
+ return 0;
+}
+
+subsys_initcall(crash_save_vmcoreinfo_init);
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index c04917cad1bf..1b2be63c8528 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -229,12 +229,18 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
}
if (regs) {
+ mm_segment_t fs;
+
if (crosstask)
goto exit_put;
if (add_mark)
perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
+
+ fs = get_fs();
+ set_fs(USER_DS);
perf_callchain_user(&ctx, regs);
+ set_fs(fs);
}
}
diff --git a/kernel/fork.c b/kernel/fork.c
index dd5a371c392a..aa1076c5e4a9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -179,6 +179,24 @@ void __weak arch_release_thread_stack(unsigned long *stack)
*/
#define NR_CACHED_STACKS 2
static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
+
+static int free_vm_stack_cache(unsigned int cpu)
+{
+ struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
+ int i;
+
+ for (i = 0; i < NR_CACHED_STACKS; i++) {
+ struct vm_struct *vm_stack = cached_vm_stacks[i];
+
+ if (!vm_stack)
+ continue;
+
+ vfree(vm_stack->addr);
+ cached_vm_stacks[i] = NULL;
+ }
+
+ return 0;
+}
#endif
static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
@@ -203,7 +221,7 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
VMALLOC_START, VMALLOC_END,
- THREADINFO_GFP | __GFP_HIGHMEM,
+ THREADINFO_GFP,
PAGE_KERNEL,
0, node, __builtin_return_address(0));
@@ -467,6 +485,11 @@ void __init fork_init(void)
for (i = 0; i < UCOUNT_COUNTS; i++) {
init_user_ns.ucount_max[i] = max_threads/2;
}
+
+#ifdef CONFIG_VMAP_STACK
+ cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
+ NULL, free_vm_stack_cache);
+#endif
}
int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -537,7 +560,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
set_task_stack_end_magic(tsk);
#ifdef CONFIG_CC_STACKPROTECTOR
- tsk->stack_canary = get_random_int();
+ tsk->stack_canary = get_random_long();
#endif
/*
@@ -1314,7 +1337,7 @@ void __cleanup_sighand(struct sighand_struct *sighand)
if (atomic_dec_and_test(&sighand->count)) {
signalfd_cleanup(sighand);
/*
- * sighand_cachep is SLAB_DESTROY_BY_RCU so we can free it
+ * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it
* without an RCU grace period, see __lock_task_sighand().
*/
kmem_cache_free(sighand_cachep, sighand);
@@ -1822,11 +1845,13 @@ static __latent_entropy struct task_struct *copy_process(
*/
recalc_sigpending();
if (signal_pending(current)) {
- spin_unlock(&current->sighand->siglock);
- write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_cancel_cgroup;
}
+ if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
+ retval = -ENOMEM;
+ goto bad_fork_cancel_cgroup;
+ }
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -1884,6 +1909,8 @@ static __latent_entropy struct task_struct *copy_process(
return p;
bad_fork_cancel_cgroup:
+ spin_unlock(&current->sighand->siglock);
+ write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p);
bad_fork_free_pid:
cgroup_threadgroup_change_end(current);
@@ -2153,7 +2180,7 @@ void __init proc_caches_init(void)
{
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor);
signal_cachep = kmem_cache_create("signal_cache",
sizeof(struct signal_struct), 0,
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index 2f9df37940a0..c51a49c9be70 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -98,6 +98,12 @@ void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters)
}
EXPORT_SYMBOL(__gcov_merge_icall_topn);
+void __gcov_exit(void)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_exit);
+
/**
* gcov_enable_events - enable event reporting through gcov_event()
*
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 6a5c239c7669..46a18e72bce6 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -18,7 +18,9 @@
#include <linux/vmalloc.h>
#include "gcov.h"
-#if (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
+#if (__GNUC__ >= 7)
+#define GCOV_COUNTERS 9
+#elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
#define GCOV_COUNTERS 10
#elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9
#define GCOV_COUNTERS 9
diff --git a/kernel/groups.c b/kernel/groups.c
index 8dd7a61b7115..d09727692a2a 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -18,7 +18,7 @@ struct group_info *groups_alloc(int gidsetsize)
len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize;
gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY);
if (!gi)
- gi = __vmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_HIGHMEM, PAGE_KERNEL);
+ gi = __vmalloc(len, GFP_KERNEL_ACCOUNT, PAGE_KERNEL);
if (!gi)
return NULL;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index f0f8e2a8496f..751593ed7c0b 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -43,6 +43,7 @@ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_
int __read_mostly sysctl_hung_task_warnings = 10;
static int __read_mostly did_panic;
+static bool hung_task_show_lock;
static struct task_struct *watchdog_task;
@@ -120,12 +121,14 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
" disables this message.\n");
sched_show_task(t);
- debug_show_all_locks();
+ hung_task_show_lock = true;
}
touch_nmi_watchdog();
if (sysctl_hung_task_panic) {
+ if (hung_task_show_lock)
+ debug_show_all_locks();
trigger_all_cpu_backtrace();
panic("hung_task: blocked tasks");
}
@@ -172,6 +175,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
if (test_taint(TAINT_DIE) || did_panic)
return;
+ hung_task_show_lock = false;
rcu_read_lock();
for_each_process_thread(g, t) {
if (!max_count--)
@@ -187,6 +191,8 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
}
unlock:
rcu_read_unlock();
+ if (hung_task_show_lock)
+ debug_show_all_locks();
}
static long hung_timeout_jiffies(unsigned long last_checked,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ae1c90f20381..070be980c37a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1559,7 +1559,7 @@ void remove_irq(unsigned int irq, struct irqaction *act)
struct irq_desc *desc = irq_to_desc(irq);
if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
- __free_irq(irq, act->dev_id);
+ __free_irq(irq, act->dev_id);
}
EXPORT_SYMBOL_GPL(remove_irq);
@@ -1576,20 +1576,27 @@ EXPORT_SYMBOL_GPL(remove_irq);
* have completed.
*
* This function must not be called from interrupt context.
+ *
+ * Returns the devname argument passed to request_irq.
*/
-void free_irq(unsigned int irq, void *dev_id)
+const void *free_irq(unsigned int irq, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
+ struct irqaction *action;
+ const char *devname;
if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
- return;
+ return NULL;
#ifdef CONFIG_SMP
if (WARN_ON(desc->affinity_notify))
desc->affinity_notify = NULL;
#endif
- kfree(__free_irq(irq, dev_id));
+ action = __free_irq(irq, dev_id);
+ devname = action->name;
+ kfree(action);
+ return devname;
}
EXPORT_SYMBOL(free_irq);
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 85e5546cd791..cd771993f96f 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -60,15 +60,8 @@ void notrace __sanitizer_cov_trace_pc(void)
/*
* We are interested in code coverage as a function of a syscall inputs,
* so we ignore code executed in interrupts.
- * The checks for whether we are in an interrupt are open-coded, because
- * 1. We can't use in_interrupt() here, since it also returns true
- * when we are inside local_bh_disable() section.
- * 2. We don't want to use (in_irq() | in_serving_softirq() | in_nmi()),
- * since that leads to slower generated code (three separate tests,
- * one for each of the flags).
*/
- if (!t || (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET
- | NMI_MASK)))
+ if (!t || !in_task())
return;
mode = READ_ONCE(t->kcov_mode);
if (mode == KCOV_MODE_TRACE) {
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index bfe62d5b3872..ae1a3ba24df5 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -51,12 +51,6 @@ DEFINE_MUTEX(kexec_mutex);
/* Per cpu memory for storing cpu states in case of system crash. */
note_buf_t __percpu *crash_notes;
-/* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
-size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
-
/* Flag to indicate we are going to kexec a new kernel */
bool kexec_in_progress = false;
@@ -996,34 +990,6 @@ unlock:
return ret;
}
-static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
- size_t data_len)
-{
- struct elf_note note;
-
- note.n_namesz = strlen(name) + 1;
- note.n_descsz = data_len;
- note.n_type = type;
- memcpy(buf, &note, sizeof(note));
- buf += (sizeof(note) + 3)/4;
- memcpy(buf, name, note.n_namesz);
- buf += (note.n_namesz + 3)/4;
- memcpy(buf, data, note.n_descsz);
- buf += (note.n_descsz + 3)/4;
-
- return buf;
-}
-
-static void final_note(u32 *buf)
-{
- struct elf_note note;
-
- note.n_namesz = 0;
- note.n_descsz = 0;
- note.n_type = 0;
- memcpy(buf, &note, sizeof(note));
-}
-
void crash_save_cpu(struct pt_regs *regs, int cpu)
{
struct elf_prstatus prstatus;
@@ -1085,403 +1051,6 @@ subsys_initcall(crash_notes_memory_init);
/*
- * parsing the "crashkernel" commandline
- *
- * this code is intended to be called from architecture specific code
- */
-
-
-/*
- * This function parses command lines in the format
- *
- * crashkernel=ramsize-range:size[,...][@offset]
- *
- * The function returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_mem(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- char *cur = cmdline, *tmp;
-
- /* for each entry of the comma-separated list */
- do {
- unsigned long long start, end = ULLONG_MAX, size;
-
- /* get the start of the range */
- start = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("crashkernel: Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (*cur != '-') {
- pr_warn("crashkernel: '-' expected\n");
- return -EINVAL;
- }
- cur++;
-
- /* if no ':' is here, than we read the end */
- if (*cur != ':') {
- end = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("crashkernel: Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (end <= start) {
- pr_warn("crashkernel: end <= start\n");
- return -EINVAL;
- }
- }
-
- if (*cur != ':') {
- pr_warn("crashkernel: ':' expected\n");
- return -EINVAL;
- }
- cur++;
-
- size = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (size >= system_ram) {
- pr_warn("crashkernel: invalid size\n");
- return -EINVAL;
- }
-
- /* match ? */
- if (system_ram >= start && system_ram < end) {
- *crash_size = size;
- break;
- }
- } while (*cur++ == ',');
-
- if (*crash_size > 0) {
- while (*cur && *cur != ' ' && *cur != '@')
- cur++;
- if (*cur == '@') {
- cur++;
- *crash_base = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("Memory value expected after '@'\n");
- return -EINVAL;
- }
- }
- }
-
- return 0;
-}
-
-/*
- * That function parses "simple" (old) crashkernel command lines like
- *
- * crashkernel=size[@offset]
- *
- * It returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_simple(char *cmdline,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- char *cur = cmdline;
-
- *crash_size = memparse(cmdline, &cur);
- if (cmdline == cur) {
- pr_warn("crashkernel: memory value expected\n");
- return -EINVAL;
- }
-
- if (*cur == '@')
- *crash_base = memparse(cur+1, &cur);
- else if (*cur != ' ' && *cur != '\0') {
- pr_warn("crashkernel: unrecognized char: %c\n", *cur);
- return -EINVAL;
- }
-
- return 0;
-}
-
-#define SUFFIX_HIGH 0
-#define SUFFIX_LOW 1
-#define SUFFIX_NULL 2
-static __initdata char *suffix_tbl[] = {
- [SUFFIX_HIGH] = ",high",
- [SUFFIX_LOW] = ",low",
- [SUFFIX_NULL] = NULL,
-};
-
-/*
- * That function parses "suffix" crashkernel command lines like
- *
- * crashkernel=size,[high|low]
- *
- * It returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_suffix(char *cmdline,
- unsigned long long *crash_size,
- const char *suffix)
-{
- char *cur = cmdline;
-
- *crash_size = memparse(cmdline, &cur);
- if (cmdline == cur) {
- pr_warn("crashkernel: memory value expected\n");
- return -EINVAL;
- }
-
- /* check with suffix */
- if (strncmp(cur, suffix, strlen(suffix))) {
- pr_warn("crashkernel: unrecognized char: %c\n", *cur);
- return -EINVAL;
- }
- cur += strlen(suffix);
- if (*cur != ' ' && *cur != '\0') {
- pr_warn("crashkernel: unrecognized char: %c\n", *cur);
- return -EINVAL;
- }
-
- return 0;
-}
-
-static __init char *get_last_crashkernel(char *cmdline,
- const char *name,
- const char *suffix)
-{
- char *p = cmdline, *ck_cmdline = NULL;
-
- /* find crashkernel and use the last one if there are more */
- p = strstr(p, name);
- while (p) {
- char *end_p = strchr(p, ' ');
- char *q;
-
- if (!end_p)
- end_p = p + strlen(p);
-
- if (!suffix) {
- int i;
-
- /* skip the one with any known suffix */
- for (i = 0; suffix_tbl[i]; i++) {
- q = end_p - strlen(suffix_tbl[i]);
- if (!strncmp(q, suffix_tbl[i],
- strlen(suffix_tbl[i])))
- goto next;
- }
- ck_cmdline = p;
- } else {
- q = end_p - strlen(suffix);
- if (!strncmp(q, suffix, strlen(suffix)))
- ck_cmdline = p;
- }
-next:
- p = strstr(p+1, name);
- }
-
- if (!ck_cmdline)
- return NULL;
-
- return ck_cmdline;
-}
-
-static int __init __parse_crashkernel(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base,
- const char *name,
- const char *suffix)
-{
- char *first_colon, *first_space;
- char *ck_cmdline;
-
- BUG_ON(!crash_size || !crash_base);
- *crash_size = 0;
- *crash_base = 0;
-
- ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
-
- if (!ck_cmdline)
- return -EINVAL;
-
- ck_cmdline += strlen(name);
-
- if (suffix)
- return parse_crashkernel_suffix(ck_cmdline, crash_size,
- suffix);
- /*
- * if the commandline contains a ':', then that's the extended
- * syntax -- if not, it must be the classic syntax
- */
- first_colon = strchr(ck_cmdline, ':');
- first_space = strchr(ck_cmdline, ' ');
- if (first_colon && (!first_space || first_colon < first_space))
- return parse_crashkernel_mem(ck_cmdline, system_ram,
- crash_size, crash_base);
-
- return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
-}
-
-/*
- * That function is the entry point for command line parsing and should be
- * called from the arch-specific code.
- */
-int __init parse_crashkernel(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", NULL);
-}
-
-int __init parse_crashkernel_high(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", suffix_tbl[SUFFIX_HIGH]);
-}
-
-int __init parse_crashkernel_low(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", suffix_tbl[SUFFIX_LOW]);
-}
-
-static void update_vmcoreinfo_note(void)
-{
- u32 *buf = vmcoreinfo_note;
-
- if (!vmcoreinfo_size)
- return;
- buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
- vmcoreinfo_size);
- final_note(buf);
-}
-
-void crash_save_vmcoreinfo(void)
-{
- vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
- update_vmcoreinfo_note();
-}
-
-void vmcoreinfo_append_str(const char *fmt, ...)
-{
- va_list args;
- char buf[0x50];
- size_t r;
-
- va_start(args, fmt);
- r = vscnprintf(buf, sizeof(buf), fmt, args);
- va_end(args);
-
- r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
-
- memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
-
- vmcoreinfo_size += r;
-}
-
-/*
- * provide an empty default implementation here -- architecture
- * code may override this
- */
-void __weak arch_crash_save_vmcoreinfo(void)
-{}
-
-phys_addr_t __weak paddr_vmcoreinfo_note(void)
-{
- return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
-}
-
-static int __init crash_save_vmcoreinfo_init(void)
-{
- VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
- VMCOREINFO_PAGESIZE(PAGE_SIZE);
-
- VMCOREINFO_SYMBOL(init_uts_ns);
- VMCOREINFO_SYMBOL(node_online_map);
-#ifdef CONFIG_MMU
- VMCOREINFO_SYMBOL(swapper_pg_dir);
-#endif
- VMCOREINFO_SYMBOL(_stext);
- VMCOREINFO_SYMBOL(vmap_area_list);
-
-#ifndef CONFIG_NEED_MULTIPLE_NODES
- VMCOREINFO_SYMBOL(mem_map);
- VMCOREINFO_SYMBOL(contig_page_data);
-#endif
-#ifdef CONFIG_SPARSEMEM
- VMCOREINFO_SYMBOL(mem_section);
- VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
- VMCOREINFO_STRUCT_SIZE(mem_section);
- VMCOREINFO_OFFSET(mem_section, section_mem_map);
-#endif
- VMCOREINFO_STRUCT_SIZE(page);
- VMCOREINFO_STRUCT_SIZE(pglist_data);
- VMCOREINFO_STRUCT_SIZE(zone);
- VMCOREINFO_STRUCT_SIZE(free_area);
- VMCOREINFO_STRUCT_SIZE(list_head);
- VMCOREINFO_SIZE(nodemask_t);
- VMCOREINFO_OFFSET(page, flags);
- VMCOREINFO_OFFSET(page, _refcount);
- VMCOREINFO_OFFSET(page, mapping);
- VMCOREINFO_OFFSET(page, lru);
- VMCOREINFO_OFFSET(page, _mapcount);
- VMCOREINFO_OFFSET(page, private);
- VMCOREINFO_OFFSET(page, compound_dtor);
- VMCOREINFO_OFFSET(page, compound_order);
- VMCOREINFO_OFFSET(page, compound_head);
- VMCOREINFO_OFFSET(pglist_data, node_zones);
- VMCOREINFO_OFFSET(pglist_data, nr_zones);
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
- VMCOREINFO_OFFSET(pglist_data, node_mem_map);
-#endif
- VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
- VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
- VMCOREINFO_OFFSET(pglist_data, node_id);
- VMCOREINFO_OFFSET(zone, free_area);
- VMCOREINFO_OFFSET(zone, vm_stat);
- VMCOREINFO_OFFSET(zone, spanned_pages);
- VMCOREINFO_OFFSET(free_area, free_list);
- VMCOREINFO_OFFSET(list_head, next);
- VMCOREINFO_OFFSET(list_head, prev);
- VMCOREINFO_OFFSET(vmap_area, va_start);
- VMCOREINFO_OFFSET(vmap_area, list);
- VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
- log_buf_kexec_setup();
- VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
- VMCOREINFO_NUMBER(NR_FREE_PAGES);
- VMCOREINFO_NUMBER(PG_lru);
- VMCOREINFO_NUMBER(PG_private);
- VMCOREINFO_NUMBER(PG_swapcache);
- VMCOREINFO_NUMBER(PG_slab);
-#ifdef CONFIG_MEMORY_FAILURE
- VMCOREINFO_NUMBER(PG_hwpoison);
-#endif
- VMCOREINFO_NUMBER(PG_head_mask);
- VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
-#ifdef CONFIG_HUGETLB_PAGE
- VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
-#endif
-
- arch_crash_save_vmcoreinfo();
- update_vmcoreinfo_note();
-
- return 0;
-}
-
-subsys_initcall(crash_save_vmcoreinfo_init);
-
-/*
* Move into place and start executing a preloaded standalone
* executable. If nothing was preloaded return an error.
*/
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 0999679d6f26..23cd70651238 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -125,6 +125,10 @@ static ssize_t kexec_crash_size_store(struct kobject *kobj,
}
KERNEL_ATTR_RW(kexec_crash_size);
+#endif /* CONFIG_KEXEC_CORE */
+
+#ifdef CONFIG_CRASH_CORE
+
static ssize_t vmcoreinfo_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
@@ -134,7 +138,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
}
KERNEL_ATTR_RO(vmcoreinfo);
-#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_CRASH_CORE */
/* whether file capabilities are enabled */
static ssize_t fscaps_show(struct kobject *kobj,
@@ -219,6 +223,8 @@ static struct attribute * kernel_attrs[] = {
&kexec_loaded_attr.attr,
&kexec_crash_loaded_attr.attr,
&kexec_crash_size_attr.attr,
+#endif
+#ifdef CONFIG_CRASH_CORE
&vmcoreinfo_attr.attr,
#endif
#ifndef CONFIG_TINY_RCU
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 0a1b3c748478..c0e31bfee25c 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1158,10 +1158,10 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth,
return 0;
printk("\n");
- printk("======================================================\n");
- printk("[ INFO: possible circular locking dependency detected ]\n");
+ pr_warn("======================================================\n");
+ pr_warn("WARNING: possible circular locking dependency detected\n");
print_kernel_ident();
- printk("-------------------------------------------------------\n");
+ pr_warn("------------------------------------------------------\n");
printk("%s/%d is trying to acquire lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(check_src);
@@ -1496,11 +1496,11 @@ print_bad_irq_dependency(struct task_struct *curr,
return 0;
printk("\n");
- printk("======================================================\n");
- printk("[ INFO: %s-safe -> %s-unsafe lock order detected ]\n",
+ pr_warn("=====================================================\n");
+ pr_warn("WARNING: %s-safe -> %s-unsafe lock order detected\n",
irqclass, irqclass);
print_kernel_ident();
- printk("------------------------------------------------------\n");
+ pr_warn("-----------------------------------------------------\n");
printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
curr->comm, task_pid_nr(curr),
curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT,
@@ -1725,10 +1725,10 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
return 0;
printk("\n");
- printk("=============================================\n");
- printk("[ INFO: possible recursive locking detected ]\n");
+ pr_warn("============================================\n");
+ pr_warn("WARNING: possible recursive locking detected\n");
print_kernel_ident();
- printk("---------------------------------------------\n");
+ pr_warn("--------------------------------------------\n");
printk("%s/%d is trying to acquire lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(next);
@@ -2075,10 +2075,10 @@ static void print_collision(struct task_struct *curr,
struct lock_chain *chain)
{
printk("\n");
- printk("======================\n");
- printk("[chain_key collision ]\n");
+ pr_warn("============================\n");
+ pr_warn("WARNING: chain_key collision\n");
print_kernel_ident();
- printk("----------------------\n");
+ pr_warn("----------------------------\n");
printk("%s/%d: ", current->comm, task_pid_nr(current));
printk("Hash chain already cached but the contents don't match!\n");
@@ -2374,10 +2374,10 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
return 0;
printk("\n");
- printk("=================================\n");
- printk("[ INFO: inconsistent lock state ]\n");
+ pr_warn("================================\n");
+ pr_warn("WARNING: inconsistent lock state\n");
print_kernel_ident();
- printk("---------------------------------\n");
+ pr_warn("--------------------------------\n");
printk("inconsistent {%s} -> {%s} usage.\n",
usage_str[prev_bit], usage_str[new_bit]);
@@ -2439,10 +2439,10 @@ print_irq_inversion_bug(struct task_struct *curr,
return 0;
printk("\n");
- printk("=========================================================\n");
- printk("[ INFO: possible irq lock inversion dependency detected ]\n");
+ pr_warn("========================================================\n");
+ pr_warn("WARNING: possible irq lock inversion dependency detected\n");
print_kernel_ident();
- printk("---------------------------------------------------------\n");
+ pr_warn("--------------------------------------------------------\n");
printk("%s/%d just changed the state of lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(this);
@@ -3190,10 +3190,10 @@ print_lock_nested_lock_not_held(struct task_struct *curr,
return 0;
printk("\n");
- printk("==================================\n");
- printk("[ BUG: Nested lock was not taken ]\n");
+ pr_warn("==================================\n");
+ pr_warn("WARNING: Nested lock was not taken\n");
print_kernel_ident();
- printk("----------------------------------\n");
+ pr_warn("----------------------------------\n");
printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr));
print_lock(hlock);
@@ -3403,10 +3403,10 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock,
return 0;
printk("\n");
- printk("=====================================\n");
- printk("[ BUG: bad unlock balance detected! ]\n");
+ pr_warn("=====================================\n");
+ pr_warn("WARNING: bad unlock balance detected!\n");
print_kernel_ident();
- printk("-------------------------------------\n");
+ pr_warn("-------------------------------------\n");
printk("%s/%d is trying to release lock (",
curr->comm, task_pid_nr(curr));
print_lockdep_cache(lock);
@@ -3975,10 +3975,10 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock,
return 0;
printk("\n");
- printk("=================================\n");
- printk("[ BUG: bad contention detected! ]\n");
+ pr_warn("=================================\n");
+ pr_warn("WARNING: bad contention detected!\n");
print_kernel_ident();
- printk("---------------------------------\n");
+ pr_warn("---------------------------------\n");
printk("%s/%d is trying to contend lock (",
curr->comm, task_pid_nr(curr));
print_lockdep_cache(lock);
@@ -4319,10 +4319,10 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from,
return;
printk("\n");
- printk("=========================\n");
- printk("[ BUG: held lock freed! ]\n");
+ pr_warn("=========================\n");
+ pr_warn("WARNING: held lock freed!\n");
print_kernel_ident();
- printk("-------------------------\n");
+ pr_warn("-------------------------\n");
printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n",
curr->comm, task_pid_nr(curr), mem_from, mem_to-1);
print_lock(hlock);
@@ -4377,11 +4377,11 @@ static void print_held_locks_bug(void)
return;
printk("\n");
- printk("=====================================\n");
- printk("[ BUG: %s/%d still has locks held! ]\n",
+ pr_warn("====================================\n");
+ pr_warn("WARNING: %s/%d still has locks held!\n",
current->comm, task_pid_nr(current));
print_kernel_ident();
- printk("-------------------------------------\n");
+ pr_warn("------------------------------------\n");
lockdep_print_held_locks(current);
printk("\nstack backtrace:\n");
dump_stack();
@@ -4446,7 +4446,7 @@ retry:
} while_each_thread(g, p);
printk("\n");
- printk("=============================================\n\n");
+ pr_warn("=============================================\n\n");
if (unlock)
read_unlock(&tasklist_lock);
@@ -4476,10 +4476,10 @@ asmlinkage __visible void lockdep_sys_exit(void)
if (!debug_locks_off())
return;
printk("\n");
- printk("================================================\n");
- printk("[ BUG: lock held when returning to user space! ]\n");
+ pr_warn("================================================\n");
+ pr_warn("WARNING: lock held when returning to user space!\n");
print_kernel_ident();
- printk("------------------------------------------------\n");
+ pr_warn("------------------------------------------------\n");
printk("%s/%d is leaving the kernel with locks still held!\n",
curr->comm, curr->pid);
lockdep_print_held_locks(curr);
@@ -4496,13 +4496,13 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
/* Note: the following can be executed concurrently, so be careful. */
printk("\n");
- pr_err("===============================\n");
- pr_err("[ ERR: suspicious RCU usage. ]\n");
+ pr_warn("=============================\n");
+ pr_warn("WARNING: suspicious RCU usage\n");
print_kernel_ident();
- pr_err("-------------------------------\n");
- pr_err("%s:%d %s!\n", file, line, s);
- pr_err("\nother info that might help us debug this:\n\n");
- pr_err("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
+ pr_warn("-----------------------------\n");
+ printk("%s:%d %s!\n", file, line, s);
+ printk("\nother info that might help us debug this:\n\n");
+ printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
!rcu_lockdep_current_cpu_online()
? "RCU used illegally from offline CPU!\n"
: !rcu_is_watching()
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 32fe775a2eaf..58e366ad36f4 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -102,10 +102,11 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter)
return;
}
- printk("\n============================================\n");
- printk( "[ BUG: circular locking deadlock detected! ]\n");
- printk("%s\n", print_tainted());
- printk( "--------------------------------------------\n");
+ pr_warn("\n");
+ pr_warn("============================================\n");
+ pr_warn("WARNING: circular locking deadlock detected!\n");
+ pr_warn("%s\n", print_tainted());
+ pr_warn("--------------------------------------------\n");
printk("%s/%d is deadlocking current task %s/%d\n\n",
task->comm, task_pid_nr(task),
current->comm, task_pid_nr(current));
diff --git a/kernel/module.c b/kernel/module.c
index f37308b733d8..4a3665f8f837 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -49,6 +49,9 @@
#include <linux/rculist.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
+#ifdef CONFIG_STRICT_MODULE_RWX
+#include <asm/set_memory.h>
+#endif
#include <asm/mmu_context.h>
#include <linux/license.h>
#include <asm/sections.h>
@@ -2864,7 +2867,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
/* Suck in entire file: we'll want most of it. */
info->hdr = __vmalloc(info->len,
- GFP_KERNEL | __GFP_HIGHMEM | __GFP_NOWARN, PAGE_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN, PAGE_KERNEL);
if (!info->hdr)
return -ENOMEM;
diff --git a/kernel/pid.c b/kernel/pid.c
index 0143ac0ddceb..fd1cde1e4576 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -321,8 +321,10 @@ struct pid *alloc_pid(struct pid_namespace *ns)
}
if (unlikely(is_child_reaper(pid))) {
- if (pid_ns_prepare_proc(ns))
+ if (pid_ns_prepare_proc(ns)) {
+ disable_pid_allocation(ns);
goto out_free;
+ }
}
get_pid_ns(ns);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index de461aa0bf9a..74a5a7255b4d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -277,7 +277,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
* if reparented.
*/
for (;;) {
- set_current_state(TASK_UNINTERRUPTIBLE);
+ set_current_state(TASK_INTERRUPTIBLE);
if (pid_ns->nr_hashed == init_pids)
break;
schedule();
@@ -374,6 +374,29 @@ static struct ns_common *pidns_get(struct task_struct *task)
return ns ? &ns->ns : NULL;
}
+static struct ns_common *pidns_for_children_get(struct task_struct *task)
+{
+ struct pid_namespace *ns = NULL;
+
+ task_lock(task);
+ if (task->nsproxy) {
+ ns = task->nsproxy->pid_ns_for_children;
+ get_pid_ns(ns);
+ }
+ task_unlock(task);
+
+ if (ns) {
+ read_lock(&tasklist_lock);
+ if (!ns->child_reaper) {
+ put_pid_ns(ns);
+ ns = NULL;
+ }
+ read_unlock(&tasklist_lock);
+ }
+
+ return ns ? &ns->ns : NULL;
+}
+
static void pidns_put(struct ns_common *ns)
{
put_pid_ns(to_pid_ns(ns));
@@ -443,6 +466,17 @@ const struct proc_ns_operations pidns_operations = {
.get_parent = pidns_get_parent,
};
+const struct proc_ns_operations pidns_for_children_operations = {
+ .name = "pid_for_children",
+ .real_ns_name = "pid",
+ .type = CLONE_NEWPID,
+ .get = pidns_for_children_get,
+ .put = pidns_put,
+ .install = pidns_install,
+ .owner = pidns_owner,
+ .get_parent = pidns_get_parent,
+};
+
static __init int pid_namespaces_init(void)
{
pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index c7209f060eeb..78672d324a6e 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -132,7 +132,7 @@ int freeze_processes(void)
if (!pm_freezing)
atomic_inc(&system_freezing_cnt);
- pm_wakeup_clear();
+ pm_wakeup_clear(true);
pr_info("Freezing user space processes ... ");
pm_freezing = true;
error = try_to_freeze_tasks(true);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index d79a38de425a..3b1e0f3ad07f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -36,6 +36,9 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
+#ifdef CONFIG_STRICT_KERNEL_RWX
+#include <asm/set_memory.h>
+#endif
#include "power.h"
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 15e6baef5c73..c0248c74d6d4 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -72,6 +72,8 @@ static void freeze_begin(void)
static void freeze_enter(void)
{
+ trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, true);
+
spin_lock_irq(&suspend_freeze_lock);
if (pm_wakeup_pending())
goto out;
@@ -98,6 +100,27 @@ static void freeze_enter(void)
out:
suspend_freeze_state = FREEZE_STATE_NONE;
spin_unlock_irq(&suspend_freeze_lock);
+
+ trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, false);
+}
+
+static void s2idle_loop(void)
+{
+ do {
+ freeze_enter();
+
+ if (freeze_ops && freeze_ops->wake)
+ freeze_ops->wake();
+
+ dpm_resume_noirq(PMSG_RESUME);
+ if (freeze_ops && freeze_ops->sync)
+ freeze_ops->sync();
+
+ if (pm_wakeup_pending())
+ break;
+
+ pm_wakeup_clear(false);
+ } while (!dpm_suspend_noirq(PMSG_SUSPEND));
}
void freeze_wake(void)
@@ -371,10 +394,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
* all the devices are suspended.
*/
if (state == PM_SUSPEND_FREEZE) {
- trace_suspend_resume(TPS("machine_suspend"), state, true);
- freeze_enter();
- trace_suspend_resume(TPS("machine_suspend"), state, false);
- goto Platform_wake;
+ s2idle_loop();
+ goto Platform_early_resume;
}
error = disable_nonboot_cpus();
diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c
index d5760c42f042..61d41ca41844 100644
--- a/kernel/printk/braille.c
+++ b/kernel/printk/braille.c
@@ -2,12 +2,13 @@
#include <linux/kernel.h>
#include <linux/console.h>
+#include <linux/errno.h>
#include <linux/string.h>
#include "console_cmdline.h"
#include "braille.h"
-char *_braille_console_setup(char **str, char **brl_options)
+int _braille_console_setup(char **str, char **brl_options)
{
if (!strncmp(*str, "brl,", 4)) {
*brl_options = "";
@@ -15,14 +16,14 @@ char *_braille_console_setup(char **str, char **brl_options)
} else if (!strncmp(*str, "brl=", 4)) {
*brl_options = *str + 4;
*str = strchr(*brl_options, ',');
- if (!*str)
+ if (!*str) {
pr_err("need port name after brl=\n");
- else
- *((*str)++) = 0;
- } else
- return NULL;
+ return -EINVAL;
+ }
+ *((*str)++) = 0;
+ }
- return *str;
+ return 0;
}
int
diff --git a/kernel/printk/braille.h b/kernel/printk/braille.h
index 769d771145c8..749a6756843a 100644
--- a/kernel/printk/braille.h
+++ b/kernel/printk/braille.h
@@ -9,7 +9,14 @@ braille_set_options(struct console_cmdline *c, char *brl_options)
c->brl_options = brl_options;
}
-char *
+/*
+ * Setup console according to braille options.
+ * Return -EINVAL on syntax error, 0 on success (or no braille option was
+ * actually given).
+ * Modifies str to point to the serial options
+ * Sets brl_options to the parsed braille options.
+ */
+int
_braille_console_setup(char **str, char **brl_options);
int
@@ -25,10 +32,10 @@ braille_set_options(struct console_cmdline *c, char *brl_options)
{
}
-static inline char *
+static inline int
_braille_console_setup(char **str, char **brl_options)
{
- return NULL;
+ return 0;
}
static inline int
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 779479ac9f57..a1aecf44ab07 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -32,7 +32,7 @@
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/syscalls.h>
-#include <linux/kexec.h>
+#include <linux/crash_core.h>
#include <linux/kdb.h>
#include <linux/ratelimit.h>
#include <linux/kmsg_dump.h>
@@ -1002,7 +1002,7 @@ const struct file_operations kmsg_fops = {
.release = devkmsg_release,
};
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_CORE
/*
* This appends the listed symbols to /proc/vmcore
*
@@ -1011,7 +1011,7 @@ const struct file_operations kmsg_fops = {
* symbols are specifically used so that utilities can access and extract the
* dmesg log from a vmcore file after a crash.
*/
-void log_buf_kexec_setup(void)
+void log_buf_vmcoreinfo_setup(void)
{
VMCOREINFO_SYMBOL(log_buf);
VMCOREINFO_SYMBOL(log_buf_len);
@@ -2642,6 +2642,30 @@ int unregister_console(struct console *console)
EXPORT_SYMBOL(unregister_console);
/*
+ * Initialize the console device. This is called *early*, so
+ * we can't necessarily depend on lots of kernel help here.
+ * Just do some early initializations, and do the complex setup
+ * later.
+ */
+void __init console_init(void)
+{
+ initcall_t *call;
+
+ /* Setup the default TTY line discipline. */
+ n_tty_init();
+
+ /*
+ * set up the console device so that later boot sequences can
+ * inform about problems etc..
+ */
+ call = __con_initcall_start;
+ while (call < __con_initcall_end) {
+ (*call)();
+ call++;
+ }
+}
+
+/*
* Some boot consoles access data that is in the init section and which will
* be discarded after the initcalls have been run. To make sure that no code
* will access this data, unregister the boot consoles in a late initcall.
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 18dfc485225c..23803c7d5180 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -3,10 +3,13 @@
KCOV_INSTRUMENT := n
obj-y += update.o sync.o
-obj-$(CONFIG_SRCU) += srcu.o
+obj-$(CONFIG_CLASSIC_SRCU) += srcu.o
+obj-$(CONFIG_TREE_SRCU) += srcutree.o
+obj-$(CONFIG_TINY_SRCU) += srcutiny.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
obj-$(CONFIG_TREE_RCU) += tree.o
obj-$(CONFIG_PREEMPT_RCU) += tree.o
obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
obj-$(CONFIG_TINY_RCU) += tiny.o
+obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 0d6ff3e471be..73e16ec4054b 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -56,6 +56,83 @@
#define DYNTICK_TASK_EXIT_IDLE (DYNTICK_TASK_NEST_VALUE + \
DYNTICK_TASK_FLAG)
+
+/*
+ * Grace-period counter management.
+ */
+
+#define RCU_SEQ_CTR_SHIFT 2
+#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1)
+
+/*
+ * Return the counter portion of a sequence number previously returned
+ * by rcu_seq_snap() or rcu_seq_current().
+ */
+static inline unsigned long rcu_seq_ctr(unsigned long s)
+{
+ return s >> RCU_SEQ_CTR_SHIFT;
+}
+
+/*
+ * Return the state portion of a sequence number previously returned
+ * by rcu_seq_snap() or rcu_seq_current().
+ */
+static inline int rcu_seq_state(unsigned long s)
+{
+ return s & RCU_SEQ_STATE_MASK;
+}
+
+/*
+ * Set the state portion of the pointed-to sequence number.
+ * The caller is responsible for preventing conflicting updates.
+ */
+static inline void rcu_seq_set_state(unsigned long *sp, int newstate)
+{
+ WARN_ON_ONCE(newstate & ~RCU_SEQ_STATE_MASK);
+ WRITE_ONCE(*sp, (*sp & ~RCU_SEQ_STATE_MASK) + newstate);
+}
+
+/* Adjust sequence number for start of update-side operation. */
+static inline void rcu_seq_start(unsigned long *sp)
+{
+ WRITE_ONCE(*sp, *sp + 1);
+ smp_mb(); /* Ensure update-side operation after counter increment. */
+ WARN_ON_ONCE(rcu_seq_state(*sp) != 1);
+}
+
+/* Adjust sequence number for end of update-side operation. */
+static inline void rcu_seq_end(unsigned long *sp)
+{
+ smp_mb(); /* Ensure update-side operation before counter increment. */
+ WARN_ON_ONCE(!rcu_seq_state(*sp));
+ WRITE_ONCE(*sp, (*sp | RCU_SEQ_STATE_MASK) + 1);
+}
+
+/* Take a snapshot of the update side's sequence number. */
+static inline unsigned long rcu_seq_snap(unsigned long *sp)
+{
+ unsigned long s;
+
+ s = (READ_ONCE(*sp) + 2 * RCU_SEQ_STATE_MASK + 1) & ~RCU_SEQ_STATE_MASK;
+ smp_mb(); /* Above access must not bleed into critical section. */
+ return s;
+}
+
+/* Return the current value the update side's sequence number, no ordering. */
+static inline unsigned long rcu_seq_current(unsigned long *sp)
+{
+ return READ_ONCE(*sp);
+}
+
+/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not a
+ * full update-side operation has occurred.
+ */
+static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
+{
+ return ULONG_CMP_GE(READ_ONCE(*sp), s);
+}
+
/*
* debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
* by call_rcu() and rcu callback execution, and are therefore not part of the
@@ -109,12 +186,12 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
rcu_lock_acquire(&rcu_callback_map);
if (__is_kfree_rcu_offset(offset)) {
- RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
+ RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset);)
kfree((void *)head - offset);
rcu_lock_release(&rcu_callback_map);
return true;
} else {
- RCU_TRACE(trace_rcu_invoke_callback(rn, head));
+ RCU_TRACE(trace_rcu_invoke_callback(rn, head);)
head->func(head);
rcu_lock_release(&rcu_callback_map);
return false;
@@ -144,4 +221,76 @@ void rcu_test_sync_prims(void);
*/
extern void resched_cpu(int cpu);
+#if defined(SRCU) || !defined(TINY_RCU)
+
+#include <linux/rcu_node_tree.h>
+
+extern int rcu_num_lvls;
+extern int num_rcu_lvl[];
+extern int rcu_num_nodes;
+static bool rcu_fanout_exact;
+static int rcu_fanout_leaf;
+
+/*
+ * Compute the per-level fanout, either using the exact fanout specified
+ * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
+ */
+static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
+{
+ int i;
+
+ if (rcu_fanout_exact) {
+ levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+ for (i = rcu_num_lvls - 2; i >= 0; i--)
+ levelspread[i] = RCU_FANOUT;
+ } else {
+ int ccur;
+ int cprv;
+
+ cprv = nr_cpu_ids;
+ for (i = rcu_num_lvls - 1; i >= 0; i--) {
+ ccur = levelcnt[i];
+ levelspread[i] = (cprv + ccur - 1) / ccur;
+ cprv = ccur;
+ }
+ }
+}
+
+/*
+ * Do a full breadth-first scan of the rcu_node structures for the
+ * specified rcu_state structure.
+ */
+#define rcu_for_each_node_breadth_first(rsp, rnp) \
+ for ((rnp) = &(rsp)->node[0]; \
+ (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
+
+/*
+ * Do a breadth-first scan of the non-leaf rcu_node structures for the
+ * specified rcu_state structure. Note that if there is a singleton
+ * rcu_node tree with but one rcu_node structure, this loop is a no-op.
+ */
+#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
+ for ((rnp) = &(rsp)->node[0]; \
+ (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
+
+/*
+ * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
+ * structure. Note that if there is a singleton rcu_node tree with but
+ * one rcu_node structure, this loop -will- visit the rcu_node structure.
+ * It is still a leaf node, even if it is also the root node.
+ */
+#define rcu_for_each_leaf_node(rsp, rnp) \
+ for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
+ (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
+
+/*
+ * Iterate over all possible CPUs in a leaf RCU node.
+ */
+#define for_each_leaf_node_possible_cpu(rnp, cpu) \
+ for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
+ cpu <= rnp->grphi; \
+ cpu = cpumask_next((cpu), cpu_possible_mask))
+
+#endif /* #if defined(SRCU) || !defined(TINY_RCU) */
+
#endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
new file mode 100644
index 000000000000..2b62a38b080f
--- /dev/null
+++ b/kernel/rcu/rcu_segcblist.c
@@ -0,0 +1,505 @@
+/*
+ * 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>
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+
+#include "rcu_segcblist.h"
+
+/* Initialize simple callback list. */
+void rcu_cblist_init(struct rcu_cblist *rclp)
+{
+ rclp->head = NULL;
+ rclp->tail = &rclp->head;
+ rclp->len = 0;
+ rclp->len_lazy = 0;
+}
+
+/*
+ * Debug function to actually count the number of callbacks.
+ * If the number exceeds the limit specified, return -1.
+ */
+long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim)
+{
+ int cnt = 0;
+ struct rcu_head **rhpp = &rclp->head;
+
+ for (;;) {
+ if (!*rhpp)
+ return cnt;
+ if (++cnt > lim)
+ return -1;
+ rhpp = &(*rhpp)->next;
+ }
+}
+
+/*
+ * Dequeue the oldest rcu_head structure from the specified callback
+ * list. This function assumes that the callback is non-lazy, but
+ * the caller can later invoke rcu_cblist_dequeued_lazy() if it
+ * finds otherwise (and if it cares about laziness). This allows
+ * different users to have different ways of determining laziness.
+ */
+struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
+{
+ struct rcu_head *rhp;
+
+ rhp = rclp->head;
+ if (!rhp)
+ return NULL;
+ rclp->len--;
+ rclp->head = rhp->next;
+ if (!rclp->head)
+ rclp->tail = &rclp->head;
+ return rhp;
+}
+
+/*
+ * Initialize an rcu_segcblist structure.
+ */
+void rcu_segcblist_init(struct rcu_segcblist *rsclp)
+{
+ int i;
+
+ BUILD_BUG_ON(RCU_NEXT_TAIL + 1 != ARRAY_SIZE(rsclp->gp_seq));
+ BUILD_BUG_ON(ARRAY_SIZE(rsclp->tails) != ARRAY_SIZE(rsclp->gp_seq));
+ rsclp->head = NULL;
+ for (i = 0; i < RCU_CBLIST_NSEGS; i++)
+ rsclp->tails[i] = &rsclp->head;
+ rsclp->len = 0;
+ rsclp->len_lazy = 0;
+}
+
+/*
+ * Disable the specified rcu_segcblist structure, so that callbacks can
+ * no longer be posted to it. This structure must be empty.
+ */
+void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
+{
+ WARN_ON_ONCE(!rcu_segcblist_empty(rsclp));
+ WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp));
+ WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp));
+ rsclp->tails[RCU_NEXT_TAIL] = NULL;
+}
+
+/*
+ * Is the specified segment of the specified rcu_segcblist structure
+ * empty of callbacks?
+ */
+bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg)
+{
+ if (seg == RCU_DONE_TAIL)
+ return &rsclp->head == rsclp->tails[RCU_DONE_TAIL];
+ return rsclp->tails[seg - 1] == rsclp->tails[seg];
+}
+
+/*
+ * Does the specified rcu_segcblist structure contain callbacks that
+ * are ready to be invoked?
+ */
+bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp)
+{
+ return rcu_segcblist_is_enabled(rsclp) &&
+ &rsclp->head != rsclp->tails[RCU_DONE_TAIL];
+}
+
+/*
+ * Does the specified rcu_segcblist structure contain callbacks that
+ * are still pending, that is, not yet ready to be invoked?
+ */
+bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp)
+{
+ return rcu_segcblist_is_enabled(rsclp) &&
+ !rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL);
+}
+
+/*
+ * Dequeue and return the first ready-to-invoke callback. If there
+ * are no ready-to-invoke callbacks, return NULL. Disables interrupts
+ * to avoid interference. Does not protect from interference from other
+ * CPUs or tasks.
+ */
+struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp)
+{
+ unsigned long flags;
+ int i;
+ struct rcu_head *rhp;
+
+ local_irq_save(flags);
+ if (!rcu_segcblist_ready_cbs(rsclp)) {
+ local_irq_restore(flags);
+ return NULL;
+ }
+ rhp = rsclp->head;
+ BUG_ON(!rhp);
+ rsclp->head = rhp->next;
+ for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++) {
+ if (rsclp->tails[i] != &rhp->next)
+ break;
+ rsclp->tails[i] = &rsclp->head;
+ }
+ smp_mb(); /* Dequeue before decrement for rcu_barrier(). */
+ WRITE_ONCE(rsclp->len, rsclp->len - 1);
+ local_irq_restore(flags);
+ return rhp;
+}
+
+/*
+ * Account for the fact that a previously dequeued callback turned out
+ * to be marked as lazy.
+ */
+void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ rsclp->len_lazy--;
+ local_irq_restore(flags);
+}
+
+/*
+ * Return a pointer to the first callback in the specified rcu_segcblist
+ * structure. This is useful for diagnostics.
+ */
+struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp)
+{
+ if (rcu_segcblist_is_enabled(rsclp))
+ return rsclp->head;
+ return NULL;
+}
+
+/*
+ * Return a pointer to the first pending callback in the specified
+ * rcu_segcblist structure. This is useful just after posting a given
+ * callback -- if that callback is the first pending callback, then
+ * you cannot rely on someone else having already started up the required
+ * grace period.
+ */
+struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp)
+{
+ if (rcu_segcblist_is_enabled(rsclp))
+ return *rsclp->tails[RCU_DONE_TAIL];
+ return NULL;
+}
+
+/*
+ * Does the specified rcu_segcblist structure contain callbacks that
+ * have not yet been processed beyond having been posted, that is,
+ * does it contain callbacks in its last segment?
+ */
+bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp)
+{
+ return rcu_segcblist_is_enabled(rsclp) &&
+ !rcu_segcblist_restempty(rsclp, RCU_NEXT_READY_TAIL);
+}
+
+/*
+ * Enqueue the specified callback onto the specified rcu_segcblist
+ * structure, updating accounting as needed. Note that the ->len
+ * field may be accessed locklessly, hence the WRITE_ONCE().
+ * The ->len field is used by rcu_barrier() and friends to determine
+ * if it must post a callback on this structure, and it is OK
+ * for rcu_barrier() to sometimes post callbacks needlessly, but
+ * absolutely not OK for it to ever miss posting a callback.
+ */
+void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
+ struct rcu_head *rhp, bool lazy)
+{
+ WRITE_ONCE(rsclp->len, rsclp->len + 1); /* ->len sampled locklessly. */
+ if (lazy)
+ rsclp->len_lazy++;
+ smp_mb(); /* Ensure counts are updated before callback is enqueued. */
+ rhp->next = NULL;
+ *rsclp->tails[RCU_NEXT_TAIL] = rhp;
+ rsclp->tails[RCU_NEXT_TAIL] = &rhp->next;
+}
+
+/*
+ * Entrain the specified callback onto the specified rcu_segcblist at
+ * the end of the last non-empty segment. If the entire rcu_segcblist
+ * is empty, make no change, but return false.
+ *
+ * This is intended for use by rcu_barrier()-like primitives, -not-
+ * for normal grace-period use. IMPORTANT: The callback you enqueue
+ * will wait for all prior callbacks, NOT necessarily for a grace
+ * period. You have been warned.
+ */
+bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
+ struct rcu_head *rhp, bool lazy)
+{
+ int i;
+
+ if (rcu_segcblist_n_cbs(rsclp) == 0)
+ return false;
+ WRITE_ONCE(rsclp->len, rsclp->len + 1);
+ if (lazy)
+ rsclp->len_lazy++;
+ smp_mb(); /* Ensure counts are updated before callback is entrained. */
+ rhp->next = NULL;
+ for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
+ if (rsclp->tails[i] != rsclp->tails[i - 1])
+ break;
+ *rsclp->tails[i] = rhp;
+ for (; i <= RCU_NEXT_TAIL; i++)
+ rsclp->tails[i] = &rhp->next;
+ return true;
+}
+
+/*
+ * Extract only the counts from the specified rcu_segcblist structure,
+ * and place them in the specified rcu_cblist structure. This function
+ * supports both callback orphaning and invocation, hence the separation
+ * of counts and callbacks. (Callbacks ready for invocation must be
+ * orphaned and adopted separately from pending callbacks, but counts
+ * apply to all callbacks. Locking must be used to make sure that
+ * both orphaned-callbacks lists are consistent.)
+ */
+void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ rclp->len_lazy += rsclp->len_lazy;
+ rclp->len += rsclp->len;
+ rsclp->len_lazy = 0;
+ WRITE_ONCE(rsclp->len, 0); /* ->len sampled locklessly. */
+}
+
+/*
+ * Extract only those callbacks ready to be invoked from the specified
+ * rcu_segcblist structure and place them in the specified rcu_cblist
+ * structure.
+ */
+void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ int i;
+
+ if (!rcu_segcblist_ready_cbs(rsclp))
+ return; /* Nothing to do. */
+ *rclp->tail = rsclp->head;
+ rsclp->head = *rsclp->tails[RCU_DONE_TAIL];
+ *rsclp->tails[RCU_DONE_TAIL] = NULL;
+ rclp->tail = rsclp->tails[RCU_DONE_TAIL];
+ for (i = RCU_CBLIST_NSEGS - 1; i >= RCU_DONE_TAIL; i--)
+ if (rsclp->tails[i] == rsclp->tails[RCU_DONE_TAIL])
+ rsclp->tails[i] = &rsclp->head;
+}
+
+/*
+ * Extract only those callbacks still pending (not yet ready to be
+ * invoked) from the specified rcu_segcblist structure and place them in
+ * the specified rcu_cblist structure. Note that this loses information
+ * about any callbacks that might have been partway done waiting for
+ * their grace period. Too bad! They will have to start over.
+ */
+void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ int i;
+
+ if (!rcu_segcblist_pend_cbs(rsclp))
+ return; /* Nothing to do. */
+ *rclp->tail = *rsclp->tails[RCU_DONE_TAIL];
+ rclp->tail = rsclp->tails[RCU_NEXT_TAIL];
+ *rsclp->tails[RCU_DONE_TAIL] = NULL;
+ for (i = RCU_DONE_TAIL + 1; i < RCU_CBLIST_NSEGS; i++)
+ rsclp->tails[i] = rsclp->tails[RCU_DONE_TAIL];
+}
+
+/*
+ * Insert counts from the specified rcu_cblist structure in the
+ * specified rcu_segcblist structure.
+ */
+void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ rsclp->len_lazy += rclp->len_lazy;
+ /* ->len sampled locklessly. */
+ WRITE_ONCE(rsclp->len, rsclp->len + rclp->len);
+ rclp->len_lazy = 0;
+ rclp->len = 0;
+}
+
+/*
+ * Move callbacks from the specified rcu_cblist to the beginning of the
+ * done-callbacks segment of the specified rcu_segcblist.
+ */
+void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ int i;
+
+ if (!rclp->head)
+ return; /* No callbacks to move. */
+ *rclp->tail = rsclp->head;
+ rsclp->head = rclp->head;
+ for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++)
+ if (&rsclp->head == rsclp->tails[i])
+ rsclp->tails[i] = rclp->tail;
+ else
+ break;
+ rclp->head = NULL;
+ rclp->tail = &rclp->head;
+}
+
+/*
+ * Move callbacks from the specified rcu_cblist to the end of the
+ * new-callbacks segment of the specified rcu_segcblist.
+ */
+void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ if (!rclp->head)
+ return; /* Nothing to do. */
+ *rsclp->tails[RCU_NEXT_TAIL] = rclp->head;
+ rsclp->tails[RCU_NEXT_TAIL] = rclp->tail;
+ rclp->head = NULL;
+ rclp->tail = &rclp->head;
+}
+
+/*
+ * Advance the callbacks in the specified rcu_segcblist structure based
+ * on the current value passed in for the grace-period counter.
+ */
+void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq)
+{
+ int i, j;
+
+ WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
+ if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
+ return;
+
+ /*
+ * Find all callbacks whose ->gp_seq numbers indicate that they
+ * are ready to invoke, and put them into the RCU_DONE_TAIL segment.
+ */
+ for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
+ if (ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
+ break;
+ rsclp->tails[RCU_DONE_TAIL] = rsclp->tails[i];
+ }
+
+ /* If no callbacks moved, nothing more need be done. */
+ if (i == RCU_WAIT_TAIL)
+ return;
+
+ /* Clean up tail pointers that might have been misordered above. */
+ for (j = RCU_WAIT_TAIL; j < i; j++)
+ rsclp->tails[j] = rsclp->tails[RCU_DONE_TAIL];
+
+ /*
+ * Callbacks moved, so clean up the misordered ->tails[] pointers
+ * that now point into the middle of the list of ready-to-invoke
+ * callbacks. The overall effect is to copy down the later pointers
+ * into the gap that was created by the now-ready segments.
+ */
+ for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
+ if (rsclp->tails[j] == rsclp->tails[RCU_NEXT_TAIL])
+ break; /* No more callbacks. */
+ rsclp->tails[j] = rsclp->tails[i];
+ rsclp->gp_seq[j] = rsclp->gp_seq[i];
+ }
+}
+
+/*
+ * "Accelerate" callbacks based on more-accurate grace-period information.
+ * The reason for this is that RCU does not synchronize the beginnings and
+ * ends of grace periods, and that callbacks are posted locally. This in
+ * turn means that the callbacks must be labelled conservatively early
+ * on, as getting exact information would degrade both performance and
+ * scalability. When more accurate grace-period information becomes
+ * available, previously posted callbacks can be "accelerated", marking
+ * them to complete at the end of the earlier grace period.
+ *
+ * This function operates on an rcu_segcblist structure, and also the
+ * grace-period sequence number seq at which new callbacks would become
+ * ready to invoke. Returns true if there are callbacks that won't be
+ * ready to invoke until seq, false otherwise.
+ */
+bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
+{
+ int i;
+
+ WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
+ if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
+ return false;
+
+ /*
+ * Find the segment preceding the oldest segment of callbacks
+ * whose ->gp_seq[] completion is at or after that passed in via
+ * "seq", skipping any empty segments. This oldest segment, along
+ * with any later segments, can be merged in with any newly arrived
+ * callbacks in the RCU_NEXT_TAIL segment, and assigned "seq"
+ * as their ->gp_seq[] grace-period completion sequence number.
+ */
+ for (i = RCU_NEXT_READY_TAIL; i > RCU_DONE_TAIL; i--)
+ if (rsclp->tails[i] != rsclp->tails[i - 1] &&
+ ULONG_CMP_LT(rsclp->gp_seq[i], seq))
+ break;
+
+ /*
+ * If all the segments contain callbacks that correspond to
+ * earlier grace-period sequence numbers than "seq", leave.
+ * Assuming that the rcu_segcblist structure has enough
+ * segments in its arrays, this can only happen if some of
+ * the non-done segments contain callbacks that really are
+ * ready to invoke. This situation will get straightened
+ * out by the next call to rcu_segcblist_advance().
+ *
+ * Also advance to the oldest segment of callbacks whose
+ * ->gp_seq[] completion is at or after that passed in via "seq",
+ * skipping any empty segments.
+ */
+ if (++i >= RCU_NEXT_TAIL)
+ return false;
+
+ /*
+ * Merge all later callbacks, including newly arrived callbacks,
+ * into the segment located by the for-loop above. Assign "seq"
+ * as the ->gp_seq[] value in order to correctly handle the case
+ * where there were no pending callbacks in the rcu_segcblist
+ * structure other than in the RCU_NEXT_TAIL segment.
+ */
+ for (; i < RCU_NEXT_TAIL; i++) {
+ rsclp->tails[i] = rsclp->tails[RCU_NEXT_TAIL];
+ rsclp->gp_seq[i] = seq;
+ }
+ return true;
+}
+
+/*
+ * Scan the specified rcu_segcblist structure for callbacks that need
+ * a grace period later than the one specified by "seq". We don't look
+ * at the RCU_DONE_TAIL or RCU_NEXT_TAIL segments because they don't
+ * have a grace-period sequence number.
+ */
+bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
+ unsigned long seq)
+{
+ int i;
+
+ for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
+ if (rsclp->tails[i - 1] != rsclp->tails[i] &&
+ ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
+ return true;
+ return false;
+}
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
new file mode 100644
index 000000000000..6e36e36478cd
--- /dev/null
+++ b/kernel/rcu/rcu_segcblist.h
@@ -0,0 +1,164 @@
+/*
+ * 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>
+ */
+
+#include <linux/rcu_segcblist.h>
+
+/*
+ * Account for the fact that a previously dequeued callback turned out
+ * to be marked as lazy.
+ */
+static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
+{
+ rclp->len_lazy--;
+}
+
+/*
+ * Interim function to return rcu_cblist head pointer. Longer term, the
+ * rcu_cblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head *rcu_cblist_head(struct rcu_cblist *rclp)
+{
+ return rclp->head;
+}
+
+/*
+ * Interim function to return rcu_cblist head pointer. Longer term, the
+ * rcu_cblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head **rcu_cblist_tail(struct rcu_cblist *rclp)
+{
+ WARN_ON_ONCE(!rclp->head);
+ return rclp->tail;
+}
+
+void rcu_cblist_init(struct rcu_cblist *rclp);
+long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim);
+struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp);
+
+/*
+ * Is the specified rcu_segcblist structure empty?
+ *
+ * But careful! The fact that the ->head field is NULL does not
+ * necessarily imply that there are no callbacks associated with
+ * this structure. When callbacks are being invoked, they are
+ * removed as a group. If callback invocation must be preempted,
+ * the remaining callbacks will be added back to the list. Either
+ * way, the counts are updated later.
+ *
+ * So it is often the case that rcu_segcblist_n_cbs() should be used
+ * instead.
+ */
+static inline bool rcu_segcblist_empty(struct rcu_segcblist *rsclp)
+{
+ return !rsclp->head;
+}
+
+/* Return number of callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
+{
+ return READ_ONCE(rsclp->len);
+}
+
+/* Return number of lazy callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp)
+{
+ return rsclp->len_lazy;
+}
+
+/* Return number of lazy callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp)
+{
+ return rsclp->len - rsclp->len_lazy;
+}
+
+/*
+ * Is the specified rcu_segcblist enabled, for example, not corresponding
+ * to an offline or callback-offloaded CPU?
+ */
+static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
+{
+ return !!rsclp->tails[RCU_NEXT_TAIL];
+}
+
+/*
+ * Are all segments following the specified segment of the specified
+ * rcu_segcblist structure empty of callbacks? (The specified
+ * segment might well contain callbacks.)
+ */
+static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg)
+{
+ return !*rsclp->tails[seg];
+}
+
+/*
+ * Interim function to return rcu_segcblist head pointer. Longer term, the
+ * rcu_segcblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head *rcu_segcblist_head(struct rcu_segcblist *rsclp)
+{
+ return rsclp->head;
+}
+
+/*
+ * Interim function to return rcu_segcblist head pointer. Longer term, the
+ * rcu_segcblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp)
+{
+ WARN_ON_ONCE(rcu_segcblist_empty(rsclp));
+ return rsclp->tails[RCU_NEXT_TAIL];
+}
+
+void rcu_segcblist_init(struct rcu_segcblist *rsclp);
+void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg);
+bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp);
+void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp);
+void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
+ struct rcu_head *rhp, bool lazy);
+bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
+ struct rcu_head *rhp, bool lazy);
+void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
+bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
+bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
+ unsigned long seq);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index cccc417a8135..ae6e574d4cf5 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -559,19 +559,34 @@ static void srcu_torture_barrier(void)
static void srcu_torture_stats(void)
{
- int cpu;
- int idx = srcu_ctlp->completed & 0x1;
+ int __maybe_unused cpu;
+ int idx;
- pr_alert("%s%s per-CPU(idx=%d):",
+#if defined(CONFIG_TREE_SRCU) || defined(CONFIG_CLASSIC_SRCU)
+#ifdef CONFIG_TREE_SRCU
+ idx = srcu_ctlp->srcu_idx & 0x1;
+#else /* #ifdef CONFIG_TREE_SRCU */
+ idx = srcu_ctlp->completed & 0x1;
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
+ pr_alert("%s%s Tree SRCU per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
unsigned long l0, l1;
unsigned long u0, u1;
long c0, c1;
- struct srcu_array *counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
+#ifdef CONFIG_TREE_SRCU
+ struct srcu_data *counts;
+ counts = per_cpu_ptr(srcu_ctlp->sda, cpu);
+ u0 = counts->srcu_unlock_count[!idx];
+ u1 = counts->srcu_unlock_count[idx];
+#else /* #ifdef CONFIG_TREE_SRCU */
+ struct srcu_array *counts;
+
+ counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
u0 = counts->unlock_count[!idx];
u1 = counts->unlock_count[idx];
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
/*
* Make sure that a lock is always counted if the corresponding
@@ -579,14 +594,26 @@ static void srcu_torture_stats(void)
*/
smp_rmb();
+#ifdef CONFIG_TREE_SRCU
+ l0 = counts->srcu_lock_count[!idx];
+ l1 = counts->srcu_lock_count[idx];
+#else /* #ifdef CONFIG_TREE_SRCU */
l0 = counts->lock_count[!idx];
l1 = counts->lock_count[idx];
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
c0 = l0 - u0;
c1 = l1 - u1;
pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
}
pr_cont("\n");
+#elif defined(CONFIG_TINY_SRCU)
+ idx = READ_ONCE(srcu_ctlp->srcu_idx) & 0x1;
+ pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%d,%d)\n",
+ torture_type, TORTURE_FLAG, idx,
+ READ_ONCE(srcu_ctlp->srcu_lock_nesting[!idx]),
+ READ_ONCE(srcu_ctlp->srcu_lock_nesting[idx]));
+#endif
}
static void srcu_torture_synchronize_expedited(void)
@@ -1333,12 +1360,14 @@ rcu_torture_stats_print(void)
cur_ops->stats();
if (rtcv_snap == rcu_torture_current_version &&
rcu_torture_current != NULL) {
- int __maybe_unused flags;
- unsigned long __maybe_unused gpnum;
- unsigned long __maybe_unused completed;
+ int __maybe_unused flags = 0;
+ unsigned long __maybe_unused gpnum = 0;
+ unsigned long __maybe_unused completed = 0;
rcutorture_get_gp_data(cur_ops->ttype,
&flags, &gpnum, &completed);
+ srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
+ &flags, &gpnum, &completed);
wtp = READ_ONCE(writer_task);
pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx\n",
rcu_torture_writer_state_getname(),
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index ef3bcfb15b39..584d8a983883 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -22,7 +22,7 @@
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
- * Documentation/RCU/ *.txt
+ * Documentation/RCU/ *.txt
*
*/
@@ -243,8 +243,14 @@ static bool srcu_readers_active(struct srcu_struct *sp)
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
* @sp: structure to clean up.
*
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
+ * Must invoke this only after you are finished using a given srcu_struct
+ * that was initialized via init_srcu_struct(). This code does some
+ * probabalistic checking, spotting late uses of srcu_read_lock(),
+ * synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu().
+ * If any such late uses are detected, the per-CPU memory associated with
+ * the srcu_struct is simply leaked and WARN_ON() is invoked. If the
+ * caller frees the srcu_struct itself, a use-after-free crash will likely
+ * ensue, but at least there will be a warning printed.
*/
void cleanup_srcu_struct(struct srcu_struct *sp)
{
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
new file mode 100644
index 000000000000..36e1f82faed1
--- /dev/null
+++ b/kernel/rcu/srcutiny.c
@@ -0,0 +1,216 @@
+/*
+ * 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>
+ */
+
+#include <linux/export.h>
+#include <linux/mutex.h>
+#include <linux/preempt.h>
+#include <linux/rcupdate_wait.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/srcu.h>
+
+#include <linux/rcu_node_tree.h>
+#include "rcu_segcblist.h"
+#include "rcu.h"
+
+static int init_srcu_struct_fields(struct srcu_struct *sp)
+{
+ sp->srcu_lock_nesting[0] = 0;
+ sp->srcu_lock_nesting[1] = 0;
+ init_swait_queue_head(&sp->srcu_wq);
+ sp->srcu_gp_seq = 0;
+ rcu_segcblist_init(&sp->srcu_cblist);
+ sp->srcu_gp_running = false;
+ sp->srcu_gp_waiting = false;
+ sp->srcu_idx = 0;
+ INIT_WORK(&sp->srcu_work, srcu_drive_gp);
+ return 0;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+ struct lock_class_key *key)
+{
+ /* Don't re-initialize a lock while it is held. */
+ debug_check_no_locks_freed((void *)sp, sizeof(*sp));
+ lockdep_init_map(&sp->dep_map, name, key, 0);
+ return init_srcu_struct_fields(sp);
+}
+EXPORT_SYMBOL_GPL(__init_srcu_struct);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * init_srcu_struct - initialize a sleep-RCU structure
+ * @sp: structure to initialize.
+ *
+ * Must invoke this on a given srcu_struct before passing that srcu_struct
+ * to any other function. Each srcu_struct represents a separate domain
+ * of SRCU protection.
+ */
+int init_srcu_struct(struct srcu_struct *sp)
+{
+ return init_srcu_struct_fields(sp);
+}
+EXPORT_SYMBOL_GPL(init_srcu_struct);
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+ WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
+ flush_work(&sp->srcu_work);
+ WARN_ON(rcu_seq_state(sp->srcu_gp_seq));
+ WARN_ON(sp->srcu_gp_running);
+ WARN_ON(sp->srcu_gp_waiting);
+ WARN_ON(!rcu_segcblist_empty(&sp->srcu_cblist));
+}
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct. Must be called from process context.
+ * Returns an index that must be passed to the matching srcu_read_unlock().
+ */
+int __srcu_read_lock(struct srcu_struct *sp)
+{
+ int idx;
+
+ idx = READ_ONCE(sp->srcu_idx);
+ WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1);
+ return idx;
+}
+EXPORT_SYMBOL_GPL(__srcu_read_lock);
+
+/*
+ * Removes the count for the old reader from the appropriate element of
+ * the srcu_struct. Must be called from process context.
+ */
+void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+{
+ int newval = sp->srcu_lock_nesting[idx] - 1;
+
+ WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
+ if (!newval && READ_ONCE(sp->srcu_gp_waiting))
+ swake_up(&sp->srcu_wq);
+}
+EXPORT_SYMBOL_GPL(__srcu_read_unlock);
+
+/*
+ * Workqueue handler to drive one grace period and invoke any callbacks
+ * that become ready as a result. Single-CPU and !PREEMPT operation
+ * means that we get away with murder on synchronization. ;-)
+ */
+void srcu_drive_gp(struct work_struct *wp)
+{
+ int idx;
+ struct rcu_cblist ready_cbs;
+ struct srcu_struct *sp;
+ struct rcu_head *rhp;
+
+ sp = container_of(wp, struct srcu_struct, srcu_work);
+ if (sp->srcu_gp_running || rcu_segcblist_empty(&sp->srcu_cblist))
+ return; /* Already running or nothing to do. */
+
+ /* Tag recently arrived callbacks and wait for readers. */
+ WRITE_ONCE(sp->srcu_gp_running, true);
+ rcu_segcblist_accelerate(&sp->srcu_cblist,
+ rcu_seq_snap(&sp->srcu_gp_seq));
+ rcu_seq_start(&sp->srcu_gp_seq);
+ idx = sp->srcu_idx;
+ WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
+ WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
+ swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+ WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
+ rcu_seq_end(&sp->srcu_gp_seq);
+
+ /* Update callback list based on GP, and invoke ready callbacks. */
+ rcu_segcblist_advance(&sp->srcu_cblist,
+ rcu_seq_current(&sp->srcu_gp_seq));
+ if (rcu_segcblist_ready_cbs(&sp->srcu_cblist)) {
+ rcu_cblist_init(&ready_cbs);
+ local_irq_disable();
+ rcu_segcblist_extract_done_cbs(&sp->srcu_cblist, &ready_cbs);
+ local_irq_enable();
+ rhp = rcu_cblist_dequeue(&ready_cbs);
+ for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
+ local_bh_disable();
+ rhp->func(rhp);
+ local_bh_enable();
+ }
+ local_irq_disable();
+ rcu_segcblist_insert_count(&sp->srcu_cblist, &ready_cbs);
+ local_irq_enable();
+ }
+ WRITE_ONCE(sp->srcu_gp_running, false);
+
+ /*
+ * If more callbacks, reschedule ourselves. This can race with
+ * a call_srcu() at interrupt level, but the ->srcu_gp_running
+ * checks will straighten that out.
+ */
+ if (!rcu_segcblist_empty(&sp->srcu_cblist))
+ schedule_work(&sp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(srcu_drive_gp);
+
+/*
+ * Enqueue an SRCU callback on the specified srcu_struct structure,
+ * initiating grace-period processing if it is not already running.
+ */
+void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
+ rcu_callback_t func)
+{
+ unsigned long flags;
+
+ head->func = func;
+ local_irq_save(flags);
+ rcu_segcblist_enqueue(&sp->srcu_cblist, head, false);
+ local_irq_restore(flags);
+ if (!READ_ONCE(sp->srcu_gp_running))
+ schedule_work(&sp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(call_srcu);
+
+/*
+ * synchronize_srcu - wait for prior SRCU read-side critical-section completion
+ */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+ struct rcu_synchronize rs;
+
+ init_rcu_head_on_stack(&rs.head);
+ init_completion(&rs.completion);
+ call_srcu(sp, &rs.head, wakeme_after_rcu);
+ wait_for_completion(&rs.completion);
+ destroy_rcu_head_on_stack(&rs.head);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu);
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
new file mode 100644
index 000000000000..3ae8474557df
--- /dev/null
+++ b/kernel/rcu/srcutree.c
@@ -0,0 +1,1155 @@
+/*
+ * 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>
+ * Lai Jiangshan <laijs@cn.fujitsu.com>
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ * Documentation/RCU/ *.txt
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/rcupdate_wait.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/srcu.h>
+
+#include "rcu.h"
+#include "rcu_segcblist.h"
+
+ulong exp_holdoff = 25 * 1000; /* Holdoff (ns) for auto-expediting. */
+module_param(exp_holdoff, ulong, 0444);
+
+static void srcu_invoke_callbacks(struct work_struct *work);
+static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
+
+/*
+ * Initialize SRCU combining tree. Note that statically allocated
+ * srcu_struct structures might already have srcu_read_lock() and
+ * srcu_read_unlock() running against them. So if the is_static parameter
+ * is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[].
+ */
+static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
+{
+ int cpu;
+ int i;
+ int level = 0;
+ int levelspread[RCU_NUM_LVLS];
+ struct srcu_data *sdp;
+ struct srcu_node *snp;
+ struct srcu_node *snp_first;
+
+ /* Work out the overall tree geometry. */
+ sp->level[0] = &sp->node[0];
+ for (i = 1; i < rcu_num_lvls; i++)
+ sp->level[i] = sp->level[i - 1] + num_rcu_lvl[i - 1];
+ rcu_init_levelspread(levelspread, num_rcu_lvl);
+
+ /* Each pass through this loop initializes one srcu_node structure. */
+ rcu_for_each_node_breadth_first(sp, snp) {
+ spin_lock_init(&snp->lock);
+ WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
+ ARRAY_SIZE(snp->srcu_data_have_cbs));
+ for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
+ snp->srcu_have_cbs[i] = 0;
+ snp->srcu_data_have_cbs[i] = 0;
+ }
+ snp->srcu_gp_seq_needed_exp = 0;
+ snp->grplo = -1;
+ snp->grphi = -1;
+ if (snp == &sp->node[0]) {
+ /* Root node, special case. */
+ snp->srcu_parent = NULL;
+ continue;
+ }
+
+ /* Non-root node. */
+ if (snp == sp->level[level + 1])
+ level++;
+ snp->srcu_parent = sp->level[level - 1] +
+ (snp - sp->level[level]) /
+ levelspread[level - 1];
+ }
+
+ /*
+ * Initialize the per-CPU srcu_data array, which feeds into the
+ * leaves of the srcu_node tree.
+ */
+ WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
+ ARRAY_SIZE(sdp->srcu_unlock_count));
+ level = rcu_num_lvls - 1;
+ snp_first = sp->level[level];
+ for_each_possible_cpu(cpu) {
+ sdp = per_cpu_ptr(sp->sda, cpu);
+ spin_lock_init(&sdp->lock);
+ rcu_segcblist_init(&sdp->srcu_cblist);
+ sdp->srcu_cblist_invoking = false;
+ sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
+ sdp->srcu_gp_seq_needed_exp = sp->srcu_gp_seq;
+ sdp->mynode = &snp_first[cpu / levelspread[level]];
+ for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
+ if (snp->grplo < 0)
+ snp->grplo = cpu;
+ snp->grphi = cpu;
+ }
+ sdp->cpu = cpu;
+ INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
+ sdp->sp = sp;
+ sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
+ if (is_static)
+ continue;
+
+ /* Dynamically allocated, better be no srcu_read_locks()! */
+ for (i = 0; i < ARRAY_SIZE(sdp->srcu_lock_count); i++) {
+ sdp->srcu_lock_count[i] = 0;
+ sdp->srcu_unlock_count[i] = 0;
+ }
+ }
+}
+
+/*
+ * Initialize non-compile-time initialized fields, including the
+ * associated srcu_node and srcu_data structures. The is_static
+ * parameter is passed through to init_srcu_struct_nodes(), and
+ * also tells us that ->sda has already been wired up to srcu_data.
+ */
+static int init_srcu_struct_fields(struct srcu_struct *sp, bool is_static)
+{
+ mutex_init(&sp->srcu_cb_mutex);
+ mutex_init(&sp->srcu_gp_mutex);
+ sp->srcu_idx = 0;
+ sp->srcu_gp_seq = 0;
+ sp->srcu_barrier_seq = 0;
+ mutex_init(&sp->srcu_barrier_mutex);
+ atomic_set(&sp->srcu_barrier_cpu_cnt, 0);
+ INIT_DELAYED_WORK(&sp->work, process_srcu);
+ if (!is_static)
+ sp->sda = alloc_percpu(struct srcu_data);
+ init_srcu_struct_nodes(sp, is_static);
+ sp->srcu_gp_seq_needed_exp = 0;
+ sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+ smp_store_release(&sp->srcu_gp_seq_needed, 0); /* Init done. */
+ return sp->sda ? 0 : -ENOMEM;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+ struct lock_class_key *key)
+{
+ /* Don't re-initialize a lock while it is held. */
+ debug_check_no_locks_freed((void *)sp, sizeof(*sp));
+ lockdep_init_map(&sp->dep_map, name, key, 0);
+ spin_lock_init(&sp->gp_lock);
+ return init_srcu_struct_fields(sp, false);
+}
+EXPORT_SYMBOL_GPL(__init_srcu_struct);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/**
+ * init_srcu_struct - initialize a sleep-RCU structure
+ * @sp: structure to initialize.
+ *
+ * Must invoke this on a given srcu_struct before passing that srcu_struct
+ * to any other function. Each srcu_struct represents a separate domain
+ * of SRCU protection.
+ */
+int init_srcu_struct(struct srcu_struct *sp)
+{
+ spin_lock_init(&sp->gp_lock);
+ return init_srcu_struct_fields(sp, false);
+}
+EXPORT_SYMBOL_GPL(init_srcu_struct);
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * First-use initialization of statically allocated srcu_struct
+ * structure. Wiring up the combining tree is more than can be
+ * done with compile-time initialization, so this check is added
+ * to each update-side SRCU primitive. Use ->gp_lock, which -is-
+ * compile-time initialized, to resolve races involving multiple
+ * CPUs trying to garner first-use privileges.
+ */
+static void check_init_srcu_struct(struct srcu_struct *sp)
+{
+ unsigned long flags;
+
+ WARN_ON_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INIT);
+ /* The smp_load_acquire() pairs with the smp_store_release(). */
+ if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
+ return; /* Already initialized. */
+ spin_lock_irqsave(&sp->gp_lock, flags);
+ if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
+ spin_unlock_irqrestore(&sp->gp_lock, flags);
+ return;
+ }
+ init_srcu_struct_fields(sp, true);
+ spin_unlock_irqrestore(&sp->gp_lock, flags);
+}
+
+/*
+ * Returns approximate total of the readers' ->srcu_lock_count[] values
+ * for the rank of per-CPU counters specified by idx.
+ */
+static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
+{
+ int cpu;
+ unsigned long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+
+ sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
+ }
+ return sum;
+}
+
+/*
+ * Returns approximate total of the readers' ->srcu_unlock_count[] values
+ * for the rank of per-CPU counters specified by idx.
+ */
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
+{
+ int cpu;
+ unsigned long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+
+ sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
+ }
+ return sum;
+}
+
+/*
+ * Return true if the number of pre-existing readers is determined to
+ * be zero.
+ */
+static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
+{
+ unsigned long unlocks;
+
+ unlocks = srcu_readers_unlock_idx(sp, idx);
+
+ /*
+ * Make sure that a lock is always counted if the corresponding
+ * unlock is counted. Needs to be a smp_mb() as the read side may
+ * contain a read from a variable that is written to before the
+ * synchronize_srcu() in the write side. In this case smp_mb()s
+ * A and B act like the store buffering pattern.
+ *
+ * This smp_mb() also pairs with smp_mb() C to prevent accesses
+ * after the synchronize_srcu() from being executed before the
+ * grace period ends.
+ */
+ smp_mb(); /* A */
+
+ /*
+ * If the locks are the same as the unlocks, then there must have
+ * been no readers on this index at some time in between. This does
+ * not mean that there are no more readers, as one could have read
+ * the current index but not have incremented the lock counter yet.
+ *
+ * Possible bug: There is no guarantee that there haven't been
+ * ULONG_MAX increments of ->srcu_lock_count[] since the unlocks were
+ * counted, meaning that this could return true even if there are
+ * still active readers. Since there are no memory barriers around
+ * srcu_flip(), the CPU is not required to increment ->srcu_idx
+ * before running srcu_readers_unlock_idx(), which means that there
+ * could be an arbitrarily large number of critical sections that
+ * execute after srcu_readers_unlock_idx() but use the old value
+ * of ->srcu_idx.
+ */
+ return srcu_readers_lock_idx(sp, idx) == unlocks;
+}
+
+/**
+ * srcu_readers_active - returns true if there are readers. and false
+ * otherwise
+ * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
+ *
+ * Note that this is not an atomic primitive, and can therefore suffer
+ * severe errors when invoked on an active srcu_struct. That said, it
+ * can be useful as an error check at cleanup time.
+ */
+static bool srcu_readers_active(struct srcu_struct *sp)
+{
+ int cpu;
+ unsigned long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+
+ sum += READ_ONCE(cpuc->srcu_lock_count[0]);
+ sum += READ_ONCE(cpuc->srcu_lock_count[1]);
+ sum -= READ_ONCE(cpuc->srcu_unlock_count[0]);
+ sum -= READ_ONCE(cpuc->srcu_unlock_count[1]);
+ }
+ return sum;
+}
+
+#define SRCU_INTERVAL 1
+
+/*
+ * Return grace-period delay, zero if there are expedited grace
+ * periods pending, SRCU_INTERVAL otherwise.
+ */
+static unsigned long srcu_get_delay(struct srcu_struct *sp)
+{
+ if (ULONG_CMP_LT(READ_ONCE(sp->srcu_gp_seq),
+ READ_ONCE(sp->srcu_gp_seq_needed_exp)))
+ return 0;
+ return SRCU_INTERVAL;
+}
+
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+ int cpu;
+
+ if (WARN_ON(!srcu_get_delay(sp)))
+ return; /* Leakage unless caller handles error. */
+ if (WARN_ON(srcu_readers_active(sp)))
+ return; /* Leakage unless caller handles error. */
+ flush_delayed_work(&sp->work);
+ for_each_possible_cpu(cpu)
+ flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+ if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
+ WARN_ON(srcu_readers_active(sp))) {
+ pr_info("cleanup_srcu_struct: Active srcu_struct %p state: %d\n", sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+ return; /* Caller forgot to stop doing call_srcu()? */
+ }
+ free_percpu(sp->sda);
+ sp->sda = NULL;
+}
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct. Must be called from process context.
+ * Returns an index that must be passed to the matching srcu_read_unlock().
+ */
+int __srcu_read_lock(struct srcu_struct *sp)
+{
+ int idx;
+
+ idx = READ_ONCE(sp->srcu_idx) & 0x1;
+ __this_cpu_inc(sp->sda->srcu_lock_count[idx]);
+ smp_mb(); /* B */ /* Avoid leaking the critical section. */
+ return idx;
+}
+EXPORT_SYMBOL_GPL(__srcu_read_lock);
+
+/*
+ * Removes the count for the old reader from the appropriate per-CPU
+ * element of the srcu_struct. Note that this may well be a different
+ * CPU than that which was incremented by the corresponding srcu_read_lock().
+ * Must be called from process context.
+ */
+void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+{
+ smp_mb(); /* C */ /* Avoid leaking the critical section. */
+ this_cpu_inc(sp->sda->srcu_unlock_count[idx]);
+}
+EXPORT_SYMBOL_GPL(__srcu_read_unlock);
+
+/*
+ * We use an adaptive strategy for synchronize_srcu() and especially for
+ * synchronize_srcu_expedited(). We spin for a fixed time period
+ * (defined below) to allow SRCU readers to exit their read-side critical
+ * sections. If there are still some readers after a few microseconds,
+ * we repeatedly block for 1-millisecond time periods.
+ */
+#define SRCU_RETRY_CHECK_DELAY 5
+
+/*
+ * Start an SRCU grace period.
+ */
+static void srcu_gp_start(struct srcu_struct *sp)
+{
+ struct srcu_data *sdp = this_cpu_ptr(sp->sda);
+ int state;
+
+ RCU_LOCKDEP_WARN(!lockdep_is_held(&sp->gp_lock),
+ "Invoked srcu_gp_start() without ->gp_lock!");
+ WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
+ rcu_segcblist_advance(&sdp->srcu_cblist,
+ rcu_seq_current(&sp->srcu_gp_seq));
+ (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
+ rcu_seq_snap(&sp->srcu_gp_seq));
+ smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
+ rcu_seq_start(&sp->srcu_gp_seq);
+ state = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+ 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)
+{
+ WRITE_ONCE(per_cpu(srcu_online, cpu), true);
+}
+
+void srcu_offline_cpu(unsigned int cpu)
+{
+ WRITE_ONCE(per_cpu(srcu_online, cpu), false);
+}
+
+/*
+ * 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,
+ unsigned long delay)
+{
+ bool ret;
+
+ 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;
+}
+
+/*
+ * Schedule callback invocation for the specified srcu_data structure,
+ * if possible, on the corresponding CPU.
+ */
+static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
+{
+ srcu_queue_delayed_work_on(sdp->cpu, system_power_efficient_wq,
+ &sdp->work, delay);
+}
+
+/*
+ * Schedule callback invocation for all srcu_data structures associated
+ * with the specified srcu_node structure that have callbacks for the
+ * just-completed grace period, the one corresponding to idx. If possible,
+ * schedule this invocation on the corresponding CPUs.
+ */
+static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
+ unsigned long mask, unsigned long delay)
+{
+ int cpu;
+
+ for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
+ if (!(mask & (1 << (cpu - snp->grplo))))
+ continue;
+ srcu_schedule_cbs_sdp(per_cpu_ptr(sp->sda, cpu), delay);
+ }
+}
+
+/*
+ * Note the end of an SRCU grace period. Initiates callback invocation
+ * and starts a new grace period if needed.
+ *
+ * The ->srcu_cb_mutex acquisition does not protect any data, but
+ * instead prevents more than one grace period from starting while we
+ * are initiating callback invocation. This allows the ->srcu_have_cbs[]
+ * array to have a finite number of elements.
+ */
+static void srcu_gp_end(struct srcu_struct *sp)
+{
+ unsigned long cbdelay;
+ bool cbs;
+ unsigned long gpseq;
+ int idx;
+ int idxnext;
+ unsigned long mask;
+ struct srcu_node *snp;
+
+ /* Prevent more than one additional grace period. */
+ mutex_lock(&sp->srcu_cb_mutex);
+
+ /* End the current grace period. */
+ spin_lock_irq(&sp->gp_lock);
+ idx = rcu_seq_state(sp->srcu_gp_seq);
+ WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
+ cbdelay = srcu_get_delay(sp);
+ sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+ rcu_seq_end(&sp->srcu_gp_seq);
+ gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+ if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq))
+ sp->srcu_gp_seq_needed_exp = gpseq;
+ spin_unlock_irq(&sp->gp_lock);
+ mutex_unlock(&sp->srcu_gp_mutex);
+ /* A new grace period can start at this point. But only one. */
+
+ /* Initiate callback invocation as needed. */
+ idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
+ idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs);
+ rcu_for_each_node_breadth_first(sp, snp) {
+ spin_lock_irq(&snp->lock);
+ cbs = false;
+ if (snp >= sp->level[rcu_num_lvls - 1])
+ cbs = snp->srcu_have_cbs[idx] == gpseq;
+ snp->srcu_have_cbs[idx] = gpseq;
+ rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
+ if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq))
+ snp->srcu_gp_seq_needed_exp = gpseq;
+ mask = snp->srcu_data_have_cbs[idx];
+ snp->srcu_data_have_cbs[idx] = 0;
+ spin_unlock_irq(&snp->lock);
+ if (cbs) {
+ smp_mb(); /* GP end before CB invocation. */
+ srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
+ }
+ }
+
+ /* Callback initiation done, allow grace periods after next. */
+ mutex_unlock(&sp->srcu_cb_mutex);
+
+ /* Start a new grace period if needed. */
+ spin_lock_irq(&sp->gp_lock);
+ gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+ if (!rcu_seq_state(gpseq) &&
+ ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
+ srcu_gp_start(sp);
+ spin_unlock_irq(&sp->gp_lock);
+ /* Throttle expedited grace periods: Should be rare! */
+ srcu_reschedule(sp, rcu_seq_ctr(gpseq) & 0x3ff
+ ? 0 : SRCU_INTERVAL);
+ } else {
+ spin_unlock_irq(&sp->gp_lock);
+ }
+}
+
+/*
+ * Funnel-locking scheme to scalably mediate many concurrent expedited
+ * grace-period requests. This function is invoked for the first known
+ * expedited request for a grace period that has already been requested,
+ * but without expediting. To start a completely new grace period,
+ * whether expedited or not, use srcu_funnel_gp_start() instead.
+ */
+static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
+ unsigned long s)
+{
+ unsigned long flags;
+
+ for (; snp != NULL; snp = snp->srcu_parent) {
+ if (rcu_seq_done(&sp->srcu_gp_seq, s) ||
+ ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
+ return;
+ spin_lock_irqsave(&snp->lock, flags);
+ if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) {
+ spin_unlock_irqrestore(&snp->lock, flags);
+ return;
+ }
+ WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
+ spin_unlock_irqrestore(&snp->lock, flags);
+ }
+ spin_lock_irqsave(&sp->gp_lock, flags);
+ if (!ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
+ sp->srcu_gp_seq_needed_exp = s;
+ spin_unlock_irqrestore(&sp->gp_lock, flags);
+}
+
+/*
+ * Funnel-locking scheme to scalably mediate many concurrent grace-period
+ * requests. The winner has to do the work of actually starting grace
+ * period s. Losers must either ensure that their desired grace-period
+ * number is recorded on at least their leaf srcu_node structure, or they
+ * must take steps to invoke their own callbacks.
+ */
+static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
+ unsigned long s, bool do_norm)
+{
+ unsigned long flags;
+ int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs);
+ struct srcu_node *snp = sdp->mynode;
+ unsigned long snp_seq;
+
+ /* Each pass through the loop does one level of the srcu_node tree. */
+ for (; snp != NULL; snp = snp->srcu_parent) {
+ if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode)
+ return; /* GP already done and CBs recorded. */
+ spin_lock_irqsave(&snp->lock, flags);
+ if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
+ snp_seq = snp->srcu_have_cbs[idx];
+ if (snp == sdp->mynode && snp_seq == s)
+ snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
+ spin_unlock_irqrestore(&snp->lock, flags);
+ if (snp == sdp->mynode && snp_seq != s) {
+ smp_mb(); /* CBs after GP! */
+ srcu_schedule_cbs_sdp(sdp, do_norm
+ ? SRCU_INTERVAL
+ : 0);
+ return;
+ }
+ if (!do_norm)
+ srcu_funnel_exp_start(sp, snp, s);
+ return;
+ }
+ snp->srcu_have_cbs[idx] = s;
+ if (snp == sdp->mynode)
+ snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
+ if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
+ snp->srcu_gp_seq_needed_exp = s;
+ spin_unlock_irqrestore(&snp->lock, flags);
+ }
+
+ /* Top of tree, must ensure the grace period will be started. */
+ spin_lock_irqsave(&sp->gp_lock, flags);
+ if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
+ /*
+ * Record need for grace period s. Pair with load
+ * acquire setting up for initialization.
+ */
+ smp_store_release(&sp->srcu_gp_seq_needed, s); /*^^^*/
+ }
+ if (!do_norm && ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
+ sp->srcu_gp_seq_needed_exp = s;
+
+ /* If grace period not already done and none in progress, start it. */
+ if (!rcu_seq_done(&sp->srcu_gp_seq, s) &&
+ rcu_seq_state(sp->srcu_gp_seq) == SRCU_STATE_IDLE) {
+ WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
+ srcu_gp_start(sp);
+ queue_delayed_work(system_power_efficient_wq, &sp->work,
+ srcu_get_delay(sp));
+ }
+ spin_unlock_irqrestore(&sp->gp_lock, flags);
+}
+
+/*
+ * Wait until all readers counted by array index idx complete, but
+ * loop an additional time if there is an expedited grace period pending.
+ * The caller must ensure that ->srcu_idx is not changed while checking.
+ */
+static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
+{
+ for (;;) {
+ if (srcu_readers_active_idx_check(sp, idx))
+ return true;
+ if (--trycount + !srcu_get_delay(sp) <= 0)
+ return false;
+ udelay(SRCU_RETRY_CHECK_DELAY);
+ }
+}
+
+/*
+ * Increment the ->srcu_idx counter so that future SRCU readers will
+ * use the other rank of the ->srcu_(un)lock_count[] arrays. This allows
+ * us to wait for pre-existing readers in a starvation-free manner.
+ */
+static void srcu_flip(struct srcu_struct *sp)
+{
+ WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1);
+
+ /*
+ * Ensure that if the updater misses an __srcu_read_unlock()
+ * increment, that task's next __srcu_read_lock() will see the
+ * above counter update. Note that both this memory barrier
+ * and the one in srcu_readers_active_idx_check() provide the
+ * guarantee for __srcu_read_lock().
+ */
+ smp_mb(); /* D */ /* Pairs with C. */
+}
+
+/*
+ * If SRCU is likely idle, return true, otherwise return false.
+ *
+ * Note that it is OK for several current from-idle requests for a new
+ * grace period from idle to specify expediting because they will all end
+ * up requesting the same grace period anyhow. So no loss.
+ *
+ * Note also that if any CPU (including the current one) is still invoking
+ * callbacks, this function will nevertheless say "idle". This is not
+ * ideal, but the overhead of checking all CPUs' callback lists is even
+ * less ideal, especially on large systems. Furthermore, the wakeup
+ * can happen before the callback is fully removed, so we have no choice
+ * but to accept this type of error.
+ *
+ * This function is also subject to counter-wrap errors, but let's face
+ * it, if this function was preempted for enough time for the counters
+ * to wrap, it really doesn't matter whether or not we expedite the grace
+ * period. The extra overhead of a needlessly expedited grace period is
+ * negligible when amoritized over that time period, and the extra latency
+ * of a needlessly non-expedited grace period is similarly negligible.
+ */
+static bool srcu_might_be_idle(struct srcu_struct *sp)
+{
+ unsigned long curseq;
+ unsigned long flags;
+ struct srcu_data *sdp;
+ unsigned long t;
+
+ /* If the local srcu_data structure has callbacks, not idle. */
+ local_irq_save(flags);
+ sdp = this_cpu_ptr(sp->sda);
+ if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
+ local_irq_restore(flags);
+ return false; /* Callbacks already present, so not idle. */
+ }
+ local_irq_restore(flags);
+
+ /*
+ * No local callbacks, so probabalistically probe global state.
+ * Exact information would require acquiring locks, which would
+ * kill scalability, hence the probabalistic nature of the probe.
+ */
+
+ /* First, see if enough time has passed since the last GP. */
+ t = ktime_get_mono_fast_ns();
+ if (exp_holdoff == 0 ||
+ time_in_range_open(t, sp->srcu_last_gp_end,
+ sp->srcu_last_gp_end + exp_holdoff))
+ return false; /* Too soon after last GP. */
+
+ /* Next, check for probable idleness. */
+ curseq = rcu_seq_current(&sp->srcu_gp_seq);
+ smp_mb(); /* Order ->srcu_gp_seq with ->srcu_gp_seq_needed. */
+ if (ULONG_CMP_LT(curseq, READ_ONCE(sp->srcu_gp_seq_needed)))
+ return false; /* Grace period in progress, so not idle. */
+ smp_mb(); /* Order ->srcu_gp_seq with prior access. */
+ if (curseq != rcu_seq_current(&sp->srcu_gp_seq))
+ return false; /* GP # changed, so not idle. */
+ return true; /* With reasonable probability, idle! */
+}
+
+/*
+ * Enqueue an SRCU callback on the srcu_data structure associated with
+ * the current CPU and the specified srcu_struct structure, initiating
+ * grace-period processing if it is not already running.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing SRCU read-side critical section. On systems with
+ * more than one CPU, this means that when "func()" is invoked, each CPU
+ * is guaranteed to have executed a full memory barrier since the end of
+ * its last corresponding SRCU read-side critical section whose beginning
+ * preceded the call to call_rcu(). It also means that each CPU executing
+ * an SRCU read-side critical section that continues beyond the start of
+ * "func()" must have executed a memory barrier after the call_rcu()
+ * but before the beginning of that SRCU 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 call_rcu() and CPU B invoked the
+ * resulting SRCU callback function "func()", then both CPU A and CPU
+ * B are guaranteed to execute a full memory barrier during the time
+ * interval between the call to call_rcu() and the invocation of "func()".
+ * This guarantee applies even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ *
+ * Of course, these guarantees apply only for invocations of call_srcu(),
+ * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
+ * srcu_struct structure.
+ */
+void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+ rcu_callback_t func, bool do_norm)
+{
+ unsigned long flags;
+ bool needexp = false;
+ bool needgp = false;
+ unsigned long s;
+ struct srcu_data *sdp;
+
+ check_init_srcu_struct(sp);
+ rhp->func = func;
+ local_irq_save(flags);
+ sdp = this_cpu_ptr(sp->sda);
+ spin_lock(&sdp->lock);
+ rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
+ rcu_segcblist_advance(&sdp->srcu_cblist,
+ rcu_seq_current(&sp->srcu_gp_seq));
+ s = rcu_seq_snap(&sp->srcu_gp_seq);
+ (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
+ if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
+ sdp->srcu_gp_seq_needed = s;
+ needgp = true;
+ }
+ if (!do_norm && ULONG_CMP_LT(sdp->srcu_gp_seq_needed_exp, s)) {
+ sdp->srcu_gp_seq_needed_exp = s;
+ needexp = true;
+ }
+ spin_unlock_irqrestore(&sdp->lock, flags);
+ if (needgp)
+ srcu_funnel_gp_start(sp, sdp, s, do_norm);
+ else if (needexp)
+ srcu_funnel_exp_start(sp, sdp->mynode, s);
+}
+
+void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+ rcu_callback_t func)
+{
+ __call_srcu(sp, rhp, func, true);
+}
+EXPORT_SYMBOL_GPL(call_srcu);
+
+/*
+ * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
+ */
+static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
+{
+ struct rcu_synchronize rcu;
+
+ RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
+ lock_is_held(&rcu_bh_lock_map) ||
+ lock_is_held(&rcu_lock_map) ||
+ lock_is_held(&rcu_sched_lock_map),
+ "Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section");
+
+ if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
+ return;
+ might_sleep();
+ check_init_srcu_struct(sp);
+ init_completion(&rcu.completion);
+ init_rcu_head_on_stack(&rcu.head);
+ __call_srcu(sp, &rcu.head, wakeme_after_rcu, do_norm);
+ wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
+}
+
+/**
+ * synchronize_srcu_expedited - Brute-force SRCU grace period
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Wait for an SRCU grace period to elapse, but be more aggressive about
+ * spinning rather than blocking when waiting.
+ *
+ * Note that synchronize_srcu_expedited() has the same deadlock and
+ * memory-ordering properties as does synchronize_srcu().
+ */
+void synchronize_srcu_expedited(struct srcu_struct *sp)
+{
+ __synchronize_srcu(sp, rcu_gp_is_normal());
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
+
+/**
+ * synchronize_srcu - wait for prior SRCU read-side critical-section completion
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Wait for the count to drain to zero of both indexes. To avoid the
+ * possible starvation of synchronize_srcu(), it waits for the count of
+ * the index=((->srcu_idx & 1) ^ 1) to drain to zero at first,
+ * and then flip the srcu_idx and wait for the count of the other index.
+ *
+ * Can block; must be called from process context.
+ *
+ * Note that it is illegal to call synchronize_srcu() from the corresponding
+ * SRCU read-side critical section; doing so will result in deadlock.
+ * However, it is perfectly legal to call synchronize_srcu() on one
+ * srcu_struct from some other srcu_struct's read-side critical section,
+ * as long as the resulting graph of srcu_structs is acyclic.
+ *
+ * There are memory-ordering constraints implied by synchronize_srcu().
+ * On systems with more than one CPU, when synchronize_srcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last corresponding SRCU-sched read-side critical section
+ * whose beginning preceded the call to synchronize_srcu(). In addition,
+ * each CPU having an SRCU read-side critical section that extends beyond
+ * the return from synchronize_srcu() is guaranteed to have executed a
+ * full memory barrier after the beginning of synchronize_srcu() and before
+ * the beginning of that SRCU 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_srcu(), 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_srcu(). This guarantee applies even if CPU A and CPU B
+ * are the same CPU, but again only if the system has more than one CPU.
+ *
+ * Of course, these memory-ordering guarantees apply only when
+ * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
+ * passed the same srcu_struct structure.
+ *
+ * If SRCU is likely idle, expedite the first request. This semantic
+ * was provided by Classic SRCU, and is relied upon by its users, so TREE
+ * SRCU must also provide it. Note that detecting idleness is heuristic
+ * and subject to both false positives and negatives.
+ */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+ if (srcu_might_be_idle(sp) || rcu_gp_is_expedited())
+ synchronize_srcu_expedited(sp);
+ else
+ __synchronize_srcu(sp, true);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu);
+
+/*
+ * Callback function for srcu_barrier() use.
+ */
+static void srcu_barrier_cb(struct rcu_head *rhp)
+{
+ struct srcu_data *sdp;
+ struct srcu_struct *sp;
+
+ sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
+ sp = sdp->sp;
+ if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
+ complete(&sp->srcu_barrier_completion);
+}
+
+/**
+ * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ * @sp: srcu_struct on which to wait for in-flight callbacks.
+ */
+void srcu_barrier(struct srcu_struct *sp)
+{
+ int cpu;
+ struct srcu_data *sdp;
+ unsigned long s = rcu_seq_snap(&sp->srcu_barrier_seq);
+
+ check_init_srcu_struct(sp);
+ mutex_lock(&sp->srcu_barrier_mutex);
+ if (rcu_seq_done(&sp->srcu_barrier_seq, s)) {
+ smp_mb(); /* Force ordering following return. */
+ mutex_unlock(&sp->srcu_barrier_mutex);
+ return; /* Someone else did our work for us. */
+ }
+ rcu_seq_start(&sp->srcu_barrier_seq);
+ init_completion(&sp->srcu_barrier_completion);
+
+ /* Initial count prevents reaching zero until all CBs are posted. */
+ atomic_set(&sp->srcu_barrier_cpu_cnt, 1);
+
+ /*
+ * Each pass through this loop enqueues a callback, but only
+ * on CPUs already having callbacks enqueued. Note that if
+ * a CPU already has callbacks enqueue, it must have already
+ * registered the need for a future grace period, so all we
+ * need do is enqueue a callback that will use the same
+ * grace period as the last callback already in the queue.
+ */
+ for_each_possible_cpu(cpu) {
+ sdp = per_cpu_ptr(sp->sda, cpu);
+ spin_lock_irq(&sdp->lock);
+ atomic_inc(&sp->srcu_barrier_cpu_cnt);
+ sdp->srcu_barrier_head.func = srcu_barrier_cb;
+ if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
+ &sdp->srcu_barrier_head, 0))
+ atomic_dec(&sp->srcu_barrier_cpu_cnt);
+ spin_unlock_irq(&sdp->lock);
+ }
+
+ /* Remove the initial count, at which point reaching zero can happen. */
+ if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
+ complete(&sp->srcu_barrier_completion);
+ wait_for_completion(&sp->srcu_barrier_completion);
+
+ rcu_seq_end(&sp->srcu_barrier_seq);
+ mutex_unlock(&sp->srcu_barrier_mutex);
+}
+EXPORT_SYMBOL_GPL(srcu_barrier);
+
+/**
+ * srcu_batches_completed - return batches completed.
+ * @sp: srcu_struct on which to report batch completion.
+ *
+ * Report the number of batches, correlated with, but not necessarily
+ * precisely the same as, the number of grace periods that have elapsed.
+ */
+unsigned long srcu_batches_completed(struct srcu_struct *sp)
+{
+ return sp->srcu_idx;
+}
+EXPORT_SYMBOL_GPL(srcu_batches_completed);
+
+/*
+ * Core SRCU state machine. Push state bits of ->srcu_gp_seq
+ * to SRCU_STATE_SCAN2, and invoke srcu_gp_end() when scan has
+ * completed in that state.
+ */
+static void srcu_advance_state(struct srcu_struct *sp)
+{
+ int idx;
+
+ mutex_lock(&sp->srcu_gp_mutex);
+
+ /*
+ * Because readers might be delayed for an extended period after
+ * fetching ->srcu_idx for their index, at any point in time there
+ * might well be readers using both idx=0 and idx=1. We therefore
+ * need to wait for readers to clear from both index values before
+ * invoking a callback.
+ *
+ * The load-acquire ensures that we see the accesses performed
+ * by the prior grace period.
+ */
+ idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
+ if (idx == SRCU_STATE_IDLE) {
+ spin_lock_irq(&sp->gp_lock);
+ if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
+ WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq));
+ spin_unlock_irq(&sp->gp_lock);
+ mutex_unlock(&sp->srcu_gp_mutex);
+ return;
+ }
+ idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+ if (idx == SRCU_STATE_IDLE)
+ srcu_gp_start(sp);
+ spin_unlock_irq(&sp->gp_lock);
+ if (idx != SRCU_STATE_IDLE) {
+ mutex_unlock(&sp->srcu_gp_mutex);
+ return; /* Someone else started the grace period. */
+ }
+ }
+
+ if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
+ idx = 1 ^ (sp->srcu_idx & 1);
+ if (!try_check_zero(sp, idx, 1)) {
+ mutex_unlock(&sp->srcu_gp_mutex);
+ return; /* readers present, retry later. */
+ }
+ srcu_flip(sp);
+ rcu_seq_set_state(&sp->srcu_gp_seq, SRCU_STATE_SCAN2);
+ }
+
+ if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
+
+ /*
+ * SRCU read-side critical sections are normally short,
+ * so check at least twice in quick succession after a flip.
+ */
+ idx = 1 ^ (sp->srcu_idx & 1);
+ if (!try_check_zero(sp, idx, 2)) {
+ mutex_unlock(&sp->srcu_gp_mutex);
+ return; /* readers present, retry later. */
+ }
+ srcu_gp_end(sp); /* Releases ->srcu_gp_mutex. */
+ }
+}
+
+/*
+ * Invoke a limited number of SRCU callbacks that have passed through
+ * their grace period. If there are more to do, SRCU will reschedule
+ * the workqueue. Note that needed memory barriers have been executed
+ * in this task's context by srcu_readers_active_idx_check().
+ */
+static void srcu_invoke_callbacks(struct work_struct *work)
+{
+ bool more;
+ struct rcu_cblist ready_cbs;
+ struct rcu_head *rhp;
+ struct srcu_data *sdp;
+ struct srcu_struct *sp;
+
+ sdp = container_of(work, struct srcu_data, work.work);
+ sp = sdp->sp;
+ rcu_cblist_init(&ready_cbs);
+ spin_lock_irq(&sdp->lock);
+ smp_mb(); /* Old grace periods before callback invocation! */
+ rcu_segcblist_advance(&sdp->srcu_cblist,
+ rcu_seq_current(&sp->srcu_gp_seq));
+ if (sdp->srcu_cblist_invoking ||
+ !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
+ spin_unlock_irq(&sdp->lock);
+ return; /* Someone else on the job or nothing to do. */
+ }
+
+ /* We are on the job! Extract and invoke ready callbacks. */
+ sdp->srcu_cblist_invoking = true;
+ rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
+ spin_unlock_irq(&sdp->lock);
+ rhp = rcu_cblist_dequeue(&ready_cbs);
+ for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
+ local_bh_disable();
+ rhp->func(rhp);
+ local_bh_enable();
+ }
+
+ /*
+ * Update counts, accelerate new callbacks, and if needed,
+ * schedule another round of callback invocation.
+ */
+ spin_lock_irq(&sdp->lock);
+ rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
+ (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
+ rcu_seq_snap(&sp->srcu_gp_seq));
+ sdp->srcu_cblist_invoking = false;
+ more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
+ spin_unlock_irq(&sdp->lock);
+ if (more)
+ srcu_schedule_cbs_sdp(sdp, 0);
+}
+
+/*
+ * Finished one round of SRCU grace period. Start another if there are
+ * more SRCU callbacks queued, otherwise put SRCU into not-running state.
+ */
+static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
+{
+ bool pushgp = true;
+
+ spin_lock_irq(&sp->gp_lock);
+ if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
+ if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
+ /* All requests fulfilled, time to go idle. */
+ pushgp = false;
+ }
+ } else if (!rcu_seq_state(sp->srcu_gp_seq)) {
+ /* Outstanding request and no GP. Start one. */
+ srcu_gp_start(sp);
+ }
+ spin_unlock_irq(&sp->gp_lock);
+
+ if (pushgp)
+ queue_delayed_work(system_power_efficient_wq, &sp->work, delay);
+}
+
+/*
+ * This is the work-queue function that handles SRCU grace periods.
+ */
+void process_srcu(struct work_struct *work)
+{
+ struct srcu_struct *sp;
+
+ sp = container_of(work, struct srcu_struct, work.work);
+
+ srcu_advance_state(sp);
+ srcu_reschedule(sp, srcu_get_delay(sp));
+}
+EXPORT_SYMBOL_GPL(process_srcu);
+
+void srcutorture_get_gp_data(enum rcutorture_type test_type,
+ struct srcu_struct *sp, int *flags,
+ unsigned long *gpnum, unsigned long *completed)
+{
+ if (test_type != SRCU_FLAVOR)
+ return;
+ *flags = 0;
+ *completed = rcu_seq_ctr(sp->srcu_gp_seq);
+ *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed);
+}
+EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 6ad330dbbae2..e5385731e391 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -79,7 +79,7 @@ EXPORT_SYMBOL(__rcu_is_watching);
*/
static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
{
- RCU_TRACE(reset_cpu_stall_ticks(rcp));
+ RCU_TRACE(reset_cpu_stall_ticks(rcp);)
if (rcp->donetail != rcp->curtail) {
rcp->donetail = rcp->curtail;
return 1;
@@ -125,7 +125,7 @@ void rcu_bh_qs(void)
*/
void rcu_check_callbacks(int user)
{
- RCU_TRACE(check_cpu_stalls());
+ RCU_TRACE(check_cpu_stalls();)
if (user)
rcu_sched_qs();
else if (!in_softirq())
@@ -143,7 +143,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
const char *rn = NULL;
struct rcu_head *next, *list;
unsigned long flags;
- RCU_TRACE(int cb_count = 0);
+ RCU_TRACE(int cb_count = 0;)
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
@@ -152,7 +152,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
local_irq_restore(flags);
return;
}
- RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
+ RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1);)
list = rcp->rcucblist;
rcp->rcucblist = *rcp->donetail;
*rcp->donetail = NULL;
@@ -162,7 +162,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
local_irq_restore(flags);
/* Invoke the callbacks on the local list. */
- RCU_TRACE(rn = rcp->name);
+ RCU_TRACE(rn = rcp->name;)
while (list) {
next = list->next;
prefetch(next);
@@ -171,9 +171,9 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
__rcu_reclaim(rn, list);
local_bh_enable();
list = next;
- RCU_TRACE(cb_count++);
+ RCU_TRACE(cb_count++;)
}
- RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
+ RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count);)
RCU_TRACE(trace_rcu_batch_end(rcp->name,
cb_count, 0, need_resched(),
is_idle_task(current),
@@ -221,7 +221,7 @@ static void __call_rcu(struct rcu_head *head,
local_irq_save(flags);
*rcp->curtail = head;
rcp->curtail = &head->next;
- RCU_TRACE(rcp->qlen++);
+ RCU_TRACE(rcp->qlen++;)
local_irq_restore(flags);
if (unlikely(is_idle_task(current))) {
@@ -254,8 +254,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh);
void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
- RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk));
- RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk));
+ RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk);)
+ RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk);)
rcu_early_boot_tests();
}
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index c64b827ecbca..371034e77f87 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -52,7 +52,7 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
RCU_TRACE(.name = "rcu_bh")
};
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
#include <linux/kernel_stat.h>
int rcu_scheduler_active __read_mostly;
@@ -65,15 +65,16 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
* to RCU_SCHEDULER_RUNNING, skipping the RCU_SCHEDULER_INIT stage.
* The reason for this is that Tiny RCU does not need kthreads, so does
* not have to care about the fact that the scheduler is half-initialized
- * at a certain phase of the boot process.
+ * at a certain phase of the boot process. Unless SRCU is in the mix.
*/
void __init rcu_scheduler_starting(void)
{
WARN_ON(nr_context_switches() > 0);
- rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+ rcu_scheduler_active = IS_ENABLED(CONFIG_SRCU)
+ ? RCU_SCHEDULER_INIT : RCU_SCHEDULER_RUNNING;
}
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
#ifdef CONFIG_RCU_TRACE
@@ -162,8 +163,8 @@ static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
static void check_cpu_stalls(void)
{
- RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk));
- RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk));
+ RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk);)
+ RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk);)
}
#endif /* #ifdef CONFIG_RCU_TRACE */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a6dcf3bd244f..e354e475e645 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -98,8 +98,8 @@ struct rcu_state sname##_state = { \
.gpnum = 0UL - 300UL, \
.completed = 0UL - 300UL, \
.orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \
- .orphan_nxttail = &sname##_state.orphan_nxtlist, \
- .orphan_donetail = &sname##_state.orphan_donelist, \
+ .orphan_pend = RCU_CBLIST_INITIALIZER(sname##_state.orphan_pend), \
+ .orphan_done = RCU_CBLIST_INITIALIZER(sname##_state.orphan_done), \
.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
.name = RCU_STATE_NAME(sname), \
.abbr = sabbr, \
@@ -124,7 +124,7 @@ static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
module_param(rcu_fanout_leaf, int, 0444);
int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
/* Number of rcu_nodes at specified level. */
-static int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
+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;
@@ -200,7 +200,7 @@ static const int gp_cleanup_delay;
/*
* Number of grace periods between delays, normalized by the duration of
- * the delay. The longer the the delay, the more the grace periods between
+ * the delay. The longer the delay, the more the grace periods between
* each delay. The reason for this normalization is that it means that,
* for non-zero delays, the overall slowdown of grace periods is constant
* regardless of the duration of the delay. This arrangement balances
@@ -273,11 +273,19 @@ void rcu_bh_qs(void)
}
}
-static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
+/*
+ * Steal a bit from the bottom of ->dynticks for idle entry/exit
+ * control. Initially this is for TLB flushing.
+ */
+#define RCU_DYNTICK_CTRL_MASK 0x1
+#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1)
+#ifndef rcu_eqs_special_exit
+#define rcu_eqs_special_exit() do { } while (0)
+#endif
static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
- .dynticks = ATOMIC_INIT(1),
+ .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
.dynticks_idle = ATOMIC_INIT(1),
@@ -305,15 +313,20 @@ bool rcu_irq_enter_disabled(void)
static void rcu_dynticks_eqs_enter(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- int special;
+ int seq;
/*
- * CPUs seeing atomic_inc_return() must see prior RCU read-side
+ * CPUs seeing atomic_add_return() must see prior RCU read-side
* critical sections, and we also must force ordering with the
* next idle sojourn.
*/
- special = atomic_inc_return(&rdtp->dynticks);
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && special & 0x1);
+ seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ /* Better be in an extended quiescent state! */
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ (seq & RCU_DYNTICK_CTRL_CTR));
+ /* Better not have special action (TLB flush) pending! */
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ (seq & RCU_DYNTICK_CTRL_MASK));
}
/*
@@ -323,15 +336,22 @@ static void rcu_dynticks_eqs_enter(void)
static void rcu_dynticks_eqs_exit(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- int special;
+ int seq;
/*
- * CPUs seeing atomic_inc_return() must see prior idle sojourns,
+ * CPUs seeing atomic_add_return() must see prior idle sojourns,
* and we also must force ordering with the next RCU read-side
* critical section.
*/
- special = atomic_inc_return(&rdtp->dynticks);
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(special & 0x1));
+ seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ !(seq & RCU_DYNTICK_CTRL_CTR));
+ if (seq & RCU_DYNTICK_CTRL_MASK) {
+ atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdtp->dynticks);
+ smp_mb__after_atomic(); /* _exit after clearing mask. */
+ /* Prefer duplicate flushes to losing a flush. */
+ rcu_eqs_special_exit();
+ }
}
/*
@@ -348,9 +368,9 @@ static void rcu_dynticks_eqs_online(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- if (atomic_read(&rdtp->dynticks) & 0x1)
+ if (atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR)
return;
- atomic_add(0x1, &rdtp->dynticks);
+ atomic_add(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
}
/*
@@ -362,7 +382,7 @@ bool rcu_dynticks_curr_cpu_in_eqs(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- return !(atomic_read(&rdtp->dynticks) & 0x1);
+ return !(atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR);
}
/*
@@ -373,7 +393,7 @@ int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
{
int snap = atomic_add_return(0, &rdtp->dynticks);
- return snap;
+ return snap & ~RCU_DYNTICK_CTRL_MASK;
}
/*
@@ -382,7 +402,7 @@ int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
*/
static bool rcu_dynticks_in_eqs(int snap)
{
- return !(snap & 0x1);
+ return !(snap & RCU_DYNTICK_CTRL_CTR);
}
/*
@@ -402,14 +422,34 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
static void rcu_dynticks_momentary_idle(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- int special = atomic_add_return(2, &rdtp->dynticks);
+ int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
+ &rdtp->dynticks);
/* It is illegal to call this from idle state. */
- WARN_ON_ONCE(!(special & 0x1));
+ WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
}
-DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
-EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
+/*
+ * Set the special (bottom) bit of the specified CPU so that it
+ * will take special action (such as flushing its TLB) on the
+ * next exit from an extended quiescent state. Returns true if
+ * the bit was successfully set, or false if the CPU was not in
+ * an extended quiescent state.
+ */
+bool rcu_eqs_special_set(int cpu)
+{
+ int old;
+ int new;
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+ do {
+ old = atomic_read(&rdtp->dynticks);
+ if (old & RCU_DYNTICK_CTRL_CTR)
+ return false;
+ new = old | RCU_DYNTICK_CTRL_MASK;
+ } while (atomic_cmpxchg(&rdtp->dynticks, old, new) != old);
+ return true;
+}
/*
* Let the RCU core know that this CPU has gone through the scheduler,
@@ -418,44 +458,14 @@ EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
* memory barriers to let the RCU core know about it, regardless of what
* this CPU might (or might not) do in the near future.
*
- * We inform the RCU core by emulating a zero-duration dyntick-idle
- * period, which we in turn do by incrementing the ->dynticks counter
- * by two.
+ * We inform the RCU core by emulating a zero-duration dyntick-idle period.
*
* The caller must have disabled interrupts.
*/
static void rcu_momentary_dyntick_idle(void)
{
- struct rcu_data *rdp;
- int resched_mask;
- struct rcu_state *rsp;
-
- /*
- * Yes, we can lose flag-setting operations. This is OK, because
- * the flag will be set again after some delay.
- */
- resched_mask = raw_cpu_read(rcu_sched_qs_mask);
- raw_cpu_write(rcu_sched_qs_mask, 0);
-
- /* Find the flavor that needs a quiescent state. */
- for_each_rcu_flavor(rsp) {
- rdp = raw_cpu_ptr(rsp->rda);
- if (!(resched_mask & rsp->flavor_mask))
- continue;
- smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
- if (READ_ONCE(rdp->mynode->completed) !=
- READ_ONCE(rdp->cond_resched_completed))
- continue;
-
- /*
- * Pretend to be momentarily idle for the quiescent state.
- * This allows the grace-period kthread to record the
- * quiescent state, with no need for this CPU to do anything
- * further.
- */
- rcu_dynticks_momentary_idle();
- break;
- }
+ raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false);
+ rcu_dynticks_momentary_idle();
}
/*
@@ -463,14 +473,22 @@ static void rcu_momentary_dyntick_idle(void)
* and requires special handling for preemptible RCU.
* The caller must have disabled interrupts.
*/
-void rcu_note_context_switch(void)
+void rcu_note_context_switch(bool preempt)
{
barrier(); /* Avoid RCU read-side critical sections leaking down. */
trace_rcu_utilization(TPS("Start context switch"));
rcu_sched_qs();
rcu_preempt_note_context_switch();
- if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+ /* Load rcu_urgent_qs before other flags. */
+ if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs)))
+ goto out;
+ this_cpu_write(rcu_dynticks.rcu_urgent_qs, false);
+ if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs)))
rcu_momentary_dyntick_idle();
+ this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
+ if (!preempt)
+ rcu_note_voluntary_context_switch_lite(current);
+out:
trace_rcu_utilization(TPS("End context switch"));
barrier(); /* Avoid RCU read-side critical sections leaking up. */
}
@@ -493,29 +511,26 @@ void rcu_all_qs(void)
{
unsigned long flags;
+ if (!raw_cpu_read(rcu_dynticks.rcu_urgent_qs))
+ return;
+ preempt_disable();
+ /* Load rcu_urgent_qs before other flags. */
+ if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) {
+ preempt_enable();
+ return;
+ }
+ this_cpu_write(rcu_dynticks.rcu_urgent_qs, false);
barrier(); /* Avoid RCU read-side critical sections leaking down. */
- if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) {
+ if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs))) {
local_irq_save(flags);
rcu_momentary_dyntick_idle();
local_irq_restore(flags);
}
- if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))) {
- /*
- * Yes, we just checked a per-CPU variable with preemption
- * enabled, so we might be migrated to some other CPU at
- * this point. That is OK because in that case, the
- * migration will supply the needed quiescent state.
- * We might end up needlessly disabling preemption and
- * invoking rcu_sched_qs() on the destination CPU, but
- * the probability and cost are both quite low, so this
- * should not be a problem in practice.
- */
- preempt_disable();
+ if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)))
rcu_sched_qs();
- preempt_enable();
- }
- this_cpu_inc(rcu_qs_ctr);
+ this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
barrier(); /* Avoid RCU read-side critical sections leaking up. */
+ preempt_enable();
}
EXPORT_SYMBOL_GPL(rcu_all_qs);
@@ -704,15 +719,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
default:
break;
}
- if (rsp != NULL) {
- *flags = READ_ONCE(rsp->gp_flags);
- *gpnum = READ_ONCE(rsp->gpnum);
- *completed = READ_ONCE(rsp->completed);
+ if (rsp == NULL)
return;
- }
- *flags = 0;
- *gpnum = 0;
- *completed = 0;
+ *flags = READ_ONCE(rsp->gp_flags);
+ *gpnum = READ_ONCE(rsp->gpnum);
+ *completed = READ_ONCE(rsp->completed);
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
@@ -728,16 +739,6 @@ void rcutorture_record_progress(unsigned long vernum)
EXPORT_SYMBOL_GPL(rcutorture_record_progress);
/*
- * Does the CPU have callbacks ready to be invoked?
- */
-static int
-cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
-{
- return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
- rdp->nxttail[RCU_NEXT_TAIL] != NULL;
-}
-
-/*
* Return the root node of the specified rcu_state structure.
*/
static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
@@ -767,21 +768,17 @@ static int rcu_future_needs_gp(struct rcu_state *rsp)
static bool
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
- int i;
-
if (rcu_gp_in_progress(rsp))
return false; /* No, a grace period is already in progress. */
if (rcu_future_needs_gp(rsp))
return true; /* Yes, a no-CBs CPU needs one. */
- if (!rdp->nxttail[RCU_NEXT_TAIL])
+ if (!rcu_segcblist_is_enabled(&rdp->cblist))
return false; /* No, this is a no-CBs (or offline) CPU. */
- if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
+ if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return true; /* Yes, CPU has newly registered callbacks. */
- for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
- if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
- ULONG_CMP_LT(READ_ONCE(rsp->completed),
- rdp->nxtcompleted[i]))
- return true; /* Yes, CBs for future grace period. */
+ if (rcu_segcblist_future_gp_needed(&rdp->cblist,
+ READ_ONCE(rsp->completed)))
+ return true; /* Yes, CBs for future grace period. */
return false; /* No grace period needed. */
}
@@ -1162,6 +1159,24 @@ bool notrace rcu_is_watching(void)
}
EXPORT_SYMBOL_GPL(rcu_is_watching);
+/*
+ * If a holdout task is actually running, request an urgent quiescent
+ * state from its CPU. This is unsynchronized, so migrations can cause
+ * the request to go to the wrong CPU. Which is OK, all that will happen
+ * is that the CPU's next context switch will be a bit slower and next
+ * time around this task will generate another request.
+ */
+void rcu_request_urgent_qs_task(struct task_struct *t)
+{
+ int cpu;
+
+ barrier();
+ cpu = task_cpu(t);
+ if (!task_curr(t))
+ return; /* This task is not running on that CPU. */
+ smp_store_release(per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, cpu), true);
+}
+
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
@@ -1247,7 +1262,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
bool *isidle, unsigned long *maxj)
{
unsigned long jtsq;
- int *rcrmp;
+ bool *rnhqp;
+ bool *ruqp;
unsigned long rjtsc;
struct rcu_node *rnp;
@@ -1283,11 +1299,15 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
* might not be the case for nohz_full CPUs looping in the kernel.
*/
rnp = rdp->mynode;
+ ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
- READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_qs_ctr, rdp->cpu) &&
+ READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
return 1;
+ } else {
+ /* Load rcu_qs_ctr before store to rcu_urgent_qs. */
+ smp_store_release(ruqp, true);
}
/* Check for the CPU being offline. */
@@ -1304,7 +1324,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
* in-kernel CPU-bound tasks cannot advance grace periods.
* So if the grace period is old enough, make the CPU pay attention.
* Note that the unsynchronized assignments to the per-CPU
- * rcu_sched_qs_mask variable are safe. Yes, setting of
+ * rcu_need_heavy_qs variable are safe. Yes, setting of
* bits can be lost, but they will be set again on the next
* force-quiescent-state pass. So lost bit sets do not result
* in incorrect behavior, merely in a grace period lasting
@@ -1318,16 +1338,13 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
* is set too high, we override with half of the RCU CPU stall
* warning delay.
*/
- rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
- if (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
- time_after(jiffies, rdp->rsp->jiffies_resched)) {
- if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
- WRITE_ONCE(rdp->cond_resched_completed,
- READ_ONCE(rdp->mynode->completed));
- smp_mb(); /* ->cond_resched_completed before *rcrmp. */
- WRITE_ONCE(*rcrmp,
- READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask);
- }
+ rnhqp = &per_cpu(rcu_dynticks.rcu_need_heavy_qs, rdp->cpu);
+ if (!READ_ONCE(*rnhqp) &&
+ (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
+ time_after(jiffies, rdp->rsp->jiffies_resched))) {
+ WRITE_ONCE(*rnhqp, true);
+ /* Store rcu_need_heavy_qs before rcu_urgent_qs. */
+ smp_store_release(ruqp, true);
rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
}
@@ -1487,7 +1504,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
- totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
+ totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
+ cpu)->cblist);
pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start),
(long)rsp->gpnum, (long)rsp->completed, totqlen);
@@ -1541,7 +1559,8 @@ static void print_cpu_stall(struct rcu_state *rsp)
print_cpu_stall_info(rsp, smp_processor_id());
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
- totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
+ totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
+ cpu)->cblist);
pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
jiffies - rsp->gp_start,
(long)rsp->gpnum, (long)rsp->completed, totqlen);
@@ -1644,30 +1663,6 @@ void rcu_cpu_stall_reset(void)
}
/*
- * Initialize the specified rcu_data structure's default callback list
- * to empty. The default callback list is the one that is not used by
- * no-callbacks CPUs.
- */
-static void init_default_callback_list(struct rcu_data *rdp)
-{
- int i;
-
- rdp->nxtlist = NULL;
- for (i = 0; i < RCU_NEXT_SIZE; i++)
- rdp->nxttail[i] = &rdp->nxtlist;
-}
-
-/*
- * Initialize the specified rcu_data structure's callback list to empty.
- */
-static void init_callback_list(struct rcu_data *rdp)
-{
- if (init_nocb_callback_list(rdp))
- return;
- init_default_callback_list(rdp);
-}
-
-/*
* Determine the value that ->completed will have at the end of the
* next subsequent grace period. This is used to tag callbacks so that
* a CPU can invoke callbacks in a timely fashion even if that CPU has
@@ -1721,7 +1716,6 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long *c_out)
{
unsigned long c;
- int i;
bool ret = false;
struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
@@ -1767,13 +1761,11 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
/*
* Get a new grace-period number. If there really is no grace
* period in progress, it will be smaller than the one we obtained
- * earlier. Adjust callbacks as needed. Note that even no-CBs
- * CPUs have a ->nxtcompleted[] array, so no no-CBs checks needed.
+ * earlier. Adjust callbacks as needed.
*/
c = rcu_cbs_completed(rdp->rsp, rnp_root);
- for (i = RCU_DONE_TAIL; i < RCU_NEXT_TAIL; i++)
- if (ULONG_CMP_LT(c, rdp->nxtcompleted[i]))
- rdp->nxtcompleted[i] = c;
+ if (!rcu_is_nocb_cpu(rdp->cpu))
+ (void)rcu_segcblist_accelerate(&rdp->cblist, c);
/*
* If the needed for the required grace period is already
@@ -1805,9 +1797,7 @@ out:
/*
* Clean up any old requests for the just-ended grace period. Also return
- * whether any additional grace periods have been requested. Also invoke
- * rcu_nocb_gp_cleanup() in order to wake up any no-callbacks kthreads
- * waiting for this grace period to complete.
+ * whether any additional grace periods have been requested.
*/
static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
@@ -1853,57 +1843,27 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
- unsigned long c;
- int i;
- bool ret;
-
- /* If the CPU has no callbacks, nothing to do. */
- if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
- return false;
-
- /*
- * Starting from the sublist containing the callbacks most
- * recently assigned a ->completed number and working down, find the
- * first sublist that is not assignable to an upcoming grace period.
- * Such a sublist has something in it (first two tests) and has
- * a ->completed number assigned that will complete sooner than
- * the ->completed number for newly arrived callbacks (last test).
- *
- * The key point is that any later sublist can be assigned the
- * same ->completed number as the newly arrived callbacks, which
- * means that the callbacks in any of these later sublist can be
- * grouped into a single sublist, whether or not they have already
- * been assigned a ->completed number.
- */
- c = rcu_cbs_completed(rsp, rnp);
- for (i = RCU_NEXT_TAIL - 1; i > RCU_DONE_TAIL; i--)
- if (rdp->nxttail[i] != rdp->nxttail[i - 1] &&
- !ULONG_CMP_GE(rdp->nxtcompleted[i], c))
- break;
+ bool ret = false;
- /*
- * If there are no sublist for unassigned callbacks, leave.
- * At the same time, advance "i" one sublist, so that "i" will
- * index into the sublist where all the remaining callbacks should
- * be grouped into.
- */
- if (++i >= RCU_NEXT_TAIL)
+ /* If no pending (not yet ready to invoke) callbacks, nothing to do. */
+ if (!rcu_segcblist_pend_cbs(&rdp->cblist))
return false;
/*
- * Assign all subsequent callbacks' ->completed number to the next
- * full grace period and group them all in the sublist initially
- * indexed by "i".
+ * Callbacks are often registered with incomplete grace-period
+ * information. Something about the fact that getting exact
+ * information requires acquiring a global lock... RCU therefore
+ * makes a conservative estimate of the grace period number at which
+ * a given callback will become ready to invoke. The following
+ * code checks this estimate and improves it when possible, thus
+ * accelerating callback invocation to an earlier grace-period
+ * number.
*/
- for (; i <= RCU_NEXT_TAIL; i++) {
- rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL];
- rdp->nxtcompleted[i] = c;
- }
- /* Record any needed additional grace periods. */
- ret = rcu_start_future_gp(rnp, rdp, NULL);
+ if (rcu_segcblist_accelerate(&rdp->cblist, rcu_cbs_completed(rsp, rnp)))
+ ret = rcu_start_future_gp(rnp, rdp, NULL);
/* Trace depending on how much we were able to accelerate. */
- if (!*rdp->nxttail[RCU_WAIT_TAIL])
+ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
else
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
@@ -1923,32 +1883,15 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
- int i, j;
-
- /* If the CPU has no callbacks, nothing to do. */
- if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
+ /* If no pending (not yet ready to invoke) callbacks, nothing to do. */
+ if (!rcu_segcblist_pend_cbs(&rdp->cblist))
return false;
/*
* Find all callbacks whose ->completed numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
*/
- for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
- if (ULONG_CMP_LT(rnp->completed, rdp->nxtcompleted[i]))
- break;
- rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[i];
- }
- /* Clean up any sublist tail pointers that were misordered above. */
- for (j = RCU_WAIT_TAIL; j < i; j++)
- rdp->nxttail[j] = rdp->nxttail[RCU_DONE_TAIL];
-
- /* Copy down callbacks to fill in empty sublists. */
- for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
- if (rdp->nxttail[j] == rdp->nxttail[RCU_NEXT_TAIL])
- break;
- rdp->nxttail[j] = rdp->nxttail[i];
- rdp->nxtcompleted[j] = rdp->nxtcompleted[i];
- }
+ rcu_segcblist_advance(&rdp->cblist, rnp->completed);
/* Classify any remaining callbacks. */
return rcu_accelerate_cbs(rsp, rnp, rdp);
@@ -1993,7 +1936,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
need_gp = !!(rnp->qsmask & rdp->grpmask);
rdp->cpu_no_qs.b.norm = need_gp;
- rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
rdp->core_needs_qs = need_gp;
zero_cpu_stall_ticks(rdp);
WRITE_ONCE(rdp->gpwrap, false);
@@ -2591,7 +2534,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
* within the current grace period.
*/
rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */
- rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
@@ -2665,13 +2608,8 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
* because _rcu_barrier() excludes CPU-hotplug operations, so it
* cannot be running now. Thus no memory barrier is required.
*/
- if (rdp->nxtlist != NULL) {
- rsp->qlen_lazy += rdp->qlen_lazy;
- rsp->qlen += rdp->qlen;
- rdp->n_cbs_orphaned += rdp->qlen;
- rdp->qlen_lazy = 0;
- WRITE_ONCE(rdp->qlen, 0);
- }
+ rdp->n_cbs_orphaned += rcu_segcblist_n_cbs(&rdp->cblist);
+ rcu_segcblist_extract_count(&rdp->cblist, &rsp->orphan_done);
/*
* Next, move those callbacks still needing a grace period to
@@ -2679,31 +2617,18 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
* Some of the callbacks might have gone partway through a grace
* period, but that is too bad. They get to start over because we
* cannot assume that grace periods are synchronized across CPUs.
- * We don't bother updating the ->nxttail[] array yet, instead
- * we just reset the whole thing later on.
*/
- if (*rdp->nxttail[RCU_DONE_TAIL] != NULL) {
- *rsp->orphan_nxttail = *rdp->nxttail[RCU_DONE_TAIL];
- rsp->orphan_nxttail = rdp->nxttail[RCU_NEXT_TAIL];
- *rdp->nxttail[RCU_DONE_TAIL] = NULL;
- }
+ rcu_segcblist_extract_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
/*
* Then move the ready-to-invoke callbacks to the orphanage,
* where some other CPU will pick them up. These will not be
* required to pass though another grace period: They are done.
*/
- if (rdp->nxtlist != NULL) {
- *rsp->orphan_donetail = rdp->nxtlist;
- rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL];
- }
+ rcu_segcblist_extract_done_cbs(&rdp->cblist, &rsp->orphan_done);
- /*
- * Finally, initialize the rcu_data structure's list to empty and
- * disallow further callbacks on this CPU.
- */
- init_callback_list(rdp);
- rdp->nxttail[RCU_NEXT_TAIL] = NULL;
+ /* Finally, disallow further callbacks on this CPU. */
+ rcu_segcblist_disable(&rdp->cblist);
}
/*
@@ -2712,7 +2637,6 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
*/
static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
{
- int i;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
/* No-CBs CPUs are handled specially. */
@@ -2721,13 +2645,10 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
return;
/* Do the accounting first. */
- rdp->qlen_lazy += rsp->qlen_lazy;
- rdp->qlen += rsp->qlen;
- rdp->n_cbs_adopted += rsp->qlen;
- if (rsp->qlen_lazy != rsp->qlen)
+ rdp->n_cbs_adopted += rsp->orphan_done.len;
+ if (rsp->orphan_done.len_lazy != rsp->orphan_done.len)
rcu_idle_count_callbacks_posted();
- rsp->qlen_lazy = 0;
- rsp->qlen = 0;
+ rcu_segcblist_insert_count(&rdp->cblist, &rsp->orphan_done);
/*
* We do not need a memory barrier here because the only way we
@@ -2735,24 +2656,13 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
* we are the task doing the rcu_barrier().
*/
- /* First adopt the ready-to-invoke callbacks. */
- if (rsp->orphan_donelist != NULL) {
- *rsp->orphan_donetail = *rdp->nxttail[RCU_DONE_TAIL];
- *rdp->nxttail[RCU_DONE_TAIL] = rsp->orphan_donelist;
- for (i = RCU_NEXT_SIZE - 1; i >= RCU_DONE_TAIL; i--)
- if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
- rdp->nxttail[i] = rsp->orphan_donetail;
- rsp->orphan_donelist = NULL;
- rsp->orphan_donetail = &rsp->orphan_donelist;
- }
-
- /* And then adopt the callbacks that still need a grace period. */
- if (rsp->orphan_nxtlist != NULL) {
- *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxtlist;
- rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxttail;
- rsp->orphan_nxtlist = NULL;
- rsp->orphan_nxttail = &rsp->orphan_nxtlist;
- }
+ /* First adopt the ready-to-invoke callbacks, then the done ones. */
+ rcu_segcblist_insert_done_cbs(&rdp->cblist, &rsp->orphan_done);
+ WARN_ON_ONCE(rsp->orphan_done.head);
+ rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
+ WARN_ON_ONCE(rsp->orphan_pend.head);
+ WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) !=
+ !rcu_segcblist_n_cbs(&rdp->cblist));
}
/*
@@ -2760,14 +2670,14 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
*/
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
- RCU_TRACE(unsigned long mask);
- RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
- RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
+ RCU_TRACE(unsigned long mask;)
+ RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);)
+ RCU_TRACE(struct rcu_node *rnp = rdp->mynode;)
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
- RCU_TRACE(mask = rdp->grpmask);
+ RCU_TRACE(mask = rdp->grpmask;)
trace_rcu_grace_period(rsp->name,
rnp->gpnum + 1 - !!(rnp->qsmask & mask),
TPS("cpuofl"));
@@ -2840,9 +2750,11 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
rcu_adopt_orphan_cbs(rsp, flags);
raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
- WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
- "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n",
- cpu, rdp->qlen, rdp->nxtlist);
+ WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
+ !rcu_segcblist_empty(&rdp->cblist),
+ "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
+ cpu, rcu_segcblist_n_cbs(&rdp->cblist),
+ rcu_segcblist_first_cb(&rdp->cblist));
}
/*
@@ -2852,14 +2764,17 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
- struct rcu_head *next, *list, **tail;
- long bl, count, count_lazy;
- int i;
+ struct rcu_head *rhp;
+ struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
+ long bl, count;
/* If no callbacks are ready, just return. */
- if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
- trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
- trace_rcu_batch_end(rsp->name, 0, !!READ_ONCE(rdp->nxtlist),
+ if (!rcu_segcblist_ready_cbs(&rdp->cblist)) {
+ trace_rcu_batch_start(rsp->name,
+ rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ rcu_segcblist_n_cbs(&rdp->cblist), 0);
+ trace_rcu_batch_end(rsp->name, 0,
+ !rcu_segcblist_empty(&rdp->cblist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
return;
@@ -2867,73 +2782,61 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
/*
* Extract the list of ready callbacks, disabling to prevent
- * races with call_rcu() from interrupt handlers.
+ * races with call_rcu() from interrupt handlers. Leave the
+ * callback counts, as rcu_barrier() needs to be conservative.
*/
local_irq_save(flags);
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
bl = rdp->blimit;
- trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl);
- list = rdp->nxtlist;
- rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
- *rdp->nxttail[RCU_DONE_TAIL] = NULL;
- tail = rdp->nxttail[RCU_DONE_TAIL];
- for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
- if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
- rdp->nxttail[i] = &rdp->nxtlist;
+ trace_rcu_batch_start(rsp->name, rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ rcu_segcblist_n_cbs(&rdp->cblist), bl);
+ rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
local_irq_restore(flags);
/* Invoke callbacks. */
- count = count_lazy = 0;
- while (list) {
- next = list->next;
- prefetch(next);
- debug_rcu_head_unqueue(list);
- if (__rcu_reclaim(rsp->name, list))
- count_lazy++;
- list = next;
- /* Stop only if limit reached and CPU has something to do. */
- if (++count >= bl &&
+ rhp = rcu_cblist_dequeue(&rcl);
+ for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+ debug_rcu_head_unqueue(rhp);
+ if (__rcu_reclaim(rsp->name, rhp))
+ rcu_cblist_dequeued_lazy(&rcl);
+ /*
+ * Stop only if limit reached and CPU has something to do.
+ * Note: The rcl structure counts down from zero.
+ */
+ if (-rcl.len >= bl &&
(need_resched() ||
(!is_idle_task(current) && !rcu_is_callbacks_kthread())))
break;
}
local_irq_save(flags);
- trace_rcu_batch_end(rsp->name, count, !!list, need_resched(),
- is_idle_task(current),
- rcu_is_callbacks_kthread());
-
- /* Update count, and requeue any remaining callbacks. */
- if (list != NULL) {
- *tail = rdp->nxtlist;
- rdp->nxtlist = list;
- for (i = 0; i < RCU_NEXT_SIZE; i++)
- if (&rdp->nxtlist == rdp->nxttail[i])
- rdp->nxttail[i] = tail;
- else
- break;
- }
+ count = -rcl.len;
+ trace_rcu_batch_end(rsp->name, count, !!rcl.head, need_resched(),
+ is_idle_task(current), rcu_is_callbacks_kthread());
+
+ /* Update counts and requeue any remaining callbacks. */
+ rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl);
smp_mb(); /* List handling before counting for rcu_barrier(). */
- rdp->qlen_lazy -= count_lazy;
- WRITE_ONCE(rdp->qlen, rdp->qlen - count);
rdp->n_cbs_invoked += count;
+ rcu_segcblist_insert_count(&rdp->cblist, &rcl);
/* Reinstate batch limit if we have worked down the excess. */
- if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
+ count = rcu_segcblist_n_cbs(&rdp->cblist);
+ if (rdp->blimit == LONG_MAX && count <= qlowmark)
rdp->blimit = blimit;
/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
- if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
+ if (count == 0 && rdp->qlen_last_fqs_check != 0) {
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
- } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
- rdp->qlen_last_fqs_check = rdp->qlen;
- WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0));
+ } else if (count < rdp->qlen_last_fqs_check - qhimark)
+ rdp->qlen_last_fqs_check = count;
+ WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) != (count == 0));
local_irq_restore(flags);
/* Re-invoke RCU core processing if there are callbacks remaining. */
- if (cpu_has_callbacks_ready_to_invoke(rdp))
+ if (rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_core();
}
@@ -3099,7 +3002,7 @@ __rcu_process_callbacks(struct rcu_state *rsp)
bool needwake;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
- WARN_ON_ONCE(rdp->beenonline == 0);
+ WARN_ON_ONCE(!rdp->beenonline);
/* Update RCU state based on any recent quiescent states. */
rcu_check_quiescent_state(rsp, rdp);
@@ -3117,7 +3020,7 @@ __rcu_process_callbacks(struct rcu_state *rsp)
}
/* If there are callbacks ready, invoke them. */
- if (cpu_has_callbacks_ready_to_invoke(rdp))
+ if (rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_callbacks(rsp, rdp);
/* Do any needed deferred wakeups of rcuo kthreads. */
@@ -3189,7 +3092,8 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
* invoking force_quiescent_state() if the newly enqueued callback
* is the only one waiting for a grace period to complete.
*/
- if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
+ if (unlikely(rcu_segcblist_n_cbs(&rdp->cblist) >
+ rdp->qlen_last_fqs_check + qhimark)) {
/* Are we ignoring a completed grace period? */
note_gp_changes(rsp, rdp);
@@ -3207,10 +3111,10 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
/* Give the grace period a kick. */
rdp->blimit = LONG_MAX;
if (rsp->n_force_qs == rdp->n_force_qs_snap &&
- *rdp->nxttail[RCU_DONE_TAIL] != head)
+ rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
force_quiescent_state(rsp);
rdp->n_force_qs_snap = rsp->n_force_qs;
- rdp->qlen_last_fqs_check = rdp->qlen;
+ rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
}
}
}
@@ -3250,7 +3154,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func,
rdp = this_cpu_ptr(rsp->rda);
/* Add the callback to our list. */
- if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL) || cpu != -1) {
+ if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist)) || cpu != -1) {
int offline;
if (cpu != -1)
@@ -3269,23 +3173,21 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func,
*/
BUG_ON(cpu != -1);
WARN_ON_ONCE(!rcu_is_watching());
- if (!likely(rdp->nxtlist))
- init_default_callback_list(rdp);
+ if (rcu_segcblist_empty(&rdp->cblist))
+ rcu_segcblist_init(&rdp->cblist);
}
- WRITE_ONCE(rdp->qlen, rdp->qlen + 1);
- if (lazy)
- rdp->qlen_lazy++;
- else
+ rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
+ if (!lazy)
rcu_idle_count_callbacks_posted();
- smp_mb(); /* Count before adding callback for rcu_barrier(). */
- *rdp->nxttail[RCU_NEXT_TAIL] = head;
- rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
if (__is_kfree_rcu_offset((unsigned long)func))
trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func,
- rdp->qlen_lazy, rdp->qlen);
+ rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ rcu_segcblist_n_cbs(&rdp->cblist));
else
- trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen);
+ trace_rcu_callback(rsp->name, head,
+ rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ rcu_segcblist_n_cbs(&rdp->cblist));
/* Go handle any RCU core processing required. */
__call_rcu_core(rsp, rdp, head, flags);
@@ -3531,41 +3433,6 @@ void cond_synchronize_sched(unsigned long oldstate)
}
EXPORT_SYMBOL_GPL(cond_synchronize_sched);
-/* Adjust sequence number for start of update-side operation. */
-static void rcu_seq_start(unsigned long *sp)
-{
- WRITE_ONCE(*sp, *sp + 1);
- smp_mb(); /* Ensure update-side operation after counter increment. */
- WARN_ON_ONCE(!(*sp & 0x1));
-}
-
-/* Adjust sequence number for end of update-side operation. */
-static void rcu_seq_end(unsigned long *sp)
-{
- smp_mb(); /* Ensure update-side operation before counter increment. */
- WRITE_ONCE(*sp, *sp + 1);
- WARN_ON_ONCE(*sp & 0x1);
-}
-
-/* Take a snapshot of the update side's sequence number. */
-static unsigned long rcu_seq_snap(unsigned long *sp)
-{
- unsigned long s;
-
- s = (READ_ONCE(*sp) + 3) & ~0x1;
- smp_mb(); /* Above access must not bleed into critical section. */
- return s;
-}
-
-/*
- * Given a snapshot from rcu_seq_snap(), determine whether or not a
- * full update-side operation has occurred.
- */
-static bool rcu_seq_done(unsigned long *sp, unsigned long s)
-{
- return ULONG_CMP_GE(READ_ONCE(*sp), s);
-}
-
/*
* Check to see if there is any immediate RCU-related work to be done
* by the current CPU, for the specified type of RCU, returning 1 if so.
@@ -3589,7 +3456,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
/* Is the RCU core waiting for a quiescent state from this CPU? */
if (rcu_scheduler_fully_active &&
rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
- rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
+ rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_dynticks.rcu_qs_ctr)) {
rdp->n_rp_core_needs_qs++;
} else if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm) {
rdp->n_rp_report_qs++;
@@ -3597,7 +3464,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
}
/* Does this CPU have callbacks ready to invoke? */
- if (cpu_has_callbacks_ready_to_invoke(rdp)) {
+ if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
rdp->n_rp_cb_ready++;
return 1;
}
@@ -3661,10 +3528,10 @@ static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
- if (!rdp->nxtlist)
+ if (rcu_segcblist_empty(&rdp->cblist))
continue;
hc = true;
- if (rdp->qlen != rdp->qlen_lazy || !all_lazy) {
+ if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist) || !all_lazy) {
al = false;
break;
}
@@ -3773,7 +3640,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
__call_rcu(&rdp->barrier_head,
rcu_barrier_callback, rsp, cpu, 0);
}
- } else if (READ_ONCE(rdp->qlen)) {
+ } else if (rcu_segcblist_n_cbs(&rdp->cblist)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu,
rsp->barrier_sequence);
smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
@@ -3882,8 +3749,9 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
- if (!rdp->nxtlist)
- init_callback_list(rdp); /* Re-enable callbacks on this CPU. */
+ if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */
+ !init_nocb_callback_list(rdp))
+ rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */
rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
rcu_sysidle_init_percpu_data(rdp->dynticks);
rcu_dynticks_eqs_online();
@@ -3902,12 +3770,16 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
rdp->completed = rnp->completed;
rdp->cpu_no_qs.b.norm = true;
- rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
+ rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
rdp->core_needs_qs = false;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
+/*
+ * Invoked early in the CPU-online process, when pretty much all
+ * services are available. The incoming CPU is not present.
+ */
int rcutree_prepare_cpu(unsigned int cpu)
{
struct rcu_state *rsp;
@@ -3921,6 +3793,9 @@ int rcutree_prepare_cpu(unsigned int cpu)
return 0;
}
+/*
+ * Update RCU priority boot kthread affinity for CPU-hotplug changes.
+ */
static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
{
struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
@@ -3928,20 +3803,34 @@ static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
rcu_boost_kthread_setaffinity(rdp->mynode, outgoing);
}
+/*
+ * Near the end of the CPU-online process. Pretty much all services
+ * enabled, and the CPU is now very much alive.
+ */
int rcutree_online_cpu(unsigned int cpu)
{
sync_sched_exp_online_cleanup(cpu);
rcutree_affinity_setting(cpu, -1);
+ if (IS_ENABLED(CONFIG_TREE_SRCU))
+ srcu_online_cpu(cpu);
return 0;
}
+/*
+ * Near the beginning of the process. The CPU is still very much alive
+ * with pretty much all services enabled.
+ */
int rcutree_offline_cpu(unsigned int cpu)
{
rcutree_affinity_setting(cpu, cpu);
+ if (IS_ENABLED(CONFIG_TREE_SRCU))
+ srcu_offline_cpu(cpu);
return 0;
}
-
+/*
+ * Near the end of the offline process. We do only tracing here.
+ */
int rcutree_dying_cpu(unsigned int cpu)
{
struct rcu_state *rsp;
@@ -3951,6 +3840,9 @@ int rcutree_dying_cpu(unsigned int cpu)
return 0;
}
+/*
+ * The outgoing CPU is gone and we are running elsewhere.
+ */
int rcutree_dead_cpu(unsigned int cpu)
{
struct rcu_state *rsp;
@@ -3968,6 +3860,10 @@ int rcutree_dead_cpu(unsigned int cpu)
* incoming CPUs are not allowed to use RCU read-side critical sections
* until this function is called. Failing to observe this restriction
* will result in lockdep splats.
+ *
+ * Note that this function is special in that it is invoked directly
+ * from the incoming CPU rather than from the cpuhp_step mechanism.
+ * This is because this function must be invoked at a precise location.
*/
void rcu_cpu_starting(unsigned int cpu)
{
@@ -3993,9 +3889,6 @@ void rcu_cpu_starting(unsigned int cpu)
* The CPU is exiting the idle loop into the arch_cpu_idle_dead()
* function. We now remove it from the rcu_node tree's ->qsmaskinit
* bit masks.
- * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function. We now remove it from the rcu_node tree's ->qsmaskinit
- * bit masks.
*/
static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
{
@@ -4011,6 +3904,14 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
+/*
+ * The outgoing function has no further need of RCU, so remove it from
+ * the list of CPUs that RCU must track.
+ *
+ * Note that this function is special in that it is invoked directly
+ * from the outgoing CPU rather than from the cpuhp_step mechanism.
+ * This is because this function must be invoked at a precise location.
+ */
void rcu_report_dead(unsigned int cpu)
{
struct rcu_state *rsp;
@@ -4025,6 +3926,10 @@ void rcu_report_dead(unsigned int cpu)
}
#endif
+/*
+ * On non-huge systems, use expedited RCU grace periods to make suspend
+ * and hibernation run faster.
+ */
static int rcu_pm_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
@@ -4095,7 +4000,7 @@ early_initcall(rcu_spawn_gp_kthread);
* task is booting the system, and such primitives are no-ops). After this
* function is called, any synchronous grace-period primitives are run as
* expedited, with the requesting task driving the grace period forward.
- * A later core_initcall() rcu_exp_runtime_mode() will switch to full
+ * A later core_initcall() rcu_set_runtime_mode() will switch to full
* runtime RCU functionality.
*/
void rcu_scheduler_starting(void)
@@ -4108,31 +4013,6 @@ void rcu_scheduler_starting(void)
}
/*
- * Compute the per-level fanout, either using the exact fanout specified
- * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
- */
-static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt)
-{
- int i;
-
- if (rcu_fanout_exact) {
- levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
- for (i = rcu_num_lvls - 2; i >= 0; i--)
- levelspread[i] = RCU_FANOUT;
- } else {
- int ccur;
- int cprv;
-
- cprv = nr_cpu_ids;
- for (i = rcu_num_lvls - 1; i >= 0; i--) {
- ccur = levelcnt[i];
- levelspread[i] = (cprv + ccur - 1) / ccur;
- cprv = ccur;
- }
- }
-}
-
-/*
* Helper function for rcu_init() that initializes one rcu_state structure.
*/
static void __init rcu_init_one(struct rcu_state *rsp)
@@ -4141,9 +4021,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
static const char * const fqs[] = RCU_FQS_NAME_INIT;
static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
- static u8 fl_mask = 0x1;
- int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */
int levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */
int cpustride = 1;
int i;
@@ -4158,20 +4036,16 @@ static void __init rcu_init_one(struct rcu_state *rsp)
/* Initialize the level-tracking arrays. */
- for (i = 0; i < rcu_num_lvls; i++)
- levelcnt[i] = num_rcu_lvl[i];
for (i = 1; i < rcu_num_lvls; i++)
- rsp->level[i] = rsp->level[i - 1] + levelcnt[i - 1];
- rcu_init_levelspread(levelspread, levelcnt);
- rsp->flavor_mask = fl_mask;
- fl_mask <<= 1;
+ rsp->level[i] = rsp->level[i - 1] + num_rcu_lvl[i - 1];
+ rcu_init_levelspread(levelspread, num_rcu_lvl);
/* Initialize the elements themselves, starting from the leaves. */
for (i = rcu_num_lvls - 1; i >= 0; i--) {
cpustride *= levelspread[i];
rnp = rsp->level[i];
- for (j = 0; j < levelcnt[i]; j++, rnp++) {
+ for (j = 0; j < num_rcu_lvl[i]; j++, rnp++) {
raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock));
lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock),
&rcu_node_class[i], buf[i]);
@@ -4344,6 +4218,8 @@ void __init rcu_init(void)
for_each_online_cpu(cpu) {
rcutree_prepare_cpu(cpu);
rcu_cpu_starting(cpu);
+ if (IS_ENABLED(CONFIG_TREE_SRCU))
+ srcu_online_cpu(cpu);
}
}
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index ec62a05bfdb3..ba38262c3554 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -30,80 +30,9 @@
#include <linux/seqlock.h>
#include <linux/swait.h>
#include <linux/stop_machine.h>
+#include <linux/rcu_node_tree.h>
-/*
- * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
- * CONFIG_RCU_FANOUT_LEAF.
- * In theory, it should be possible to add more levels straightforwardly.
- * In practice, this did work well going from three levels to four.
- * Of course, your mileage may vary.
- */
-
-#ifdef CONFIG_RCU_FANOUT
-#define RCU_FANOUT CONFIG_RCU_FANOUT
-#else /* #ifdef CONFIG_RCU_FANOUT */
-# ifdef CONFIG_64BIT
-# define RCU_FANOUT 64
-# else
-# define RCU_FANOUT 32
-# endif
-#endif /* #else #ifdef CONFIG_RCU_FANOUT */
-
-#ifdef CONFIG_RCU_FANOUT_LEAF
-#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
-#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
-# ifdef CONFIG_64BIT
-# define RCU_FANOUT_LEAF 64
-# else
-# define RCU_FANOUT_LEAF 32
-# endif
-#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
-
-#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
-#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
-#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
-#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
-
-#if NR_CPUS <= RCU_FANOUT_1
-# define RCU_NUM_LVLS 1
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_NODES NUM_RCU_LVL_0
-# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 }
-# define RCU_NODE_NAME_INIT { "rcu_node_0" }
-# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" }
-#elif NR_CPUS <= RCU_FANOUT_2
-# define RCU_NUM_LVLS 2
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
-# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
-# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" }
-# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" }
-#elif NR_CPUS <= RCU_FANOUT_3
-# define RCU_NUM_LVLS 3
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
-# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
-# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
-# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
-#elif NR_CPUS <= RCU_FANOUT_4
-# define RCU_NUM_LVLS 4
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
-# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
-# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
-# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
-# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
-#else
-# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
-
-extern int rcu_num_lvls;
-extern int rcu_num_nodes;
+#include "rcu_segcblist.h"
/*
* Dynticks per-CPU state.
@@ -113,6 +42,9 @@ struct rcu_dynticks {
/* Process level is worth LLONG_MAX/2. */
int dynticks_nmi_nesting; /* Track NMI nesting level. */
atomic_t dynticks; /* Even value for idle, else odd. */
+ bool rcu_need_heavy_qs; /* GP old, need heavy quiescent state. */
+ unsigned long rcu_qs_ctr; /* Light universal quiescent state ctr. */
+ bool rcu_urgent_qs; /* GP old need light quiescent state. */
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
long long dynticks_idle_nesting;
/* irq/process nesting level from idle. */
@@ -262,41 +194,6 @@ struct rcu_node {
#define leaf_node_cpu_bit(rnp, cpu) (1UL << ((cpu) - (rnp)->grplo))
/*
- * Do a full breadth-first scan of the rcu_node structures for the
- * specified rcu_state structure.
- */
-#define rcu_for_each_node_breadth_first(rsp, rnp) \
- for ((rnp) = &(rsp)->node[0]; \
- (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
-
-/*
- * Do a breadth-first scan of the non-leaf rcu_node structures for the
- * specified rcu_state structure. Note that if there is a singleton
- * rcu_node tree with but one rcu_node structure, this loop is a no-op.
- */
-#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
- for ((rnp) = &(rsp)->node[0]; \
- (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
-
-/*
- * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
- * structure. Note that if there is a singleton rcu_node tree with but
- * one rcu_node structure, this loop -will- visit the rcu_node structure.
- * It is still a leaf node, even if it is also the root node.
- */
-#define rcu_for_each_leaf_node(rsp, rnp) \
- for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
- (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
-
-/*
- * Iterate over all possible CPUs in a leaf RCU node.
- */
-#define for_each_leaf_node_possible_cpu(rnp, cpu) \
- for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
- cpu <= rnp->grphi; \
- cpu = cpumask_next((cpu), cpu_possible_mask))
-
-/*
* Union to allow "aggregate OR" operation on the need for a quiescent
* state by the normal and expedited grace periods.
*/
@@ -336,34 +233,9 @@ struct rcu_data {
/* period it is aware of. */
/* 2) batch handling */
- /*
- * If nxtlist is not NULL, it is partitioned as follows.
- * Any of the partitions might be empty, in which case the
- * pointer to that partition will be equal to the pointer for
- * the following partition. When the list is empty, all of
- * the nxttail elements point to the ->nxtlist pointer itself,
- * which in that case is NULL.
- *
- * [nxtlist, *nxttail[RCU_DONE_TAIL]):
- * Entries that batch # <= ->completed
- * The grace period for these entries has completed, and
- * the other grace-period-completed entries may be moved
- * here temporarily in rcu_process_callbacks().
- * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
- * Entries that batch # <= ->completed - 1: waiting for current GP
- * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
- * Entries known to have arrived before current GP ended
- * [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]):
- * Entries that might have arrived after current GP ended
- * Note that the value of *nxttail[RCU_NEXT_TAIL] will
- * always be NULL, as this is the end of the list.
- */
- struct rcu_head *nxtlist;
- struct rcu_head **nxttail[RCU_NEXT_SIZE];
- unsigned long nxtcompleted[RCU_NEXT_SIZE];
- /* grace periods for sublists. */
- long qlen_lazy; /* # of lazy queued callbacks */
- long qlen; /* # of queued callbacks, incl lazy */
+ struct rcu_segcblist cblist; /* Segmented callback list, with */
+ /* different callbacks waiting for */
+ /* different grace periods. */
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */
@@ -482,7 +354,6 @@ struct rcu_state {
struct rcu_node *level[RCU_NUM_LVLS + 1];
/* Hierarchy levels (+1 to */
/* shut bogus gcc warning) */
- u8 flavor_mask; /* bit in flavor mask. */
struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */
call_rcu_func_t call; /* call_rcu() flavor. */
int ncpus; /* # CPUs seen so far. */
@@ -502,14 +373,11 @@ struct rcu_state {
raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp;
/* Protect following fields. */
- struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */
+ struct rcu_cblist orphan_pend; /* Orphaned callbacks that */
/* need a grace period. */
- struct rcu_head **orphan_nxttail; /* Tail of above. */
- struct rcu_head *orphan_donelist; /* Orphaned callbacks that */
+ struct rcu_cblist orphan_done; /* Orphaned callbacks that */
/* are ready to invoke. */
- struct rcu_head **orphan_donetail; /* Tail of above. */
- long qlen_lazy; /* Number of lazy callbacks. */
- long qlen; /* Total number of callbacks. */
+ /* (Contains counts.) */
/* End of fields guarded by orphan_lock. */
struct mutex barrier_mutex; /* Guards barrier fields. */
@@ -596,6 +464,7 @@ extern struct rcu_state rcu_preempt_state;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
+bool rcu_eqs_special_set(int cpu);
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@@ -673,6 +542,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
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 */
+
#endif /* #ifndef RCU_TREE_NONCORE */
#ifdef CONFIG_RCU_TRACE
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index a7b639ccd46e..e513b4ab1197 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -292,7 +292,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
trace_rcu_exp_funnel_lock(rsp->name, rnp->level,
rnp->grplo, rnp->grphi,
TPS("wait"));
- wait_event(rnp->exp_wq[(s >> 1) & 0x3],
+ wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(rsp,
&rdp->exp_workdone2, s));
return true;
@@ -331,6 +331,8 @@ static void sync_sched_exp_handler(void *data)
return;
}
__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
+ /* Store .exp before .rcu_urgent_qs. */
+ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
resched_cpu(smp_processor_id());
}
@@ -531,7 +533,8 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
rnp->exp_seq_rq = s;
spin_unlock(&rnp->exp_lock);
}
- wake_up_all(&rnp->exp_wq[(rsp->expedited_sequence >> 1) & 0x3]);
+ smp_mb(); /* All above changes before wakeup. */
+ wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rsp->expedited_sequence) & 0x3]);
}
trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake"));
mutex_unlock(&rsp->exp_wake_mutex);
@@ -609,9 +612,9 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
/* Wait for expedited grace period to complete. */
rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
rnp = rcu_get_root(rsp);
- wait_event(rnp->exp_wq[(s >> 1) & 0x3],
- sync_exp_work_done(rsp,
- &rdp->exp_workdone0, s));
+ wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
+ sync_exp_work_done(rsp, &rdp->exp_workdone0, s));
+ smp_mb(); /* Workqueue actions happen before return. */
/* Let the next expedited grace period start. */
mutex_unlock(&rsp->exp_mutex);
@@ -735,15 +738,3 @@ void synchronize_rcu_expedited(void)
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
-/*
- * Switch to run-time mode once Tree RCU has fully initialized.
- */
-static int __init rcu_exp_runtime_mode(void)
-{
- rcu_test_sync_prims();
- rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
- rcu_test_sync_prims();
- return 0;
-}
-core_initcall(rcu_exp_runtime_mode);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0a62a8f1caac..c9a48657512a 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1350,10 +1350,10 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
*/
if ((rdp->completed != rnp->completed ||
unlikely(READ_ONCE(rdp->gpwrap))) &&
- rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
+ rcu_segcblist_pend_cbs(&rdp->cblist))
note_gp_changes(rsp, rdp);
- if (cpu_has_callbacks_ready_to_invoke(rdp))
+ if (rcu_segcblist_ready_cbs(&rdp->cblist))
cbs_ready = true;
}
return cbs_ready;
@@ -1461,7 +1461,7 @@ static void rcu_prepare_for_idle(void)
rdtp->last_accelerate = jiffies;
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
- if (!*rdp->nxttail[RCU_DONE_TAIL])
+ if (rcu_segcblist_pend_cbs(&rdp->cblist))
continue;
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
@@ -1529,7 +1529,7 @@ static void rcu_oom_notify_cpu(void *unused)
for_each_rcu_flavor(rsp) {
rdp = raw_cpu_ptr(rsp->rda);
- if (rdp->qlen_lazy != 0) {
+ if (rcu_segcblist_n_lazy_cbs(&rdp->cblist)) {
atomic_inc(&oom_callback_count);
rsp->call(&rdp->oom_head, rcu_oom_callback);
}
@@ -1709,7 +1709,7 @@ __setup("rcu_nocbs=", rcu_nocb_setup);
static int __init parse_rcu_nocb_poll(char *arg)
{
- rcu_nocb_poll = 1;
+ rcu_nocb_poll = true;
return 0;
}
early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
@@ -1860,7 +1860,9 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeEmpty"));
} else {
- rdp->nocb_defer_wakeup = RCU_NOGP_WAKE;
+ WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE);
+ /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */
+ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeEmptyIsDeferred"));
}
@@ -1872,7 +1874,9 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvf"));
} else {
- rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE;
+ WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_FORCE);
+ /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */
+ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvfIsDeferred"));
}
@@ -1930,30 +1934,26 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
struct rcu_data *rdp,
unsigned long flags)
{
- long ql = rsp->qlen;
- long qll = rsp->qlen_lazy;
+ long ql = rsp->orphan_done.len;
+ long qll = rsp->orphan_done.len_lazy;
/* If this is not a no-CBs CPU, tell the caller to do it the old way. */
if (!rcu_is_nocb_cpu(smp_processor_id()))
return false;
- rsp->qlen = 0;
- rsp->qlen_lazy = 0;
/* First, enqueue the donelist, if any. This preserves CB ordering. */
- if (rsp->orphan_donelist != NULL) {
- __call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
- rsp->orphan_donetail, ql, qll, flags);
- ql = qll = 0;
- rsp->orphan_donelist = NULL;
- rsp->orphan_donetail = &rsp->orphan_donelist;
+ if (rsp->orphan_done.head) {
+ __call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_done),
+ rcu_cblist_tail(&rsp->orphan_done),
+ ql, qll, flags);
}
- if (rsp->orphan_nxtlist != NULL) {
- __call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
- rsp->orphan_nxttail, ql, qll, flags);
- ql = qll = 0;
- rsp->orphan_nxtlist = NULL;
- rsp->orphan_nxttail = &rsp->orphan_nxtlist;
+ if (rsp->orphan_pend.head) {
+ __call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_pend),
+ rcu_cblist_tail(&rsp->orphan_pend),
+ ql, qll, flags);
}
+ rcu_cblist_init(&rsp->orphan_done);
+ rcu_cblist_init(&rsp->orphan_pend);
return true;
}
@@ -2395,16 +2395,16 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
return false;
/* If there are early-boot callbacks, move them to nocb lists. */
- if (rdp->nxtlist) {
- rdp->nocb_head = rdp->nxtlist;
- rdp->nocb_tail = rdp->nxttail[RCU_NEXT_TAIL];
- atomic_long_set(&rdp->nocb_q_count, rdp->qlen);
- atomic_long_set(&rdp->nocb_q_count_lazy, rdp->qlen_lazy);
- rdp->nxtlist = NULL;
- rdp->qlen = 0;
- rdp->qlen_lazy = 0;
+ if (!rcu_segcblist_empty(&rdp->cblist)) {
+ rdp->nocb_head = rcu_segcblist_head(&rdp->cblist);
+ rdp->nocb_tail = rcu_segcblist_tail(&rdp->cblist);
+ atomic_long_set(&rdp->nocb_q_count,
+ rcu_segcblist_n_cbs(&rdp->cblist));
+ atomic_long_set(&rdp->nocb_q_count_lazy,
+ rcu_segcblist_n_lazy_cbs(&rdp->cblist));
+ rcu_segcblist_init(&rdp->cblist);
}
- rdp->nxttail[RCU_NEXT_TAIL] = NULL;
+ rcu_segcblist_disable(&rdp->cblist);
return true;
}
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 8751a748499a..6cea17a1ea30 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -41,11 +41,11 @@
#include <linux/mutex.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/prefetch.h>
#define RCU_TREE_NONCORE
#include "tree.h"
-
-DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+#include "rcu.h"
static int r_open(struct inode *inode, struct file *file,
const struct seq_operations *op)
@@ -121,7 +121,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
cpu_is_offline(rdp->cpu) ? '!' : ' ',
ulong2long(rdp->completed), ulong2long(rdp->gpnum),
rdp->cpu_no_qs.b.norm,
- rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
+ rdp->rcu_qs_ctr_snap == per_cpu(rdp->dynticks->rcu_qs_ctr, rdp->cpu),
rdp->core_needs_qs);
seq_printf(m, " dt=%d/%llx/%d df=%lu",
rcu_dynticks_snap(rdp->dynticks),
@@ -130,17 +130,15 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
rdp->dynticks_fqs);
seq_printf(m, " of=%lu", rdp->offline_fqs);
rcu_nocb_q_lengths(rdp, &ql, &qll);
- qll += rdp->qlen_lazy;
- ql += rdp->qlen;
+ qll += rcu_segcblist_n_lazy_cbs(&rdp->cblist);
+ ql += rcu_segcblist_n_cbs(&rdp->cblist);
seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c",
qll, ql,
- ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
- rdp->nxttail[RCU_NEXT_TAIL]],
- ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
- rdp->nxttail[RCU_NEXT_READY_TAIL]],
- ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
- rdp->nxttail[RCU_WAIT_TAIL]],
- ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
+ ".N"[!rcu_segcblist_segempty(&rdp->cblist, RCU_NEXT_TAIL)],
+ ".R"[!rcu_segcblist_segempty(&rdp->cblist,
+ RCU_NEXT_READY_TAIL)],
+ ".W"[!rcu_segcblist_segempty(&rdp->cblist, RCU_WAIT_TAIL)],
+ ".D"[!rcu_segcblist_segempty(&rdp->cblist, RCU_DONE_TAIL)]);
#ifdef CONFIG_RCU_BOOST
seq_printf(m, " kt=%d/%c ktl=%x",
per_cpu(rcu_cpu_has_work, rdp->cpu),
@@ -278,7 +276,9 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
- READ_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
+ READ_ONCE(rsp->n_force_qs_lh),
+ rsp->orphan_done.len_lazy,
+ rsp->orphan_done.len);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 55c8530316c7..273e869ca21d 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -124,7 +124,7 @@ EXPORT_SYMBOL(rcu_read_lock_sched_held);
* non-expedited counterparts? Intended for use within RCU. Note
* that if the user specifies both rcu_expedited and rcu_normal, then
* rcu_normal wins. (Except during the time period during boot from
- * when the first task is spawned until the rcu_exp_runtime_mode()
+ * when the first task is spawned until the rcu_set_runtime_mode()
* core_initcall() is invoked, at which point everything is expedited.)
*/
bool rcu_gp_is_normal(void)
@@ -190,6 +190,39 @@ void rcu_end_inkernel_boot(void)
#endif /* #ifndef CONFIG_TINY_RCU */
+/*
+ * Test each non-SRCU synchronous grace-period wait API. This is
+ * useful just after a change in mode for these primitives, and
+ * during early boot.
+ */
+void rcu_test_sync_prims(void)
+{
+ if (!IS_ENABLED(CONFIG_PROVE_RCU))
+ return;
+ synchronize_rcu();
+ synchronize_rcu_bh();
+ synchronize_sched();
+ synchronize_rcu_expedited();
+ synchronize_rcu_bh_expedited();
+ synchronize_sched_expedited();
+}
+
+#if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU)
+
+/*
+ * Switch to run-time mode once RCU has fully initialized.
+ */
+static int __init rcu_set_runtime_mode(void)
+{
+ rcu_test_sync_prims();
+ rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+ rcu_test_sync_prims();
+ return 0;
+}
+core_initcall(rcu_set_runtime_mode);
+
+#endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */
+
#ifdef CONFIG_PREEMPT_RCU
/*
@@ -632,6 +665,7 @@ static void check_holdout_task(struct task_struct *t,
put_task_struct(t);
return;
}
+ rcu_request_urgent_qs_task(t);
if (!needreport)
return;
if (*firstreport) {
@@ -817,23 +851,6 @@ static void rcu_spawn_tasks_kthread(void)
#endif /* #ifdef CONFIG_TASKS_RCU */
-/*
- * Test each non-SRCU synchronous grace-period wait API. This is
- * useful just after a change in mode for these primitives, and
- * during early boot.
- */
-void rcu_test_sync_prims(void)
-{
- if (!IS_ENABLED(CONFIG_PROVE_RCU))
- return;
- synchronize_rcu();
- synchronize_rcu_bh();
- synchronize_sched();
- synchronize_rcu_expedited();
- synchronize_rcu_bh_expedited();
- synchronize_sched_expedited();
-}
-
#ifdef CONFIG_PROVE_RCU
/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c51147a1204c..759f4bd52cd6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3382,7 +3382,7 @@ static void __sched notrace __schedule(bool preempt)
hrtick_clear(rq);
local_irq_disable();
- rcu_note_context_switch();
+ rcu_note_context_switch(preempt);
/*
* Make sure that signal_pending_state()->signal_pending() below
diff --git a/kernel/signal.c b/kernel/signal.c
index a8c54f384553..ca92bcfeb322 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1237,7 +1237,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
}
/*
* This sighand can be already freed and even reused, but
- * we rely on SLAB_DESTROY_BY_RCU and sighand_ctor() which
+ * we rely on SLAB_TYPESAFE_BY_RCU and sighand_ctor() which
* initializes ->siglock: this slab can't go away, it has
* the same object type, ->siglock can't be reinitialized.
*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 21343d110296..4dfba1a76cc3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2576,7 +2576,7 @@ static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
int write, void *data)
{
if (write) {
- if (*lvalp > LONG_MAX / HZ)
+ if (*lvalp > INT_MAX / HZ)
return 1;
*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
} else {
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 8a5e44236f78..4559e914452b 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -30,6 +30,7 @@
#include <linux/pid_namespace.h>
#include <net/genetlink.h>
#include <linux/atomic.h>
+#include <linux/sched/cputime.h>
/*
* Maximum length of a cpumask that can be specified in
@@ -210,6 +211,8 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
struct task_struct *tsk, *first;
unsigned long flags;
int rc = -ESRCH;
+ u64 delta, utime, stime;
+ u64 start_time;
/*
* Add additional stats from live tasks except zombie thread group
@@ -227,6 +230,7 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
memset(stats, 0, sizeof(*stats));
tsk = first;
+ start_time = ktime_get_ns();
do {
if (tsk->exit_state)
continue;
@@ -238,6 +242,16 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
*/
delayacct_add_tsk(stats, tsk);
+ /* calculate task elapsed time in nsec */
+ delta = start_time - tsk->start_time;
+ /* Convert to micro seconds */
+ do_div(delta, NSEC_PER_USEC);
+ stats->ac_etime += delta;
+
+ task_cputime(tsk, &utime, &stime);
+ stats->ac_utime += div_u64(utime, NSEC_PER_USEC);
+ stats->ac_stime += div_u64(stime, NSEC_PER_USEC);
+
stats->nvcsw += tsk->nvcsw;
stats->nivcsw += tsk->nivcsw;
} while_each_thread(first, tsk);
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 6574bba44b55..49c73c6ed648 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -230,20 +230,6 @@ SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret;
}
-/**
- * current_fs_time - Return FS time
- * @sb: Superblock.
- *
- * Return the current time truncated to the time granularity supported by
- * the fs.
- */
-struct timespec current_fs_time(struct super_block *sb)
-{
- struct timespec now = current_kernel_time();
- return timespec_trunc(now, sb->s_time_gran);
-}
-EXPORT_SYMBOL(current_fs_time);
-
/*
* Convert jiffies to milliseconds and back.
*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 00077a57b746..39dca4e86a94 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3631,22 +3631,20 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
/* blank module name to match all modules */
if (!mod_g->len) {
/* blank module globbing: modname xor exclude_mod */
- if ((!exclude_mod) != (!modname))
+ if (!exclude_mod != !modname)
goto func_match;
return 0;
}
- /* not matching the module */
- if (!modname || !mod_matches) {
- if (exclude_mod)
- goto func_match;
- else
- return 0;
- }
-
- if (mod_matches && exclude_mod)
+ /*
+ * exclude_mod is set to trace everything but the given
+ * module. If it is set and the module matches, then
+ * return 0. If it is not set, and the module doesn't match
+ * also return 0. Otherwise, check the function to see if
+ * that matches.
+ */
+ if (!mod_matches == !exclude_mod)
return 0;
-
func_match:
/* blank search means to match all funcs in the mod */
if (!func_g->len)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 80eda7d254ed..c4536c449021 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1976,7 +1976,7 @@ static void __trace_find_cmdline(int pid, char comm[])
map = savedcmd->map_pid_to_cmdline[pid];
if (map != NO_CMDLINE_MAP)
- strcpy(comm, get_saved_cmdlines(map));
+ strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
else
strcpy(comm, "<...>");
}
@@ -3311,13 +3311,14 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
return;
- if (iter->started && cpumask_test_cpu(iter->cpu, iter->started))
+ if (cpumask_available(iter->started) &&
+ cpumask_test_cpu(iter->cpu, iter->started))
return;
if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries)
return;
- if (iter->started)
+ if (cpumask_available(iter->started))
cpumask_set_cpu(iter->cpu, iter->started);
/* Don't print started cpu buffer for the first entry of the trace */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index c203ac4df791..adcdbbeae010 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -348,14 +348,14 @@ FTRACE_ENTRY(hwlat, hwlat_entry,
__field( u64, duration )
__field( u64, outer_duration )
__field( u64, nmi_total_ts )
- __field_struct( struct timespec, timestamp )
- __field_desc( long, timestamp, tv_sec )
+ __field_struct( struct timespec64, timestamp )
+ __field_desc( s64, timestamp, tv_sec )
__field_desc( long, timestamp, tv_nsec )
__field( unsigned int, nmi_count )
__field( unsigned int, seqnum )
),
- F_printk("cnt:%u\tts:%010lu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
+ F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
__entry->seqnum,
__entry->tv_sec,
__entry->tv_nsec,
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 21ea6ae77d93..d7c8e4ec3d9d 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -79,12 +79,12 @@ static u64 last_tracing_thresh = DEFAULT_LAT_THRESHOLD * NSEC_PER_USEC;
/* Individual latency samples are stored here when detected. */
struct hwlat_sample {
- u64 seqnum; /* unique sequence */
- u64 duration; /* delta */
- u64 outer_duration; /* delta (outer loop) */
- u64 nmi_total_ts; /* Total time spent in NMIs */
- struct timespec timestamp; /* wall time */
- int nmi_count; /* # NMIs during this sample */
+ u64 seqnum; /* unique sequence */
+ u64 duration; /* delta */
+ u64 outer_duration; /* delta (outer loop) */
+ u64 nmi_total_ts; /* Total time spent in NMIs */
+ struct timespec64 timestamp; /* wall time */
+ int nmi_count; /* # NMIs during this sample */
};
/* keep the global state somewhere. */
@@ -250,7 +250,7 @@ static int get_sample(void)
s.seqnum = hwlat_data.count;
s.duration = sample;
s.outer_duration = outer_sample;
- s.timestamp = CURRENT_TIME;
+ ktime_get_real_ts64(&s.timestamp);
s.nmi_total_ts = nmi_total_ts;
s.nmi_count = nmi_count;
trace_hwlat_sample(&s);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 02a4aeb22c47..08f9bab8089e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -4,7 +4,6 @@
* Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
*/
-
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/ftrace.h>
@@ -1161,11 +1160,11 @@ trace_hwlat_print(struct trace_iterator *iter, int flags,
trace_assign_type(field, entry);
- trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%ld.%09ld",
+ trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld",
field->seqnum,
field->duration,
field->outer_duration,
- field->timestamp.tv_sec,
+ (long long)field->timestamp.tv_sec,
field->timestamp.tv_nsec);
if (field->nmi_count) {
@@ -1195,10 +1194,10 @@ trace_hwlat_raw(struct trace_iterator *iter, int flags,
trace_assign_type(field, iter->ent);
- trace_seq_printf(s, "%llu %lld %ld %09ld %u\n",
+ trace_seq_printf(s, "%llu %lld %lld %09ld %u\n",
field->duration,
field->outer_duration,
- field->timestamp.tv_sec,
+ (long long)field->timestamp.tv_sec,
field->timestamp.tv_nsec,
field->seqnum);