summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile4
-rw-r--r--kernel/bounds.c4
-rw-r--r--kernel/bpf/btf.c140
-rw-r--r--kernel/bpf/core.c96
-rw-r--r--kernel/bpf/devmap.c3
-rw-r--r--kernel/bpf/helpers.c2
-rw-r--r--kernel/bpf/local_storage.c3
-rw-r--r--kernel/bpf/queue_stack_maps.c18
-rw-r--r--kernel/bpf/syscall.c35
-rw-r--r--kernel/bpf/verifier.c152
-rw-r--r--kernel/cgroup/cgroup.c95
-rw-r--r--kernel/configs/kvm_guest.config1
-rw-r--r--kernel/cpu.c15
-rw-r--r--kernel/debug/kdb/kdb_bt.c4
-rw-r--r--kernel/debug/kdb/kdb_io.c15
-rw-r--r--kernel/debug/kdb/kdb_keyboard.c4
-rw-r--r--kernel/debug/kdb/kdb_main.c42
-rw-r--r--kernel/debug/kdb/kdb_private.h2
-rw-r--r--kernel/debug/kdb/kdb_support.c28
-rw-r--r--kernel/delayacct.c15
-rw-r--r--kernel/dma/direct.c11
-rw-r--r--kernel/dma/swiotlb.c335
-rw-r--r--kernel/events/core.c55
-rw-r--r--kernel/events/hw_breakpoint.c2
-rw-r--r--kernel/events/uprobes.c292
-rw-r--r--kernel/fail_function.c3
-rw-r--r--kernel/fork.c71
-rw-r--r--kernel/futex.c71
-rw-r--r--kernel/hung_task.c30
-rw-r--r--kernel/irq/affinity.c176
-rw-r--r--kernel/irq/chip.c2
-rw-r--r--kernel/irq/devres.c4
-rw-r--r--kernel/irq/ipi.c4
-rw-r--r--kernel/irq/irq_sim.c23
-rw-r--r--kernel/irq/irqdesc.c28
-rw-r--r--kernel/irq/irqdomain.c4
-rw-r--r--kernel/irq/manage.c2
-rw-r--r--kernel/irq/matrix.c36
-rw-r--r--kernel/irq/msi.c8
-rw-r--r--kernel/irq/spurious.c6
-rw-r--r--kernel/kallsyms.c4
-rw-r--r--kernel/kcov.c4
-rw-r--r--kernel/kexec_file.c72
-rw-r--r--kernel/kprobes.c77
-rw-r--r--kernel/livepatch/patch.c4
-rw-r--r--kernel/livepatch/transition.c4
-rw-r--r--kernel/locking/lockdep.c78
-rw-r--r--kernel/locking/mutex-debug.c4
-rw-r--r--kernel/locking/qspinlock_paravirt.h2
-rw-r--r--kernel/memremap.c98
-rw-r--r--kernel/module.c14
-rw-r--r--kernel/panic.c10
-rw-r--r--kernel/pid.c2
-rw-r--r--kernel/power/Kconfig15
-rw-r--r--kernel/power/Makefile2
-rw-r--r--kernel/power/energy_model.c201
-rw-r--r--kernel/power/main.c15
-rw-r--r--kernel/power/qos.c15
-rw-r--r--kernel/power/snapshot.c5
-rw-r--r--kernel/printk/printk.c5
-rw-r--r--kernel/profile.c2
-rw-r--r--kernel/ptrace.c10
-rw-r--r--kernel/rcu/rcu.h4
-rw-r--r--kernel/rcu/rcutorture.c389
-rw-r--r--kernel/rcu/srcutiny.c120
-rw-r--r--kernel/rcu/srcutree.c489
-rw-r--r--kernel/rcu/sync.c25
-rw-r--r--kernel/rcu/tree.c114
-rw-r--r--kernel/rcu/tree.h18
-rw-r--r--kernel/rcu/tree_exp.h10
-rw-r--r--kernel/rcu/tree_plugin.h81
-rw-r--r--kernel/rcu/update.c9
-rw-r--r--kernel/resource.c19
-rw-r--r--kernel/sched/Makefile1
-rw-r--r--kernel/sched/core.c82
-rw-r--r--kernel/sched/cpufreq.c5
-rw-r--r--kernel/sched/cpufreq_schedutil.c95
-rw-r--r--kernel/sched/cputime.c2
-rw-r--r--kernel/sched/deadline.c25
-rw-r--r--kernel/sched/debug.c2
-rw-r--r--kernel/sched/fair.c461
-rw-r--r--kernel/sched/isolation.c14
-rw-r--r--kernel/sched/loadavg.c139
-rw-r--r--kernel/sched/membarrier.c6
-rw-r--r--kernel/sched/psi.c772
-rw-r--r--kernel/sched/rt.c30
-rw-r--r--kernel/sched/sched.h279
-rw-r--r--kernel/sched/stats.h86
-rw-r--r--kernel/sched/topology.c233
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/stackleak.c134
-rw-r--r--kernel/sys.c8
-rw-r--r--kernel/sysctl.c16
-rw-r--r--kernel/time/alarmtimer.c5
-rw-r--r--kernel/time/clockevents.c18
-rw-r--r--kernel/time/clocksource.c20
-rw-r--r--kernel/time/hrtimer.c19
-rw-r--r--kernel/time/itimer.c2
-rw-r--r--kernel/time/jiffies.c28
-rw-r--r--kernel/time/ntp.c1
-rw-r--r--kernel/time/posix-clock.c17
-rw-r--r--kernel/time/posix-cpu-timers.c3
-rw-r--r--kernel/time/posix-stubs.c5
-rw-r--r--kernel/time/posix-timers.c30
-rw-r--r--kernel/time/sched_clock.c9
-rw-r--r--kernel/time/test_udelay.c10
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c4
-rw-r--r--kernel/time/tick-broadcast.c6
-rw-r--r--kernel/time/tick-common.c6
-rw-r--r--kernel/time/tick-oneshot.c6
-rw-r--r--kernel/time/tick-sched.c5
-rw-r--r--kernel/time/time.c15
-rw-r--r--kernel/time/timeconst.bc2
-rw-r--r--kernel/time/timeconv.c1
-rw-r--r--kernel/time/timecounter.c17
-rw-r--r--kernel/time/timekeeping.c15
-rw-r--r--kernel/time/timekeeping_debug.c26
-rw-r--r--kernel/time/timer.c3
-rw-r--r--kernel/time/timer_list.c7
-rw-r--r--kernel/torture.c34
-rw-r--r--kernel/trace/blktrace.c4
-rw-r--r--kernel/trace/bpf_trace.c8
-rw-r--r--kernel/trace/ftrace.c32
-rw-r--r--kernel/trace/ring_buffer.c12
-rw-r--r--kernel/trace/trace.c22
-rw-r--r--kernel/trace/trace.h57
-rw-r--r--kernel/trace/trace_event_perf.c7
-rw-r--r--kernel/trace/trace_events_filter.c9
-rw-r--r--kernel/trace/trace_events_hist.c4
-rw-r--r--kernel/trace/trace_events_trigger.c6
-rw-r--r--kernel/trace/trace_functions_graph.c53
-rw-r--r--kernel/trace/trace_irqsoff.c2
-rw-r--r--kernel/trace/trace_kprobe.c414
-rw-r--r--kernel/trace/trace_printk.c2
-rw-r--r--kernel/trace/trace_probe.c672
-rw-r--r--kernel/trace/trace_probe.h289
-rw-r--r--kernel/trace/trace_probe_tmpl.h216
-rw-r--r--kernel/trace/trace_sched_wakeup.c2
-rw-r--r--kernel/trace/trace_stack.c2
-rw-r--r--kernel/trace/trace_uprobe.c255
-rw-r--r--kernel/tracepoint.c4
-rw-r--r--kernel/user_namespace.c12
-rw-r--r--kernel/workqueue.c8
143 files changed, 5647 insertions, 2913 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 7a63d567fdb5..7343b3a9bff0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -117,6 +117,10 @@ obj-$(CONFIG_HAS_IOMEM) += iomem.o
obj-$(CONFIG_ZONE_DEVICE) += memremap.o
obj-$(CONFIG_RSEQ) += rseq.o
+obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o
+KASAN_SANITIZE_stackleak.o := n
+KCOV_INSTRUMENT_stackleak.o := n
+
$(obj)/configs.o: $(obj)/config_data.h
targets += config_data.gz
diff --git a/kernel/bounds.c b/kernel/bounds.c
index c373e887c066..9795d75b09b2 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -13,7 +13,7 @@
#include <linux/log2.h>
#include <linux/spinlock_types.h>
-void foo(void)
+int main(void)
{
/* The enum constants to put into include/generated/bounds.h */
DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
@@ -23,4 +23,6 @@ void foo(void)
#endif
DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
/* End of constants */
+
+ return 0;
}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 378cef70341c..4da543d6bea2 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5,6 +5,7 @@
#include <uapi/linux/types.h>
#include <linux/seq_file.h>
#include <linux/compiler.h>
+#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/anon_inodes.h>
@@ -426,6 +427,30 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
offset < btf->hdr.str_len;
}
+/* Only C-style identifier is permitted. This can be relaxed if
+ * necessary.
+ */
+static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+{
+ /* offset must be valid */
+ const char *src = &btf->strings[offset];
+ const char *src_limit;
+
+ if (!isalpha(*src) && *src != '_')
+ return false;
+
+ /* set a limit on identifier length */
+ src_limit = src + KSYM_NAME_LEN;
+ src++;
+ while (*src && src < src_limit) {
+ if (!isalnum(*src) && *src != '_')
+ return false;
+ src++;
+ }
+
+ return !*src;
+}
+
static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
{
if (!offset)
@@ -1143,6 +1168,22 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* typedef type must have a valid name, and other ref types,
+ * volatile, const, restrict, should have a null name.
+ */
+ if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) {
+ if (!t->name_off ||
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+ } else {
+ if (t->name_off) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+ }
+
btf_verifier_log_type(env, t, NULL);
return 0;
@@ -1300,6 +1341,13 @@ static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* fwd type must have a valid name */
+ if (!t->name_off ||
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
btf_verifier_log_type(env, t, NULL);
return 0;
@@ -1356,6 +1404,12 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* array type should not have a name */
+ if (t->name_off) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
if (btf_type_vlen(t)) {
btf_verifier_log_type(env, t, "vlen != 0");
return -EINVAL;
@@ -1532,6 +1586,13 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* struct type either no name or a valid one */
+ if (t->name_off &&
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
btf_verifier_log_type(env, t, NULL);
last_offset = 0;
@@ -1543,6 +1604,12 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* struct member either no name or a valid one */
+ if (member->name_off &&
+ !btf_name_valid_identifier(btf, member->name_off)) {
+ btf_verifier_log_member(env, t, member, "Invalid name");
+ return -EINVAL;
+ }
/* A member cannot be in type void */
if (!member->type || !BTF_TYPE_ID_VALID(member->type)) {
btf_verifier_log_member(env, t, member,
@@ -1730,6 +1797,13 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* enum type either no name or a valid one */
+ if (t->name_off &&
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
btf_verifier_log_type(env, t, NULL);
for (i = 0; i < nr_enums; i++) {
@@ -1739,6 +1813,14 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* enum member must have a valid name */
+ if (!enums[i].name_off ||
+ !btf_name_valid_identifier(btf, enums[i].name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+
btf_verifier_log(env, "\t%s val=%d\n",
btf_name_by_offset(btf, enums[i].name_off),
enums[i].val);
@@ -2067,56 +2149,47 @@ static int btf_check_sec_info(struct btf_verifier_env *env,
return 0;
}
-static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data,
- u32 btf_data_size)
+static int btf_parse_hdr(struct btf_verifier_env *env)
{
+ u32 hdr_len, hdr_copy, btf_data_size;
const struct btf_header *hdr;
- u32 hdr_len, hdr_copy;
- /*
- * Minimal part of the "struct btf_header" that
- * contains the hdr_len.
- */
- struct btf_min_header {
- u16 magic;
- u8 version;
- u8 flags;
- u32 hdr_len;
- } __user *min_hdr;
struct btf *btf;
int err;
btf = env->btf;
- min_hdr = btf_data;
+ btf_data_size = btf->data_size;
- if (btf_data_size < sizeof(*min_hdr)) {
+ if (btf_data_size <
+ offsetof(struct btf_header, hdr_len) + sizeof(hdr->hdr_len)) {
btf_verifier_log(env, "hdr_len not found");
return -EINVAL;
}
- if (get_user(hdr_len, &min_hdr->hdr_len))
- return -EFAULT;
-
+ hdr = btf->data;
+ hdr_len = hdr->hdr_len;
if (btf_data_size < hdr_len) {
btf_verifier_log(env, "btf_header not found");
return -EINVAL;
}
- err = bpf_check_uarg_tail_zero(btf_data, sizeof(btf->hdr), hdr_len);
- if (err) {
- if (err == -E2BIG)
- btf_verifier_log(env, "Unsupported btf_header");
- return err;
+ /* Ensure the unsupported header fields are zero */
+ if (hdr_len > sizeof(btf->hdr)) {
+ u8 *expected_zero = btf->data + sizeof(btf->hdr);
+ u8 *end = btf->data + hdr_len;
+
+ for (; expected_zero < end; expected_zero++) {
+ if (*expected_zero) {
+ btf_verifier_log(env, "Unsupported btf_header");
+ return -E2BIG;
+ }
+ }
}
hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr));
- if (copy_from_user(&btf->hdr, btf_data, hdr_copy))
- return -EFAULT;
+ memcpy(&btf->hdr, btf->data, hdr_copy);
hdr = &btf->hdr;
- if (hdr->hdr_len != hdr_len)
- return -EINVAL;
-
btf_verifier_log_hdr(env, btf_data_size);
if (hdr->magic != BTF_MAGIC) {
@@ -2186,10 +2259,6 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
}
env->btf = btf;
- err = btf_parse_hdr(env, btf_data, btf_data_size);
- if (err)
- goto errout;
-
data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN);
if (!data) {
err = -ENOMEM;
@@ -2198,13 +2267,18 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
btf->data = data;
btf->data_size = btf_data_size;
- btf->nohdr_data = btf->data + btf->hdr.hdr_len;
if (copy_from_user(data, btf_data, btf_data_size)) {
err = -EFAULT;
goto errout;
}
+ err = btf_parse_hdr(env);
+ if (err)
+ goto errout;
+
+ btf->nohdr_data = btf->data + btf->hdr.hdr_len;
+
err = btf_parse_str_sec(env);
if (err)
goto errout;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7c7eeea8cffc..b2890c268cb3 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -369,6 +369,7 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
int bpf_jit_harden __read_mostly;
int bpf_jit_kallsyms __read_mostly;
+long bpf_jit_limit __read_mostly;
static __always_inline void
bpf_get_prog_addr_region(const struct bpf_prog *prog,
@@ -550,7 +551,6 @@ bool is_bpf_text_address(unsigned long addr)
int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
char *sym)
{
- unsigned long symbol_start, symbol_end;
struct bpf_prog_aux *aux;
unsigned int it = 0;
int ret = -ERANGE;
@@ -563,10 +563,9 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
if (it++ != symnum)
continue;
- bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
bpf_get_prog_name(aux->prog, sym);
- *value = symbol_start;
+ *value = (unsigned long)aux->prog->bpf_func;
*type = BPF_SYM_ELF_TYPE;
ret = 0;
@@ -577,27 +576,75 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
return ret;
}
+static atomic_long_t bpf_jit_current;
+
+/* Can be overridden by an arch's JIT compiler if it has a custom,
+ * dedicated BPF backend memory area, or if neither of the two
+ * below apply.
+ */
+u64 __weak bpf_jit_alloc_exec_limit(void)
+{
+#if defined(MODULES_VADDR)
+ return MODULES_END - MODULES_VADDR;
+#else
+ return VMALLOC_END - VMALLOC_START;
+#endif
+}
+
+static int __init bpf_jit_charge_init(void)
+{
+ /* Only used as heuristic here to derive limit. */
+ bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2,
+ PAGE_SIZE), LONG_MAX);
+ return 0;
+}
+pure_initcall(bpf_jit_charge_init);
+
+static int bpf_jit_charge_modmem(u32 pages)
+{
+ if (atomic_long_add_return(pages, &bpf_jit_current) >
+ (bpf_jit_limit >> PAGE_SHIFT)) {
+ if (!capable(CAP_SYS_ADMIN)) {
+ atomic_long_sub(pages, &bpf_jit_current);
+ return -EPERM;
+ }
+ }
+
+ return 0;
+}
+
+static void bpf_jit_uncharge_modmem(u32 pages)
+{
+ atomic_long_sub(pages, &bpf_jit_current);
+}
+
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
unsigned int alignment,
bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
struct bpf_binary_header *hdr;
- unsigned int size, hole, start;
+ u32 size, hole, start, pages;
/* Most of BPF filters are really small, but if some of them
* fill a page, allow at least 128 extra bytes to insert a
* random section of illegal instructions.
*/
size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE);
+ pages = size / PAGE_SIZE;
+
+ if (bpf_jit_charge_modmem(pages))
+ return NULL;
hdr = module_alloc(size);
- if (hdr == NULL)
+ if (!hdr) {
+ bpf_jit_uncharge_modmem(pages);
return NULL;
+ }
/* Fill space with illegal/arch-dep instructions. */
bpf_fill_ill_insns(hdr, size);
- hdr->pages = size / PAGE_SIZE;
+ hdr->pages = pages;
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (get_random_int() % hole) & ~(alignment - 1);
@@ -610,7 +657,10 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
void bpf_jit_binary_free(struct bpf_binary_header *hdr)
{
+ u32 pages = hdr->pages;
+
module_memfree(hdr);
+ bpf_jit_uncharge_modmem(pages);
}
/* This symbol is only overridden by archs that have different
@@ -631,6 +681,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
bpf_prog_unlock_free(fp);
}
+int bpf_jit_get_func_addr(const struct bpf_prog *prog,
+ const struct bpf_insn *insn, bool extra_pass,
+ u64 *func_addr, bool *func_addr_fixed)
+{
+ s16 off = insn->off;
+ s32 imm = insn->imm;
+ u8 *addr;
+
+ *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
+ if (!*func_addr_fixed) {
+ /* Place-holder address till the last pass has collected
+ * all addresses for JITed subprograms in which case we
+ * can pick them up from prog->aux.
+ */
+ if (!extra_pass)
+ addr = NULL;
+ else if (prog->aux->func &&
+ off >= 0 && off < prog->aux->func_cnt)
+ addr = (u8 *)prog->aux->func[off]->bpf_func;
+ else
+ return -EINVAL;
+ } else {
+ /* Address of a BPF helper call. Since part of the core
+ * kernel, it's always at a fixed location. __bpf_call_base
+ * and the helper with imm relative to it are both in core
+ * kernel.
+ */
+ addr = (u8 *)__bpf_call_base + imm;
+ }
+
+ *func_addr = (unsigned long)addr;
+ return 0;
+}
+
static int bpf_jit_blind_insn(const struct bpf_insn *from,
const struct bpf_insn *aux,
struct bpf_insn *to_buff)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 141710b82a6c..191b79948424 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -512,8 +512,7 @@ static int dev_map_notification(struct notifier_block *notifier,
struct bpf_dtab_netdev *dev, *odev;
dev = READ_ONCE(dtab->netdev_map[i]);
- if (!dev ||
- dev->dev->ifindex != netdev->ifindex)
+ if (!dev || netdev != dev->dev)
continue;
odev = cmpxchg(&dtab->netdev_map[i], dev, NULL);
if (dev == odev)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index ab0d5e3f9892..a74972b07e74 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -99,7 +99,6 @@ BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value)
const struct bpf_func_proto bpf_map_pop_elem_proto = {
.func = bpf_map_pop_elem,
.gpl_only = false,
- .pkt_access = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE,
@@ -113,7 +112,6 @@ BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
const struct bpf_func_proto bpf_map_peek_elem_proto = {
.func = bpf_map_pop_elem,
.gpl_only = false,
- .pkt_access = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE,
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c97a8f968638..bed9d48a7ae9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
return -ENOENT;
new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
- map->value_size, __GFP_ZERO | GFP_USER,
+ map->value_size,
+ __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
map->numa_node);
if (!new)
return -ENOMEM;
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 12a93fb37449..b384ea9f3254 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -7,6 +7,7 @@
#include <linux/bpf.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/capability.h>
#include "percpu_freelist.h"
#define QUEUE_STACK_CREATE_FLAG_MASK \
@@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
/* Called from syscall */
static int queue_stack_map_alloc_check(union bpf_attr *attr)
{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 0 ||
+ attr->value_size == 0 ||
attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
return -EINVAL;
@@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
{
int ret, numa_node = bpf_map_attr_numa_node(attr);
struct bpf_queue_stack *qs;
- u32 size, value_size;
- u64 queue_size, cost;
-
- size = attr->max_entries + 1;
- value_size = attr->value_size;
-
- queue_size = sizeof(*qs) + (u64) value_size * size;
+ u64 size, queue_size, cost;
- cost = queue_size;
+ size = (u64) attr->max_entries + 1;
+ cost = queue_size = sizeof(*qs) + size * attr->value_size;
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-E2BIG);
@@ -122,6 +122,7 @@ static int __queue_map_get(struct bpf_map *map, void *value, bool delete)
raw_spin_lock_irqsave(&qs->lock, flags);
if (queue_stack_map_is_empty(qs)) {
+ memset(value, 0, qs->map.value_size);
err = -ENOENT;
goto out;
}
@@ -151,6 +152,7 @@ static int __stack_map_get(struct bpf_map *map, void *value, bool delete)
raw_spin_lock_irqsave(&qs->lock, flags);
if (queue_stack_map_is_empty(qs)) {
+ memset(value, 0, qs->map.value_size);
err = -ENOENT;
goto out;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ccb93277aae2..cf5040fd5434 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2078,6 +2078,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
info.jited_prog_len = 0;
info.xlated_prog_len = 0;
info.nr_jited_ksyms = 0;
+ info.nr_jited_func_lens = 0;
goto done;
}
@@ -2158,11 +2159,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}
ulen = info.nr_jited_ksyms;
- info.nr_jited_ksyms = prog->aux->func_cnt;
+ info.nr_jited_ksyms = prog->aux->func_cnt ? : 1;
if (info.nr_jited_ksyms && ulen) {
if (bpf_dump_raw_ok()) {
+ unsigned long ksym_addr;
u64 __user *user_ksyms;
- ulong ksym_addr;
u32 i;
/* copy the address of the kernel symbol
@@ -2170,10 +2171,17 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
*/
ulen = min_t(u32, info.nr_jited_ksyms, ulen);
user_ksyms = u64_to_user_ptr(info.jited_ksyms);
- for (i = 0; i < ulen; i++) {
- ksym_addr = (ulong) prog->aux->func[i]->bpf_func;
- ksym_addr &= PAGE_MASK;
- if (put_user((u64) ksym_addr, &user_ksyms[i]))
+ if (prog->aux->func_cnt) {
+ for (i = 0; i < ulen; i++) {
+ ksym_addr = (unsigned long)
+ prog->aux->func[i]->bpf_func;
+ if (put_user((u64) ksym_addr,
+ &user_ksyms[i]))
+ return -EFAULT;
+ }
+ } else {
+ ksym_addr = (unsigned long) prog->bpf_func;
+ if (put_user((u64) ksym_addr, &user_ksyms[0]))
return -EFAULT;
}
} else {
@@ -2182,7 +2190,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}
ulen = info.nr_jited_func_lens;
- info.nr_jited_func_lens = prog->aux->func_cnt;
+ info.nr_jited_func_lens = prog->aux->func_cnt ? : 1;
if (info.nr_jited_func_lens && ulen) {
if (bpf_dump_raw_ok()) {
u32 __user *user_lens;
@@ -2191,9 +2199,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
/* copy the JITed image lengths for each function */
ulen = min_t(u32, info.nr_jited_func_lens, ulen);
user_lens = u64_to_user_ptr(info.jited_func_lens);
- for (i = 0; i < ulen; i++) {
- func_len = prog->aux->func[i]->jited_len;
- if (put_user(func_len, &user_lens[i]))
+ if (prog->aux->func_cnt) {
+ for (i = 0; i < ulen; i++) {
+ func_len =
+ prog->aux->func[i]->jited_len;
+ if (put_user(func_len, &user_lens[i]))
+ return -EFAULT;
+ }
+ } else {
+ func_len = prog->jited_len;
+ if (put_user(func_len, &user_lens[0]))
return -EFAULT;
}
} else {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 98fa0be35370..51ba84d4d34a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -175,6 +175,7 @@ struct bpf_verifier_stack_elem {
#define BPF_COMPLEXITY_LIMIT_INSNS 131072
#define BPF_COMPLEXITY_LIMIT_STACK 1024
+#define BPF_COMPLEXITY_LIMIT_STATES 64
#define BPF_MAP_PTR_UNPRIV 1UL
#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \
@@ -1387,21 +1388,24 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
enum bpf_access_type t)
{
switch (env->prog->type) {
+ /* Program types only with direct read access go here! */
case BPF_PROG_TYPE_LWT_IN:
case BPF_PROG_TYPE_LWT_OUT:
case BPF_PROG_TYPE_LWT_SEG6LOCAL:
case BPF_PROG_TYPE_SK_REUSEPORT:
- /* dst_input() and dst_output() can't write for now */
+ case BPF_PROG_TYPE_FLOW_DISSECTOR:
+ case BPF_PROG_TYPE_CGROUP_SKB:
if (t == BPF_WRITE)
return false;
/* fallthrough */
+
+ /* Program types with direct read + write access go here! */
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
case BPF_PROG_TYPE_XDP:
case BPF_PROG_TYPE_LWT_XMIT:
case BPF_PROG_TYPE_SK_SKB:
case BPF_PROG_TYPE_SK_MSG:
- case BPF_PROG_TYPE_FLOW_DISSECTOR:
if (meta)
return meta->pkt_access;
@@ -2849,10 +2853,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
fn->ret_type == RET_PTR_TO_MAP_VALUE) {
- if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
- else
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
/* remember map_ptr, so that check_map_access()
@@ -2865,7 +2865,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return -EINVAL;
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
- regs[BPF_REG_0].id = ++env->id_gen;
+ if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ } else {
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ regs[BPF_REG_0].id = ++env->id_gen;
+ }
} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
int id = acquire_reference_state(env, insn_idx);
if (id < 0)
@@ -3043,7 +3048,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
dst_reg->umax_value = umax_ptr;
dst_reg->var_off = ptr_reg->var_off;
dst_reg->off = ptr_reg->off + smin_val;
- dst_reg->range = ptr_reg->range;
+ dst_reg->raw = ptr_reg->raw;
break;
}
/* A new variable offset is created. Note that off_reg->off
@@ -3073,10 +3078,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
+ dst_reg->raw = ptr_reg->raw;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
- dst_reg->range = 0;
+ dst_reg->raw = 0;
}
break;
case BPF_SUB:
@@ -3105,7 +3111,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
dst_reg->var_off = ptr_reg->var_off;
dst_reg->id = ptr_reg->id;
dst_reg->off = ptr_reg->off - smin_val;
- dst_reg->range = ptr_reg->range;
+ dst_reg->raw = ptr_reg->raw;
break;
}
/* A new variable offset is created. If the subtrahend is known
@@ -3131,11 +3137,12 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
+ dst_reg->raw = ptr_reg->raw;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
if (smin_val < 0)
- dst_reg->range = 0;
+ dst_reg->raw = 0;
}
break;
case BPF_AND:
@@ -3745,6 +3752,79 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
}
}
+/* compute branch direction of the expression "if (reg opcode val) goto target;"
+ * and return:
+ * 1 - branch will be taken and "goto target" will be executed
+ * 0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
+ */
+static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+{
+ if (__is_pointer_value(false, reg))
+ return -1;
+
+ switch (opcode) {
+ case BPF_JEQ:
+ if (tnum_is_const(reg->var_off))
+ return !!tnum_equals_const(reg->var_off, val);
+ break;
+ case BPF_JNE:
+ if (tnum_is_const(reg->var_off))
+ return !tnum_equals_const(reg->var_off, val);
+ break;
+ case BPF_JGT:
+ if (reg->umin_value > val)
+ return 1;
+ else if (reg->umax_value <= val)
+ return 0;
+ break;
+ case BPF_JSGT:
+ if (reg->smin_value > (s64)val)
+ return 1;
+ else if (reg->smax_value < (s64)val)
+ return 0;
+ break;
+ case BPF_JLT:
+ if (reg->umax_value < val)
+ return 1;
+ else if (reg->umin_value >= val)
+ return 0;
+ break;
+ case BPF_JSLT:
+ if (reg->smax_value < (s64)val)
+ return 1;
+ else if (reg->smin_value >= (s64)val)
+ return 0;
+ break;
+ case BPF_JGE:
+ if (reg->umin_value >= val)
+ return 1;
+ else if (reg->umax_value < val)
+ return 0;
+ break;
+ case BPF_JSGE:
+ if (reg->smin_value >= (s64)val)
+ return 1;
+ else if (reg->smax_value < (s64)val)
+ return 0;
+ break;
+ case BPF_JLE:
+ if (reg->umax_value <= val)
+ return 1;
+ else if (reg->umin_value > val)
+ return 0;
+ break;
+ case BPF_JSLE:
+ if (reg->smax_value <= (s64)val)
+ return 1;
+ else if (reg->smin_value > (s64)val)
+ return 0;
+ break;
+ }
+
+ return -1;
+}
+
/* Adjusts the register min/max values in the case that the dst_reg is the
* variable register that we are working on, and src_reg is a constant or we're
* simply doing a BPF_K check.
@@ -4146,21 +4226,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
dst_reg = &regs[insn->dst_reg];
- /* detect if R == 0 where R was initialized to zero earlier */
- if (BPF_SRC(insn->code) == BPF_K &&
- (opcode == BPF_JEQ || opcode == BPF_JNE) &&
- dst_reg->type == SCALAR_VALUE &&
- tnum_is_const(dst_reg->var_off)) {
- if ((opcode == BPF_JEQ && dst_reg->var_off.value == insn->imm) ||
- (opcode == BPF_JNE && dst_reg->var_off.value != insn->imm)) {
- /* if (imm == imm) goto pc+off;
- * only follow the goto, ignore fall-through
- */
+ if (BPF_SRC(insn->code) == BPF_K) {
+ int pred = is_branch_taken(dst_reg, insn->imm, opcode);
+
+ if (pred == 1) {
+ /* only follow the goto, ignore fall-through */
*insn_idx += insn->off;
return 0;
- } else {
- /* if (imm != imm) goto pc+off;
- * only follow fall-through branch, since
+ } else if (pred == 0) {
+ /* only follow fall-through branch, since
* that's where the program will go
*/
return 0;
@@ -4974,7 +5048,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
struct bpf_verifier_state_list *new_sl;
struct bpf_verifier_state_list *sl;
struct bpf_verifier_state *cur = env->cur_state, *new;
- int i, j, err;
+ int i, j, err, states_cnt = 0;
sl = env->explored_states[insn_idx];
if (!sl)
@@ -5001,8 +5075,12 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
return 1;
}
sl = sl->next;
+ states_cnt++;
}
+ if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
+ return 0;
+
/* there were no equivalent states, remember current one.
* technically the current state is not proven to be safe yet,
* but it will either reach outer most bpf_exit (which means it's safe)
@@ -5024,9 +5102,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
}
new_sl->next = env->explored_states[insn_idx];
env->explored_states[insn_idx] = new_sl;
- /* connect new state to parentage chain */
- for (i = 0; i < BPF_REG_FP; i++)
- cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i];
+ /* connect new state to parentage chain. Current frame needs all
+ * registers connected. Only r6 - r9 of the callers are alive (pushed
+ * to the stack implicitly by JITs) so in callers' frames connect just
+ * r6 - r9 as an optimization. Callers will have r1 - r5 connected to
+ * the state of the call instruction (with WRITTEN set), and r0 comes
+ * from callee with its full parentage chain, anyway.
+ */
+ for (j = 0; j <= cur->curframe; j++)
+ for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++)
+ cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i];
/* clear write marks in current state: the writes we did are not writes
* our child did, so they don't screen off its reads from us.
* (There are no read marks in current state, because reads always mark
@@ -5142,6 +5227,9 @@ static int do_check(struct bpf_verifier_env *env)
goto process_bpf_exit;
}
+ if (signal_pending(current))
+ return -EAGAIN;
+
if (need_resched())
cond_resched();
@@ -5644,7 +5732,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
return;
/* NOTE: fake 'exit' subprog should be updated as well. */
for (i = 0; i <= env->subprog_cnt; i++) {
- if (env->subprog_info[i].start < off)
+ if (env->subprog_info[i].start <= off)
continue;
env->subprog_info[i].start += len - 1;
}
@@ -5706,7 +5794,11 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
bool is_narrower_load;
u32 target_size;
- if (ops->gen_prologue) {
+ if (ops->gen_prologue || env->seen_direct_write) {
+ if (!ops->gen_prologue) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
env->prog);
if (cnt >= ARRAY_SIZE(insn_buf)) {
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4c1cf0969a80..7a8429f8e280 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -55,6 +55,7 @@
#include <linux/nsproxy.h>
#include <linux/file.h>
#include <linux/sched/cputime.h>
+#include <linux/psi.h>
#include <net/sock.h>
#define CREATE_TRACE_POINTS
@@ -492,7 +493,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
}
/**
- * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss
+ * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
* @cgrp: the cgroup of interest
* @ss: the subsystem of interest (%NULL returns @cgrp->self)
*
@@ -501,8 +502,8 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
* enabled. If @ss is associated with the hierarchy @cgrp is on, this
* function is guaranteed to return non-NULL css.
*/
-static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp,
- struct cgroup_subsys *ss)
+static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
+ struct cgroup_subsys *ss)
{
lockdep_assert_held(&cgroup_mutex);
@@ -523,35 +524,6 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp,
}
/**
- * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
- * @cgrp: the cgroup of interest
- * @ss: the subsystem of interest
- *
- * Find and get the effective css of @cgrp for @ss. The effective css is
- * defined as the matching css of the nearest ancestor including self which
- * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on,
- * the root css is returned, so this function always returns a valid css.
- *
- * The returned css is not guaranteed to be online, and therefore it is the
- * callers responsiblity to tryget a reference for it.
- */
-struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
- struct cgroup_subsys *ss)
-{
- struct cgroup_subsys_state *css;
-
- do {
- css = cgroup_css(cgrp, ss);
-
- if (css)
- return css;
- cgrp = cgroup_parent(cgrp);
- } while (cgrp);
-
- return init_css_set.subsys[ss->id];
-}
-
-/**
* cgroup_get_e_css - get a cgroup's effective css for the specified subsystem
* @cgrp: the cgroup of interest
* @ss: the subsystem of interest
@@ -633,11 +605,10 @@ EXPORT_SYMBOL_GPL(of_css);
*
* Should be called under cgroup_[tree_]mutex.
*/
-#define for_each_e_css(css, ssid, cgrp) \
- for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
- if (!((css) = cgroup_e_css_by_mask(cgrp, \
- cgroup_subsys[(ssid)]))) \
- ; \
+#define for_each_e_css(css, ssid, cgrp) \
+ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
+ if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \
+ ; \
else
/**
@@ -862,7 +833,7 @@ static void css_set_move_task(struct task_struct *task,
*/
WARN_ON_ONCE(task->flags & PF_EXITING);
- rcu_assign_pointer(task->cgroups, to_cset);
+ cgroup_move_task(task, to_cset);
list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
&to_cset->tasks);
}
@@ -1036,7 +1007,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
* @ss is in this hierarchy, so we want the
* effective css from @cgrp.
*/
- template[i] = cgroup_e_css_by_mask(cgrp, ss);
+ template[i] = cgroup_e_css(cgrp, ss);
} else {
/*
* @ss is not in this hierarchy, so we don't want
@@ -3053,7 +3024,7 @@ static int cgroup_apply_control(struct cgroup *cgrp)
return ret;
/*
- * At this point, cgroup_e_css_by_mask() results reflect the new csses
+ * At this point, cgroup_e_css() results reflect the new csses
* making the following cgroup_update_dfl_csses() properly update
* css associations of all tasks in the subtree.
*/
@@ -3446,6 +3417,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
return ret;
}
+#ifdef CONFIG_PSI
+static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO);
+}
+static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM);
+}
+static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU);
+}
+#endif
+
static int cgroup_file_open(struct kernfs_open_file *of)
{
struct cftype *cft = of->kn->priv;
@@ -4576,6 +4562,23 @@ static struct cftype cgroup_base_files[] = {
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cpu_stat_show,
},
+#ifdef CONFIG_PSI
+ {
+ .name = "io.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_io_pressure_show,
+ },
+ {
+ .name = "memory.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_memory_pressure_show,
+ },
+ {
+ .name = "cpu.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_cpu_pressure_show,
+ },
+#endif
{ } /* terminate */
};
@@ -4636,6 +4639,7 @@ static void css_free_rwork_fn(struct work_struct *work)
*/
cgroup_put(cgroup_parent(cgrp));
kernfs_put(cgrp->kn);
+ psi_cgroup_free(cgrp);
if (cgroup_on_dfl(cgrp))
cgroup_rstat_exit(cgrp);
kfree(cgrp);
@@ -4892,10 +4896,15 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
cgrp->self.parent = &parent->self;
cgrp->root = root;
cgrp->level = level;
- ret = cgroup_bpf_inherit(cgrp);
+
+ ret = psi_cgroup_alloc(cgrp);
if (ret)
goto out_idr_free;
+ ret = cgroup_bpf_inherit(cgrp);
+ if (ret)
+ goto out_psi_free;
+
for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
@@ -4933,6 +4942,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
return cgrp;
+out_psi_free:
+ psi_cgroup_free(cgrp);
out_idr_free:
cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
out_stat_exit:
@@ -5332,7 +5343,7 @@ int __init cgroup_init(void)
cgroup_rstat_boot();
/*
- * The latency of the synchronize_sched() is too high for cgroups,
+ * The latency of the synchronize_rcu() is too high for cgroups,
* avoid it at the cost of forcing all readers into the slow path.
*/
rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
diff --git a/kernel/configs/kvm_guest.config b/kernel/configs/kvm_guest.config
index 108fecc20fc1..208481d91090 100644
--- a/kernel/configs/kvm_guest.config
+++ b/kernel/configs/kvm_guest.config
@@ -20,6 +20,7 @@ CONFIG_PARAVIRT=y
CONFIG_KVM_GUEST=y
CONFIG_S390_GUEST=y
CONFIG_VIRTIO=y
+CONFIG_VIRTIO_MENU=y
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_BLK=y
CONFIG_VIRTIO_CONSOLE=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3c7f3b4c453c..91d5c38eb7e5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -10,6 +10,7 @@
#include <linux/sched/signal.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task.h>
+#include <linux/sched/smt.h>
#include <linux/unistd.h>
#include <linux/cpu.h>
#include <linux/oom.h>
@@ -367,6 +368,12 @@ static void lockdep_release_cpus_lock(void)
#endif /* CONFIG_HOTPLUG_CPU */
+/*
+ * Architectures that need SMT-specific errata handling during SMT hotplug
+ * should override this.
+ */
+void __weak arch_smt_update(void) { }
+
#ifdef CONFIG_HOTPLUG_SMT
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
EXPORT_SYMBOL_GPL(cpu_smt_control);
@@ -1011,6 +1018,7 @@ out:
* concurrent CPU hotplug via cpu_add_remove_lock.
*/
lockup_detector_cleanup();
+ arch_smt_update();
return ret;
}
@@ -1139,6 +1147,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
ret = cpuhp_up_callbacks(cpu, st, target);
out:
cpus_write_unlock();
+ arch_smt_update();
return ret;
}
@@ -2055,12 +2064,6 @@ static void cpuhp_online_cpu_device(unsigned int cpu)
kobject_uevent(&dev->kobj, KOBJ_ONLINE);
}
-/*
- * Architectures that need SMT-specific errata handling during SMT hotplug
- * should override this.
- */
-void __weak arch_smt_update(void) { };
-
static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
{
int cpu, ret = 0;
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index 6ad4a9fcbd6f..7921ae4fca8d 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -179,14 +179,14 @@ kdb_bt(int argc, const char **argv)
kdb_printf("no process for cpu %ld\n", cpu);
return 0;
}
- sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+ sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
kdb_parse(buf);
return 0;
}
kdb_printf("btc: cpu status: ");
kdb_parse("cpu\n");
for_each_online_cpu(cpu) {
- sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+ sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
kdb_parse(buf);
touch_nmi_watchdog();
}
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index ed5d34925ad0..6a4b41484afe 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -216,7 +216,7 @@ static char *kdb_read(char *buffer, size_t bufsize)
int count;
int i;
int diag, dtab_count;
- int key;
+ int key, buf_size, ret;
diag = kdbgetintenv("DTABCOUNT", &dtab_count);
@@ -336,9 +336,8 @@ poll_again:
else
p_tmp = tmpbuffer;
len = strlen(p_tmp);
- count = kallsyms_symbol_complete(p_tmp,
- sizeof(tmpbuffer) -
- (p_tmp - tmpbuffer));
+ buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer);
+ count = kallsyms_symbol_complete(p_tmp, buf_size);
if (tab == 2 && count > 0) {
kdb_printf("\n%d symbols are found.", count);
if (count > dtab_count) {
@@ -350,9 +349,13 @@ poll_again:
}
kdb_printf("\n");
for (i = 0; i < count; i++) {
- if (WARN_ON(!kallsyms_symbol_next(p_tmp, i)))
+ ret = kallsyms_symbol_next(p_tmp, i, buf_size);
+ if (WARN_ON(!ret))
break;
- kdb_printf("%s ", p_tmp);
+ if (ret != -E2BIG)
+ kdb_printf("%s ", p_tmp);
+ else
+ kdb_printf("%s... ", p_tmp);
*(p_tmp + len) = '\0';
}
if (i >= dtab_count)
diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c
index 118527aa60ea..750497b0003a 100644
--- a/kernel/debug/kdb/kdb_keyboard.c
+++ b/kernel/debug/kdb/kdb_keyboard.c
@@ -173,11 +173,11 @@ int kdb_get_kbd_char(void)
case KT_LATIN:
if (isprint(keychar))
break; /* printable characters */
- /* drop through */
+ /* fall through */
case KT_SPEC:
if (keychar == K_ENTER)
break;
- /* drop through */
+ /* fall through */
default:
return -1; /* ignore unprintables */
}
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 2ddfce8f1e8f..d72b32c66f7d 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1192,7 +1192,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
if (reason == KDB_REASON_DEBUG) {
/* special case below */
} else {
- kdb_printf("\nEntering kdb (current=0x%p, pid %d) ",
+ kdb_printf("\nEntering kdb (current=0x%px, pid %d) ",
kdb_current, kdb_current ? kdb_current->pid : 0);
#if defined(CONFIG_SMP)
kdb_printf("on processor %d ", raw_smp_processor_id());
@@ -1208,7 +1208,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
*/
switch (db_result) {
case KDB_DB_BPT:
- kdb_printf("\nEntering kdb (0x%p, pid %d) ",
+ kdb_printf("\nEntering kdb (0x%px, pid %d) ",
kdb_current, kdb_current->pid);
#if defined(CONFIG_SMP)
kdb_printf("on processor %d ", raw_smp_processor_id());
@@ -1493,6 +1493,7 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr,
char cbuf[32];
char *c = cbuf;
int i;
+ int j;
unsigned long word;
memset(cbuf, '\0', sizeof(cbuf));
@@ -1538,25 +1539,9 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr,
wc.word = word;
#define printable_char(c) \
({unsigned char __c = c; isascii(__c) && isprint(__c) ? __c : '.'; })
- switch (bytesperword) {
- case 8:
+ for (j = 0; j < bytesperword; j++)
*c++ = printable_char(*cp++);
- *c++ = printable_char(*cp++);
- *c++ = printable_char(*cp++);
- *c++ = printable_char(*cp++);
- addr += 4;
- case 4:
- *c++ = printable_char(*cp++);
- *c++ = printable_char(*cp++);
- addr += 2;
- case 2:
- *c++ = printable_char(*cp++);
- addr++;
- case 1:
- *c++ = printable_char(*cp++);
- addr++;
- break;
- }
+ addr += bytesperword;
#undef printable_char
}
}
@@ -2048,7 +2033,7 @@ static int kdb_lsmod(int argc, const char **argv)
if (mod->state == MODULE_STATE_UNFORMED)
continue;
- kdb_printf("%-20s%8u 0x%p ", mod->name,
+ kdb_printf("%-20s%8u 0x%px ", mod->name,
mod->core_layout.size, (void *)mod);
#ifdef CONFIG_MODULE_UNLOAD
kdb_printf("%4d ", module_refcount(mod));
@@ -2059,7 +2044,7 @@ static int kdb_lsmod(int argc, const char **argv)
kdb_printf(" (Loading)");
else
kdb_printf(" (Live)");
- kdb_printf(" 0x%p", mod->core_layout.base);
+ kdb_printf(" 0x%px", mod->core_layout.base);
#ifdef CONFIG_MODULE_UNLOAD
{
@@ -2341,7 +2326,7 @@ void kdb_ps1(const struct task_struct *p)
return;
cpu = kdb_process_cpu(p);
- kdb_printf("0x%p %8d %8d %d %4d %c 0x%p %c%s\n",
+ kdb_printf("0x%px %8d %8d %d %4d %c 0x%px %c%s\n",
(void *)p, p->pid, p->parent->pid,
kdb_task_has_cpu(p), kdb_process_cpu(p),
kdb_task_state_char(p),
@@ -2354,7 +2339,7 @@ void kdb_ps1(const struct task_struct *p)
} else {
if (KDB_TSK(cpu) != p)
kdb_printf(" Error: does not match running "
- "process table (0x%p)\n", KDB_TSK(cpu));
+ "process table (0x%px)\n", KDB_TSK(cpu));
}
}
}
@@ -2556,16 +2541,11 @@ static int kdb_summary(int argc, const char **argv)
}
kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60);
- /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n",
LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]),
LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]),
LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2]));
-#undef LOAD_INT
-#undef LOAD_FRAC
+
/* Display in kilobytes */
#define K(x) ((x) << (PAGE_SHIFT - 10))
kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n"
@@ -2692,7 +2672,7 @@ int kdb_register_flags(char *cmd,
for_each_kdbcmd(kp, i) {
if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) {
kdb_printf("Duplicate kdb command registered: "
- "%s, func %p help %s\n", cmd, func, help);
+ "%s, func %px help %s\n", cmd, func, help);
return 1;
}
}
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 1e5a502ba4a7..2118d8258b7c 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -83,7 +83,7 @@ typedef struct __ksymtab {
unsigned long sym_start;
unsigned long sym_end;
} kdb_symtab_t;
-extern int kallsyms_symbol_next(char *prefix_name, int flag);
+extern int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size);
extern int kallsyms_symbol_complete(char *prefix_name, int max_len);
/* Exported Symbols for kernel loadable modules to use. */
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 990b3cc526c8..50bf9b119bad 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -40,7 +40,7 @@
int kdbgetsymval(const char *symname, kdb_symtab_t *symtab)
{
if (KDB_DEBUG(AR))
- kdb_printf("kdbgetsymval: symname=%s, symtab=%p\n", symname,
+ kdb_printf("kdbgetsymval: symname=%s, symtab=%px\n", symname,
symtab);
memset(symtab, 0, sizeof(*symtab));
symtab->sym_start = kallsyms_lookup_name(symname);
@@ -88,7 +88,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
char *knt1 = NULL;
if (KDB_DEBUG(AR))
- kdb_printf("kdbnearsym: addr=0x%lx, symtab=%p\n", addr, symtab);
+ kdb_printf("kdbnearsym: addr=0x%lx, symtab=%px\n", addr, symtab);
memset(symtab, 0, sizeof(*symtab));
if (addr < 4096)
@@ -149,7 +149,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
symtab->mod_name = "kernel";
if (KDB_DEBUG(AR))
kdb_printf("kdbnearsym: returns %d symtab->sym_start=0x%lx, "
- "symtab->mod_name=%p, symtab->sym_name=%p (%s)\n", ret,
+ "symtab->mod_name=%px, symtab->sym_name=%px (%s)\n", ret,
symtab->sym_start, symtab->mod_name, symtab->sym_name,
symtab->sym_name);
@@ -221,11 +221,13 @@ int kallsyms_symbol_complete(char *prefix_name, int max_len)
* Parameters:
* prefix_name prefix of a symbol name to lookup
* flag 0 means search from the head, 1 means continue search.
+ * buf_size maximum length that can be written to prefix_name
+ * buffer
* Returns:
* 1 if a symbol matches the given prefix.
* 0 if no string found
*/
-int kallsyms_symbol_next(char *prefix_name, int flag)
+int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size)
{
int prefix_len = strlen(prefix_name);
static loff_t pos;
@@ -235,10 +237,8 @@ int kallsyms_symbol_next(char *prefix_name, int flag)
pos = 0;
while ((name = kdb_walk_kallsyms(&pos))) {
- if (strncmp(name, prefix_name, prefix_len) == 0) {
- strncpy(prefix_name, name, strlen(name)+1);
- return 1;
- }
+ if (!strncmp(name, prefix_name, prefix_len))
+ return strscpy(prefix_name, name, buf_size);
}
return 0;
}
@@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size)
*word = w8;
break;
}
- /* drop through */
+ /* fall through */
default:
diag = KDB_BADWIDTH;
kdb_printf("kdb_getphysword: bad width %ld\n", (long) size);
@@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size)
*word = w8;
break;
}
- /* drop through */
+ /* fall through */
default:
diag = KDB_BADWIDTH;
kdb_printf("kdb_getword: bad width %ld\n", (long) size);
@@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size)
diag = kdb_putarea(addr, w8);
break;
}
- /* drop through */
+ /* fall through */
default:
diag = KDB_BADWIDTH;
kdb_printf("kdb_putword: bad width %ld\n", (long) size);
@@ -887,13 +887,13 @@ void debug_kusage(void)
__func__, dah_first);
if (dah_first) {
h_used = (struct debug_alloc_header *)debug_alloc_pool;
- kdb_printf("%s: h_used %p size %d\n", __func__, h_used,
+ kdb_printf("%s: h_used %px size %d\n", __func__, h_used,
h_used->size);
}
do {
h_used = (struct debug_alloc_header *)
((char *)h_free + dah_overhead + h_free->size);
- kdb_printf("%s: h_used %p size %d caller %p\n",
+ kdb_printf("%s: h_used %px size %d caller %px\n",
__func__, h_used, h_used->size, h_used->caller);
h_free = (struct debug_alloc_header *)
(debug_alloc_pool + h_free->next);
@@ -902,7 +902,7 @@ void debug_kusage(void)
((char *)h_free + dah_overhead + h_free->size);
if ((char *)h_used - debug_alloc_pool !=
sizeof(debug_alloc_pool_aligned))
- kdb_printf("%s: h_used %p size %d caller %p\n",
+ kdb_printf("%s: h_used %px size %d caller %px\n",
__func__, h_used, h_used->size, h_used->caller);
out:
spin_unlock(&dap_lock);
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index ca8ac2824f0b..2a12b988c717 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
+ tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
+ d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
d->blkio_count += tsk->delays->blkio_count;
d->swapin_count += tsk->delays->swapin_count;
d->freepages_count += tsk->delays->freepages_count;
+ d->thrashing_count += tsk->delays->thrashing_count;
raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
return 0;
@@ -169,3 +172,15 @@ void __delayacct_freepages_end(void)
&current->delays->freepages_count);
}
+void __delayacct_thrashing_start(void)
+{
+ current->delays->thrashing_start = ktime_get_ns();
+}
+
+void __delayacct_thrashing_end(void)
+{
+ delayacct_end(&current->delays->lock,
+ &current->delays->thrashing_start,
+ &current->delays->thrashing_delay,
+ &current->delays->thrashing_count);
+}
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 87a6bc2a96c0..375c77e8d52f 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -4,7 +4,7 @@
*
* DMA operations that map physical memory directly without using an IOMMU.
*/
-#include <linux/bootmem.h> /* for max_pfn */
+#include <linux/memblock.h> /* for max_pfn */
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/dma-direct.h>
@@ -14,8 +14,6 @@
#include <linux/pfn.h>
#include <linux/set_memory.h>
-#define DIRECT_MAPPING_ERROR 0
-
/*
* Most architectures use ZONE_DMA for the first 16 Megabytes, but
* some use it for entirely different regions:
@@ -311,7 +309,12 @@ int dma_direct_supported(struct device *dev, u64 mask)
min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT);
- return mask >= phys_to_dma(dev, min_mask);
+ /*
+ * This check needs to be against the actual bit mask value, so
+ * use __phys_to_dma() here so that the SME encryption mask isn't
+ * part of the check.
+ */
+ return mask >= __phys_to_dma(dev, min_mask);
}
int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 4f8a6dbf0b60..045930e32c0e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -21,6 +21,7 @@
#include <linux/cache.h>
#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/spinlock.h>
@@ -39,7 +40,7 @@
#include <asm/dma.h>
#include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/iommu-helper.h>
#define CREATE_TRACE_POINTS
@@ -73,13 +74,6 @@ static phys_addr_t io_tlb_start, io_tlb_end;
static unsigned long io_tlb_nslabs;
/*
- * When the IOMMU overflows we return a fallback buffer. This sets the size.
- */
-static unsigned long io_tlb_overflow = 32*1024;
-
-static phys_addr_t io_tlb_overflow_buffer;
-
-/*
* This is a free list describing the number of free entries available from
* each index
*/
@@ -126,7 +120,6 @@ setup_io_tlb_npages(char *str)
return 0;
}
early_param("swiotlb", setup_io_tlb_npages);
-/* make io_tlb_overflow tunable too? */
unsigned long swiotlb_nr_tbl(void)
{
@@ -194,16 +187,10 @@ void __init swiotlb_update_mem_attributes(void)
bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
memset(vaddr, 0, bytes);
-
- vaddr = phys_to_virt(io_tlb_overflow_buffer);
- bytes = PAGE_ALIGN(io_tlb_overflow);
- set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
- memset(vaddr, 0, bytes);
}
int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
{
- void *v_overflow_buffer;
unsigned long i, bytes;
bytes = nslabs << IO_TLB_SHIFT;
@@ -213,25 +200,14 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
io_tlb_end = io_tlb_start + bytes;
/*
- * Get the overflow emergency buffer
- */
- v_overflow_buffer = memblock_virt_alloc_low_nopanic(
- PAGE_ALIGN(io_tlb_overflow),
- PAGE_SIZE);
- if (!v_overflow_buffer)
- return -ENOMEM;
-
- io_tlb_overflow_buffer = __pa(v_overflow_buffer);
-
- /*
* Allocate and initialize the free list array. This array is used
* to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
* between io_tlb_start and io_tlb_end.
*/
- io_tlb_list = memblock_virt_alloc(
+ io_tlb_list = memblock_alloc(
PAGE_ALIGN(io_tlb_nslabs * sizeof(int)),
PAGE_SIZE);
- io_tlb_orig_addr = memblock_virt_alloc(
+ io_tlb_orig_addr = memblock_alloc(
PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)),
PAGE_SIZE);
for (i = 0; i < io_tlb_nslabs; i++) {
@@ -266,7 +242,7 @@ swiotlb_init(int verbose)
bytes = io_tlb_nslabs << IO_TLB_SHIFT;
/* Get IO TLB memory from the low pages */
- vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE);
+ vstart = memblock_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE);
if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
return;
@@ -330,7 +306,6 @@ int
swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
{
unsigned long i, bytes;
- unsigned char *v_overflow_buffer;
bytes = nslabs << IO_TLB_SHIFT;
@@ -342,19 +317,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
memset(tlb, 0, bytes);
/*
- * Get the overflow emergency buffer
- */
- v_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
- get_order(io_tlb_overflow));
- if (!v_overflow_buffer)
- goto cleanup2;
-
- set_memory_decrypted((unsigned long)v_overflow_buffer,
- io_tlb_overflow >> PAGE_SHIFT);
- memset(v_overflow_buffer, 0, io_tlb_overflow);
- io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
-
- /*
* Allocate and initialize the free list array. This array is used
* to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
* between io_tlb_start and io_tlb_end.
@@ -390,10 +352,6 @@ cleanup4:
sizeof(int)));
io_tlb_list = NULL;
cleanup3:
- free_pages((unsigned long)v_overflow_buffer,
- get_order(io_tlb_overflow));
- io_tlb_overflow_buffer = 0;
-cleanup2:
io_tlb_end = 0;
io_tlb_start = 0;
io_tlb_nslabs = 0;
@@ -407,8 +365,6 @@ void __init swiotlb_exit(void)
return;
if (late_alloc) {
- free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer),
- get_order(io_tlb_overflow));
free_pages((unsigned long)io_tlb_orig_addr,
get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
@@ -416,8 +372,6 @@ void __init swiotlb_exit(void)
free_pages((unsigned long)phys_to_virt(io_tlb_start),
get_order(io_tlb_nslabs << IO_TLB_SHIFT));
} else {
- memblock_free_late(io_tlb_overflow_buffer,
- PAGE_ALIGN(io_tlb_overflow));
memblock_free_late(__pa(io_tlb_orig_addr),
PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
memblock_free_late(__pa(io_tlb_list),
@@ -429,7 +383,7 @@ void __init swiotlb_exit(void)
max_segment = 0;
}
-int is_swiotlb_buffer(phys_addr_t paddr)
+static int is_swiotlb_buffer(phys_addr_t paddr)
{
return paddr >= io_tlb_start && paddr < io_tlb_end;
}
@@ -591,26 +545,6 @@ found:
}
/*
- * Allocates bounce buffer and returns its physical address.
- */
-static phys_addr_t
-map_single(struct device *hwdev, phys_addr_t phys, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- dma_addr_t start_dma_addr;
-
- if (swiotlb_force == SWIOTLB_NO_FORCE) {
- dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
- &phys);
- return SWIOTLB_MAP_ERROR;
- }
-
- start_dma_addr = __phys_to_dma(hwdev, io_tlb_start);
- return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
- dir, attrs);
-}
-
-/*
* tlb_addr is the physical address of the bounce buffer to unmap.
*/
void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
@@ -689,104 +623,32 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
}
}
-static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
- size_t size)
-{
- u64 mask = DMA_BIT_MASK(32);
-
- if (dev && dev->coherent_dma_mask)
- mask = dev->coherent_dma_mask;
- return addr + size - 1 <= mask;
-}
-
-static void *
-swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
- unsigned long attrs)
+static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
{
- phys_addr_t phys_addr;
-
- if (swiotlb_force == SWIOTLB_NO_FORCE)
- goto out_warn;
-
- phys_addr = swiotlb_tbl_map_single(dev,
- __phys_to_dma(dev, io_tlb_start),
- 0, size, DMA_FROM_DEVICE, attrs);
- if (phys_addr == SWIOTLB_MAP_ERROR)
- goto out_warn;
-
- *dma_handle = __phys_to_dma(dev, phys_addr);
- if (!dma_coherent_ok(dev, *dma_handle, size))
- goto out_unmap;
-
- memset(phys_to_virt(phys_addr), 0, size);
- return phys_to_virt(phys_addr);
+ dma_addr_t dma_addr;
-out_unmap:
- dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
- (unsigned long long)dev->coherent_dma_mask,
- (unsigned long long)*dma_handle);
-
- /*
- * DMA_TO_DEVICE to avoid memcpy in unmap_single.
- * DMA_ATTR_SKIP_CPU_SYNC is optional.
- */
- swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
-out_warn:
- if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
- dev_warn(dev,
- "swiotlb: coherent allocation failed, size=%zu\n",
- size);
- dump_stack();
+ if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
+ dev_warn_ratelimited(dev,
+ "Cannot do DMA to address %pa\n", phys);
+ return DIRECT_MAPPING_ERROR;
}
- return NULL;
-}
-
-static bool swiotlb_free_buffer(struct device *dev, size_t size,
- dma_addr_t dma_addr)
-{
- phys_addr_t phys_addr = dma_to_phys(dev, dma_addr);
- WARN_ON_ONCE(irqs_disabled());
-
- if (!is_swiotlb_buffer(phys_addr))
- return false;
-
- /*
- * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single.
- * DMA_ATTR_SKIP_CPU_SYNC is optional.
- */
- swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
- return true;
-}
-
-static void
-swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
- int do_panic)
-{
- if (swiotlb_force == SWIOTLB_NO_FORCE)
- return;
-
- /*
- * Ran out of IOMMU space for this operation. This is very bad.
- * Unfortunately the drivers cannot handle this operation properly.
- * unless they check for dma_mapping_error (most don't)
- * When the mapping is small enough return a static buffer to limit
- * the damage, or panic when the transfer is too big.
- */
- dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n",
- size);
+ /* Oh well, have to allocate and map a bounce buffer. */
+ *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
+ *phys, size, dir, attrs);
+ if (*phys == SWIOTLB_MAP_ERROR)
+ return DIRECT_MAPPING_ERROR;
- if (size <= io_tlb_overflow || !do_panic)
- return;
+ /* Ensure that the address returned is DMA'ble */
+ dma_addr = __phys_to_dma(dev, *phys);
+ if (unlikely(!dma_capable(dev, dma_addr, size))) {
+ swiotlb_tbl_unmap_single(dev, *phys, size, dir,
+ attrs | DMA_ATTR_SKIP_CPU_SYNC);
+ return DIRECT_MAPPING_ERROR;
+ }
- if (dir == DMA_BIDIRECTIONAL)
- panic("DMA: Random memory could be DMA accessed\n");
- if (dir == DMA_FROM_DEVICE)
- panic("DMA: Random memory could be DMA written\n");
- if (dir == DMA_TO_DEVICE)
- panic("DMA: Random memory could be DMA read\n");
+ return dma_addr;
}
/*
@@ -801,7 +663,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
enum dma_data_direction dir,
unsigned long attrs)
{
- phys_addr_t map, phys = page_to_phys(page) + offset;
+ phys_addr_t phys = page_to_phys(page) + offset;
dma_addr_t dev_addr = phys_to_dma(dev, phys);
BUG_ON(dir == DMA_NONE);
@@ -810,28 +672,18 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
* we can safely return the device addr and not worry about bounce
* buffering it.
*/
- if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
- return dev_addr;
-
- trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
-
- /* Oh well, have to allocate and map a bounce buffer. */
- map = map_single(dev, phys, size, dir, attrs);
- if (map == SWIOTLB_MAP_ERROR) {
- swiotlb_full(dev, size, dir, 1);
- return __phys_to_dma(dev, io_tlb_overflow_buffer);
+ if (!dma_capable(dev, dev_addr, size) ||
+ swiotlb_force == SWIOTLB_FORCE) {
+ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+ dev_addr = swiotlb_bounce_page(dev, &phys, size, dir, attrs);
}
- dev_addr = __phys_to_dma(dev, map);
+ if (!dev_is_dma_coherent(dev) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 &&
+ dev_addr != DIRECT_MAPPING_ERROR)
+ arch_sync_dma_for_device(dev, phys, size, dir);
- /* Ensure that the address returned is DMA'ble */
- if (dma_capable(dev, dev_addr, size))
- return dev_addr;
-
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
- swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
-
- return __phys_to_dma(dev, io_tlb_overflow_buffer);
+ return dev_addr;
}
/*
@@ -842,14 +694,18 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
* After this call, reads by the cpu to the buffer are guaranteed to see
* whatever the device wrote there.
*/
-static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
+void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
{
phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
BUG_ON(dir == DMA_NONE);
+ if (!dev_is_dma_coherent(hwdev) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
+
if (is_swiotlb_buffer(paddr)) {
swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
return;
@@ -867,13 +723,6 @@ static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
dma_mark_clean(phys_to_virt(paddr), size);
}
-void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- unmap_single(hwdev, dev_addr, size, dir, attrs);
-}
-
/*
* Make physical memory consistent for a single streaming mode DMA translation
* after a transfer.
@@ -893,15 +742,17 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(paddr)) {
+ if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_CPU)
+ arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
+
+ if (is_swiotlb_buffer(paddr))
swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
- return;
- }
- if (dir != DMA_FROM_DEVICE)
- return;
+ if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE)
+ arch_sync_dma_for_device(hwdev, paddr, size, dir);
- dma_mark_clean(phys_to_virt(paddr), size);
+ if (!is_swiotlb_buffer(paddr) && dir == DMA_FROM_DEVICE)
+ dma_mark_clean(phys_to_virt(paddr), size);
}
void
@@ -925,48 +776,31 @@ swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
* appropriate dma address and length. They are obtained via
* sg_dma_{address,length}(SG).
*
- * NOTE: An implementation may be able to use a smaller number of
- * DMA address/length pairs than there are SG table elements.
- * (for example via virtual mapping capabilities)
- * The routine returns the number of addr/length pairs actually
- * used, at most nents.
- *
* Device ownership issues as mentioned above for swiotlb_map_page are the
* same here.
*/
int
-swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
+swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems,
enum dma_data_direction dir, unsigned long attrs)
{
struct scatterlist *sg;
int i;
- BUG_ON(dir == DMA_NONE);
-
for_each_sg(sgl, sg, nelems, i) {
- phys_addr_t paddr = sg_phys(sg);
- dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
-
- if (swiotlb_force == SWIOTLB_FORCE ||
- !dma_capable(hwdev, dev_addr, sg->length)) {
- phys_addr_t map = map_single(hwdev, sg_phys(sg),
- sg->length, dir, attrs);
- if (map == SWIOTLB_MAP_ERROR) {
- /* Don't panic here, we expect map_sg users
- to do proper error handling. */
- swiotlb_full(hwdev, sg->length, dir, 0);
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
- swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
- attrs);
- sg_dma_len(sgl) = 0;
- return 0;
- }
- sg->dma_address = __phys_to_dma(hwdev, map);
- } else
- sg->dma_address = dev_addr;
+ sg->dma_address = swiotlb_map_page(dev, sg_page(sg), sg->offset,
+ sg->length, dir, attrs);
+ if (sg->dma_address == DIRECT_MAPPING_ERROR)
+ goto out_error;
sg_dma_len(sg) = sg->length;
}
+
return nelems;
+
+out_error:
+ swiotlb_unmap_sg_attrs(dev, sgl, i, dir,
+ attrs | DMA_ATTR_SKIP_CPU_SYNC);
+ sg_dma_len(sgl) = 0;
+ return 0;
}
/*
@@ -984,7 +818,7 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
BUG_ON(dir == DMA_NONE);
for_each_sg(sgl, sg, nelems, i)
- unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir,
+ swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), dir,
attrs);
}
@@ -1022,12 +856,6 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
}
-int
-swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
-{
- return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer));
-}
-
/*
* Return whether the given device DMA address mask can be supported
* properly. For example, if your device can only drive the low 24-bits
@@ -1040,39 +868,10 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask)
return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
}
-void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
-{
- void *vaddr;
-
- /* temporary workaround: */
- if (gfp & __GFP_NOWARN)
- attrs |= DMA_ATTR_NO_WARN;
-
- /*
- * Don't print a warning when the first allocation attempt fails.
- * swiotlb_alloc_coherent() will print a warning when the DMA memory
- * allocation ultimately failed.
- */
- gfp |= __GFP_NOWARN;
-
- vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
- if (!vaddr)
- vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs);
- return vaddr;
-}
-
-void swiotlb_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr, unsigned long attrs)
-{
- if (!swiotlb_free_buffer(dev, size, dma_addr))
- dma_direct_free(dev, size, vaddr, dma_addr, attrs);
-}
-
const struct dma_map_ops swiotlb_dma_ops = {
- .mapping_error = swiotlb_dma_mapping_error,
- .alloc = swiotlb_alloc,
- .free = swiotlb_free,
+ .mapping_error = dma_direct_mapping_error,
+ .alloc = dma_direct_alloc,
+ .free = dma_direct_free,
.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
.sync_single_for_device = swiotlb_sync_single_for_device,
.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5a97f34bc14c..67ecac337374 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -750,7 +750,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
/*
* Do not update time when cgroup is not active
*/
- if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
+ if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
__update_cgrp_time(event->cgrp);
}
@@ -5541,7 +5541,7 @@ out_put:
static const struct vm_operations_struct perf_mmap_vmops = {
.open = perf_mmap_open,
- .close = perf_mmap_close, /* non mergable */
+ .close = perf_mmap_close, /* non mergeable */
.fault = perf_mmap_fault,
.page_mkwrite = perf_mmap_fault,
};
@@ -8376,30 +8376,39 @@ static struct pmu perf_tracepoint = {
*
* PERF_PROBE_CONFIG_IS_RETPROBE if set, create kretprobe/uretprobe
* if not set, create kprobe/uprobe
+ *
+ * The following values specify a reference counter (or semaphore in the
+ * terminology of tools like dtrace, systemtap, etc.) Userspace Statically
+ * Defined Tracepoints (USDT). Currently, we use 40 bit for the offset.
+ *
+ * PERF_UPROBE_REF_CTR_OFFSET_BITS # of bits in config as th offset
+ * PERF_UPROBE_REF_CTR_OFFSET_SHIFT # of bits to shift left
*/
enum perf_probe_config {
PERF_PROBE_CONFIG_IS_RETPROBE = 1U << 0, /* [k,u]retprobe */
+ PERF_UPROBE_REF_CTR_OFFSET_BITS = 32,
+ PERF_UPROBE_REF_CTR_OFFSET_SHIFT = 64 - PERF_UPROBE_REF_CTR_OFFSET_BITS,
};
PMU_FORMAT_ATTR(retprobe, "config:0");
+#endif
-static struct attribute *probe_attrs[] = {
+#ifdef CONFIG_KPROBE_EVENTS
+static struct attribute *kprobe_attrs[] = {
&format_attr_retprobe.attr,
NULL,
};
-static struct attribute_group probe_format_group = {
+static struct attribute_group kprobe_format_group = {
.name = "format",
- .attrs = probe_attrs,
+ .attrs = kprobe_attrs,
};
-static const struct attribute_group *probe_attr_groups[] = {
- &probe_format_group,
+static const struct attribute_group *kprobe_attr_groups[] = {
+ &kprobe_format_group,
NULL,
};
-#endif
-#ifdef CONFIG_KPROBE_EVENTS
static int perf_kprobe_event_init(struct perf_event *event);
static struct pmu perf_kprobe = {
.task_ctx_nr = perf_sw_context,
@@ -8409,7 +8418,7 @@ static struct pmu perf_kprobe = {
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
- .attr_groups = probe_attr_groups,
+ .attr_groups = kprobe_attr_groups,
};
static int perf_kprobe_event_init(struct perf_event *event)
@@ -8441,6 +8450,24 @@ static int perf_kprobe_event_init(struct perf_event *event)
#endif /* CONFIG_KPROBE_EVENTS */
#ifdef CONFIG_UPROBE_EVENTS
+PMU_FORMAT_ATTR(ref_ctr_offset, "config:32-63");
+
+static struct attribute *uprobe_attrs[] = {
+ &format_attr_retprobe.attr,
+ &format_attr_ref_ctr_offset.attr,
+ NULL,
+};
+
+static struct attribute_group uprobe_format_group = {
+ .name = "format",
+ .attrs = uprobe_attrs,
+};
+
+static const struct attribute_group *uprobe_attr_groups[] = {
+ &uprobe_format_group,
+ NULL,
+};
+
static int perf_uprobe_event_init(struct perf_event *event);
static struct pmu perf_uprobe = {
.task_ctx_nr = perf_sw_context,
@@ -8450,12 +8477,13 @@ static struct pmu perf_uprobe = {
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
- .attr_groups = probe_attr_groups,
+ .attr_groups = uprobe_attr_groups,
};
static int perf_uprobe_event_init(struct perf_event *event)
{
int err;
+ unsigned long ref_ctr_offset;
bool is_retprobe;
if (event->attr.type != perf_uprobe.type)
@@ -8471,7 +8499,8 @@ static int perf_uprobe_event_init(struct perf_event *event)
return -EOPNOTSUPP;
is_retprobe = event->attr.config & PERF_PROBE_CONFIG_IS_RETPROBE;
- err = perf_uprobe_init(event, is_retprobe);
+ ref_ctr_offset = event->attr.config >> PERF_UPROBE_REF_CTR_OFFSET_SHIFT;
+ err = perf_uprobe_init(event, ref_ctr_offset, is_retprobe);
if (err)
return err;
@@ -9889,7 +9918,7 @@ static void account_event(struct perf_event *event)
* call the perf scheduling hooks before proceeding to
* install events that need them.
*/
- synchronize_sched();
+ synchronize_rcu();
}
/*
* Now that we have waited for the sync_sched(), allow further
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index d6b56180827c..5befb338a18d 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -238,7 +238,7 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
}
/*
- * Contraints to check before allowing this new breakpoint counter:
+ * Constraints to check before allowing this new breakpoint counter:
*
* == Non-pinned counter == (Considered as pinned for now)
*
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2bf792d22087..abbd8da9ac21 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -73,6 +73,7 @@ struct uprobe {
struct uprobe_consumer *consumers;
struct inode *inode; /* Also hold a ref to inode */
loff_t offset;
+ loff_t ref_ctr_offset;
unsigned long flags;
/*
@@ -88,6 +89,15 @@ struct uprobe {
struct arch_uprobe arch;
};
+struct delayed_uprobe {
+ struct list_head list;
+ struct uprobe *uprobe;
+ struct mm_struct *mm;
+};
+
+static DEFINE_MUTEX(delayed_uprobe_lock);
+static LIST_HEAD(delayed_uprobe_list);
+
/*
* Execute out of line area: anonymous executable mapping installed
* by the probed task to execute the copy of the original instruction
@@ -282,6 +292,166 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
return 1;
}
+static struct delayed_uprobe *
+delayed_uprobe_check(struct uprobe *uprobe, struct mm_struct *mm)
+{
+ struct delayed_uprobe *du;
+
+ list_for_each_entry(du, &delayed_uprobe_list, list)
+ if (du->uprobe == uprobe && du->mm == mm)
+ return du;
+ return NULL;
+}
+
+static int delayed_uprobe_add(struct uprobe *uprobe, struct mm_struct *mm)
+{
+ struct delayed_uprobe *du;
+
+ if (delayed_uprobe_check(uprobe, mm))
+ return 0;
+
+ du = kzalloc(sizeof(*du), GFP_KERNEL);
+ if (!du)
+ return -ENOMEM;
+
+ du->uprobe = uprobe;
+ du->mm = mm;
+ list_add(&du->list, &delayed_uprobe_list);
+ return 0;
+}
+
+static void delayed_uprobe_delete(struct delayed_uprobe *du)
+{
+ if (WARN_ON(!du))
+ return;
+ list_del(&du->list);
+ kfree(du);
+}
+
+static void delayed_uprobe_remove(struct uprobe *uprobe, struct mm_struct *mm)
+{
+ struct list_head *pos, *q;
+ struct delayed_uprobe *du;
+
+ if (!uprobe && !mm)
+ return;
+
+ list_for_each_safe(pos, q, &delayed_uprobe_list) {
+ du = list_entry(pos, struct delayed_uprobe, list);
+
+ if (uprobe && du->uprobe != uprobe)
+ continue;
+ if (mm && du->mm != mm)
+ continue;
+
+ delayed_uprobe_delete(du);
+ }
+}
+
+static bool valid_ref_ctr_vma(struct uprobe *uprobe,
+ struct vm_area_struct *vma)
+{
+ unsigned long vaddr = offset_to_vaddr(vma, uprobe->ref_ctr_offset);
+
+ return uprobe->ref_ctr_offset &&
+ vma->vm_file &&
+ file_inode(vma->vm_file) == uprobe->inode &&
+ (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE &&
+ vma->vm_start <= vaddr &&
+ vma->vm_end > vaddr;
+}
+
+static struct vm_area_struct *
+find_ref_ctr_vma(struct uprobe *uprobe, struct mm_struct *mm)
+{
+ struct vm_area_struct *tmp;
+
+ for (tmp = mm->mmap; tmp; tmp = tmp->vm_next)
+ if (valid_ref_ctr_vma(uprobe, tmp))
+ return tmp;
+
+ return NULL;
+}
+
+static int
+__update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d)
+{
+ void *kaddr;
+ struct page *page;
+ struct vm_area_struct *vma;
+ int ret;
+ short *ptr;
+
+ if (!vaddr || !d)
+ return -EINVAL;
+
+ ret = get_user_pages_remote(NULL, mm, vaddr, 1,
+ FOLL_WRITE, &page, &vma, NULL);
+ if (unlikely(ret <= 0)) {
+ /*
+ * We are asking for 1 page. If get_user_pages_remote() fails,
+ * it may return 0, in that case we have to return error.
+ */
+ return ret == 0 ? -EBUSY : ret;
+ }
+
+ kaddr = kmap_atomic(page);
+ ptr = kaddr + (vaddr & ~PAGE_MASK);
+
+ if (unlikely(*ptr + d < 0)) {
+ pr_warn("ref_ctr going negative. vaddr: 0x%lx, "
+ "curr val: %d, delta: %d\n", vaddr, *ptr, d);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ *ptr += d;
+ ret = 0;
+out:
+ kunmap_atomic(kaddr);
+ put_page(page);
+ return ret;
+}
+
+static void update_ref_ctr_warn(struct uprobe *uprobe,
+ struct mm_struct *mm, short d)
+{
+ pr_warn("ref_ctr %s failed for inode: 0x%lx offset: "
+ "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n",
+ d > 0 ? "increment" : "decrement", uprobe->inode->i_ino,
+ (unsigned long long) uprobe->offset,
+ (unsigned long long) uprobe->ref_ctr_offset, mm);
+}
+
+static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
+ short d)
+{
+ struct vm_area_struct *rc_vma;
+ unsigned long rc_vaddr;
+ int ret = 0;
+
+ rc_vma = find_ref_ctr_vma(uprobe, mm);
+
+ if (rc_vma) {
+ rc_vaddr = offset_to_vaddr(rc_vma, uprobe->ref_ctr_offset);
+ ret = __update_ref_ctr(mm, rc_vaddr, d);
+ if (ret)
+ update_ref_ctr_warn(uprobe, mm, d);
+
+ if (d > 0)
+ return ret;
+ }
+
+ mutex_lock(&delayed_uprobe_lock);
+ if (d > 0)
+ ret = delayed_uprobe_add(uprobe, mm);
+ else
+ delayed_uprobe_remove(uprobe, mm);
+ mutex_unlock(&delayed_uprobe_lock);
+
+ return ret;
+}
+
/*
* NOTE:
* Expect the breakpoint instruction to be the smallest size instruction for
@@ -302,9 +472,13 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
unsigned long vaddr, uprobe_opcode_t opcode)
{
+ struct uprobe *uprobe;
struct page *old_page, *new_page;
struct vm_area_struct *vma;
- int ret;
+ int ret, is_register, ref_ctr_updated = 0;
+
+ is_register = is_swbp_insn(&opcode);
+ uprobe = container_of(auprobe, struct uprobe, arch);
retry:
/* Read the page with vaddr into memory */
@@ -317,6 +491,15 @@ retry:
if (ret <= 0)
goto put_old;
+ /* We are going to replace instruction, update ref_ctr. */
+ if (!ref_ctr_updated && uprobe->ref_ctr_offset) {
+ ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1);
+ if (ret)
+ goto put_old;
+
+ ref_ctr_updated = 1;
+ }
+
ret = anon_vma_prepare(vma);
if (ret)
goto put_old;
@@ -337,6 +520,11 @@ put_old:
if (unlikely(ret == -EAGAIN))
goto retry;
+
+ /* Revert back reference counter if instruction update failed. */
+ if (ret && is_register && ref_ctr_updated)
+ update_ref_ctr(uprobe, mm, -1);
+
return ret;
}
@@ -378,8 +566,17 @@ static struct uprobe *get_uprobe(struct uprobe *uprobe)
static void put_uprobe(struct uprobe *uprobe)
{
- if (atomic_dec_and_test(&uprobe->ref))
+ if (atomic_dec_and_test(&uprobe->ref)) {
+ /*
+ * If application munmap(exec_vma) before uprobe_unregister()
+ * gets called, we don't get a chance to remove uprobe from
+ * delayed_uprobe_list from remove_breakpoint(). Do it here.
+ */
+ mutex_lock(&delayed_uprobe_lock);
+ delayed_uprobe_remove(uprobe, NULL);
+ mutex_unlock(&delayed_uprobe_lock);
kfree(uprobe);
+ }
}
static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -484,7 +681,18 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe)
return u;
}
-static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
+static void
+ref_ctr_mismatch_warn(struct uprobe *cur_uprobe, struct uprobe *uprobe)
+{
+ pr_warn("ref_ctr_offset mismatch. inode: 0x%lx offset: 0x%llx "
+ "ref_ctr_offset(old): 0x%llx ref_ctr_offset(new): 0x%llx\n",
+ uprobe->inode->i_ino, (unsigned long long) uprobe->offset,
+ (unsigned long long) cur_uprobe->ref_ctr_offset,
+ (unsigned long long) uprobe->ref_ctr_offset);
+}
+
+static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset,
+ loff_t ref_ctr_offset)
{
struct uprobe *uprobe, *cur_uprobe;
@@ -494,6 +702,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
uprobe->inode = inode;
uprobe->offset = offset;
+ uprobe->ref_ctr_offset = ref_ctr_offset;
init_rwsem(&uprobe->register_rwsem);
init_rwsem(&uprobe->consumer_rwsem);
@@ -501,6 +710,12 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
cur_uprobe = insert_uprobe(uprobe);
/* a uprobe exists for this inode:offset combination */
if (cur_uprobe) {
+ if (cur_uprobe->ref_ctr_offset != uprobe->ref_ctr_offset) {
+ ref_ctr_mismatch_warn(cur_uprobe, uprobe);
+ put_uprobe(cur_uprobe);
+ kfree(uprobe);
+ return ERR_PTR(-EINVAL);
+ }
kfree(uprobe);
uprobe = cur_uprobe;
}
@@ -616,7 +831,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
BUG_ON((uprobe->offset & ~PAGE_MASK) +
UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
- smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+ smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
set_bit(UPROBE_COPY_INSN, &uprobe->flags);
out:
@@ -895,7 +1110,7 @@ EXPORT_SYMBOL_GPL(uprobe_unregister);
* else return 0 (success)
*/
static int __uprobe_register(struct inode *inode, loff_t offset,
- struct uprobe_consumer *uc)
+ loff_t ref_ctr_offset, struct uprobe_consumer *uc)
{
struct uprobe *uprobe;
int ret;
@@ -912,9 +1127,12 @@ static int __uprobe_register(struct inode *inode, loff_t offset,
return -EINVAL;
retry:
- uprobe = alloc_uprobe(inode, offset);
+ uprobe = alloc_uprobe(inode, offset, ref_ctr_offset);
if (!uprobe)
return -ENOMEM;
+ if (IS_ERR(uprobe))
+ return PTR_ERR(uprobe);
+
/*
* We can race with uprobe_unregister()->delete_uprobe().
* Check uprobe_is_active() and retry if it is false.
@@ -938,10 +1156,17 @@ static int __uprobe_register(struct inode *inode, loff_t offset,
int uprobe_register(struct inode *inode, loff_t offset,
struct uprobe_consumer *uc)
{
- return __uprobe_register(inode, offset, uc);
+ return __uprobe_register(inode, offset, 0, uc);
}
EXPORT_SYMBOL_GPL(uprobe_register);
+int uprobe_register_refctr(struct inode *inode, loff_t offset,
+ loff_t ref_ctr_offset, struct uprobe_consumer *uc)
+{
+ return __uprobe_register(inode, offset, ref_ctr_offset, uc);
+}
+EXPORT_SYMBOL_GPL(uprobe_register_refctr);
+
/*
* uprobe_apply - unregister an already registered probe.
* @inode: the file in which the probe has to be removed.
@@ -1060,6 +1285,35 @@ static void build_probe_list(struct inode *inode,
spin_unlock(&uprobes_treelock);
}
+/* @vma contains reference counter, not the probed instruction. */
+static int delayed_ref_ctr_inc(struct vm_area_struct *vma)
+{
+ struct list_head *pos, *q;
+ struct delayed_uprobe *du;
+ unsigned long vaddr;
+ int ret = 0, err = 0;
+
+ mutex_lock(&delayed_uprobe_lock);
+ list_for_each_safe(pos, q, &delayed_uprobe_list) {
+ du = list_entry(pos, struct delayed_uprobe, list);
+
+ if (du->mm != vma->vm_mm ||
+ !valid_ref_ctr_vma(du->uprobe, vma))
+ continue;
+
+ vaddr = offset_to_vaddr(vma, du->uprobe->ref_ctr_offset);
+ ret = __update_ref_ctr(vma->vm_mm, vaddr, 1);
+ if (ret) {
+ update_ref_ctr_warn(du->uprobe, vma->vm_mm, 1);
+ if (!err)
+ err = ret;
+ }
+ delayed_uprobe_delete(du);
+ }
+ mutex_unlock(&delayed_uprobe_lock);
+ return err;
+}
+
/*
* Called from mmap_region/vma_adjust with mm->mmap_sem acquired.
*
@@ -1072,7 +1326,15 @@ int uprobe_mmap(struct vm_area_struct *vma)
struct uprobe *uprobe, *u;
struct inode *inode;
- if (no_uprobe_events() || !valid_vma(vma, true))
+ if (no_uprobe_events())
+ return 0;
+
+ if (vma->vm_file &&
+ (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE &&
+ test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags))
+ delayed_ref_ctr_inc(vma);
+
+ if (!valid_vma(vma, true))
return 0;
inode = file_inode(vma->vm_file);
@@ -1246,6 +1508,10 @@ void uprobe_clear_state(struct mm_struct *mm)
{
struct xol_area *area = mm->uprobes_state.xol_area;
+ mutex_lock(&delayed_uprobe_lock);
+ delayed_uprobe_remove(NULL, mm);
+ mutex_unlock(&delayed_uprobe_lock);
+
if (!area)
return;
@@ -1914,10 +2180,18 @@ static void handle_swbp(struct pt_regs *regs)
* After we hit the bp, _unregister + _register can install the
* new and not-yet-analyzed uprobe at the same address, restart.
*/
- smp_rmb(); /* pairs with wmb() in install_breakpoint() */
if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
goto out;
+ /*
+ * Pairs with the smp_wmb() in prepare_uprobe().
+ *
+ * Guarantees that if we see the UPROBE_COPY_INSN bit set, then
+ * we must also see the stores to &uprobe->arch performed by the
+ * prepare_uprobe() call.
+ */
+ smp_rmb();
+
/* Tracing handlers use ->utask to communicate with fetch methods */
if (!get_utask())
goto out;
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index bc80a4e268c0..17f75b545f66 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -173,8 +173,7 @@ static void fei_debugfs_remove_attr(struct fei_attr *attr)
struct dentry *dir;
dir = debugfs_lookup(attr->kp.symbol_name, fei_debugfs_dir);
- if (dir)
- debugfs_remove_recursive(dir);
+ debugfs_remove_recursive(dir);
}
static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
diff --git a/kernel/fork.c b/kernel/fork.c
index f0b58479534f..e2a5156bc9c3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -91,6 +91,7 @@
#include <linux/kcov.h>
#include <linux/livepatch.h>
#include <linux/thread_info.h>
+#include <linux/stackleak.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -223,9 +224,14 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
return s->addr;
}
+ /*
+ * Allocated stacks are cached and later reused by new threads,
+ * so memcg accounting is performed manually on assigning/releasing
+ * stacks to tasks. Drop __GFP_ACCOUNT.
+ */
stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
VMALLOC_START, VMALLOC_END,
- THREADINFO_GFP,
+ THREADINFO_GFP & ~__GFP_ACCOUNT,
PAGE_KERNEL,
0, node, __builtin_return_address(0));
@@ -234,8 +240,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
* free_thread_stack() can be called in interrupt context,
* so cache the vm_struct.
*/
- if (stack)
+ if (stack) {
tsk->stack_vm_area = find_vm_area(stack);
+ tsk->stack = stack;
+ }
return stack;
#else
struct page *page = alloc_pages_node(node, THREADINFO_GFP,
@@ -248,9 +256,19 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
static inline void free_thread_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
- if (task_stack_vm_area(tsk)) {
+ struct vm_struct *vm = task_stack_vm_area(tsk);
+
+ if (vm) {
int i;
+ for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
+ mod_memcg_page_state(vm->pages[i],
+ MEMCG_KERNEL_STACK_KB,
+ -(int)(PAGE_SIZE / 1024));
+
+ memcg_kmem_uncharge(vm->pages[i], 0);
+ }
+
for (i = 0; i < NR_CACHED_STACKS; i++) {
if (this_cpu_cmpxchg(cached_stacks[i],
NULL, tsk->stack_vm_area) != NULL)
@@ -272,7 +290,10 @@ static struct kmem_cache *thread_stack_cache;
static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
+ unsigned long *stack;
+ stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
+ tsk->stack = stack;
+ return stack;
}
static void free_thread_stack(struct task_struct *tsk)
@@ -351,10 +372,6 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
NR_KERNEL_STACK_KB,
PAGE_SIZE / 1024 * account);
}
-
- /* All stack pages belong to the same memcg. */
- mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB,
- account * (THREAD_SIZE / 1024));
} else {
/*
* All stack pages are in the same zone and belong to the
@@ -370,6 +387,35 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
}
}
+static int memcg_charge_kernel_stack(struct task_struct *tsk)
+{
+#ifdef CONFIG_VMAP_STACK
+ struct vm_struct *vm = task_stack_vm_area(tsk);
+ int ret;
+
+ if (vm) {
+ int i;
+
+ for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
+ /*
+ * If memcg_kmem_charge() fails, page->mem_cgroup
+ * pointer is NULL, and both memcg_kmem_uncharge()
+ * and mod_memcg_page_state() in free_thread_stack()
+ * will ignore this page. So it's safe.
+ */
+ ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0);
+ if (ret)
+ return ret;
+
+ mod_memcg_page_state(vm->pages[i],
+ MEMCG_KERNEL_STACK_KB,
+ PAGE_SIZE / 1024);
+ }
+ }
+#endif
+ return 0;
+}
+
static void release_task_stack(struct task_struct *tsk)
{
if (WARN_ON(tsk->state != TASK_DEAD))
@@ -807,6 +853,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
if (!stack)
goto free_tsk;
+ if (memcg_charge_kernel_stack(tsk))
+ goto free_stack;
+
stack_vm_area = task_stack_vm_area(tsk);
err = arch_dup_task_struct(tsk, orig);
@@ -1779,6 +1828,10 @@ static __latent_entropy struct task_struct *copy_process(
p->default_timer_slack_ns = current->timer_slack_ns;
+#ifdef CONFIG_PSI
+ p->psi_flags = 0;
+#endif
+
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
@@ -1879,6 +1932,8 @@ static __latent_entropy struct task_struct *copy_process(
if (retval)
goto bad_fork_cleanup_io;
+ stackleak_task_init(p);
+
if (pid != &init_struct_pid) {
pid = alloc_pid(p->nsproxy->pid_ns_for_children);
if (IS_ERR(pid)) {
diff --git a/kernel/futex.c b/kernel/futex.c
index 3e2de8fc1891..5cc8083a4c89 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -65,7 +65,7 @@
#include <linux/sched/mm.h>
#include <linux/hugetlb.h>
#include <linux/freezer.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/fault-inject.h>
#include <asm/futex.h>
@@ -1148,11 +1148,65 @@ out_error:
return ret;
}
+static int handle_exit_race(u32 __user *uaddr, u32 uval,
+ struct task_struct *tsk)
+{
+ u32 uval2;
+
+ /*
+ * If PF_EXITPIDONE is not yet set, then try again.
+ */
+ if (tsk && !(tsk->flags & PF_EXITPIDONE))
+ return -EAGAIN;
+
+ /*
+ * Reread the user space value to handle the following situation:
+ *
+ * CPU0 CPU1
+ *
+ * sys_exit() sys_futex()
+ * do_exit() futex_lock_pi()
+ * futex_lock_pi_atomic()
+ * exit_signals(tsk) No waiters:
+ * tsk->flags |= PF_EXITING; *uaddr == 0x00000PID
+ * mm_release(tsk) Set waiter bit
+ * exit_robust_list(tsk) { *uaddr = 0x80000PID;
+ * Set owner died attach_to_pi_owner() {
+ * *uaddr = 0xC0000000; tsk = get_task(PID);
+ * } if (!tsk->flags & PF_EXITING) {
+ * ... attach();
+ * tsk->flags |= PF_EXITPIDONE; } else {
+ * if (!(tsk->flags & PF_EXITPIDONE))
+ * return -EAGAIN;
+ * return -ESRCH; <--- FAIL
+ * }
+ *
+ * Returning ESRCH unconditionally is wrong here because the
+ * user space value has been changed by the exiting task.
+ *
+ * The same logic applies to the case where the exiting task is
+ * already gone.
+ */
+ if (get_futex_value_locked(&uval2, uaddr))
+ return -EFAULT;
+
+ /* If the user space value has changed, try again. */
+ if (uval2 != uval)
+ return -EAGAIN;
+
+ /*
+ * The exiting task did not have a robust list, the robust list was
+ * corrupted or the user space value in *uaddr is simply bogus.
+ * Give up and tell user space.
+ */
+ return -ESRCH;
+}
+
/*
* Lookup the task for the TID provided from user space and attach to
* it after doing proper sanity checks.
*/
-static int attach_to_pi_owner(u32 uval, union futex_key *key,
+static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
struct futex_pi_state **ps)
{
pid_t pid = uval & FUTEX_TID_MASK;
@@ -1162,12 +1216,15 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
/*
* We are the first waiter - try to look up the real owner and attach
* the new pi_state to it, but bail out when TID = 0 [1]
+ *
+ * The !pid check is paranoid. None of the call sites should end up
+ * with pid == 0, but better safe than sorry. Let the caller retry
*/
if (!pid)
- return -ESRCH;
+ return -EAGAIN;
p = find_get_task_by_vpid(pid);
if (!p)
- return -ESRCH;
+ return handle_exit_race(uaddr, uval, NULL);
if (unlikely(p->flags & PF_KTHREAD)) {
put_task_struct(p);
@@ -1187,7 +1244,7 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
* set, we know that the task has finished the
* cleanup:
*/
- int ret = (p->flags & PF_EXITPIDONE) ? -ESRCH : -EAGAIN;
+ int ret = handle_exit_race(uaddr, uval, p);
raw_spin_unlock_irq(&p->pi_lock);
put_task_struct(p);
@@ -1244,7 +1301,7 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
* We are the first waiter - try to look up the owner based on
* @uval and attach to it.
*/
- return attach_to_pi_owner(uval, key, ps);
+ return attach_to_pi_owner(uaddr, uval, key, ps);
}
static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
@@ -1352,7 +1409,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
* attach to the owner. If that fails, no harm done, we only
* set the FUTEX_WAITERS bit in the user space variable.
*/
- return attach_to_pi_owner(uval, key, ps);
+ return attach_to_pi_owner(uaddr, newval, key, ps);
}
/**
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index b9132d1269ef..cb8e3e8ac7b9 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -15,6 +15,7 @@
#include <linux/lockdep.h>
#include <linux/export.h>
#include <linux/sysctl.h>
+#include <linux/suspend.h>
#include <linux/utsname.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
@@ -242,6 +243,28 @@ void reset_hung_task_detector(void)
}
EXPORT_SYMBOL_GPL(reset_hung_task_detector);
+static bool hung_detector_suspended;
+
+static int hungtask_pm_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ switch (action) {
+ case PM_SUSPEND_PREPARE:
+ case PM_HIBERNATION_PREPARE:
+ case PM_RESTORE_PREPARE:
+ hung_detector_suspended = true;
+ break;
+ case PM_POST_SUSPEND:
+ case PM_POST_HIBERNATION:
+ case PM_POST_RESTORE:
+ hung_detector_suspended = false;
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
/*
* kthread which checks for tasks stuck in D state
*/
@@ -261,7 +284,8 @@ static int watchdog(void *dummy)
interval = min_t(unsigned long, interval, timeout);
t = hung_timeout_jiffies(hung_last_checked, interval);
if (t <= 0) {
- if (!atomic_xchg(&reset_hung_task, 0))
+ if (!atomic_xchg(&reset_hung_task, 0) &&
+ !hung_detector_suspended)
check_hung_uninterruptible_tasks(timeout);
hung_last_checked = jiffies;
continue;
@@ -275,6 +299,10 @@ static int watchdog(void *dummy)
static int __init hung_task_init(void)
{
atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+
+ /* Disable hung task detector on suspend */
+ pm_notifier(hungtask_pm_notify, 0);
+
watchdog_task = kthread_run(watchdog, NULL, "khungtaskd");
return 0;
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index f4f29b9d90ee..45b68b4ea48b 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -94,15 +94,15 @@ static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask,
return nodes;
}
-static int irq_build_affinity_masks(const struct irq_affinity *affd,
- int startvec, int numvecs,
- cpumask_var_t *node_to_cpumask,
- const struct cpumask *cpu_mask,
- struct cpumask *nmsk,
- struct cpumask *masks)
+static int __irq_build_affinity_masks(const struct irq_affinity *affd,
+ int startvec, int numvecs, int firstvec,
+ cpumask_var_t *node_to_cpumask,
+ const struct cpumask *cpu_mask,
+ struct cpumask *nmsk,
+ struct irq_affinity_desc *masks)
{
int n, nodes, cpus_per_vec, extra_vecs, done = 0;
- int last_affv = affd->pre_vectors + numvecs;
+ int last_affv = firstvec + numvecs;
int curvec = startvec;
nodemask_t nodemsk = NODE_MASK_NONE;
@@ -117,12 +117,13 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
*/
if (numvecs <= nodes) {
for_each_node_mask(n, nodemsk) {
- cpumask_copy(masks + curvec, node_to_cpumask[n]);
- if (++done == numvecs)
- break;
+ cpumask_or(&masks[curvec].mask,
+ &masks[curvec].mask,
+ node_to_cpumask[n]);
if (++curvec == last_affv)
- curvec = affd->pre_vectors;
+ curvec = firstvec;
}
+ done = numvecs;
goto out;
}
@@ -130,7 +131,7 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
int ncpus, v, vecs_to_assign, vecs_per_node;
/* Spread the vectors per node */
- vecs_per_node = (numvecs - (curvec - affd->pre_vectors)) / nodes;
+ vecs_per_node = (numvecs - (curvec - firstvec)) / nodes;
/* Get the cpus on this node which are in the mask */
cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
@@ -151,14 +152,15 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
cpus_per_vec++;
--extra_vecs;
}
- irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec);
+ irq_spread_init_one(&masks[curvec].mask, nmsk,
+ cpus_per_vec);
}
done += v;
if (done >= numvecs)
break;
if (curvec >= last_affv)
- curvec = affd->pre_vectors;
+ curvec = firstvec;
--nodes;
}
@@ -166,20 +168,77 @@ out:
return done;
}
+/*
+ * build affinity in two stages:
+ * 1) spread present CPU on these vectors
+ * 2) spread other possible CPUs on these vectors
+ */
+static int irq_build_affinity_masks(const struct irq_affinity *affd,
+ int startvec, int numvecs, int firstvec,
+ cpumask_var_t *node_to_cpumask,
+ struct irq_affinity_desc *masks)
+{
+ int curvec = startvec, nr_present, nr_others;
+ int ret = -ENOMEM;
+ cpumask_var_t nmsk, npresmsk;
+
+ if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
+ return ret;
+
+ if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
+ goto fail;
+
+ ret = 0;
+ /* Stabilize the cpumasks */
+ get_online_cpus();
+ build_node_to_cpumask(node_to_cpumask);
+
+ /* Spread on present CPUs starting from affd->pre_vectors */
+ nr_present = __irq_build_affinity_masks(affd, curvec, numvecs,
+ firstvec, node_to_cpumask,
+ cpu_present_mask, nmsk, masks);
+
+ /*
+ * Spread on non present CPUs starting from the next vector to be
+ * handled. If the spreading of present CPUs already exhausted the
+ * vector space, assign the non present CPUs to the already spread
+ * out vectors.
+ */
+ if (nr_present >= numvecs)
+ curvec = firstvec;
+ else
+ curvec = firstvec + nr_present;
+ cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
+ nr_others = __irq_build_affinity_masks(affd, curvec, numvecs,
+ firstvec, node_to_cpumask,
+ npresmsk, nmsk, masks);
+ put_online_cpus();
+
+ if (nr_present < numvecs)
+ WARN_ON(nr_present + nr_others < numvecs);
+
+ free_cpumask_var(npresmsk);
+
+ fail:
+ free_cpumask_var(nmsk);
+ return ret;
+}
+
/**
* irq_create_affinity_masks - Create affinity masks for multiqueue spreading
* @nvecs: The total number of vectors
* @affd: Description of the affinity requirements
*
- * Returns the masks pointer or NULL if allocation failed.
+ * Returns the irq_affinity_desc pointer or NULL if allocation failed.
*/
-struct cpumask *
+struct irq_affinity_desc *
irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
{
int affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
int curvec, usedvecs;
- cpumask_var_t nmsk, npresmsk, *node_to_cpumask;
- struct cpumask *masks = NULL;
+ cpumask_var_t *node_to_cpumask;
+ struct irq_affinity_desc *masks = NULL;
+ int i, nr_sets;
/*
* If there aren't any vectors left after applying the pre/post
@@ -188,15 +247,9 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
if (nvecs == affd->pre_vectors + affd->post_vectors)
return NULL;
- if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
- return NULL;
-
- if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
- goto outcpumsk;
-
node_to_cpumask = alloc_node_to_cpumask();
if (!node_to_cpumask)
- goto outnpresmsk;
+ return NULL;
masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL);
if (!masks)
@@ -204,32 +257,29 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
/* Fill out vectors at the beginning that don't need affinity */
for (curvec = 0; curvec < affd->pre_vectors; curvec++)
- cpumask_copy(masks + curvec, irq_default_affinity);
-
- /* Stabilize the cpumasks */
- get_online_cpus();
- build_node_to_cpumask(node_to_cpumask);
-
- /* Spread on present CPUs starting from affd->pre_vectors */
- usedvecs = irq_build_affinity_masks(affd, curvec, affvecs,
- node_to_cpumask, cpu_present_mask,
- nmsk, masks);
-
+ cpumask_copy(&masks[curvec].mask, irq_default_affinity);
/*
- * Spread on non present CPUs starting from the next vector to be
- * handled. If the spreading of present CPUs already exhausted the
- * vector space, assign the non present CPUs to the already spread
- * out vectors.
+ * Spread on present CPUs starting from affd->pre_vectors. If we
+ * have multiple sets, build each sets affinity mask separately.
*/
- if (usedvecs >= affvecs)
- curvec = affd->pre_vectors;
- else
- curvec = affd->pre_vectors + usedvecs;
- cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
- usedvecs += irq_build_affinity_masks(affd, curvec, affvecs,
- node_to_cpumask, npresmsk,
- nmsk, masks);
- put_online_cpus();
+ nr_sets = affd->nr_sets;
+ if (!nr_sets)
+ nr_sets = 1;
+
+ for (i = 0, usedvecs = 0; i < nr_sets; i++) {
+ int this_vecs = affd->sets ? affd->sets[i] : affvecs;
+ int ret;
+
+ ret = irq_build_affinity_masks(affd, curvec, this_vecs,
+ curvec, node_to_cpumask, masks);
+ if (ret) {
+ kfree(masks);
+ masks = NULL;
+ goto outnodemsk;
+ }
+ curvec += this_vecs;
+ usedvecs += this_vecs;
+ }
/* Fill out vectors at the end that don't need affinity */
if (usedvecs >= affvecs)
@@ -237,14 +287,14 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
else
curvec = affd->pre_vectors + usedvecs;
for (; curvec < nvecs; curvec++)
- cpumask_copy(masks + curvec, irq_default_affinity);
+ cpumask_copy(&masks[curvec].mask, irq_default_affinity);
+
+ /* Mark the managed interrupts */
+ for (i = affd->pre_vectors; i < nvecs - affd->post_vectors; i++)
+ masks[i].is_managed = 1;
outnodemsk:
free_node_to_cpumask(node_to_cpumask);
-outnpresmsk:
- free_cpumask_var(npresmsk);
-outcpumsk:
- free_cpumask_var(nmsk);
return masks;
}
@@ -258,13 +308,21 @@ int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity
{
int resv = affd->pre_vectors + affd->post_vectors;
int vecs = maxvec - resv;
- int ret;
+ int set_vecs;
if (resv > minvec)
return 0;
- get_online_cpus();
- ret = min_t(int, cpumask_weight(cpu_possible_mask), vecs) + resv;
- put_online_cpus();
- return ret;
+ if (affd->nr_sets) {
+ int i;
+
+ for (i = 0, set_vecs = 0; i < affd->nr_sets; i++)
+ set_vecs += affd->sets[i];
+ } else {
+ get_online_cpus();
+ set_vecs = cpumask_weight(cpu_possible_mask);
+ put_online_cpus();
+ }
+
+ return resv + min(set_vecs, vecs);
}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index a2b3d9de999c..34e969069488 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -929,7 +929,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
break;
/*
* Bail out if the outer chip is not set up
- * and the interrrupt supposed to be started
+ * and the interrupt supposed to be started
* right away.
*/
if (WARN_ON(is_chained))
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index 6a682c229e10..5d5378ea0afe 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -169,7 +169,7 @@ static void devm_irq_desc_release(struct device *dev, void *res)
* @cnt: Number of consecutive irqs to allocate
* @node: Preferred node on which the irq descriptor should be allocated
* @owner: Owning module (can be NULL)
- * @affinity: Optional pointer to an affinity mask array of size @cnt
+ * @affinity: Optional pointer to an irq_affinity_desc array of size @cnt
* which hints where the irq descriptors should be allocated
* and which default affinities to use
*
@@ -179,7 +179,7 @@ static void devm_irq_desc_release(struct device *dev, void *res)
*/
int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
unsigned int cnt, int node, struct module *owner,
- const struct cpumask *affinity)
+ const struct irq_affinity_desc *affinity)
{
struct irq_desc_devres *dr;
int base;
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index 8b778e37dc6d..43e3d1be622c 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -56,7 +56,7 @@ int irq_reserve_ipi(struct irq_domain *domain,
unsigned int next;
/*
- * The IPI requires a seperate HW irq on each CPU. We require
+ * The IPI requires a separate HW irq on each CPU. We require
* that the destination mask is consecutive. If an
* implementation needs to support holes, it can reserve
* several IPI ranges.
@@ -172,7 +172,7 @@ irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu)
/*
* Get the real hardware irq number if the underlying implementation
- * uses a seperate irq per cpu. If the underlying implementation uses
+ * uses a separate irq per cpu. If the underlying implementation uses
* a single hardware irq for all cpus then the IPI send mechanism
* needs to take care of the cpu destinations.
*/
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index dd20d0d528d4..98a20e1594ce 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -34,9 +34,20 @@ static struct irq_chip irq_sim_irqchip = {
static void irq_sim_handle_irq(struct irq_work *work)
{
struct irq_sim_work_ctx *work_ctx;
+ unsigned int offset = 0;
+ struct irq_sim *sim;
+ int irqnum;
work_ctx = container_of(work, struct irq_sim_work_ctx, work);
- handle_simple_irq(irq_to_desc(work_ctx->irq));
+ sim = container_of(work_ctx, struct irq_sim, work_ctx);
+
+ while (!bitmap_empty(work_ctx->pending, sim->irq_count)) {
+ offset = find_next_bit(work_ctx->pending,
+ sim->irq_count, offset);
+ clear_bit(offset, work_ctx->pending);
+ irqnum = irq_sim_irqnum(sim, offset);
+ handle_simple_irq(irq_to_desc(irqnum));
+ }
}
/**
@@ -63,6 +74,13 @@ int irq_sim_init(struct irq_sim *sim, unsigned int num_irqs)
return sim->irq_base;
}
+ sim->work_ctx.pending = bitmap_zalloc(num_irqs, GFP_KERNEL);
+ if (!sim->work_ctx.pending) {
+ kfree(sim->irqs);
+ irq_free_descs(sim->irq_base, num_irqs);
+ return -ENOMEM;
+ }
+
for (i = 0; i < num_irqs; i++) {
sim->irqs[i].irqnum = sim->irq_base + i;
sim->irqs[i].enabled = false;
@@ -89,6 +107,7 @@ EXPORT_SYMBOL_GPL(irq_sim_init);
void irq_sim_fini(struct irq_sim *sim)
{
irq_work_sync(&sim->work_ctx.work);
+ bitmap_free(sim->work_ctx.pending);
irq_free_descs(sim->irq_base, sim->irq_count);
kfree(sim->irqs);
}
@@ -143,7 +162,7 @@ EXPORT_SYMBOL_GPL(devm_irq_sim_init);
void irq_sim_fire(struct irq_sim *sim, unsigned int offset)
{
if (sim->irqs[offset].enabled) {
- sim->work_ctx.irq = irq_sim_irqnum(sim, offset);
+ set_bit(offset, sim->work_ctx.pending);
irq_work_queue(&sim->work_ctx.work);
}
}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 578d0e5f1b5b..ee062b7939d3 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -449,30 +449,34 @@ static void free_desc(unsigned int irq)
}
static int alloc_descs(unsigned int start, unsigned int cnt, int node,
- const struct cpumask *affinity, struct module *owner)
+ const struct irq_affinity_desc *affinity,
+ struct module *owner)
{
- const struct cpumask *mask = NULL;
struct irq_desc *desc;
- unsigned int flags;
int i;
/* Validate affinity mask(s) */
if (affinity) {
- for (i = 0, mask = affinity; i < cnt; i++, mask++) {
- if (cpumask_empty(mask))
+ for (i = 0; i < cnt; i++, i++) {
+ if (cpumask_empty(&affinity[i].mask))
return -EINVAL;
}
}
- flags = affinity ? IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN : 0;
- mask = NULL;
-
for (i = 0; i < cnt; i++) {
+ const struct cpumask *mask = NULL;
+ unsigned int flags = 0;
+
if (affinity) {
- node = cpu_to_node(cpumask_first(affinity));
- mask = affinity;
+ if (affinity->is_managed) {
+ flags = IRQD_AFFINITY_MANAGED |
+ IRQD_MANAGED_SHUTDOWN;
+ }
+ mask = &affinity->mask;
+ node = cpu_to_node(cpumask_first(mask));
affinity++;
}
+
desc = alloc_desc(start + i, node, flags, mask, owner);
if (!desc)
goto err;
@@ -575,7 +579,7 @@ static void free_desc(unsigned int irq)
}
static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
- const struct cpumask *affinity,
+ const struct irq_affinity_desc *affinity,
struct module *owner)
{
u32 i;
@@ -705,7 +709,7 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
*/
int __ref
__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
- struct module *owner, const struct cpumask *affinity)
+ struct module *owner, const struct irq_affinity_desc *affinity)
{
int start, ret;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 3366d11c3e02..8b0be4bd6565 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -969,7 +969,7 @@ const struct irq_domain_ops irq_domain_simple_ops = {
EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq,
- int node, const struct cpumask *affinity)
+ int node, const struct irq_affinity_desc *affinity)
{
unsigned int hint;
@@ -1281,7 +1281,7 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
*/
int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
unsigned int nr_irqs, int node, void *arg,
- bool realloc, const struct cpumask *affinity)
+ bool realloc, const struct irq_affinity_desc *affinity)
{
int i, ret, virq;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9dbdccab3b6a..a4888ce4667a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -915,7 +915,7 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
#endif
/*
- * Interrupts which are not explicitely requested as threaded
+ * Interrupts which are not explicitly requested as threaded
* interrupts rely on the implicit bh/preempt disable of the hard irq
* context. So we need to disable bh here to avoid deadlocks and other
* side effects.
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 6e6d467f3dec..30cc217b8631 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -8,12 +8,13 @@
#include <linux/cpu.h>
#include <linux/irq.h>
-#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS) * sizeof(unsigned long))
+#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS))
struct cpumap {
unsigned int available;
unsigned int allocated;
unsigned int managed;
+ unsigned int managed_allocated;
bool initialized;
bool online;
unsigned long alloc_map[IRQ_MATRIX_SIZE];
@@ -145,6 +146,27 @@ static unsigned int matrix_find_best_cpu(struct irq_matrix *m,
return best_cpu;
}
+/* Find the best CPU which has the lowest number of managed IRQs allocated */
+static unsigned int matrix_find_best_cpu_managed(struct irq_matrix *m,
+ const struct cpumask *msk)
+{
+ unsigned int cpu, best_cpu, allocated = UINT_MAX;
+ struct cpumap *cm;
+
+ best_cpu = UINT_MAX;
+
+ for_each_cpu(cpu, msk) {
+ cm = per_cpu_ptr(m->maps, cpu);
+
+ if (!cm->online || cm->managed_allocated > allocated)
+ continue;
+
+ best_cpu = cpu;
+ allocated = cm->managed_allocated;
+ }
+ return best_cpu;
+}
+
/**
* irq_matrix_assign_system - Assign system wide entry in the matrix
* @m: Matrix pointer
@@ -269,7 +291,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk,
if (cpumask_empty(msk))
return -EINVAL;
- cpu = matrix_find_best_cpu(m, msk);
+ cpu = matrix_find_best_cpu_managed(m, msk);
if (cpu == UINT_MAX)
return -ENOSPC;
@@ -282,6 +304,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk,
return -ENOSPC;
set_bit(bit, cm->alloc_map);
cm->allocated++;
+ cm->managed_allocated++;
m->total_allocated++;
*mapped_cpu = cpu;
trace_irq_matrix_alloc_managed(bit, cpu, m, cm);
@@ -395,6 +418,8 @@ void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
clear_bit(bit, cm->alloc_map);
cm->allocated--;
+ if(managed)
+ cm->managed_allocated--;
if (cm->online)
m->total_allocated--;
@@ -464,13 +489,14 @@ void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind)
seq_printf(sf, "Total allocated: %6u\n", m->total_allocated);
seq_printf(sf, "System: %u: %*pbl\n", nsys, m->matrix_bits,
m->system_map);
- seq_printf(sf, "%*s| CPU | avl | man | act | vectors\n", ind, " ");
+ seq_printf(sf, "%*s| CPU | avl | man | mac | act | vectors\n", ind, " ");
cpus_read_lock();
for_each_online_cpu(cpu) {
struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
- seq_printf(sf, "%*s %4d %4u %4u %4u %*pbl\n", ind, " ",
- cpu, cm->available, cm->managed, cm->allocated,
+ seq_printf(sf, "%*s %4d %4u %4u %4u %4u %*pbl\n", ind, " ",
+ cpu, cm->available, cm->managed,
+ cm->managed_allocated, cm->allocated,
m->matrix_bits, cm->alloc_map);
}
cpus_read_unlock();
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 4ca2fd46645d..ad26fbcfbfc8 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -23,11 +23,11 @@
* @nvec: The number of vectors used in this entry
* @affinity: Optional pointer to an affinity mask array size of @nvec
*
- * If @affinity is not NULL then a an affinity array[@nvec] is allocated
- * and the affinity masks from @affinity are copied.
+ * If @affinity is not NULL then an affinity array[@nvec] is allocated
+ * and the affinity masks and flags from @affinity are copied.
*/
-struct msi_desc *
-alloc_msi_entry(struct device *dev, int nvec, const struct cpumask *affinity)
+struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
+ const struct irq_affinity_desc *affinity)
{
struct msi_desc *desc;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index d867d6ddafdd..6d2fa6914b30 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -66,7 +66,7 @@ static int try_one_irq(struct irq_desc *desc, bool force)
raw_spin_lock(&desc->lock);
/*
- * PER_CPU, nested thread interrupts and interrupts explicitely
+ * PER_CPU, nested thread interrupts and interrupts explicitly
* marked polled are excluded from polling.
*/
if (irq_settings_is_per_cpu(desc) ||
@@ -76,7 +76,7 @@ static int try_one_irq(struct irq_desc *desc, bool force)
/*
* Do not poll disabled interrupts unless the spurious
- * disabled poller asks explicitely.
+ * disabled poller asks explicitly.
*/
if (irqd_irq_disabled(&desc->irq_data) && !force)
goto out;
@@ -292,7 +292,7 @@ void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret)
* So in case a thread is woken, we just note the fact and
* defer the analysis to the next hardware interrupt.
*
- * The threaded handlers store whether they sucessfully
+ * The threaded handlers store whether they successfully
* handled an interrupt and we check whether that number
* changed versus the last invocation.
*
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 02a0b01380d8..f3a04994e063 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -37,7 +37,7 @@ extern const u8 kallsyms_names[] __weak;
* Tell the compiler that the count isn't in the small data section if the arch
* has one (eg: FRV).
*/
-extern const unsigned long kallsyms_num_syms
+extern const unsigned int kallsyms_num_syms
__attribute__((weak, section(".rodata")));
extern const unsigned long kallsyms_relative_base
@@ -46,7 +46,7 @@ __attribute__((weak, section(".rodata")));
extern const u8 kallsyms_token_table[] __weak;
extern const u16 kallsyms_token_index[] __weak;
-extern const unsigned long kallsyms_markers[] __weak;
+extern const unsigned int kallsyms_markers[] __weak;
/*
* Expand a compressed symbol data into the resulting uncompressed string,
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 3ebd09efe72a..97959d7b77e2 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -56,7 +56,7 @@ struct kcov {
struct task_struct *t;
};
-static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
+static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
{
unsigned int mode;
@@ -78,7 +78,7 @@ static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
return mode == needed_mode;
}
-static unsigned long canonicalize_ip(unsigned long ip)
+static notrace unsigned long canonicalize_ip(unsigned long ip)
{
#ifdef CONFIG_RANDOMIZE_BASE
ip -= kaslr_offset();
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index c6a3b6851372..f1d0e00a3971 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -16,6 +16,7 @@
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/kexec.h>
+#include <linux/memblock.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/fs.h>
@@ -25,8 +26,6 @@
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/kernel.h>
-#include <linux/kexec.h>
-#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/vmalloc.h>
#include "kexec_internal.h"
@@ -78,7 +77,7 @@ void * __weak arch_kexec_kernel_image_load(struct kimage *image)
return kexec_image_load_default(image);
}
-static int kexec_image_post_load_cleanup_default(struct kimage *image)
+int kexec_image_post_load_cleanup_default(struct kimage *image)
{
if (!image->fops || !image->fops->cleanup)
return 0;
@@ -501,8 +500,60 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
return locate_mem_hole_bottom_up(start, end, kbuf);
}
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+static int kexec_walk_memblock(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
+{
+ return 0;
+}
+#else
+static int kexec_walk_memblock(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
+{
+ int ret = 0;
+ u64 i;
+ phys_addr_t mstart, mend;
+ struct resource res = { };
+
+ if (kbuf->image->type == KEXEC_TYPE_CRASH)
+ return func(&crashk_res, kbuf);
+
+ if (kbuf->top_down) {
+ for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+ &mstart, &mend, NULL) {
+ /*
+ * In memblock, end points to the first byte after the
+ * range while in kexec, end points to the last byte
+ * in the range.
+ */
+ res.start = mstart;
+ res.end = mend - 1;
+ ret = func(&res, kbuf);
+ if (ret)
+ break;
+ }
+ } else {
+ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+ &mstart, &mend, NULL) {
+ /*
+ * In memblock, end points to the first byte after the
+ * range while in kexec, end points to the last byte
+ * in the range.
+ */
+ res.start = mstart;
+ res.end = mend - 1;
+ ret = func(&res, kbuf);
+ if (ret)
+ break;
+ }
+ }
+
+ return ret;
+}
+#endif
+
/**
- * arch_kexec_walk_mem - call func(data) on free memory regions
+ * kexec_walk_resources - call func(data) on free memory regions
* @kbuf: Context info for the search. Also passed to @func.
* @func: Function to call for each memory region.
*
@@ -510,8 +561,8 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
* and that value will be returned. If all free regions are visited without
* func returning non-zero, then zero will be returned.
*/
-int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
- int (*func)(struct resource *, void *))
+static int kexec_walk_resources(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
{
if (kbuf->image->type == KEXEC_TYPE_CRASH)
return walk_iomem_res_desc(crashk_res.desc,
@@ -534,7 +585,14 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
{
int ret;
- ret = arch_kexec_walk_mem(kbuf, locate_mem_hole_callback);
+ /* Arch knows where to place */
+ if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN)
+ return 0;
+
+ if (IS_ENABLED(CONFIG_ARCH_DISCARD_MEMBLOCK))
+ ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
+ else
+ ret = kexec_walk_memblock(kbuf, locate_mem_hole_callback);
return ret == 1 ? 0 : -EADDRNOTAVAIL;
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 90e98e233647..f4ddfdd2d07e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -229,7 +229,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c)
struct kprobe_insn_page *kip, *next;
/* Ensure no-one is interrupted on the garbages */
- synchronize_sched();
+ synchronize_rcu();
list_for_each_entry_safe(kip, next, &c->pages, list) {
int i;
@@ -1382,7 +1382,7 @@ out:
if (ret) {
ap->flags |= KPROBE_FLAG_DISABLED;
list_del_rcu(&p->list);
- synchronize_sched();
+ synchronize_rcu();
}
}
}
@@ -1597,7 +1597,7 @@ int register_kprobe(struct kprobe *p)
ret = arm_kprobe(p);
if (ret) {
hlist_del_rcu(&p->hlist);
- synchronize_sched();
+ synchronize_rcu();
goto out;
}
}
@@ -1776,7 +1776,7 @@ void unregister_kprobes(struct kprobe **kps, int num)
kps[i]->addr = NULL;
mutex_unlock(&kprobe_mutex);
- synchronize_sched();
+ synchronize_rcu();
for (i = 0; i < num; i++)
if (kps[i]->addr)
__unregister_kprobe_bottom(kps[i]);
@@ -1966,7 +1966,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
rps[i]->kp.addr = NULL;
mutex_unlock(&kprobe_mutex);
- synchronize_sched();
+ synchronize_rcu();
for (i = 0; i < num; i++) {
if (rps[i]->kp.addr) {
__unregister_kprobe_bottom(&rps[i]->kp);
@@ -2093,6 +2093,47 @@ void dump_kprobe(struct kprobe *kp)
}
NOKPROBE_SYMBOL(dump_kprobe);
+int kprobe_add_ksym_blacklist(unsigned long entry)
+{
+ struct kprobe_blacklist_entry *ent;
+ unsigned long offset = 0, size = 0;
+
+ if (!kernel_text_address(entry) ||
+ !kallsyms_lookup_size_offset(entry, &size, &offset))
+ return -EINVAL;
+
+ ent = kmalloc(sizeof(*ent), GFP_KERNEL);
+ if (!ent)
+ return -ENOMEM;
+ ent->start_addr = entry;
+ ent->end_addr = entry + size;
+ INIT_LIST_HEAD(&ent->list);
+ list_add_tail(&ent->list, &kprobe_blacklist);
+
+ return (int)size;
+}
+
+/* Add all symbols in given area into kprobe blacklist */
+int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
+{
+ unsigned long entry;
+ int ret = 0;
+
+ for (entry = start; entry < end; entry += ret) {
+ ret = kprobe_add_ksym_blacklist(entry);
+ if (ret < 0)
+ return ret;
+ if (ret == 0) /* In case of alias symbol */
+ ret = 1;
+ }
+ return 0;
+}
+
+int __init __weak arch_populate_kprobe_blacklist(void)
+{
+ return 0;
+}
+
/*
* Lookup and populate the kprobe_blacklist.
*
@@ -2104,26 +2145,24 @@ NOKPROBE_SYMBOL(dump_kprobe);
static int __init populate_kprobe_blacklist(unsigned long *start,
unsigned long *end)
{
+ unsigned long entry;
unsigned long *iter;
- struct kprobe_blacklist_entry *ent;
- unsigned long entry, offset = 0, size = 0;
+ int ret;
for (iter = start; iter < end; iter++) {
entry = arch_deref_entry_point((void *)*iter);
-
- if (!kernel_text_address(entry) ||
- !kallsyms_lookup_size_offset(entry, &size, &offset))
+ ret = kprobe_add_ksym_blacklist(entry);
+ if (ret == -EINVAL)
continue;
-
- ent = kmalloc(sizeof(*ent), GFP_KERNEL);
- if (!ent)
- return -ENOMEM;
- ent->start_addr = entry;
- ent->end_addr = entry + size;
- INIT_LIST_HEAD(&ent->list);
- list_add_tail(&ent->list, &kprobe_blacklist);
+ if (ret < 0)
+ return ret;
}
- return 0;
+
+ /* Symbols in __kprobes_text are blacklisted */
+ ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start,
+ (unsigned long)__kprobes_text_end);
+
+ return ret ? : arch_populate_kprobe_blacklist();
}
/* Module notifier call back, checking kprobes on the module */
diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
index 82d584225dc6..7702cb4064fc 100644
--- a/kernel/livepatch/patch.c
+++ b/kernel/livepatch/patch.c
@@ -61,7 +61,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
ops = container_of(fops, struct klp_ops, fops);
/*
- * A variant of synchronize_sched() is used to allow patching functions
+ * A variant of synchronize_rcu() is used to allow patching functions
* where RCU is not watching, see klp_synchronize_transition().
*/
preempt_disable_notrace();
@@ -72,7 +72,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
/*
* func should never be NULL because preemption should be disabled here
* and unregister_ftrace_function() does the equivalent of a
- * synchronize_sched() before the func_stack removal.
+ * synchronize_rcu() before the func_stack removal.
*/
if (WARN_ON_ONCE(!func))
goto unlock;
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 5bc349805e03..304d5eb8a98c 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -52,7 +52,7 @@ static DECLARE_DELAYED_WORK(klp_transition_work, klp_transition_work_fn);
/*
* This function is just a stub to implement a hard force
- * of synchronize_sched(). This requires synchronizing
+ * of synchronize_rcu(). This requires synchronizing
* tasks even in userspace and idle.
*/
static void klp_sync(struct work_struct *work)
@@ -175,7 +175,7 @@ void klp_cancel_transition(void)
void klp_update_patch_state(struct task_struct *task)
{
/*
- * A variant of synchronize_sched() is used to allow patching functions
+ * A variant of synchronize_rcu() is used to allow patching functions
* where RCU is not watching, see klp_synchronize_transition().
*/
preempt_disable_notrace();
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 1efada2dd9dd..95932333a48b 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -138,6 +138,9 @@ static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
* get freed - this significantly simplifies the debugging code.
*/
unsigned long nr_lock_classes;
+#ifndef CONFIG_DEBUG_LOCKDEP
+static
+#endif
struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
static inline struct lock_class *hlock_class(struct held_lock *hlock)
@@ -626,7 +629,8 @@ static int static_obj(void *obj)
/*
* To make lock name printouts unique, we calculate a unique
- * class->name_version generation counter:
+ * class->name_version generation counter. The caller must hold the graph
+ * lock.
*/
static int count_matching_names(struct lock_class *new_class)
{
@@ -636,7 +640,7 @@ static int count_matching_names(struct lock_class *new_class)
if (!new_class->name)
return 0;
- list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) {
+ list_for_each_entry(class, &all_lock_classes, lock_entry) {
if (new_class->key - new_class->subclass == class->key)
return class->name_version;
if (class->name && !strcmp(class->name, new_class->name))
@@ -789,7 +793,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
class->key = key;
class->name = lock->name;
class->subclass = subclass;
- INIT_LIST_HEAD(&class->lock_entry);
INIT_LIST_HEAD(&class->locks_before);
INIT_LIST_HEAD(&class->locks_after);
class->name_version = count_matching_names(class);
@@ -801,7 +804,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
/*
* Add it to the global list of classes:
*/
- list_add_tail_rcu(&class->lock_entry, &all_lock_classes);
+ list_add_tail(&class->lock_entry, &all_lock_classes);
if (verbose(class)) {
graph_unlock();
@@ -3088,7 +3091,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
/*
* Initialize a lock instance's lock-class mapping info:
*/
-static void __lockdep_init_map(struct lockdep_map *lock, const char *name,
+void lockdep_init_map(struct lockdep_map *lock, const char *name,
struct lock_class_key *key, int subclass)
{
int i;
@@ -3144,12 +3147,6 @@ static void __lockdep_init_map(struct lockdep_map *lock, const char *name,
raw_local_irq_restore(flags);
}
}
-
-void lockdep_init_map(struct lockdep_map *lock, const char *name,
- struct lock_class_key *key, int subclass)
-{
- __lockdep_init_map(lock, name, key, subclass);
-}
EXPORT_SYMBOL_GPL(lockdep_init_map);
struct lock_class_key __lockdep_no_validate__;
@@ -4126,6 +4123,9 @@ void lockdep_reset(void)
raw_local_irq_restore(flags);
}
+/*
+ * Remove all references to a lock class. The caller must hold the graph lock.
+ */
static void zap_class(struct lock_class *class)
{
int i;
@@ -4142,7 +4142,7 @@ static void zap_class(struct lock_class *class)
* Unhash the class and remove it from the all_lock_classes list:
*/
hlist_del_rcu(&class->hash_entry);
- list_del_rcu(&class->lock_entry);
+ list_del(&class->lock_entry);
RCU_INIT_POINTER(class->key, NULL);
RCU_INIT_POINTER(class->name, NULL);
@@ -4195,7 +4195,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
*
* sync_sched() is sufficient because the read-side is IRQ disable.
*/
- synchronize_sched();
+ synchronize_rcu();
/*
* XXX at this point we could return the resources to the pool;
@@ -4204,15 +4204,36 @@ void lockdep_free_key_range(void *start, unsigned long size)
*/
}
-void lockdep_reset_lock(struct lockdep_map *lock)
+/*
+ * Check whether any element of the @lock->class_cache[] array refers to a
+ * registered lock class. The caller must hold either the graph lock or the
+ * RCU read lock.
+ */
+static bool lock_class_cache_is_registered(struct lockdep_map *lock)
{
struct lock_class *class;
struct hlist_head *head;
- unsigned long flags;
int i, j;
- int locked;
+
+ for (i = 0; i < CLASSHASH_SIZE; i++) {
+ head = classhash_table + i;
+ hlist_for_each_entry_rcu(class, head, hash_entry) {
+ for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
+ if (lock->class_cache[j] == class)
+ return true;
+ }
+ }
+ return false;
+}
+
+void lockdep_reset_lock(struct lockdep_map *lock)
+{
+ struct lock_class *class;
+ unsigned long flags;
+ int j, locked;
raw_local_irq_save(flags);
+ locked = graph_lock();
/*
* Remove all classes this lock might have:
@@ -4229,25 +4250,14 @@ void lockdep_reset_lock(struct lockdep_map *lock)
* Debug check: in the end all mapped classes should
* be gone.
*/
- locked = graph_lock();
- for (i = 0; i < CLASSHASH_SIZE; i++) {
- head = classhash_table + i;
- hlist_for_each_entry_rcu(class, head, hash_entry) {
- int match = 0;
-
- for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
- match |= class == lock->class_cache[j];
-
- if (unlikely(match)) {
- if (debug_locks_off_graph_unlock()) {
- /*
- * We all just reset everything, how did it match?
- */
- WARN_ON(1);
- }
- goto out_restore;
- }
+ if (unlikely(lock_class_cache_is_registered(lock))) {
+ if (debug_locks_off_graph_unlock()) {
+ /*
+ * We all just reset everything, how did it match?
+ */
+ WARN_ON(1);
}
+ goto out_restore;
}
if (locked)
graph_unlock();
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 9aa713629387..771d4ca96dda 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -36,7 +36,7 @@ void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter)
void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter)
{
- SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
+ lockdep_assert_held(&lock->wait_lock);
DEBUG_LOCKS_WARN_ON(list_empty(&lock->wait_list));
DEBUG_LOCKS_WARN_ON(waiter->magic != waiter);
DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
@@ -51,7 +51,7 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter)
void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
struct task_struct *task)
{
- SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
+ lockdep_assert_held(&lock->wait_lock);
/* Mark the current thread as blocked on the lock: */
task->blocked_on = waiter;
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 0130e488ebfe..8f36c27c1794 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -4,7 +4,7 @@
#endif
#include <linux/hash.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/debug_locks.h>
/*
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5b8600d39931..9eced2cc9f94 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -1,47 +1,21 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
-#include <linux/radix-tree.h>
#include <linux/device.h>
-#include <linux/types.h>
-#include <linux/pfn_t.h>
#include <linux/io.h>
#include <linux/kasan.h>
-#include <linux/mm.h>
#include <linux/memory_hotplug.h>
+#include <linux/mm.h>
+#include <linux/pfn_t.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/types.h>
#include <linux/wait_bit.h>
+#include <linux/xarray.h>
-static DEFINE_MUTEX(pgmap_lock);
-static RADIX_TREE(pgmap_radix, GFP_KERNEL);
+static DEFINE_XARRAY(pgmap_array);
#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
-static unsigned long order_at(struct resource *res, unsigned long pgoff)
-{
- unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
- unsigned long nr_pages, mask;
-
- nr_pages = PHYS_PFN(resource_size(res));
- if (nr_pages == pgoff)
- return ULONG_MAX;
-
- /*
- * What is the largest aligned power-of-2 range available from
- * this resource pgoff to the end of the resource range,
- * considering the alignment of the current pgoff?
- */
- mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
- if (!mask)
- return ULONG_MAX;
-
- return find_first_bit(&mask, BITS_PER_LONG);
-}
-
-#define foreach_order_pgoff(res, order, pgoff) \
- for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
- pgoff += 1UL << order, order = order_at((res), pgoff))
-
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
unsigned long addr,
@@ -70,18 +44,10 @@ vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
EXPORT_SYMBOL(device_private_entry_fault);
#endif /* CONFIG_DEVICE_PRIVATE */
-static void pgmap_radix_release(struct resource *res, unsigned long end_pgoff)
+static void pgmap_array_delete(struct resource *res)
{
- unsigned long pgoff, order;
-
- mutex_lock(&pgmap_lock);
- foreach_order_pgoff(res, order, pgoff) {
- if (pgoff >= end_pgoff)
- break;
- radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
- }
- mutex_unlock(&pgmap_lock);
-
+ xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
+ NULL, GFP_KERNEL);
synchronize_rcu();
}
@@ -142,7 +108,7 @@ static void devm_memremap_pages_release(void *data)
mem_hotplug_done();
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
- pgmap_radix_release(res, -1);
+ pgmap_array_delete(res);
dev_WARN_ONCE(dev, pgmap->altmap.alloc,
"%s: failed to free all reserved pages\n", __func__);
}
@@ -175,10 +141,9 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
struct vmem_altmap *altmap = pgmap->altmap_valid ?
&pgmap->altmap : NULL;
struct resource *res = &pgmap->res;
- unsigned long pfn, pgoff, order;
+ struct dev_pagemap *conflict_pgmap;
pgprot_t pgprot = PAGE_KERNEL;
int error, nid, is_ram;
- struct dev_pagemap *conflict_pgmap;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -216,20 +181,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
pgmap->dev = dev;
- mutex_lock(&pgmap_lock);
- error = 0;
-
- foreach_order_pgoff(res, order, pgoff) {
- error = __radix_tree_insert(&pgmap_radix,
- PHYS_PFN(res->start) + pgoff, order, pgmap);
- if (error) {
- dev_err(dev, "%s: failed: %d\n", __func__, error);
- break;
- }
- }
- mutex_unlock(&pgmap_lock);
+ error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
+ PHYS_PFN(res->end), pgmap, GFP_KERNEL));
if (error)
- goto err_radix;
+ goto err_array;
nid = dev_to_node(dev);
if (nid < 0)
@@ -256,19 +211,14 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
if (error)
goto err_add_memory;
- for_each_device_pfn(pfn, pgmap) {
- struct page *page = pfn_to_page(pfn);
-
- /*
- * ZONE_DEVICE pages union ->lru with a ->pgmap back
- * pointer. It is a bug if a ZONE_DEVICE page is ever
- * freed or placed on a driver-private list. Seed the
- * storage with LIST_POISON* values.
- */
- list_del(&page->lru);
- page->pgmap = pgmap;
- percpu_ref_get(pgmap->ref);
- }
+ /*
+ * Initialization of the pages has been deferred until now in order
+ * to allow us to do the work while not holding the hotplug lock.
+ */
+ memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
+ align_start >> PAGE_SHIFT,
+ align_size >> PAGE_SHIFT, pgmap);
+ percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
devm_add_action(dev, devm_memremap_pages_release, pgmap);
@@ -279,8 +229,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
err_kasan:
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
err_pfn_remap:
- err_radix:
- pgmap_radix_release(res, pgoff);
+ pgmap_array_delete(res);
+ err_array:
return ERR_PTR(error);
}
EXPORT_SYMBOL(devm_memremap_pages);
@@ -320,7 +270,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
/* fall back to slow path lookup */
rcu_read_lock();
- pgmap = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
+ pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
pgmap = NULL;
rcu_read_unlock();
diff --git a/kernel/module.c b/kernel/module.c
index 49a405891587..99b46c32d579 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2159,7 +2159,7 @@ static void free_module(struct module *mod)
/* Remove this module from bug list, this uses list_del_rcu */
module_bug_cleanup(mod);
/* Wait for RCU-sched synchronizing before releasing mod->list and buglist. */
- synchronize_sched();
+ synchronize_rcu();
mutex_unlock(&module_mutex);
/* This may be empty, but that's OK */
@@ -3507,15 +3507,15 @@ static noinline int do_init_module(struct module *mod)
/*
* We want to free module_init, but be aware that kallsyms may be
* walking this with preempt disabled. In all the failure paths, we
- * call synchronize_sched(), but we don't want to slow down the success
+ * call synchronize_rcu(), but we don't want to slow down the success
* path, so use actual RCU here.
* Note that module_alloc() on most architectures creates W+X page
* mappings which won't be cleaned up until do_free_init() runs. Any
* code such as mark_rodata_ro() which depends on those mappings to
* be cleaned up needs to sync with the queued work - ie
- * rcu_barrier_sched()
+ * rcu_barrier()
*/
- call_rcu_sched(&freeinit->rcu, do_free_init);
+ call_rcu(&freeinit->rcu, do_free_init);
mutex_unlock(&module_mutex);
wake_up_all(&module_wq);
@@ -3526,7 +3526,7 @@ fail_free_freeinit:
fail:
/* Try to protect us from buggy refcounters. */
mod->state = MODULE_STATE_GOING;
- synchronize_sched();
+ synchronize_rcu();
module_put(mod);
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_GOING, mod);
@@ -3819,7 +3819,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
ddebug_cleanup:
ftrace_release_mod(mod);
dynamic_debug_remove(mod, info->debug);
- synchronize_sched();
+ synchronize_rcu();
kfree(mod->args);
free_arch_cleanup:
module_arch_cleanup(mod);
@@ -3834,7 +3834,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
mod_tree_remove(mod);
wake_up_all(&module_wq);
/* Wait for RCU-sched synchronizing before releasing mod->list. */
- synchronize_sched();
+ synchronize_rcu();
mutex_unlock(&module_mutex);
free_module:
/* Free lock-classes; relies on the preceding sync_rcu() */
diff --git a/kernel/panic.c b/kernel/panic.c
index 6a6df23acd1a..d10c340c43b0 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -137,7 +137,7 @@ void panic(const char *fmt, ...)
{
static char buf[1024];
va_list args;
- long i, i_next = 0;
+ long i, i_next = 0, len;
int state = 0;
int old_cpu, this_cpu;
bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;
@@ -174,8 +174,12 @@ void panic(const char *fmt, ...)
console_verbose();
bust_spinlocks(1);
va_start(args, fmt);
- vsnprintf(buf, sizeof(buf), fmt, args);
+ len = vscnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
+
+ if (len && buf[len - 1] == '\n')
+ buf[len - 1] = '\0';
+
pr_emerg("Kernel panic - not syncing: %s\n", buf);
#ifdef CONFIG_DEBUG_BUGVERBOSE
/*
@@ -635,7 +639,7 @@ device_initcall(register_warn_debugfs);
*/
__visible void __stack_chk_fail(void)
{
- panic("stack-protector: Kernel stack is corrupted in: %pB\n",
+ panic("stack-protector: Kernel stack is corrupted in: %pB",
__builtin_return_address(0));
}
EXPORT_SYMBOL(__stack_chk_fail);
diff --git a/kernel/pid.c b/kernel/pid.c
index cdf63e53a014..b2f6c506035d 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -31,7 +31,7 @@
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rculist.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/hash.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 3a6c2f87699e..f8fe57d1022e 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -298,3 +298,18 @@ config PM_GENERIC_DOMAINS_OF
config CPU_PM
bool
+
+config ENERGY_MODEL
+ bool "Energy Model for CPUs"
+ depends on SMP
+ depends on CPU_FREQ
+ default n
+ help
+ Several subsystems (thermal and/or the task scheduler for example)
+ can leverage information about the energy consumed by CPUs to make
+ smarter decisions. This config option enables the framework from
+ which subsystems can access the energy models.
+
+ The exact usage of the energy model is subsystem-dependent.
+
+ If in doubt, say N.
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index a3f79f0eef36..e7e47d9be1e5 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -15,3 +15,5 @@ obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o
obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
+
+obj-$(CONFIG_ENERGY_MODEL) += energy_model.o
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
new file mode 100644
index 000000000000..d9dc2c38764a
--- /dev/null
+++ b/kernel/power/energy_model.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Energy Model of CPUs
+ *
+ * Copyright (c) 2018, Arm ltd.
+ * Written by: Quentin Perret, Arm ltd.
+ */
+
+#define pr_fmt(fmt) "energy_model: " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/energy_model.h>
+#include <linux/sched/topology.h>
+#include <linux/slab.h>
+
+/* Mapping of each CPU to the performance domain to which it belongs. */
+static DEFINE_PER_CPU(struct em_perf_domain *, em_data);
+
+/*
+ * Mutex serializing the registrations of performance domains and letting
+ * callbacks defined by drivers sleep.
+ */
+static DEFINE_MUTEX(em_pd_mutex);
+
+static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
+ struct em_data_callback *cb)
+{
+ unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
+ unsigned long power, freq, prev_freq = 0;
+ int i, ret, cpu = cpumask_first(span);
+ struct em_cap_state *table;
+ struct em_perf_domain *pd;
+ u64 fmax;
+
+ if (!cb->active_power)
+ return NULL;
+
+ pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
+ if (!pd)
+ return NULL;
+
+ table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL);
+ if (!table)
+ goto free_pd;
+
+ /* Build the list of capacity states for this performance domain */
+ for (i = 0, freq = 0; i < nr_states; i++, freq++) {
+ /*
+ * active_power() is a driver callback which ceils 'freq' to
+ * lowest capacity state of 'cpu' above 'freq' and updates
+ * 'power' and 'freq' accordingly.
+ */
+ ret = cb->active_power(&power, &freq, cpu);
+ if (ret) {
+ pr_err("pd%d: invalid cap. state: %d\n", cpu, ret);
+ goto free_cs_table;
+ }
+
+ /*
+ * We expect the driver callback to increase the frequency for
+ * higher capacity states.
+ */
+ if (freq <= prev_freq) {
+ pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
+ goto free_cs_table;
+ }
+
+ /*
+ * The power returned by active_state() is expected to be
+ * positive, in milli-watts and to fit into 16 bits.
+ */
+ if (!power || power > EM_CPU_MAX_POWER) {
+ pr_err("pd%d: invalid power: %lu\n", cpu, power);
+ goto free_cs_table;
+ }
+
+ table[i].power = power;
+ table[i].frequency = prev_freq = freq;
+
+ /*
+ * The hertz/watts efficiency ratio should decrease as the
+ * frequency grows on sane platforms. But this isn't always
+ * true in practice so warn the user if a higher OPP is more
+ * power efficient than a lower one.
+ */
+ opp_eff = freq / power;
+ if (opp_eff >= prev_opp_eff)
+ pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n",
+ cpu, i, i - 1);
+ prev_opp_eff = opp_eff;
+ }
+
+ /* Compute the cost of each capacity_state. */
+ fmax = (u64) table[nr_states - 1].frequency;
+ for (i = 0; i < nr_states; i++) {
+ table[i].cost = div64_u64(fmax * table[i].power,
+ table[i].frequency);
+ }
+
+ pd->table = table;
+ pd->nr_cap_states = nr_states;
+ cpumask_copy(to_cpumask(pd->cpus), span);
+
+ return pd;
+
+free_cs_table:
+ kfree(table);
+free_pd:
+ kfree(pd);
+
+ return NULL;
+}
+
+/**
+ * em_cpu_get() - Return the performance domain for a CPU
+ * @cpu : CPU to find the performance domain for
+ *
+ * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't
+ * exist.
+ */
+struct em_perf_domain *em_cpu_get(int cpu)
+{
+ return READ_ONCE(per_cpu(em_data, cpu));
+}
+EXPORT_SYMBOL_GPL(em_cpu_get);
+
+/**
+ * em_register_perf_domain() - Register the Energy Model of a performance domain
+ * @span : Mask of CPUs in the performance domain
+ * @nr_states : Number of capacity states to register
+ * @cb : Callback functions providing the data of the Energy Model
+ *
+ * Create Energy Model tables for a performance domain using the callbacks
+ * defined in cb.
+ *
+ * If multiple clients register the same performance domain, all but the first
+ * registration will be ignored.
+ *
+ * Return 0 on success
+ */
+int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
+ struct em_data_callback *cb)
+{
+ unsigned long cap, prev_cap = 0;
+ struct em_perf_domain *pd;
+ int cpu, ret = 0;
+
+ if (!span || !nr_states || !cb)
+ return -EINVAL;
+
+ /*
+ * Use a mutex to serialize the registration of performance domains and
+ * let the driver-defined callback functions sleep.
+ */
+ mutex_lock(&em_pd_mutex);
+
+ for_each_cpu(cpu, span) {
+ /* Make sure we don't register again an existing domain. */
+ if (READ_ONCE(per_cpu(em_data, cpu))) {
+ ret = -EEXIST;
+ goto unlock;
+ }
+
+ /*
+ * All CPUs of a domain must have the same micro-architecture
+ * since they all share the same table.
+ */
+ cap = arch_scale_cpu_capacity(NULL, cpu);
+ if (prev_cap && prev_cap != cap) {
+ pr_err("CPUs of %*pbl must have the same capacity\n",
+ cpumask_pr_args(span));
+ ret = -EINVAL;
+ goto unlock;
+ }
+ prev_cap = cap;
+ }
+
+ /* Create the performance domain and add it to the Energy Model. */
+ pd = em_create_pd(span, nr_states, cb);
+ if (!pd) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+
+ for_each_cpu(cpu, span) {
+ /*
+ * The per-cpu array can be read concurrently from em_cpu_get().
+ * The barrier enforces the ordering needed to make sure readers
+ * can only access well formed em_perf_domain structs.
+ */
+ smp_store_release(per_cpu_ptr(&em_data, cpu), pd);
+ }
+
+ pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span));
+unlock:
+ mutex_unlock(&em_pd_mutex);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(em_register_perf_domain);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 35b50823d83b..98e76cad128b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -318,23 +318,12 @@ static int suspend_stats_show(struct seq_file *s, void *unused)
return 0;
}
-
-static int suspend_stats_open(struct inode *inode, struct file *file)
-{
- return single_open(file, suspend_stats_show, NULL);
-}
-
-static const struct file_operations suspend_stats_operations = {
- .open = suspend_stats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(suspend_stats);
static int __init pm_debugfs_init(void)
{
debugfs_create_file("suspend_stats", S_IFREG | S_IRUGO,
- NULL, NULL, &suspend_stats_operations);
+ NULL, NULL, &suspend_stats_fops);
return 0;
}
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 86d72ffb811b..b7a82502857a 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -184,7 +184,7 @@ static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
c->target_value = value;
}
-static int pm_qos_dbg_show_requests(struct seq_file *s, void *unused)
+static int pm_qos_debug_show(struct seq_file *s, void *unused)
{
struct pm_qos_object *qos = (struct pm_qos_object *)s->private;
struct pm_qos_constraints *c;
@@ -245,18 +245,7 @@ out:
return 0;
}
-static int pm_qos_dbg_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pm_qos_dbg_show_requests,
- inode->i_private);
-}
-
-static const struct file_operations pm_qos_debug_fops = {
- .open = pm_qos_dbg_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(pm_qos_debug);
/**
* pm_qos_update_target - manages the constraints list and calls the notifiers
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 3d37c279c090..b0308a2c6000 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -23,7 +23,7 @@
#include <linux/pm.h>
#include <linux/device.h>
#include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/nmi.h>
#include <linux/syscalls.h>
#include <linux/console.h>
@@ -963,7 +963,8 @@ void __init __register_nosave_region(unsigned long start_pfn,
BUG_ON(!region);
} else {
/* This allocation cannot fail */
- region = memblock_virt_alloc(sizeof(struct nosave_region), 0);
+ region = memblock_alloc(sizeof(struct nosave_region),
+ SMP_CACHE_BYTES);
}
region->start_pfn = start_pfn;
region->end_pfn = end_pfn;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 91db332ccf4d..1306fe0c1dc6 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -31,7 +31,6 @@
#include <linux/delay.h>
#include <linux/smp.h>
#include <linux/security.h>
-#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/syscalls.h>
#include <linux/crash_core.h>
@@ -1125,9 +1124,9 @@ void __init setup_log_buf(int early)
if (early) {
new_log_buf =
- memblock_virt_alloc(new_log_buf_len, LOG_ALIGN);
+ memblock_alloc(new_log_buf_len, LOG_ALIGN);
} else {
- new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len,
+ new_log_buf = memblock_alloc_nopanic(new_log_buf_len,
LOG_ALIGN);
}
diff --git a/kernel/profile.c b/kernel/profile.c
index 9aa2a4445b0d..9c08a2c7cb1d 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -16,7 +16,7 @@
#include <linux/export.h>
#include <linux/profile.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/notifier.h>
#include <linux/mm.h>
#include <linux/cpumask.h>
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 80b34dffdfb9..c2cee9db5204 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -261,9 +261,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
{
- if (mode & PTRACE_MODE_SCHED)
- return false;
-
if (mode & PTRACE_MODE_NOAUDIT)
return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
else
@@ -331,16 +328,9 @@ ok:
!ptrace_has_cap(mm->user_ns, mode)))
return -EPERM;
- if (mode & PTRACE_MODE_SCHED)
- return 0;
return security_ptrace_access_check(task, mode);
}
-bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode)
-{
- return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED);
-}
-
bool ptrace_may_access(struct task_struct *task, unsigned int mode)
{
int err;
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 2866166863f0..a393e24a9195 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -526,12 +526,14 @@ srcu_batches_completed(struct srcu_struct *sp) { return 0; }
static inline void rcu_force_quiescent_state(void) { }
static inline void show_rcu_gp_kthreads(void) { }
static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
+static inline void rcu_fwd_progress_check(unsigned long j) { }
#else /* #ifdef CONFIG_TINY_RCU */
unsigned long rcu_get_gp_seq(void);
unsigned long rcu_exp_batches_completed(void);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
void show_rcu_gp_kthreads(void);
int rcu_get_gp_kthreads_prio(void);
+void rcu_fwd_progress_check(unsigned long j);
void rcu_force_quiescent_state(void);
extern struct workqueue_struct *rcu_gp_wq;
extern struct workqueue_struct *rcu_par_gp_wq;
@@ -539,8 +541,10 @@ extern struct workqueue_struct *rcu_par_gp_wq;
#ifdef CONFIG_RCU_NOCB_CPU
bool rcu_is_nocb_cpu(int cpu);
+void rcu_bind_current_to_nocb(void);
#else
static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
+static inline void rcu_bind_current_to_nocb(void) { }
#endif
#endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 210c77460365..f6e85faa4ff4 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -56,6 +56,7 @@
#include <linux/vmalloc.h>
#include <linux/sched/debug.h>
#include <linux/sched/sysctl.h>
+#include <linux/oom.h>
#include "rcu.h"
@@ -80,13 +81,6 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@jos
/* Must be power of two minus one. */
#define RCUTORTURE_RDR_MAX_SEGS (RCUTORTURE_RDR_MAX_LOOPS + 3)
-torture_param(int, cbflood_inter_holdoff, HZ,
- "Holdoff between floods (jiffies)");
-torture_param(int, cbflood_intra_holdoff, 1,
- "Holdoff between bursts (jiffies)");
-torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
-torture_param(int, cbflood_n_per_burst, 20000,
- "# callbacks per burst in flood");
torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
"Extend readers by disabling bh (1), irqs (2), or preempt (4)");
torture_param(int, fqs_duration, 0,
@@ -138,12 +132,10 @@ module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, srcu, ...)");
static int nrealreaders;
-static int ncbflooders;
static struct task_struct *writer_task;
static struct task_struct **fakewriter_tasks;
static struct task_struct **reader_tasks;
static struct task_struct *stats_task;
-static struct task_struct **cbflood_task;
static struct task_struct *fqs_task;
static struct task_struct *boost_tasks[NR_CPUS];
static struct task_struct *stall_task;
@@ -181,7 +173,6 @@ static long n_rcu_torture_boosts;
static atomic_long_t n_rcu_torture_timers;
static long n_barrier_attempts;
static long n_barrier_successes; /* did rcu_barrier test succeed? */
-static atomic_long_t n_cbfloods;
static struct list_head rcu_torture_removed;
static int rcu_torture_writer_state;
@@ -259,6 +250,8 @@ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */
static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
+static bool rcu_fwd_cb_nodelay; /* Short rcu_torture_delay() delays. */
+
/*
* Allocate an element from the rcu_tortures pool.
*/
@@ -348,7 +341,8 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
* period, and we want a long delay occasionally to trigger
* force_quiescent_state. */
- if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
+ if (!rcu_fwd_cb_nodelay &&
+ !(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
started = cur_ops->get_gp_seq();
ts = rcu_trace_clock_local();
if (preempt_count() & (SOFTIRQ_MASK | HARDIRQ_MASK))
@@ -870,59 +864,6 @@ checkwait: stutter_wait("rcu_torture_boost");
return 0;
}
-static void rcu_torture_cbflood_cb(struct rcu_head *rhp)
-{
-}
-
-/*
- * RCU torture callback-flood kthread. Repeatedly induces bursts of calls
- * to call_rcu() or analogous, increasing the probability of occurrence
- * of callback-overflow corner cases.
- */
-static int
-rcu_torture_cbflood(void *arg)
-{
- int err = 1;
- int i;
- int j;
- struct rcu_head *rhp;
-
- if (cbflood_n_per_burst > 0 &&
- cbflood_inter_holdoff > 0 &&
- cbflood_intra_holdoff > 0 &&
- cur_ops->call &&
- cur_ops->cb_barrier) {
- rhp = vmalloc(array3_size(cbflood_n_burst,
- cbflood_n_per_burst,
- sizeof(*rhp)));
- err = !rhp;
- }
- if (err) {
- VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM");
- goto wait_for_stop;
- }
- VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started");
- do {
- schedule_timeout_interruptible(cbflood_inter_holdoff);
- atomic_long_inc(&n_cbfloods);
- WARN_ON(signal_pending(current));
- for (i = 0; i < cbflood_n_burst; i++) {
- for (j = 0; j < cbflood_n_per_burst; j++) {
- cur_ops->call(&rhp[i * cbflood_n_per_burst + j],
- rcu_torture_cbflood_cb);
- }
- schedule_timeout_interruptible(cbflood_intra_holdoff);
- WARN_ON(signal_pending(current));
- }
- cur_ops->cb_barrier();
- stutter_wait("rcu_torture_cbflood");
- } while (!torture_must_stop());
- vfree(rhp);
-wait_for_stop:
- torture_kthread_stopping("rcu_torture_cbflood");
- return 0;
-}
-
/*
* RCU torture force-quiescent-state kthread. Repeatedly induces
* bursts of calls to force_quiescent_state(), increasing the probability
@@ -1457,11 +1398,10 @@ rcu_torture_stats_print(void)
n_rcu_torture_boosts,
atomic_long_read(&n_rcu_torture_timers));
torture_onoff_stats();
- pr_cont("barrier: %ld/%ld:%ld ",
+ pr_cont("barrier: %ld/%ld:%ld\n",
n_barrier_successes,
n_barrier_attempts,
n_rcu_torture_barrier_error);
- pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods));
pr_alert("%s%s ", torture_type, TORTURE_FLAG);
if (atomic_read(&n_rcu_torture_mberror) != 0 ||
@@ -1674,8 +1614,90 @@ static void rcu_torture_fwd_prog_cb(struct rcu_head *rhp)
cur_ops->call(&fcsp->rh, rcu_torture_fwd_prog_cb);
}
-/* Carry out grace-period forward-progress testing. */
-static int rcu_torture_fwd_prog(void *args)
+/* State for continuous-flood RCU callbacks. */
+struct rcu_fwd_cb {
+ struct rcu_head rh;
+ struct rcu_fwd_cb *rfc_next;
+ int rfc_gps;
+};
+static DEFINE_SPINLOCK(rcu_fwd_lock);
+static struct rcu_fwd_cb *rcu_fwd_cb_head;
+static struct rcu_fwd_cb **rcu_fwd_cb_tail = &rcu_fwd_cb_head;
+static long n_launders_cb;
+static unsigned long rcu_fwd_startat;
+static bool rcu_fwd_emergency_stop;
+#define MAX_FWD_CB_JIFFIES (8 * HZ) /* Maximum CB test duration. */
+#define MIN_FWD_CB_LAUNDERS 3 /* This many CB invocations to count. */
+#define MIN_FWD_CBS_LAUNDERED 100 /* Number of counted CBs. */
+#define FWD_CBS_HIST_DIV 10 /* Histogram buckets/second. */
+static long n_launders_hist[2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)];
+
+static void rcu_torture_fwd_cb_hist(void)
+{
+ int i;
+ int j;
+
+ for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
+ if (n_launders_hist[i] > 0)
+ break;
+ pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
+ __func__, jiffies - rcu_fwd_startat);
+ for (j = 0; j <= i; j++)
+ pr_cont(" %ds/%d: %ld",
+ j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j]);
+ pr_cont("\n");
+}
+
+/* Callback function for continuous-flood RCU callbacks. */
+static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
+{
+ unsigned long flags;
+ int i;
+ struct rcu_fwd_cb *rfcp = container_of(rhp, struct rcu_fwd_cb, rh);
+ struct rcu_fwd_cb **rfcpp;
+
+ rfcp->rfc_next = NULL;
+ rfcp->rfc_gps++;
+ spin_lock_irqsave(&rcu_fwd_lock, flags);
+ rfcpp = rcu_fwd_cb_tail;
+ rcu_fwd_cb_tail = &rfcp->rfc_next;
+ WRITE_ONCE(*rfcpp, rfcp);
+ WRITE_ONCE(n_launders_cb, n_launders_cb + 1);
+ i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
+ if (i >= ARRAY_SIZE(n_launders_hist))
+ i = ARRAY_SIZE(n_launders_hist) - 1;
+ n_launders_hist[i]++;
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+}
+
+/*
+ * Free all callbacks on the rcu_fwd_cb_head list, either because the
+ * test is over or because we hit an OOM event.
+ */
+static unsigned long rcu_torture_fwd_prog_cbfree(void)
+{
+ unsigned long flags;
+ unsigned long freed = 0;
+ struct rcu_fwd_cb *rfcp;
+
+ for (;;) {
+ spin_lock_irqsave(&rcu_fwd_lock, flags);
+ rfcp = rcu_fwd_cb_head;
+ if (!rfcp)
+ break;
+ rcu_fwd_cb_head = rfcp->rfc_next;
+ if (!rcu_fwd_cb_head)
+ rcu_fwd_cb_tail = &rcu_fwd_cb_head;
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ kfree(rfcp);
+ freed++;
+ }
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ return freed;
+}
+
+/* Carry out need_resched()/cond_resched() forward-progress testing. */
+static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
{
unsigned long cver;
unsigned long dur;
@@ -1686,56 +1708,186 @@ static int rcu_torture_fwd_prog(void *args)
int sd4;
bool selfpropcb = false;
unsigned long stopat;
- int tested = 0;
- int tested_tries = 0;
static DEFINE_TORTURE_RANDOM(trs);
- VERBOSE_TOROUT_STRING("rcu_torture_fwd_progress task started");
- if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST))
- set_user_nice(current, MAX_NICE);
if (cur_ops->call && cur_ops->sync && cur_ops->cb_barrier) {
init_rcu_head_on_stack(&fcs.rh);
selfpropcb = true;
}
+
+ /* Tight loop containing cond_resched(). */
+ if (selfpropcb) {
+ WRITE_ONCE(fcs.stop, 0);
+ cur_ops->call(&fcs.rh, rcu_torture_fwd_prog_cb);
+ }
+ cver = READ_ONCE(rcu_torture_current_version);
+ gps = cur_ops->get_gp_seq();
+ sd = cur_ops->stall_dur() + 1;
+ sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div;
+ dur = sd4 + torture_random(&trs) % (sd - sd4);
+ WRITE_ONCE(rcu_fwd_startat, jiffies);
+ stopat = rcu_fwd_startat + dur;
+ while (time_before(jiffies, stopat) &&
+ !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+ idx = cur_ops->readlock();
+ udelay(10);
+ cur_ops->readunlock(idx);
+ if (!fwd_progress_need_resched || need_resched())
+ cond_resched();
+ }
+ (*tested_tries)++;
+ if (!time_before(jiffies, stopat) &&
+ !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+ (*tested)++;
+ cver = READ_ONCE(rcu_torture_current_version) - cver;
+ gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
+ WARN_ON(!cver && gps < 2);
+ pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps);
+ }
+ if (selfpropcb) {
+ WRITE_ONCE(fcs.stop, 1);
+ cur_ops->sync(); /* Wait for running CB to complete. */
+ cur_ops->cb_barrier(); /* Wait for queued callbacks. */
+ }
+
+ if (selfpropcb) {
+ WARN_ON(READ_ONCE(fcs.stop) != 2);
+ destroy_rcu_head_on_stack(&fcs.rh);
+ }
+}
+
+/* Carry out call_rcu() forward-progress testing. */
+static void rcu_torture_fwd_prog_cr(void)
+{
+ unsigned long cver;
+ unsigned long gps;
+ int i;
+ long n_launders;
+ long n_launders_cb_snap;
+ long n_launders_sa;
+ long n_max_cbs;
+ long n_max_gps;
+ struct rcu_fwd_cb *rfcp;
+ struct rcu_fwd_cb *rfcpn;
+ unsigned long stopat;
+ unsigned long stoppedat;
+
+ if (READ_ONCE(rcu_fwd_emergency_stop))
+ return; /* Get out of the way quickly, no GP wait! */
+
+ /* Loop continuously posting RCU callbacks. */
+ WRITE_ONCE(rcu_fwd_cb_nodelay, true);
+ cur_ops->sync(); /* Later readers see above write. */
+ WRITE_ONCE(rcu_fwd_startat, jiffies);
+ stopat = rcu_fwd_startat + MAX_FWD_CB_JIFFIES;
+ n_launders = 0;
+ n_launders_cb = 0;
+ n_launders_sa = 0;
+ n_max_cbs = 0;
+ n_max_gps = 0;
+ for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++)
+ n_launders_hist[i] = 0;
+ cver = READ_ONCE(rcu_torture_current_version);
+ gps = cur_ops->get_gp_seq();
+ while (time_before(jiffies, stopat) &&
+ !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+ rfcp = READ_ONCE(rcu_fwd_cb_head);
+ rfcpn = NULL;
+ if (rfcp)
+ rfcpn = READ_ONCE(rfcp->rfc_next);
+ if (rfcpn) {
+ if (rfcp->rfc_gps >= MIN_FWD_CB_LAUNDERS &&
+ ++n_max_gps >= MIN_FWD_CBS_LAUNDERED)
+ break;
+ rcu_fwd_cb_head = rfcpn;
+ n_launders++;
+ n_launders_sa++;
+ } else {
+ rfcp = kmalloc(sizeof(*rfcp), GFP_KERNEL);
+ if (WARN_ON_ONCE(!rfcp)) {
+ schedule_timeout_interruptible(1);
+ continue;
+ }
+ n_max_cbs++;
+ n_launders_sa = 0;
+ rfcp->rfc_gps = 0;
+ }
+ cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
+ cond_resched();
+ }
+ stoppedat = jiffies;
+ n_launders_cb_snap = READ_ONCE(n_launders_cb);
+ cver = READ_ONCE(rcu_torture_current_version) - cver;
+ gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
+ cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */
+ (void)rcu_torture_fwd_prog_cbfree();
+
+ WRITE_ONCE(rcu_fwd_cb_nodelay, false);
+ if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop)) {
+ WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED);
+ pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n",
+ __func__,
+ stoppedat - rcu_fwd_startat, jiffies - stoppedat,
+ n_launders + n_max_cbs - n_launders_cb_snap,
+ n_launders, n_launders_sa,
+ n_max_gps, n_max_cbs, cver, gps);
+ rcu_torture_fwd_cb_hist();
+ }
+}
+
+
+/*
+ * OOM notifier, but this only prints diagnostic information for the
+ * current forward-progress test.
+ */
+static int rcutorture_oom_notify(struct notifier_block *self,
+ unsigned long notused, void *nfreed)
+{
+ WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
+ __func__);
+ rcu_torture_fwd_cb_hist();
+ rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat) / 2));
+ WRITE_ONCE(rcu_fwd_emergency_stop, true);
+ smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ rcu_barrier();
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ rcu_barrier();
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ smp_mb(); /* Frees before return to avoid redoing OOM. */
+ (*(unsigned long *)nfreed)++; /* Forward progress CBs freed! */
+ pr_info("%s returning after OOM processing.\n", __func__);
+ return NOTIFY_OK;
+}
+
+static struct notifier_block rcutorture_oom_nb = {
+ .notifier_call = rcutorture_oom_notify
+};
+
+/* Carry out grace-period forward-progress testing. */
+static int rcu_torture_fwd_prog(void *args)
+{
+ int tested = 0;
+ int tested_tries = 0;
+
+ VERBOSE_TOROUT_STRING("rcu_torture_fwd_progress task started");
+ rcu_bind_current_to_nocb();
+ if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST))
+ set_user_nice(current, MAX_NICE);
do {
schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
- if (selfpropcb) {
- WRITE_ONCE(fcs.stop, 0);
- cur_ops->call(&fcs.rh, rcu_torture_fwd_prog_cb);
- }
- cver = READ_ONCE(rcu_torture_current_version);
- gps = cur_ops->get_gp_seq();
- sd = cur_ops->stall_dur() + 1;
- sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div;
- dur = sd4 + torture_random(&trs) % (sd - sd4);
- stopat = jiffies + dur;
- while (time_before(jiffies, stopat) && !torture_must_stop()) {
- idx = cur_ops->readlock();
- udelay(10);
- cur_ops->readunlock(idx);
- if (!fwd_progress_need_resched || need_resched())
- cond_resched();
- }
- tested_tries++;
- if (!time_before(jiffies, stopat) && !torture_must_stop()) {
- tested++;
- cver = READ_ONCE(rcu_torture_current_version) - cver;
- gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
- WARN_ON(!cver && gps < 2);
- pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps);
- }
- if (selfpropcb) {
- WRITE_ONCE(fcs.stop, 1);
- cur_ops->sync(); /* Wait for running CB to complete. */
- cur_ops->cb_barrier(); /* Wait for queued callbacks. */
- }
+ WRITE_ONCE(rcu_fwd_emergency_stop, false);
+ register_oom_notifier(&rcutorture_oom_nb);
+ rcu_torture_fwd_prog_nr(&tested, &tested_tries);
+ rcu_torture_fwd_prog_cr();
+ unregister_oom_notifier(&rcutorture_oom_nb);
+
/* Avoid slow periods, better to test when busy. */
stutter_wait("rcu_torture_fwd_prog");
} while (!torture_must_stop());
- if (selfpropcb) {
- WARN_ON(READ_ONCE(fcs.stop) != 2);
- destroy_rcu_head_on_stack(&fcs.rh);
- }
/* Short runs might not contain a valid forward-progress attempt. */
WARN_ON(!tested && tested_tries >= 5);
pr_alert("%s: tested %d tested_tries %d\n", __func__, tested, tested_tries);
@@ -1748,7 +1900,8 @@ static int __init rcu_torture_fwd_prog_init(void)
{
if (!fwd_progress)
return 0; /* Not requested, so don't do it. */
- if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0) {
+ if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0 ||
+ cur_ops == &rcu_busted_ops) {
VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, unsupported by RCU flavor under test");
return 0;
}
@@ -1968,8 +2121,6 @@ rcu_torture_cleanup(void)
cur_ops->name, gp_seq, flags);
torture_stop_kthread(rcu_torture_stats, stats_task);
torture_stop_kthread(rcu_torture_fqs, fqs_task);
- for (i = 0; i < ncbflooders; i++)
- torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
if (rcu_torture_can_boost())
cpuhp_remove_state(rcutor_hp);
@@ -2252,24 +2403,6 @@ rcu_torture_init(void)
goto unwind;
if (object_debug)
rcu_test_debug_objects();
- if (cbflood_n_burst > 0) {
- /* Create the cbflood threads */
- ncbflooders = (num_online_cpus() + 3) / 4;
- cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task),
- GFP_KERNEL);
- if (!cbflood_task) {
- VERBOSE_TOROUT_ERRSTRING("out of memory");
- firsterr = -ENOMEM;
- goto unwind;
- }
- for (i = 0; i < ncbflooders; i++) {
- firsterr = torture_create_kthread(rcu_torture_cbflood,
- NULL,
- cbflood_task[i]);
- if (firsterr)
- goto unwind;
- }
- }
torture_init_end();
return 0;
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index b46e6683f8c9..32dfd6522548 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -37,30 +37,30 @@ int rcu_scheduler_active __read_mostly;
static LIST_HEAD(srcu_boot_list);
static bool srcu_init_done;
-static int init_srcu_struct_fields(struct srcu_struct *sp)
+static int init_srcu_struct_fields(struct srcu_struct *ssp)
{
- sp->srcu_lock_nesting[0] = 0;
- sp->srcu_lock_nesting[1] = 0;
- init_swait_queue_head(&sp->srcu_wq);
- sp->srcu_cb_head = NULL;
- sp->srcu_cb_tail = &sp->srcu_cb_head;
- sp->srcu_gp_running = false;
- sp->srcu_gp_waiting = false;
- sp->srcu_idx = 0;
- INIT_WORK(&sp->srcu_work, srcu_drive_gp);
- INIT_LIST_HEAD(&sp->srcu_work.entry);
+ ssp->srcu_lock_nesting[0] = 0;
+ ssp->srcu_lock_nesting[1] = 0;
+ init_swait_queue_head(&ssp->srcu_wq);
+ ssp->srcu_cb_head = NULL;
+ ssp->srcu_cb_tail = &ssp->srcu_cb_head;
+ ssp->srcu_gp_running = false;
+ ssp->srcu_gp_waiting = false;
+ ssp->srcu_idx = 0;
+ INIT_WORK(&ssp->srcu_work, srcu_drive_gp);
+ INIT_LIST_HEAD(&ssp->srcu_work.entry);
return 0;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+int __init_srcu_struct(struct srcu_struct *ssp, 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);
+ debug_check_no_locks_freed((void *)ssp, sizeof(*ssp));
+ lockdep_init_map(&ssp->dep_map, name, key, 0);
+ return init_srcu_struct_fields(ssp);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);
@@ -68,15 +68,15 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
/*
* init_srcu_struct - initialize a sleep-RCU structure
- * @sp: structure to initialize.
+ * @ssp: 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)
+int init_srcu_struct(struct srcu_struct *ssp)
{
- return init_srcu_struct_fields(sp);
+ return init_srcu_struct_fields(ssp);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);
@@ -84,22 +84,22 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
/*
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @sp: structure to clean up.
+ * @ssp: 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, bool quiesced)
+void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
{
- WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
+ WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
if (quiesced)
- WARN_ON(work_pending(&sp->srcu_work));
+ WARN_ON(work_pending(&ssp->srcu_work));
else
- flush_work(&sp->srcu_work);
- WARN_ON(sp->srcu_gp_running);
- WARN_ON(sp->srcu_gp_waiting);
- WARN_ON(sp->srcu_cb_head);
- WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail);
+ flush_work(&ssp->srcu_work);
+ WARN_ON(ssp->srcu_gp_running);
+ WARN_ON(ssp->srcu_gp_waiting);
+ WARN_ON(ssp->srcu_cb_head);
+ WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail);
}
EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
@@ -107,13 +107,13 @@ EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
* Removes the count for the old reader from the appropriate element of
* the srcu_struct.
*/
-void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
{
- int newval = sp->srcu_lock_nesting[idx] - 1;
+ int newval = ssp->srcu_lock_nesting[idx] - 1;
- WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
- if (!newval && READ_ONCE(sp->srcu_gp_waiting))
- swake_up_one(&sp->srcu_wq);
+ WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval);
+ if (!newval && READ_ONCE(ssp->srcu_gp_waiting))
+ swake_up_one(&ssp->srcu_wq);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -127,24 +127,24 @@ void srcu_drive_gp(struct work_struct *wp)
int idx;
struct rcu_head *lh;
struct rcu_head *rhp;
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
- sp = container_of(wp, struct srcu_struct, srcu_work);
- if (sp->srcu_gp_running || !READ_ONCE(sp->srcu_cb_head))
+ ssp = container_of(wp, struct srcu_struct, srcu_work);
+ if (ssp->srcu_gp_running || !READ_ONCE(ssp->srcu_cb_head))
return; /* Already running or nothing to do. */
/* Remove recently arrived callbacks and wait for readers. */
- WRITE_ONCE(sp->srcu_gp_running, true);
+ WRITE_ONCE(ssp->srcu_gp_running, true);
local_irq_disable();
- lh = sp->srcu_cb_head;
- sp->srcu_cb_head = NULL;
- sp->srcu_cb_tail = &sp->srcu_cb_head;
+ lh = ssp->srcu_cb_head;
+ ssp->srcu_cb_head = NULL;
+ ssp->srcu_cb_tail = &ssp->srcu_cb_head;
local_irq_enable();
- 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_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
- WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
+ idx = ssp->srcu_idx;
+ WRITE_ONCE(ssp->srcu_idx, !ssp->srcu_idx);
+ WRITE_ONCE(ssp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
+ swait_event_exclusive(ssp->srcu_wq, !READ_ONCE(ssp->srcu_lock_nesting[idx]));
+ WRITE_ONCE(ssp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
/* Invoke the callbacks we removed above. */
while (lh) {
@@ -161,9 +161,9 @@ void srcu_drive_gp(struct work_struct *wp)
* at interrupt level, but the ->srcu_gp_running checks will
* straighten that out.
*/
- WRITE_ONCE(sp->srcu_gp_running, false);
- if (READ_ONCE(sp->srcu_cb_head))
- schedule_work(&sp->srcu_work);
+ WRITE_ONCE(ssp->srcu_gp_running, false);
+ if (READ_ONCE(ssp->srcu_cb_head))
+ schedule_work(&ssp->srcu_work);
}
EXPORT_SYMBOL_GPL(srcu_drive_gp);
@@ -171,7 +171,7 @@ 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 *rhp,
+void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
rcu_callback_t func)
{
unsigned long flags;
@@ -179,14 +179,14 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
rhp->func = func;
rhp->next = NULL;
local_irq_save(flags);
- *sp->srcu_cb_tail = rhp;
- sp->srcu_cb_tail = &rhp->next;
+ *ssp->srcu_cb_tail = rhp;
+ ssp->srcu_cb_tail = &rhp->next;
local_irq_restore(flags);
- if (!READ_ONCE(sp->srcu_gp_running)) {
+ if (!READ_ONCE(ssp->srcu_gp_running)) {
if (likely(srcu_init_done))
- schedule_work(&sp->srcu_work);
- else if (list_empty(&sp->srcu_work.entry))
- list_add(&sp->srcu_work.entry, &srcu_boot_list);
+ schedule_work(&ssp->srcu_work);
+ else if (list_empty(&ssp->srcu_work.entry))
+ list_add(&ssp->srcu_work.entry, &srcu_boot_list);
}
}
EXPORT_SYMBOL_GPL(call_srcu);
@@ -194,13 +194,13 @@ EXPORT_SYMBOL_GPL(call_srcu);
/*
* synchronize_srcu - wait for prior SRCU read-side critical-section completion
*/
-void synchronize_srcu(struct srcu_struct *sp)
+void synchronize_srcu(struct srcu_struct *ssp)
{
struct rcu_synchronize rs;
init_rcu_head_on_stack(&rs.head);
init_completion(&rs.completion);
- call_srcu(sp, &rs.head, wakeme_after_rcu);
+ call_srcu(ssp, &rs.head, wakeme_after_rcu);
wait_for_completion(&rs.completion);
destroy_rcu_head_on_stack(&rs.head);
}
@@ -219,13 +219,13 @@ void __init rcu_scheduler_starting(void)
*/
void __init srcu_init(void)
{
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
srcu_init_done = true;
while (!list_empty(&srcu_boot_list)) {
- sp = list_first_entry(&srcu_boot_list,
+ ssp = list_first_entry(&srcu_boot_list,
struct srcu_struct, srcu_work.entry);
- list_del_init(&sp->srcu_work.entry);
- schedule_work(&sp->srcu_work);
+ list_del_init(&ssp->srcu_work.entry);
+ schedule_work(&ssp->srcu_work);
}
}
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index a8846ed7f352..3600d88d8956 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -56,7 +56,7 @@ static LIST_HEAD(srcu_boot_list);
static bool __read_mostly srcu_init_done;
static void srcu_invoke_callbacks(struct work_struct *work);
-static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
+static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
static void process_srcu(struct work_struct *work);
/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
@@ -92,7 +92,7 @@ do { \
* 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)
+static void init_srcu_struct_nodes(struct srcu_struct *ssp, bool is_static)
{
int cpu;
int i;
@@ -103,13 +103,13 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
struct srcu_node *snp_first;
/* Work out the overall tree geometry. */
- sp->level[0] = &sp->node[0];
+ ssp->level[0] = &ssp->node[0];
for (i = 1; i < rcu_num_lvls; i++)
- sp->level[i] = sp->level[i - 1] + num_rcu_lvl[i - 1];
+ ssp->level[i] = ssp->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. */
- srcu_for_each_node_breadth_first(sp, snp) {
+ srcu_for_each_node_breadth_first(ssp, snp) {
spin_lock_init(&ACCESS_PRIVATE(snp, lock));
WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
ARRAY_SIZE(snp->srcu_data_have_cbs));
@@ -120,17 +120,17 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
snp->srcu_gp_seq_needed_exp = 0;
snp->grplo = -1;
snp->grphi = -1;
- if (snp == &sp->node[0]) {
+ if (snp == &ssp->node[0]) {
/* Root node, special case. */
snp->srcu_parent = NULL;
continue;
}
/* Non-root node. */
- if (snp == sp->level[level + 1])
+ if (snp == ssp->level[level + 1])
level++;
- snp->srcu_parent = sp->level[level - 1] +
- (snp - sp->level[level]) /
+ snp->srcu_parent = ssp->level[level - 1] +
+ (snp - ssp->level[level]) /
levelspread[level - 1];
}
@@ -141,14 +141,14 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
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];
+ snp_first = ssp->level[level];
for_each_possible_cpu(cpu) {
- sdp = per_cpu_ptr(sp->sda, cpu);
+ sdp = per_cpu_ptr(ssp->sda, cpu);
spin_lock_init(&ACCESS_PRIVATE(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->srcu_gp_seq_needed = ssp->srcu_gp_seq;
+ sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq;
sdp->mynode = &snp_first[cpu / levelspread[level]];
for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
if (snp->grplo < 0)
@@ -157,7 +157,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
}
sdp->cpu = cpu;
INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
- sdp->sp = sp;
+ sdp->ssp = ssp;
sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
if (is_static)
continue;
@@ -176,35 +176,35 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool 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)
+static int init_srcu_struct_fields(struct srcu_struct *ssp, 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);
+ mutex_init(&ssp->srcu_cb_mutex);
+ mutex_init(&ssp->srcu_gp_mutex);
+ ssp->srcu_idx = 0;
+ ssp->srcu_gp_seq = 0;
+ ssp->srcu_barrier_seq = 0;
+ mutex_init(&ssp->srcu_barrier_mutex);
+ atomic_set(&ssp->srcu_barrier_cpu_cnt, 0);
+ INIT_DELAYED_WORK(&ssp->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;
+ ssp->sda = alloc_percpu(struct srcu_data);
+ init_srcu_struct_nodes(ssp, is_static);
+ ssp->srcu_gp_seq_needed_exp = 0;
+ ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+ smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */
+ return ssp->sda ? 0 : -ENOMEM;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+int __init_srcu_struct(struct srcu_struct *ssp, 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(&ACCESS_PRIVATE(sp, lock));
- return init_srcu_struct_fields(sp, false);
+ debug_check_no_locks_freed((void *)ssp, sizeof(*ssp));
+ lockdep_init_map(&ssp->dep_map, name, key, 0);
+ spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
+ return init_srcu_struct_fields(ssp, false);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);
@@ -212,16 +212,16 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
/**
* init_srcu_struct - initialize a sleep-RCU structure
- * @sp: structure to initialize.
+ * @ssp: 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)
+int init_srcu_struct(struct srcu_struct *ssp)
{
- spin_lock_init(&ACCESS_PRIVATE(sp, lock));
- return init_srcu_struct_fields(sp, false);
+ spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
+ return init_srcu_struct_fields(ssp, false);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);
@@ -231,37 +231,37 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
* 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 sp->lock, which -is-
+ * to each update-side SRCU primitive. Use ssp->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)
+static void check_init_srcu_struct(struct srcu_struct *ssp)
{
unsigned long flags;
/* The smp_load_acquire() pairs with the smp_store_release(). */
- if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
+ if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq_needed))) /*^^^*/
return; /* Already initialized. */
- spin_lock_irqsave_rcu_node(sp, flags);
- if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
- spin_unlock_irqrestore_rcu_node(sp, flags);
+ spin_lock_irqsave_rcu_node(ssp, flags);
+ if (!rcu_seq_state(ssp->srcu_gp_seq_needed)) {
+ spin_unlock_irqrestore_rcu_node(ssp, flags);
return;
}
- init_srcu_struct_fields(sp, true);
- spin_unlock_irqrestore_rcu_node(sp, flags);
+ init_srcu_struct_fields(ssp, true);
+ spin_unlock_irqrestore_rcu_node(ssp, 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)
+static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
- struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+ struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
}
@@ -272,13 +272,13 @@ static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
* 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)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
- struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+ struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
}
@@ -289,11 +289,11 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
* 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)
+static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
{
unsigned long unlocks;
- unlocks = srcu_readers_unlock_idx(sp, idx);
+ unlocks = srcu_readers_unlock_idx(ssp, idx);
/*
* Make sure that a lock is always counted if the corresponding
@@ -329,25 +329,25 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
* of floor(ULONG_MAX/NR_CPUS/2), which should be sufficient,
* especially on 64-bit systems.
*/
- return srcu_readers_lock_idx(sp, idx) == unlocks;
+ return srcu_readers_lock_idx(ssp, 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).
+ * @ssp: 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)
+static bool srcu_readers_active(struct srcu_struct *ssp)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
- struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+ struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_lock_count[0]);
sum += READ_ONCE(cpuc->srcu_lock_count[1]);
@@ -363,44 +363,44 @@ static bool srcu_readers_active(struct srcu_struct *sp)
* 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)
+static unsigned long srcu_get_delay(struct srcu_struct *ssp)
{
- if (ULONG_CMP_LT(READ_ONCE(sp->srcu_gp_seq),
- READ_ONCE(sp->srcu_gp_seq_needed_exp)))
+ if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq),
+ READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
return 0;
return SRCU_INTERVAL;
}
/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
-void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
+void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
{
int cpu;
- if (WARN_ON(!srcu_get_delay(sp)))
+ if (WARN_ON(!srcu_get_delay(ssp)))
return; /* Just leak it! */
- if (WARN_ON(srcu_readers_active(sp)))
+ if (WARN_ON(srcu_readers_active(ssp)))
return; /* Just leak it! */
if (quiesced) {
- if (WARN_ON(delayed_work_pending(&sp->work)))
+ if (WARN_ON(delayed_work_pending(&ssp->work)))
return; /* Just leak it! */
} else {
- flush_delayed_work(&sp->work);
+ flush_delayed_work(&ssp->work);
}
for_each_possible_cpu(cpu)
if (quiesced) {
- if (WARN_ON(delayed_work_pending(&per_cpu_ptr(sp->sda, cpu)->work)))
+ if (WARN_ON(delayed_work_pending(&per_cpu_ptr(ssp->sda, cpu)->work)))
return; /* Just leak it! */
} else {
- flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+ flush_delayed_work(&per_cpu_ptr(ssp->sda, cpu)->work);
}
- if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
- WARN_ON(srcu_readers_active(sp))) {
+ if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
+ WARN_ON(srcu_readers_active(ssp))) {
pr_info("%s: Active srcu_struct %p state: %d\n",
- __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+ __func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)));
return; /* Caller forgot to stop doing call_srcu()? */
}
- free_percpu(sp->sda);
- sp->sda = NULL;
+ free_percpu(ssp->sda);
+ ssp->sda = NULL;
}
EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
@@ -409,12 +409,12 @@ EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
* srcu_struct.
* Returns an index that must be passed to the matching srcu_read_unlock().
*/
-int __srcu_read_lock(struct srcu_struct *sp)
+int __srcu_read_lock(struct srcu_struct *ssp)
{
int idx;
- idx = READ_ONCE(sp->srcu_idx) & 0x1;
- this_cpu_inc(sp->sda->srcu_lock_count[idx]);
+ idx = READ_ONCE(ssp->srcu_idx) & 0x1;
+ this_cpu_inc(ssp->sda->srcu_lock_count[idx]);
smp_mb(); /* B */ /* Avoid leaking the critical section. */
return idx;
}
@@ -425,10 +425,10 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
* 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().
*/
-void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
{
smp_mb(); /* C */ /* Avoid leaking the critical section. */
- this_cpu_inc(sp->sda->srcu_unlock_count[idx]);
+ this_cpu_inc(ssp->sda->srcu_unlock_count[idx]);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -444,20 +444,22 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock);
/*
* Start an SRCU grace period.
*/
-static void srcu_gp_start(struct srcu_struct *sp)
+static void srcu_gp_start(struct srcu_struct *ssp)
{
- struct srcu_data *sdp = this_cpu_ptr(sp->sda);
+ struct srcu_data *sdp = this_cpu_ptr(ssp->sda);
int state;
- lockdep_assert_held(&ACCESS_PRIVATE(sp, lock));
- WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
+ lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
+ WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
+ spin_lock_rcu_node(sdp); /* Interrupts already disabled. */
rcu_segcblist_advance(&sdp->srcu_cblist,
- rcu_seq_current(&sp->srcu_gp_seq));
+ rcu_seq_current(&ssp->srcu_gp_seq));
(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
- rcu_seq_snap(&sp->srcu_gp_seq));
+ rcu_seq_snap(&ssp->srcu_gp_seq));
+ spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */
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));
+ rcu_seq_start(&ssp->srcu_gp_seq);
+ state = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
}
@@ -511,7 +513,7 @@ static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
* 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,
+static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp,
unsigned long mask, unsigned long delay)
{
int cpu;
@@ -519,7 +521,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
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);
+ srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay);
}
}
@@ -532,7 +534,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
* 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)
+static void srcu_gp_end(struct srcu_struct *ssp)
{
unsigned long cbdelay;
bool cbs;
@@ -546,28 +548,28 @@ static void srcu_gp_end(struct srcu_struct *sp)
struct srcu_node *snp;
/* Prevent more than one additional grace period. */
- mutex_lock(&sp->srcu_cb_mutex);
+ mutex_lock(&ssp->srcu_cb_mutex);
/* End the current grace period. */
- spin_lock_irq_rcu_node(sp);
- idx = rcu_seq_state(sp->srcu_gp_seq);
+ spin_lock_irq_rcu_node(ssp);
+ idx = rcu_seq_state(ssp->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_rcu_node(sp);
- mutex_unlock(&sp->srcu_gp_mutex);
+ cbdelay = srcu_get_delay(ssp);
+ ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+ rcu_seq_end(&ssp->srcu_gp_seq);
+ gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
+ if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq))
+ ssp->srcu_gp_seq_needed_exp = gpseq;
+ spin_unlock_irq_rcu_node(ssp);
+ mutex_unlock(&ssp->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);
- srcu_for_each_node_breadth_first(sp, snp) {
+ srcu_for_each_node_breadth_first(ssp, snp) {
spin_lock_irq_rcu_node(snp);
cbs = false;
- last_lvl = snp >= sp->level[rcu_num_lvls - 1];
+ last_lvl = snp >= ssp->level[rcu_num_lvls - 1];
if (last_lvl)
cbs = snp->srcu_have_cbs[idx] == gpseq;
snp->srcu_have_cbs[idx] = gpseq;
@@ -578,12 +580,12 @@ static void srcu_gp_end(struct srcu_struct *sp)
snp->srcu_data_have_cbs[idx] = 0;
spin_unlock_irq_rcu_node(snp);
if (cbs)
- srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
+ srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay);
/* Occasionally prevent srcu_data counter wrap. */
if (!(gpseq & counter_wrap_check) && last_lvl)
for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
- sdp = per_cpu_ptr(sp->sda, cpu);
+ sdp = per_cpu_ptr(ssp->sda, cpu);
spin_lock_irqsave_rcu_node(sdp, flags);
if (ULONG_CMP_GE(gpseq,
sdp->srcu_gp_seq_needed + 100))
@@ -596,18 +598,18 @@ static void srcu_gp_end(struct srcu_struct *sp)
}
/* Callback initiation done, allow grace periods after next. */
- mutex_unlock(&sp->srcu_cb_mutex);
+ mutex_unlock(&ssp->srcu_cb_mutex);
/* Start a new grace period if needed. */
- spin_lock_irq_rcu_node(sp);
- gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+ spin_lock_irq_rcu_node(ssp);
+ gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
if (!rcu_seq_state(gpseq) &&
- ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
- srcu_gp_start(sp);
- spin_unlock_irq_rcu_node(sp);
- srcu_reschedule(sp, 0);
+ ULONG_CMP_LT(gpseq, ssp->srcu_gp_seq_needed)) {
+ srcu_gp_start(ssp);
+ spin_unlock_irq_rcu_node(ssp);
+ srcu_reschedule(ssp, 0);
} else {
- spin_unlock_irq_rcu_node(sp);
+ spin_unlock_irq_rcu_node(ssp);
}
}
@@ -618,13 +620,13 @@ static void srcu_gp_end(struct srcu_struct *sp)
* 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,
+static void srcu_funnel_exp_start(struct srcu_struct *ssp, 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) ||
+ if (rcu_seq_done(&ssp->srcu_gp_seq, s) ||
ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
return;
spin_lock_irqsave_rcu_node(snp, flags);
@@ -635,10 +637,10 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
spin_unlock_irqrestore_rcu_node(snp, flags);
}
- spin_lock_irqsave_rcu_node(sp, flags);
- if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
- sp->srcu_gp_seq_needed_exp = s;
- spin_unlock_irqrestore_rcu_node(sp, flags);
+ spin_lock_irqsave_rcu_node(ssp, flags);
+ if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
+ ssp->srcu_gp_seq_needed_exp = s;
+ spin_unlock_irqrestore_rcu_node(ssp, flags);
}
/*
@@ -651,7 +653,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
* Note that this function also does the work of srcu_funnel_exp_start(),
* in some cases by directly invoking it.
*/
-static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
+static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
unsigned long s, bool do_norm)
{
unsigned long flags;
@@ -661,7 +663,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
/* 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)
+ if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != sdp->mynode)
return; /* GP already done and CBs recorded. */
spin_lock_irqsave_rcu_node(snp, flags);
if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
@@ -676,7 +678,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
return;
}
if (!do_norm)
- srcu_funnel_exp_start(sp, snp, s);
+ srcu_funnel_exp_start(ssp, snp, s);
return;
}
snp->srcu_have_cbs[idx] = s;
@@ -688,29 +690,29 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
}
/* Top of tree, must ensure the grace period will be started. */
- spin_lock_irqsave_rcu_node(sp, flags);
- if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
+ spin_lock_irqsave_rcu_node(ssp, flags);
+ if (ULONG_CMP_LT(ssp->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); /*^^^*/
+ smp_store_release(&ssp->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 (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
+ ssp->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);
+ if (!rcu_seq_done(&ssp->srcu_gp_seq, s) &&
+ rcu_seq_state(ssp->srcu_gp_seq) == SRCU_STATE_IDLE) {
+ WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
+ srcu_gp_start(ssp);
if (likely(srcu_init_done))
- queue_delayed_work(rcu_gp_wq, &sp->work,
- srcu_get_delay(sp));
- else if (list_empty(&sp->work.work.entry))
- list_add(&sp->work.work.entry, &srcu_boot_list);
+ queue_delayed_work(rcu_gp_wq, &ssp->work,
+ srcu_get_delay(ssp));
+ else if (list_empty(&ssp->work.work.entry))
+ list_add(&ssp->work.work.entry, &srcu_boot_list);
}
- spin_unlock_irqrestore_rcu_node(sp, flags);
+ spin_unlock_irqrestore_rcu_node(ssp, flags);
}
/*
@@ -718,12 +720,12 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
* 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)
+static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount)
{
for (;;) {
- if (srcu_readers_active_idx_check(sp, idx))
+ if (srcu_readers_active_idx_check(ssp, idx))
return true;
- if (--trycount + !srcu_get_delay(sp) <= 0)
+ if (--trycount + !srcu_get_delay(ssp) <= 0)
return false;
udelay(SRCU_RETRY_CHECK_DELAY);
}
@@ -734,7 +736,7 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
* 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)
+static void srcu_flip(struct srcu_struct *ssp)
{
/*
* Ensure that if this updater saw a given reader's increment
@@ -746,7 +748,7 @@ static void srcu_flip(struct srcu_struct *sp)
*/
smp_mb(); /* E */ /* Pairs with B and C. */
- WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1);
+ WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);
/*
* Ensure that if the updater misses an __srcu_read_unlock()
@@ -779,7 +781,7 @@ static void srcu_flip(struct srcu_struct *sp)
* 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)
+static bool srcu_might_be_idle(struct srcu_struct *ssp)
{
unsigned long curseq;
unsigned long flags;
@@ -788,7 +790,7 @@ static bool srcu_might_be_idle(struct srcu_struct *sp)
/* If the local srcu_data structure has callbacks, not idle. */
local_irq_save(flags);
- sdp = this_cpu_ptr(sp->sda);
+ sdp = this_cpu_ptr(ssp->sda);
if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
local_irq_restore(flags);
return false; /* Callbacks already present, so not idle. */
@@ -804,17 +806,17 @@ static bool srcu_might_be_idle(struct srcu_struct *sp)
/* 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))
+ time_in_range_open(t, ssp->srcu_last_gp_end,
+ ssp->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);
+ curseq = rcu_seq_current(&ssp->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)))
+ if (ULONG_CMP_LT(curseq, READ_ONCE(ssp->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))
+ if (curseq != rcu_seq_current(&ssp->srcu_gp_seq))
return false; /* GP # changed, so not idle. */
return true; /* With reasonable probability, idle! */
}
@@ -854,16 +856,17 @@ static void srcu_leak_callback(struct rcu_head *rhp)
* 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,
+void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
rcu_callback_t func, bool do_norm)
{
unsigned long flags;
+ int idx;
bool needexp = false;
bool needgp = false;
unsigned long s;
struct srcu_data *sdp;
- check_init_srcu_struct(sp);
+ check_init_srcu_struct(ssp);
if (debug_rcu_head_queue(rhp)) {
/* Probable double call_srcu(), so leak the callback. */
WRITE_ONCE(rhp->func, srcu_leak_callback);
@@ -871,13 +874,14 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
return;
}
rhp->func = func;
+ idx = srcu_read_lock(ssp);
local_irq_save(flags);
- sdp = this_cpu_ptr(sp->sda);
+ sdp = this_cpu_ptr(ssp->sda);
spin_lock_rcu_node(sdp);
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);
+ rcu_seq_current(&ssp->srcu_gp_seq));
+ s = rcu_seq_snap(&ssp->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;
@@ -889,14 +893,15 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
}
spin_unlock_irqrestore_rcu_node(sdp, flags);
if (needgp)
- srcu_funnel_gp_start(sp, sdp, s, do_norm);
+ srcu_funnel_gp_start(ssp, sdp, s, do_norm);
else if (needexp)
- srcu_funnel_exp_start(sp, sdp->mynode, s);
+ srcu_funnel_exp_start(ssp, sdp->mynode, s);
+ srcu_read_unlock(ssp, idx);
}
/**
* call_srcu() - Queue a callback for invocation after an SRCU grace period
- * @sp: srcu_struct in queue the callback
+ * @ssp: srcu_struct in queue the callback
* @rhp: structure to be used for queueing the SRCU callback.
* @func: function to be invoked after the SRCU grace period
*
@@ -911,21 +916,21 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
* The callback will be invoked from process context, but must nevertheless
* be fast and must not block.
*/
-void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
rcu_callback_t func)
{
- __call_srcu(sp, rhp, func, true);
+ __call_srcu(ssp, 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)
+static void __synchronize_srcu(struct srcu_struct *ssp, bool do_norm)
{
struct rcu_synchronize rcu;
- RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
+ RCU_LOCKDEP_WARN(lock_is_held(&ssp->dep_map) ||
lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
@@ -934,10 +939,10 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return;
might_sleep();
- check_init_srcu_struct(sp);
+ check_init_srcu_struct(ssp);
init_completion(&rcu.completion);
init_rcu_head_on_stack(&rcu.head);
- __call_srcu(sp, &rcu.head, wakeme_after_rcu, do_norm);
+ __call_srcu(ssp, &rcu.head, wakeme_after_rcu, do_norm);
wait_for_completion(&rcu.completion);
destroy_rcu_head_on_stack(&rcu.head);
@@ -953,7 +958,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
/**
* synchronize_srcu_expedited - Brute-force SRCU grace period
- * @sp: srcu_struct with which to synchronize.
+ * @ssp: 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.
@@ -961,15 +966,15 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
* 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)
+void synchronize_srcu_expedited(struct srcu_struct *ssp)
{
- __synchronize_srcu(sp, rcu_gp_is_normal());
+ __synchronize_srcu(ssp, 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.
+ * @ssp: 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
@@ -1011,12 +1016,12 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
* 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)
+void synchronize_srcu(struct srcu_struct *ssp)
{
- if (srcu_might_be_idle(sp) || rcu_gp_is_expedited())
- synchronize_srcu_expedited(sp);
+ if (srcu_might_be_idle(ssp) || rcu_gp_is_expedited())
+ synchronize_srcu_expedited(ssp);
else
- __synchronize_srcu(sp, true);
+ __synchronize_srcu(ssp, true);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);
@@ -1026,36 +1031,36 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
static void srcu_barrier_cb(struct rcu_head *rhp)
{
struct srcu_data *sdp;
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
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);
+ ssp = sdp->ssp;
+ if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
+ complete(&ssp->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.
+ * @ssp: srcu_struct on which to wait for in-flight callbacks.
*/
-void srcu_barrier(struct srcu_struct *sp)
+void srcu_barrier(struct srcu_struct *ssp)
{
int cpu;
struct srcu_data *sdp;
- unsigned long s = rcu_seq_snap(&sp->srcu_barrier_seq);
+ unsigned long s = rcu_seq_snap(&ssp->srcu_barrier_seq);
- check_init_srcu_struct(sp);
- mutex_lock(&sp->srcu_barrier_mutex);
- if (rcu_seq_done(&sp->srcu_barrier_seq, s)) {
+ check_init_srcu_struct(ssp);
+ mutex_lock(&ssp->srcu_barrier_mutex);
+ if (rcu_seq_done(&ssp->srcu_barrier_seq, s)) {
smp_mb(); /* Force ordering following return. */
- mutex_unlock(&sp->srcu_barrier_mutex);
+ mutex_unlock(&ssp->srcu_barrier_mutex);
return; /* Someone else did our work for us. */
}
- rcu_seq_start(&sp->srcu_barrier_seq);
- init_completion(&sp->srcu_barrier_completion);
+ rcu_seq_start(&ssp->srcu_barrier_seq);
+ init_completion(&ssp->srcu_barrier_completion);
/* Initial count prevents reaching zero until all CBs are posted. */
- atomic_set(&sp->srcu_barrier_cpu_cnt, 1);
+ atomic_set(&ssp->srcu_barrier_cpu_cnt, 1);
/*
* Each pass through this loop enqueues a callback, but only
@@ -1066,39 +1071,39 @@ void srcu_barrier(struct srcu_struct *sp)
* grace period as the last callback already in the queue.
*/
for_each_possible_cpu(cpu) {
- sdp = per_cpu_ptr(sp->sda, cpu);
+ sdp = per_cpu_ptr(ssp->sda, cpu);
spin_lock_irq_rcu_node(sdp);
- atomic_inc(&sp->srcu_barrier_cpu_cnt);
+ atomic_inc(&ssp->srcu_barrier_cpu_cnt);
sdp->srcu_barrier_head.func = srcu_barrier_cb;
debug_rcu_head_queue(&sdp->srcu_barrier_head);
if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
&sdp->srcu_barrier_head, 0)) {
debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
- atomic_dec(&sp->srcu_barrier_cpu_cnt);
+ atomic_dec(&ssp->srcu_barrier_cpu_cnt);
}
spin_unlock_irq_rcu_node(sdp);
}
/* 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);
+ if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
+ complete(&ssp->srcu_barrier_completion);
+ wait_for_completion(&ssp->srcu_barrier_completion);
- rcu_seq_end(&sp->srcu_barrier_seq);
- mutex_unlock(&sp->srcu_barrier_mutex);
+ rcu_seq_end(&ssp->srcu_barrier_seq);
+ mutex_unlock(&ssp->srcu_barrier_mutex);
}
EXPORT_SYMBOL_GPL(srcu_barrier);
/**
* srcu_batches_completed - return batches completed.
- * @sp: srcu_struct on which to report batch completion.
+ * @ssp: 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)
+unsigned long srcu_batches_completed(struct srcu_struct *ssp)
{
- return sp->srcu_idx;
+ return ssp->srcu_idx;
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);
@@ -1107,11 +1112,11 @@ EXPORT_SYMBOL_GPL(srcu_batches_completed);
* 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)
+static void srcu_advance_state(struct srcu_struct *ssp)
{
int idx;
- mutex_lock(&sp->srcu_gp_mutex);
+ mutex_lock(&ssp->srcu_gp_mutex);
/*
* Because readers might be delayed for an extended period after
@@ -1123,47 +1128,47 @@ static void srcu_advance_state(struct srcu_struct *sp)
* 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)); /* ^^^ */
+ idx = rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq)); /* ^^^ */
if (idx == SRCU_STATE_IDLE) {
- spin_lock_irq_rcu_node(sp);
- 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_rcu_node(sp);
- mutex_unlock(&sp->srcu_gp_mutex);
+ spin_lock_irq_rcu_node(ssp);
+ if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
+ WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq));
+ spin_unlock_irq_rcu_node(ssp);
+ mutex_unlock(&ssp->srcu_gp_mutex);
return;
}
- idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+ idx = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
if (idx == SRCU_STATE_IDLE)
- srcu_gp_start(sp);
- spin_unlock_irq_rcu_node(sp);
+ srcu_gp_start(ssp);
+ spin_unlock_irq_rcu_node(ssp);
if (idx != SRCU_STATE_IDLE) {
- mutex_unlock(&sp->srcu_gp_mutex);
+ mutex_unlock(&ssp->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);
+ if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
+ idx = 1 ^ (ssp->srcu_idx & 1);
+ if (!try_check_zero(ssp, idx, 1)) {
+ mutex_unlock(&ssp->srcu_gp_mutex);
return; /* readers present, retry later. */
}
- srcu_flip(sp);
- rcu_seq_set_state(&sp->srcu_gp_seq, SRCU_STATE_SCAN2);
+ srcu_flip(ssp);
+ rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2);
}
- if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
+ if (rcu_seq_state(READ_ONCE(ssp->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);
+ idx = 1 ^ (ssp->srcu_idx & 1);
+ if (!try_check_zero(ssp, idx, 2)) {
+ mutex_unlock(&ssp->srcu_gp_mutex);
return; /* readers present, retry later. */
}
- srcu_gp_end(sp); /* Releases ->srcu_gp_mutex. */
+ srcu_gp_end(ssp); /* Releases ->srcu_gp_mutex. */
}
}
@@ -1179,14 +1184,14 @@ static void srcu_invoke_callbacks(struct work_struct *work)
struct rcu_cblist ready_cbs;
struct rcu_head *rhp;
struct srcu_data *sdp;
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
sdp = container_of(work, struct srcu_data, work.work);
- sp = sdp->sp;
+ ssp = sdp->ssp;
rcu_cblist_init(&ready_cbs);
spin_lock_irq_rcu_node(sdp);
rcu_segcblist_advance(&sdp->srcu_cblist,
- rcu_seq_current(&sp->srcu_gp_seq));
+ rcu_seq_current(&ssp->srcu_gp_seq));
if (sdp->srcu_cblist_invoking ||
!rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
spin_unlock_irq_rcu_node(sdp);
@@ -1212,7 +1217,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
spin_lock_irq_rcu_node(sdp);
rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
- rcu_seq_snap(&sp->srcu_gp_seq));
+ rcu_seq_snap(&ssp->srcu_gp_seq));
sdp->srcu_cblist_invoking = false;
more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
spin_unlock_irq_rcu_node(sdp);
@@ -1224,24 +1229,24 @@ static void srcu_invoke_callbacks(struct work_struct *work)
* 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)
+static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay)
{
bool pushgp = true;
- spin_lock_irq_rcu_node(sp);
- if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
- if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
+ spin_lock_irq_rcu_node(ssp);
+ if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
+ if (!WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq))) {
/* All requests fulfilled, time to go idle. */
pushgp = false;
}
- } else if (!rcu_seq_state(sp->srcu_gp_seq)) {
+ } else if (!rcu_seq_state(ssp->srcu_gp_seq)) {
/* Outstanding request and no GP. Start one. */
- srcu_gp_start(sp);
+ srcu_gp_start(ssp);
}
- spin_unlock_irq_rcu_node(sp);
+ spin_unlock_irq_rcu_node(ssp);
if (pushgp)
- queue_delayed_work(rcu_gp_wq, &sp->work, delay);
+ queue_delayed_work(rcu_gp_wq, &ssp->work, delay);
}
/*
@@ -1249,41 +1254,41 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
*/
static void process_srcu(struct work_struct *work)
{
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
- sp = container_of(work, struct srcu_struct, work.work);
+ ssp = container_of(work, struct srcu_struct, work.work);
- srcu_advance_state(sp);
- srcu_reschedule(sp, srcu_get_delay(sp));
+ srcu_advance_state(ssp);
+ srcu_reschedule(ssp, srcu_get_delay(ssp));
}
void srcutorture_get_gp_data(enum rcutorture_type test_type,
- struct srcu_struct *sp, int *flags,
+ struct srcu_struct *ssp, int *flags,
unsigned long *gp_seq)
{
if (test_type != SRCU_FLAVOR)
return;
*flags = 0;
- *gp_seq = rcu_seq_current(&sp->srcu_gp_seq);
+ *gp_seq = rcu_seq_current(&ssp->srcu_gp_seq);
}
EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
-void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
+void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
{
int cpu;
int idx;
unsigned long s0 = 0, s1 = 0;
- idx = sp->srcu_idx & 0x1;
+ idx = ssp->srcu_idx & 0x1;
pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):",
- tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx);
+ tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), idx);
for_each_possible_cpu(cpu) {
unsigned long l0, l1;
unsigned long u0, u1;
long c0, c1;
struct srcu_data *sdp;
- sdp = per_cpu_ptr(sp->sda, cpu);
+ sdp = per_cpu_ptr(ssp->sda, cpu);
u0 = sdp->srcu_unlock_count[!idx];
u1 = sdp->srcu_unlock_count[idx];
@@ -1318,14 +1323,14 @@ early_initcall(srcu_bootup_announce);
void __init srcu_init(void)
{
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
srcu_init_done = true;
while (!list_empty(&srcu_boot_list)) {
- sp = list_first_entry(&srcu_boot_list, struct srcu_struct,
+ ssp = list_first_entry(&srcu_boot_list, struct srcu_struct,
work.work.entry);
- check_init_srcu_struct(sp);
- list_del_init(&sp->work.work.entry);
- queue_work(rcu_gp_wq, &sp->work.work);
+ check_init_srcu_struct(ssp);
+ list_del_init(&ssp->work.work.entry);
+ queue_work(rcu_gp_wq, &ssp->work.work);
}
}
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index 3f943efcf61c..be10036fa621 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -44,15 +44,15 @@ static const struct {
__INIT_HELD(rcu_read_lock_held)
},
[RCU_SCHED_SYNC] = {
- .sync = synchronize_sched,
- .call = call_rcu_sched,
- .wait = rcu_barrier_sched,
+ .sync = synchronize_rcu,
+ .call = call_rcu,
+ .wait = rcu_barrier,
__INIT_HELD(rcu_read_lock_sched_held)
},
[RCU_BH_SYNC] = {
- .sync = synchronize_rcu_bh,
- .call = call_rcu_bh,
- .wait = rcu_barrier_bh,
+ .sync = synchronize_rcu,
+ .call = call_rcu,
+ .wait = rcu_barrier,
__INIT_HELD(rcu_read_lock_bh_held)
},
};
@@ -125,8 +125,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
rsp->gp_state = GP_PENDING;
spin_unlock_irq(&rsp->rss_lock);
- BUG_ON(need_wait && need_sync);
-
+ WARN_ON_ONCE(need_wait && need_sync);
if (need_sync) {
gp_ops[rsp->gp_type].sync();
rsp->gp_state = GP_PASSED;
@@ -139,7 +138,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
* Nobody has yet been allowed the 'fast' path and thus we can
* avoid doing any sync(). The callback will get 'dropped'.
*/
- BUG_ON(rsp->gp_state != GP_PASSED);
+ WARN_ON_ONCE(rsp->gp_state != GP_PASSED);
}
}
@@ -166,8 +165,8 @@ static void rcu_sync_func(struct rcu_head *rhp)
struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head);
unsigned long flags;
- BUG_ON(rsp->gp_state != GP_PASSED);
- BUG_ON(rsp->cb_state == CB_IDLE);
+ WARN_ON_ONCE(rsp->gp_state != GP_PASSED);
+ WARN_ON_ONCE(rsp->cb_state == CB_IDLE);
spin_lock_irqsave(&rsp->rss_lock, flags);
if (rsp->gp_count) {
@@ -225,7 +224,7 @@ void rcu_sync_dtor(struct rcu_sync *rsp)
{
int cb_state;
- BUG_ON(rsp->gp_count);
+ WARN_ON_ONCE(rsp->gp_count);
spin_lock_irq(&rsp->rss_lock);
if (rsp->cb_state == CB_REPLAY)
@@ -235,6 +234,6 @@ void rcu_sync_dtor(struct rcu_sync *rsp)
if (cb_state != CB_IDLE) {
gp_ops[rsp->gp_type].wait();
- BUG_ON(rsp->cb_state != CB_IDLE);
+ WARN_ON_ONCE(rsp->cb_state != CB_IDLE);
}
}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 121f833acd04..9180158756d2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -207,6 +207,19 @@ static int rcu_gp_in_progress(void)
return rcu_seq_state(rcu_seq_current(&rcu_state.gp_seq));
}
+/*
+ * Return the number of callbacks queued on the specified CPU.
+ * Handles both the nocbs and normal cases.
+ */
+static long rcu_get_n_cbs_cpu(int cpu)
+{
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+ if (rcu_segcblist_is_enabled(&rdp->cblist)) /* Online normal CPU? */
+ return rcu_segcblist_n_cbs(&rdp->cblist);
+ return rcu_get_n_cbs_nocb_cpu(rdp); /* Works for offline, too. */
+}
+
void rcu_softirq_qs(void)
{
rcu_qs();
@@ -500,16 +513,29 @@ void rcu_force_quiescent_state(void)
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
+ * Convert a ->gp_state value to a character string.
+ */
+static const char *gp_state_getname(short gs)
+{
+ if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
+ return "???";
+ return gp_state_names[gs];
+}
+
+/*
* Show the state of the grace-period kthreads.
*/
void show_rcu_gp_kthreads(void)
{
int cpu;
+ unsigned long j;
struct rcu_data *rdp;
struct rcu_node *rnp;
- pr_info("%s: wait state: %d ->state: %#lx\n", rcu_state.name,
- rcu_state.gp_state, rcu_state.gp_kthread->state);
+ j = jiffies - READ_ONCE(rcu_state.gp_activity);
+ pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %ld\n",
+ rcu_state.name, gp_state_getname(rcu_state.gp_state),
+ rcu_state.gp_state, rcu_state.gp_kthread->state, j);
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
continue;
@@ -891,12 +917,12 @@ void rcu_irq_enter_irqson(void)
}
/**
- * rcu_is_watching - see if RCU thinks that the current CPU is idle
+ * rcu_is_watching - see if RCU thinks that the current CPU is not idle
*
* Return true if RCU is watching the running CPU, which means that this
* CPU can safely enter RCU read-side critical sections. In other words,
- * if the current CPU is in its idle loop and is neither in an interrupt
- * or NMI handler, return true.
+ * if the current CPU is not in its idle loop or is in an interrupt or
+ * NMI handler, return true.
*/
bool notrace rcu_is_watching(void)
{
@@ -1143,16 +1169,6 @@ static void record_gp_stall_check_time(void)
}
/*
- * Convert a ->gp_state value to a character string.
- */
-static const char *gp_state_getname(short gs)
-{
- if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
- return "???";
- return gp_state_names[gs];
-}
-
-/*
* Complain about starvation of grace-period kthread.
*/
static void rcu_check_gp_kthread_starvation(void)
@@ -1262,8 +1278,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
- totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(&rcu_data,
- cpu)->cblist);
+ totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
@@ -1323,8 +1338,7 @@ static void print_cpu_stall(void)
raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
- totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(&rcu_data,
- cpu)->cblist);
+ totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
jiffies - rcu_state.gp_start,
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
@@ -1986,7 +2000,8 @@ static void rcu_gp_cleanup(void)
WRITE_ONCE(rcu_state.gp_activity, jiffies);
raw_spin_lock_irq_rcu_node(rnp);
- gp_duration = jiffies - rcu_state.gp_start;
+ rcu_state.gp_end = jiffies;
+ gp_duration = rcu_state.gp_end - rcu_state.gp_start;
if (gp_duration > rcu_state.gp_max)
rcu_state.gp_max = gp_duration;
@@ -2032,9 +2047,9 @@ static void rcu_gp_cleanup(void)
rnp = rcu_get_root();
raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */
- /* Declare grace period done. */
- rcu_seq_end(&rcu_state.gp_seq);
+ /* Declare grace period done, trace first to use old GP number. */
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
+ rcu_seq_end(&rcu_state.gp_seq);
rcu_state.gp_state = RCU_GP_IDLE;
/* Check for GP requests since above loop. */
rdp = this_cpu_ptr(&rcu_data);
@@ -2600,10 +2615,10 @@ static void force_quiescent_state(void)
* This function checks for grace-period requests that fail to motivate
* RCU to come out of its idle mode.
*/
-static void
-rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp)
+void
+rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+ const unsigned long gpssdelay)
{
- const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
unsigned long flags;
unsigned long j;
struct rcu_node *rnp_root = rcu_get_root();
@@ -2655,6 +2670,48 @@ rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp)
}
/*
+ * Do a forward-progress check for rcutorture. This is normally invoked
+ * due to an OOM event. The argument "j" gives the time period during
+ * which rcutorture would like progress to have been made.
+ */
+void rcu_fwd_progress_check(unsigned long j)
+{
+ unsigned long cbs;
+ int cpu;
+ unsigned long max_cbs = 0;
+ int max_cpu = -1;
+ struct rcu_data *rdp;
+
+ if (rcu_gp_in_progress()) {
+ pr_info("%s: GP age %lu jiffies\n",
+ __func__, jiffies - rcu_state.gp_start);
+ show_rcu_gp_kthreads();
+ } else {
+ pr_info("%s: Last GP end %lu jiffies ago\n",
+ __func__, jiffies - rcu_state.gp_end);
+ preempt_disable();
+ rdp = this_cpu_ptr(&rcu_data);
+ rcu_check_gp_start_stall(rdp->mynode, rdp, j);
+ preempt_enable();
+ }
+ for_each_possible_cpu(cpu) {
+ cbs = rcu_get_n_cbs_cpu(cpu);
+ if (!cbs)
+ continue;
+ if (max_cpu < 0)
+ pr_info("%s: callbacks", __func__);
+ pr_cont(" %d: %lu", cpu, cbs);
+ if (cbs <= max_cbs)
+ continue;
+ max_cbs = cbs;
+ max_cpu = cpu;
+ }
+ if (max_cpu >= 0)
+ pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
+
+/*
* This does the RCU core processing work for the specified rcu_data
* structures. This may be called only from the CPU to whom the rdp
* belongs.
@@ -2690,7 +2747,7 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused
local_irq_restore(flags);
}
- rcu_check_gp_start_stall(rnp, rdp);
+ rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
/* If there are callbacks ready, invoke them. */
if (rcu_segcblist_ready_cbs(&rdp->cblist))
@@ -2826,7 +2883,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy)
* Very early boot, before rcu_init(). Initialize if needed
* and then drop through to queue the callback.
*/
- BUG_ON(cpu != -1);
+ WARN_ON_ONCE(cpu != -1);
WARN_ON_ONCE(!rcu_is_watching());
if (rcu_segcblist_empty(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist);
@@ -3485,7 +3542,8 @@ static int __init rcu_spawn_gp_kthread(void)
rcu_scheduler_fully_active = 1;
t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name);
- BUG_ON(IS_ERR(t));
+ if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__))
+ return 0;
rnp = rcu_get_root();
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rcu_state.gp_kthread = t;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 703e19ff532d..d90b02b53c0e 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -57,7 +57,7 @@ struct rcu_node {
/* some rcu_state fields as well as */
/* following. */
unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */
- unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
+ unsigned long gp_seq_needed; /* Track furthest future GP request. */
unsigned long completedqs; /* All QSes done for this node. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
@@ -163,7 +163,7 @@ union rcu_noqs {
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */
- unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */
+ unsigned long gp_seq_needed; /* Track furthest future GP request. */
union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */
bool core_needs_qs; /* Core waits for quiesc state. */
bool beenonline; /* CPU online at least once. */
@@ -328,6 +328,8 @@ struct rcu_state {
/* force_quiescent_state(). */
unsigned long gp_start; /* Time at which GP started, */
/* but in jiffies. */
+ unsigned long gp_end; /* Time last GP ended, again */
+ /* in jiffies. */
unsigned long gp_activity; /* Time of last GP kthread */
/* activity in jiffies. */
unsigned long gp_req_activity; /* Time of last GP request */
@@ -398,17 +400,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
#define RCU_NAME rcu_name
#endif /* #else #ifdef CONFIG_TRACING */
-/*
- * RCU implementation internal declarations:
- */
-extern struct rcu_state rcu_sched_state;
-
-extern struct rcu_state rcu_bh_state;
-
-#ifdef CONFIG_PREEMPT_RCU
-extern struct rcu_state rcu_preempt_state;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-
int rcu_dynticks_snap(struct rcu_data *rdp);
#ifdef CONFIG_RCU_BOOST
@@ -466,6 +457,7 @@ static void __init rcu_spawn_nocb_kthreads(void);
static void __init rcu_organize_nocb_kthreads(void);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
static bool init_nocb_callback_list(struct rcu_data *rdp);
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp);
static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(void);
static void rcu_dynticks_task_enter(void);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 8d18c1014e2b..928fe5893a57 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -450,10 +450,12 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
}
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
preempt_disable();
- cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
+ cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
/* If all offline, queue the work on an unbound CPU. */
- if (unlikely(cpu > rnp->grphi))
+ if (unlikely(cpu > rnp->grphi - rnp->grplo))
cpu = WORK_CPU_UNBOUND;
+ else
+ cpu += rnp->grplo;
queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
preempt_enable();
rnp->exp_need_flush = true;
@@ -690,8 +692,10 @@ static void sync_rcu_exp_handler(void *unused)
*/
if (t->rcu_read_lock_nesting > 0) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if (rnp->expmask & rdp->grpmask)
+ if (rnp->expmask & rdp->grpmask) {
rdp->deferred_qs = true;
+ WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
+ }
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 05915e536336..1b3dd2fc0cd6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -397,6 +397,11 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
return rnp->gp_tasks != NULL;
}
+/* Bias and limit values for ->rcu_read_lock_nesting. */
+#define RCU_NEST_BIAS INT_MAX
+#define RCU_NEST_NMAX (-INT_MAX / 2)
+#define RCU_NEST_PMAX (INT_MAX / 2)
+
/*
* Preemptible RCU implementation for rcu_read_lock().
* Just increment ->rcu_read_lock_nesting, shared state will be updated
@@ -405,6 +410,8 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
void __rcu_read_lock(void)
{
current->rcu_read_lock_nesting++;
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING))
+ WARN_ON_ONCE(current->rcu_read_lock_nesting > RCU_NEST_PMAX);
barrier(); /* critical section after entry code. */
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -424,20 +431,18 @@ void __rcu_read_unlock(void)
--t->rcu_read_lock_nesting;
} else {
barrier(); /* critical section before exit code. */
- t->rcu_read_lock_nesting = INT_MIN;
+ t->rcu_read_lock_nesting = -RCU_NEST_BIAS;
barrier(); /* assign before ->rcu_read_unlock_special load */
if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
rcu_read_unlock_special(t);
barrier(); /* ->rcu_read_unlock_special load before assign */
t->rcu_read_lock_nesting = 0;
}
-#ifdef CONFIG_PROVE_LOCKING
- {
- int rrln = READ_ONCE(t->rcu_read_lock_nesting);
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+ int rrln = t->rcu_read_lock_nesting;
- WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+ WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX);
}
-#endif /* #ifdef CONFIG_PROVE_LOCKING */
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);
@@ -597,7 +602,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
*/
static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
{
- return (this_cpu_ptr(&rcu_data)->deferred_qs ||
+ return (__this_cpu_read(rcu_data.deferred_qs) ||
READ_ONCE(t->rcu_read_unlock_special.s)) &&
t->rcu_read_lock_nesting <= 0;
}
@@ -617,11 +622,11 @@ static void rcu_preempt_deferred_qs(struct task_struct *t)
if (!rcu_preempt_need_deferred_qs(t))
return;
if (couldrecurse)
- t->rcu_read_lock_nesting -= INT_MIN;
+ t->rcu_read_lock_nesting -= RCU_NEST_BIAS;
local_irq_save(flags);
rcu_preempt_deferred_qs_irqrestore(t, flags);
if (couldrecurse)
- t->rcu_read_lock_nesting += INT_MIN;
+ t->rcu_read_lock_nesting += RCU_NEST_BIAS;
}
/*
@@ -642,13 +647,21 @@ static void rcu_read_unlock_special(struct task_struct *t)
local_irq_save(flags);
irqs_were_disabled = irqs_disabled_flags(flags);
- if ((preempt_bh_were_disabled || irqs_were_disabled) &&
- t->rcu_read_unlock_special.b.blocked) {
+ if (preempt_bh_were_disabled || irqs_were_disabled) {
+ WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
/* Need to defer quiescent state until everything is enabled. */
- raise_softirq_irqoff(RCU_SOFTIRQ);
+ if (irqs_were_disabled) {
+ /* Enabling irqs does not reschedule, so... */
+ raise_softirq_irqoff(RCU_SOFTIRQ);
+ } else {
+ /* Enabling BH or preempt does reschedule, so... */
+ set_tsk_need_resched(current);
+ set_preempt_need_resched();
+ }
local_irq_restore(flags);
return;
}
+ WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
rcu_preempt_deferred_qs_irqrestore(t, flags);
}
@@ -1464,7 +1477,8 @@ static void __init rcu_spawn_boost_kthreads(void)
for_each_possible_cpu(cpu)
per_cpu(rcu_cpu_has_work, cpu) = 0;
- BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
+ if (WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcub kthread, OOM is now expected behavior\n", __func__))
+ return;
rcu_for_each_leaf_node(rnp)
(void)rcu_spawn_one_boost_kthread(rnp);
}
@@ -1997,7 +2011,7 @@ static bool rcu_nocb_cpu_needs_barrier(int cpu)
* (if a callback is in fact needed). This is associated with an
* atomic_inc() in the caller.
*/
- ret = atomic_long_read(&rdp->nocb_q_count);
+ ret = rcu_get_n_cbs_nocb_cpu(rdp);
#ifdef CONFIG_PROVE_RCU
rhp = READ_ONCE(rdp->nocb_head);
@@ -2052,7 +2066,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
TPS("WakeNotPoll"));
return;
}
- len = atomic_long_read(&rdp->nocb_q_count);
+ len = rcu_get_n_cbs_nocb_cpu(rdp);
if (old_rhpp == &rdp->nocb_head) {
if (!irqs_disabled_flags(flags)) {
/* ... if queue was empty ... */
@@ -2101,11 +2115,11 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
trace_rcu_kfree_callback(rcu_state.name, rhp,
(unsigned long)rhp->func,
-atomic_long_read(&rdp->nocb_q_count_lazy),
- -atomic_long_read(&rdp->nocb_q_count));
+ -rcu_get_n_cbs_nocb_cpu(rdp));
else
trace_rcu_callback(rcu_state.name, rhp,
-atomic_long_read(&rdp->nocb_q_count_lazy),
- -atomic_long_read(&rdp->nocb_q_count));
+ -rcu_get_n_cbs_nocb_cpu(rdp));
/*
* If called from an extended quiescent state with interrupts
@@ -2322,13 +2336,14 @@ static int rcu_nocb_kthread(void *arg)
tail = rdp->nocb_follower_tail;
rdp->nocb_follower_tail = &rdp->nocb_follower_head;
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
- BUG_ON(!list);
+ if (WARN_ON_ONCE(!list))
+ continue;
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeNonEmpty"));
/* Each pass through the following loop invokes a callback. */
trace_rcu_batch_start(rcu_state.name,
atomic_long_read(&rdp->nocb_q_count_lazy),
- atomic_long_read(&rdp->nocb_q_count), -1);
+ rcu_get_n_cbs_nocb_cpu(rdp), -1);
c = cl = 0;
while (list) {
next = list->next;
@@ -2495,7 +2510,8 @@ static void rcu_spawn_one_nocb_kthread(int cpu)
/* Spawn the kthread for this CPU. */
t = kthread_run(rcu_nocb_kthread, rdp_spawn,
"rcuo%c/%d", rcu_state.abbr, cpu);
- BUG_ON(IS_ERR(t));
+ if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo kthread, OOM is now expected behavior\n", __func__))
+ return;
WRITE_ONCE(rdp_spawn->nocb_kthread, t);
}
@@ -2587,6 +2603,26 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
return true;
}
+/*
+ * Bind the current task to the offloaded CPUs. If there are no offloaded
+ * CPUs, leave the task unbound. Splat if the bind attempt fails.
+ */
+void rcu_bind_current_to_nocb(void)
+{
+ if (cpumask_available(rcu_nocb_mask) && cpumask_weight(rcu_nocb_mask))
+ WARN_ON(sched_setaffinity(current->pid, rcu_nocb_mask));
+}
+EXPORT_SYMBOL_GPL(rcu_bind_current_to_nocb);
+
+/*
+ * Return the number of RCU callbacks still queued from the specified
+ * CPU, which must be a nocbs CPU.
+ */
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp)
+{
+ return atomic_long_read(&rdp->nocb_q_count);
+}
+
#else /* #ifdef CONFIG_RCU_NOCB_CPU */
static bool rcu_nocb_cpu_needs_barrier(int cpu)
@@ -2647,6 +2683,11 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
return false;
}
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp)
+{
+ return 0;
+}
+
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
/*
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index f203b94f6b5b..1971869c4072 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -335,8 +335,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
/* Initialize and register callbacks for each crcu_array element. */
for (i = 0; i < n; i++) {
if (checktiny &&
- (crcu_array[i] == call_rcu ||
- crcu_array[i] == call_rcu_bh)) {
+ (crcu_array[i] == call_rcu)) {
might_sleep();
continue;
}
@@ -352,8 +351,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
/* Wait for all callbacks to be invoked. */
for (i = 0; i < n; i++) {
if (checktiny &&
- (crcu_array[i] == call_rcu ||
- crcu_array[i] == call_rcu_bh))
+ (crcu_array[i] == call_rcu))
continue;
for (j = 0; j < i; j++)
if (crcu_array[j] == crcu_array[i])
@@ -822,7 +820,8 @@ static int __init rcu_spawn_tasks_kthread(void)
struct task_struct *t;
t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
- BUG_ON(IS_ERR(t));
+ if (WARN_ONCE(IS_ERR(t), "%s: Could not start Tasks-RCU grace-period kthread, OOM is now expected behavior\n", __func__))
+ return 0;
smp_mb(); /* Ensure others see full kthread. */
WRITE_ONCE(rcu_tasks_kthread_ptr, t);
return 0;
diff --git a/kernel/resource.c b/kernel/resource.c
index b3a3a1fc499e..b0fbf685c77a 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -319,16 +319,23 @@ int release_resource(struct resource *old)
EXPORT_SYMBOL(release_resource);
/**
- * Finds the lowest iomem resource that covers part of [start..end]. The
- * caller must specify start, end, flags, and desc (which may be
+ * Finds the lowest iomem resource that covers part of [@start..@end]. The
+ * caller must specify @start, @end, @flags, and @desc (which may be
* IORES_DESC_NONE).
*
- * If a resource is found, returns 0 and *res is overwritten with the part
- * of the resource that's within [start..end]; if none is found, returns
- * -1.
+ * If a resource is found, returns 0 and @*res is overwritten with the part
+ * of the resource that's within [@start..@end]; if none is found, returns
+ * -1 or -EINVAL for other invalid parameters.
*
* This function walks the whole tree and not just first level children
* unless @first_lvl is true.
+ *
+ * @start: start address of the resource searched for
+ * @end: end address of same resource
+ * @flags: flags which the resource must have
+ * @desc: descriptor the resource must have
+ * @first_lvl: walk only the first level children, if set
+ * @res: return ptr, if resource found
*/
static int find_next_iomem_res(resource_size_t start, resource_size_t end,
unsigned long flags, unsigned long desc,
@@ -399,6 +406,8 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
* @flags: I/O resource flags
* @start: start addr
* @end: end addr
+ * @arg: function argument for the callback @func
+ * @func: callback function that is called for each qualifying resource area
*
* NOTE: For a new descriptor search, define a new IORES_DESC in
* <linux/ioport.h> and set it in 'desc' of a target resource entry.
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 7fe183404c38..21fb5a5662b5 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o
obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
obj-$(CONFIG_MEMBARRIER) += membarrier.o
obj-$(CONFIG_CPU_ISOLATION) += isolation.o
+obj-$(CONFIG_PSI) += psi.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2e696b03e99d..f66920173370 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -697,7 +697,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
/*
* SCHED_IDLE tasks get minimal weight:
*/
- if (idle_policy(p->policy)) {
+ if (task_has_idle_policy(p)) {
load->weight = scale_load(WEIGHT_IDLEPRIO);
load->inv_weight = WMULT_IDLEPRIO;
p->se.runnable_weight = load->weight;
@@ -722,8 +722,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
if (!(flags & ENQUEUE_NOCLOCK))
update_rq_clock(rq);
- if (!(flags & ENQUEUE_RESTORE))
+ if (!(flags & ENQUEUE_RESTORE)) {
sched_info_queued(rq, p);
+ psi_enqueue(p, flags & ENQUEUE_WAKEUP);
+ }
p->sched_class->enqueue_task(rq, p, flags);
}
@@ -733,8 +735,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
if (!(flags & DEQUEUE_NOCLOCK))
update_rq_clock(rq);
- if (!(flags & DEQUEUE_SAVE))
+ if (!(flags & DEQUEUE_SAVE)) {
sched_info_dequeued(rq, p);
+ psi_dequeue(p, flags & DEQUEUE_SLEEP);
+ }
p->sched_class->dequeue_task(rq, p, flags);
}
@@ -2037,6 +2041,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
+ psi_ttwu_dequeue(p);
set_task_cpu(p, cpu);
}
@@ -2852,7 +2857,7 @@ unsigned long nr_running(void)
* preemption, thus the result might have a time-of-check-to-time-of-use
* race. The caller is responsible to use it correctly, for example:
*
- * - from a non-preemptable section (of course)
+ * - from a non-preemptible section (of course)
*
* - from a thread that is bound to a single CPU
*
@@ -2876,6 +2881,18 @@ unsigned long long nr_context_switches(void)
}
/*
+ * Consumers of these two interfaces, like for example the cpuidle menu
+ * governor, are using nonsensical data. Preferring shallow idle state selection
+ * for a CPU that has IO-wait which might not even end up running the task when
+ * it does become runnable.
+ */
+
+unsigned long nr_iowait_cpu(int cpu)
+{
+ return atomic_read(&cpu_rq(cpu)->nr_iowait);
+}
+
+/*
* IO-wait accounting, and how its mostly bollocks (on SMP).
*
* The idea behind IO-wait account is to account the idle time that we could
@@ -2910,31 +2927,11 @@ unsigned long nr_iowait(void)
unsigned long i, sum = 0;
for_each_possible_cpu(i)
- sum += atomic_read(&cpu_rq(i)->nr_iowait);
+ sum += nr_iowait_cpu(i);
return sum;
}
-/*
- * Consumers of these two interfaces, like for example the cpuidle menu
- * governor, are using nonsensical data. Preferring shallow idle state selection
- * for a CPU that has IO-wait which might not even end up running the task when
- * it does become runnable.
- */
-
-unsigned long nr_iowait_cpu(int cpu)
-{
- struct rq *this = cpu_rq(cpu);
- return atomic_read(&this->nr_iowait);
-}
-
-void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
-{
- struct rq *rq = this_rq();
- *nr_waiters = atomic_read(&rq->nr_iowait);
- *load = rq->load.weight;
-}
-
#ifdef CONFIG_SMP
/*
@@ -3051,6 +3048,7 @@ void scheduler_tick(void)
curr->sched_class->task_tick(rq, curr, 0);
cpu_load_update_active(rq);
calc_global_load_tick(rq);
+ psi_task_tick(rq);
rq_unlock(rq, &rf);
@@ -4193,7 +4191,7 @@ recheck:
* Treat SCHED_IDLE as nice 20. Only allow a switch to
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
*/
- if (idle_policy(p->policy) && !idle_policy(policy)) {
+ if (task_has_idle_policy(p) && !idle_policy(policy)) {
if (!can_nice(p, task_nice(p)))
return -EPERM;
}
@@ -4933,9 +4931,7 @@ static void do_sched_yield(void)
struct rq_flags rf;
struct rq *rq;
- local_irq_disable();
- rq = this_rq();
- rq_lock(rq, &rf);
+ rq = this_rq_lock_irq(&rf);
schedstat_inc(rq->yld_count);
current->sched_class->yield_task(rq);
@@ -5742,15 +5738,10 @@ int sched_cpu_activate(unsigned int cpu)
#ifdef CONFIG_SCHED_SMT
/*
- * The sched_smt_present static key needs to be evaluated on every
- * hotplug event because at boot time SMT might be disabled when
- * the number of booted CPUs is limited.
- *
- * If then later a sibling gets hotplugged, then the key would stay
- * off and SMT scheduling would never be functional.
+ * When going up, increment the number of cores with SMT present.
*/
- if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
- static_branch_enable_cpuslocked(&sched_smt_present);
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ static_branch_inc_cpuslocked(&sched_smt_present);
#endif
set_cpu_active(cpu, true);
@@ -5792,7 +5783,15 @@ int sched_cpu_deactivate(unsigned int cpu)
*
* Do sync before park smpboot threads to take care the rcu boost case.
*/
- synchronize_rcu_mult(call_rcu, call_rcu_sched);
+ synchronize_rcu();
+
+#ifdef CONFIG_SCHED_SMT
+ /*
+ * When going down, decrement the number of cores with SMT present.
+ */
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ static_branch_dec_cpuslocked(&sched_smt_present);
+#endif
if (!sched_smp_initialized)
return 0;
@@ -5855,11 +5854,14 @@ void __init sched_init_smp(void)
/*
* There's no userspace yet to cause hotplug operations; hence all the
* CPU masks are stable and all blatant races in the below code cannot
- * happen.
+ * happen. The hotplug lock is nevertheless taken to satisfy lockdep,
+ * but there won't be any contention on it.
*/
+ cpus_read_lock();
mutex_lock(&sched_domains_mutex);
sched_init_domains(cpu_active_mask);
mutex_unlock(&sched_domains_mutex);
+ cpus_read_unlock();
/* Move init over to a non-isolated CPU */
if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
@@ -6069,6 +6071,8 @@ void __init sched_init(void)
init_schedstats();
+ psi_init();
+
scheduler_running = 1;
}
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 5e54cbcae673..22bd8980f32f 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Scheduler code and data structures related to cpufreq.
*
* Copyright (C) 2016, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include "sched.h"
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3fffad3bc8a8..033ec7c45f13 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -1,18 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* CPUFreq governor based on scheduler-provided CPU utilization data.
*
* Copyright (C) 2016, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include "sched.h"
+#include <linux/sched/cpufreq.h>
#include <trace/events/power.h>
struct sugov_tunables {
@@ -167,7 +165,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
unsigned int freq = arch_scale_freq_invariant() ?
policy->cpuinfo.max_freq : policy->cur;
- freq = (freq + (freq >> 2)) * util / max;
+ freq = map_util_freq(util, freq, max);
if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
return sg_policy->next_freq;
@@ -197,15 +195,13 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
* based on the task model parameters and gives the minimal utilization
* required to meet deadlines.
*/
-static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
+ unsigned long max, enum schedutil_type type)
{
- struct rq *rq = cpu_rq(sg_cpu->cpu);
- unsigned long util, irq, max;
-
- sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
- sg_cpu->bw_dl = cpu_bw_dl(rq);
+ unsigned long dl_util, util, irq;
+ struct rq *rq = cpu_rq(cpu);
- if (rt_rq_is_runnable(&rq->rt))
+ if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt))
return max;
/*
@@ -223,22 +219,31 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
* utilization (PELT windows are synchronized) we can directly add them
* to obtain the CPU's actual utilization.
*/
- util = cpu_util_cfs(rq);
+ util = util_cfs;
util += cpu_util_rt(rq);
+ dl_util = cpu_util_dl(rq);
+
/*
- * We do not make cpu_util_dl() a permanent part of this sum because we
- * want to use cpu_bw_dl() later on, but we need to check if the
- * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
- * f_max when there is no idle time.
+ * For frequency selection we do not make cpu_util_dl() a permanent part
+ * of this sum because we want to use cpu_bw_dl() later on, but we need
+ * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
+ * that we select f_max when there is no idle time.
*
* NOTE: numerical errors or stop class might cause us to not quite hit
* saturation when we should -- something for later.
*/
- if ((util + cpu_util_dl(rq)) >= max)
+ if (util + dl_util >= max)
return max;
/*
+ * OTOH, for energy computation we need the estimated running time, so
+ * include util_dl and ignore dl_bw.
+ */
+ if (type == ENERGY_UTIL)
+ util += dl_util;
+
+ /*
* There is still idle time; further improve the number by using the
* irq metric. Because IRQ/steal time is hidden from the task clock we
* need to scale the task numbers:
@@ -260,7 +265,22 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
* bw_dl as requested freq. However, cpufreq is not yet ready for such
* an interface. So, we only do the latter for now.
*/
- return min(max, util + sg_cpu->bw_dl);
+ if (type == FREQUENCY_UTIL)
+ util += cpu_bw_dl(rq);
+
+ return min(max, util);
+}
+
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+{
+ struct rq *rq = cpu_rq(sg_cpu->cpu);
+ unsigned long util = cpu_util_cfs(rq);
+ unsigned long max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+
+ sg_cpu->max = max;
+ sg_cpu->bw_dl = cpu_bw_dl(rq);
+
+ return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL);
}
/**
@@ -601,7 +621,7 @@ static struct kobj_type sugov_tunables_ktype = {
/********************** cpufreq governor interface *********************/
-static struct cpufreq_governor schedutil_gov;
+struct cpufreq_governor schedutil_gov;
static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
{
@@ -860,7 +880,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
sg_policy->need_freq_update = true;
}
-static struct cpufreq_governor schedutil_gov = {
+struct cpufreq_governor schedutil_gov = {
.name = "schedutil",
.owner = THIS_MODULE,
.dynamic_switching = true,
@@ -883,3 +903,36 @@ static int __init sugov_register(void)
return cpufreq_register_governor(&schedutil_gov);
}
fs_initcall(sugov_register);
+
+#ifdef CONFIG_ENERGY_MODEL
+extern bool sched_energy_update;
+extern struct mutex sched_energy_mutex;
+
+static void rebuild_sd_workfn(struct work_struct *work)
+{
+ mutex_lock(&sched_energy_mutex);
+ sched_energy_update = true;
+ rebuild_sched_domains();
+ sched_energy_update = false;
+ mutex_unlock(&sched_energy_mutex);
+}
+static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
+
+/*
+ * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
+ * on governor changes to make sure the scheduler knows about it.
+ */
+void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+ struct cpufreq_governor *old_gov)
+{
+ if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) {
+ /*
+ * When called from the cpufreq_register_driver() path, the
+ * cpu_hotplug_lock is already held, so use a work item to
+ * avoid nested locking in rebuild_sched_domains().
+ */
+ schedule_work(&rebuild_sd_work);
+ }
+
+}
+#endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 0796f938c4f0..ba4a143bdcf3 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -525,7 +525,7 @@ void account_idle_ticks(unsigned long ticks)
/*
* Perform (stime * rtime) / total, but avoid multiplication overflow by
- * loosing precision when the numbers are big.
+ * losing precision when the numbers are big.
*/
static u64 scale_stime(u64 stime, u64 rtime, u64 total)
{
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 91e4202b0634..fb8b7b5d745d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -727,7 +727,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
* refill the runtime and set the deadline a period in the future,
* because keeping the current (absolute) deadline of the task would
* result in breaking guarantees promised to other tasks (refer to
- * Documentation/scheduler/sched-deadline.txt for more informations).
+ * Documentation/scheduler/sched-deadline.txt for more information).
*
* This function returns true if:
*
@@ -1695,6 +1695,14 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
}
#endif
+static inline void set_next_task(struct rq *rq, struct task_struct *p)
+{
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* You can't push away the running task */
+ dequeue_pushable_dl_task(rq, p);
+}
+
static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
struct dl_rq *dl_rq)
{
@@ -1750,10 +1758,8 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
BUG_ON(!dl_se);
p = dl_task_of(dl_se);
- p->se.exec_start = rq_clock_task(rq);
- /* Running task will never be pushed. */
- dequeue_pushable_dl_task(rq, p);
+ set_next_task(rq, p);
if (hrtick_enabled(rq))
start_hrtick_dl(rq, p);
@@ -1808,12 +1814,7 @@ static void task_fork_dl(struct task_struct *p)
static void set_curr_task_dl(struct rq *rq)
{
- struct task_struct *p = rq->curr;
-
- p->se.exec_start = rq_clock_task(rq);
-
- /* You can't push away the running task */
- dequeue_pushable_dl_task(rq, p);
+ set_next_task(rq, rq->curr);
}
#ifdef CONFIG_SMP
@@ -2041,10 +2042,8 @@ static int push_dl_task(struct rq *rq)
return 0;
retry:
- if (unlikely(next_task == rq->curr)) {
- WARN_ON(1);
+ if (WARN_ON(next_task == rq->curr))
return 0;
- }
/*
* If next_task preempts rq->curr, and rq->curr
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 6383aa6a60ca..02bd5f969b21 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -974,7 +974,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
#endif
P(policy);
P(prio);
- if (p->policy == SCHED_DEADLINE) {
+ if (task_has_dl_policy(p)) {
P(dl.runtime);
P(dl.deadline);
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ee271bb661cc..d1907506318a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -38,7 +38,7 @@
* (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
*/
unsigned int sysctl_sched_latency = 6000000ULL;
-unsigned int normalized_sysctl_sched_latency = 6000000ULL;
+static unsigned int normalized_sysctl_sched_latency = 6000000ULL;
/*
* The initial- and re-scaling of tunables is configurable
@@ -58,8 +58,8 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_L
*
* (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
-unsigned int sysctl_sched_min_granularity = 750000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
+unsigned int sysctl_sched_min_granularity = 750000ULL;
+static unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
/*
* This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
@@ -81,8 +81,8 @@ unsigned int sysctl_sched_child_runs_first __read_mostly;
*
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
-unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
-unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
+static unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
@@ -94,6 +94,14 @@ int __weak arch_asym_cpu_priority(int cpu)
{
return -cpu;
}
+
+/*
+ * The margin used when comparing utilization with CPU capacity:
+ * util * margin < capacity * 1024
+ *
+ * (default: ~20%)
+ */
+static unsigned int capacity_margin = 1280;
#endif
#ifdef CONFIG_CFS_BANDWIDTH
@@ -110,14 +118,6 @@ int __weak arch_asym_cpu_priority(int cpu)
unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
#endif
-/*
- * The margin used when comparing utilization with CPU capacity:
- * util * margin < capacity * 1024
- *
- * (default: ~20%)
- */
-unsigned int capacity_margin = 1280;
-
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
@@ -703,9 +703,9 @@ void init_entity_runnable_average(struct sched_entity *se)
memset(sa, 0, sizeof(*sa));
/*
- * Tasks are intialized with full load to be seen as heavy tasks until
+ * Tasks are initialized with full load to be seen as heavy tasks until
* they get a chance to stabilize to their real load level.
- * Group entities are intialized with zero load to reflect the fact that
+ * Group entities are initialized with zero load to reflect the fact that
* nothing has been attached to the task group yet.
*/
if (entity_is_task(se))
@@ -2400,8 +2400,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
local = 1;
/*
- * Retry task to preferred node migration periodically, in case it
- * case it previously failed, or the scheduler moved us.
+ * Retry to migrate task to preferred node periodically, in case it
+ * previously failed, or the scheduler moved us.
*/
if (time_after(jiffies, p->numa_migrate_retry)) {
task_numa_placement(p);
@@ -2734,6 +2734,17 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
WRITE_ONCE(*ptr, res); \
} while (0)
+/*
+ * Remove and clamp on negative, from a local variable.
+ *
+ * A variant of sub_positive(), which does not use explicit load-store
+ * and is thus optimized for local variable updates.
+ */
+#define lsub_positive(_ptr, _val) do { \
+ typeof(_ptr) ptr = (_ptr); \
+ *ptr -= min_t(typeof(*ptr), *ptr, _val); \
+} while (0)
+
#ifdef CONFIG_SMP
static inline void
enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -3604,7 +3615,7 @@ static inline unsigned long _task_util_est(struct task_struct *p)
{
struct util_est ue = READ_ONCE(p->se.avg.util_est);
- return max(ue.ewma, ue.enqueued);
+ return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
}
static inline unsigned long task_util_est(struct task_struct *p)
@@ -3622,7 +3633,7 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
/* Update root cfs_rq's estimated utilization */
enqueued = cfs_rq->avg.util_est.enqueued;
- enqueued += (_task_util_est(p) | UTIL_AVG_UNCHANGED);
+ enqueued += _task_util_est(p);
WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
}
@@ -3650,8 +3661,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
/* Update root cfs_rq's estimated utilization */
ue.enqueued = cfs_rq->avg.util_est.enqueued;
- ue.enqueued -= min_t(unsigned int, ue.enqueued,
- (_task_util_est(p) | UTIL_AVG_UNCHANGED));
+ ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p));
WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
/*
@@ -3966,8 +3976,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
/*
* When dequeuing a sched_entity, we must:
* - Update loads to have both entity and cfs_rq synced with now.
- * - Substract its load from the cfs_rq->runnable_avg.
- * - Substract its previous weight from cfs_rq->load.weight.
+ * - Subtract its load from the cfs_rq->runnable_avg.
+ * - Subtract its previous weight from cfs_rq->load.weight.
* - For group entity, update its weight to reflect the new share
* of its group cfs_rq.
*/
@@ -4640,7 +4650,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
cfs_b->distribute_running = 0;
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
- cfs_b->runtime -= min(runtime, cfs_b->runtime);
+ lsub_positive(&cfs_b->runtime, runtime);
}
/*
@@ -4774,7 +4784,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
raw_spin_lock(&cfs_b->lock);
if (expires == cfs_b->runtime_expires)
- cfs_b->runtime -= min(runtime, cfs_b->runtime);
+ lsub_positive(&cfs_b->runtime, runtime);
cfs_b->distribute_running = 0;
raw_spin_unlock(&cfs_b->lock);
}
@@ -5072,6 +5082,24 @@ static inline void hrtick_update(struct rq *rq)
}
#endif
+#ifdef CONFIG_SMP
+static inline unsigned long cpu_util(int cpu);
+static unsigned long capacity_of(int cpu);
+
+static inline bool cpu_overutilized(int cpu)
+{
+ return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin);
+}
+
+static inline void update_overutilized_status(struct rq *rq)
+{
+ if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
+ WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
+}
+#else
+static inline void update_overutilized_status(struct rq *rq) { }
+#endif
+
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
@@ -5129,8 +5157,26 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
update_cfs_group(se);
}
- if (!se)
+ if (!se) {
add_nr_running(rq, 1);
+ /*
+ * Since new tasks are assigned an initial util_avg equal to
+ * half of the spare capacity of their CPU, tiny tasks have the
+ * ability to cross the overutilized threshold, which will
+ * result in the load balancer ruining all the task placement
+ * done by EAS. As a way to mitigate that effect, do not account
+ * for the first enqueue operation of new tasks during the
+ * overutilized flag detection.
+ *
+ * A better way of solving this problem would be to wait for
+ * the PELT signals of tasks to converge before taking them
+ * into account, but that is not straightforward to implement,
+ * and the following generally works well enough in practice.
+ */
+ if (flags & ENQUEUE_WAKEUP)
+ update_overutilized_status(rq);
+
+ }
hrtick_update(rq);
}
@@ -5674,11 +5720,11 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
return target;
}
-static unsigned long cpu_util_wake(int cpu, struct task_struct *p);
+static unsigned long cpu_util_without(int cpu, struct task_struct *p);
-static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+static unsigned long capacity_spare_without(int cpu, struct task_struct *p)
{
- return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0);
+ return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0);
}
/*
@@ -5738,7 +5784,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
- spare_cap = capacity_spare_wake(i, p);
+ spare_cap = capacity_spare_without(i, p);
if (spare_cap > max_spare_cap)
max_spare_cap = spare_cap;
@@ -5889,8 +5935,8 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
return prev_cpu;
/*
- * We need task's util for capacity_spare_wake, sync it up to prev_cpu's
- * last_update_time.
+ * We need task's util for capacity_spare_without, sync it up to
+ * prev_cpu's last_update_time.
*/
if (!(sd_flag & SD_BALANCE_FORK))
sync_entity_load_avg(&p->se);
@@ -6216,10 +6262,19 @@ static inline unsigned long cpu_util(int cpu)
}
/*
- * cpu_util_wake: Compute CPU utilization with any contributions from
- * the waking task p removed.
+ * cpu_util_without: compute cpu utilization without any contributions from *p
+ * @cpu: the CPU which utilization is requested
+ * @p: the task which utilization should be discounted
+ *
+ * The utilization of a CPU is defined by the utilization of tasks currently
+ * enqueued on that CPU as well as tasks which are currently sleeping after an
+ * execution on that CPU.
+ *
+ * This method returns the utilization of the specified CPU by discounting the
+ * utilization of the specified task, whenever the task is currently
+ * contributing to the CPU utilization.
*/
-static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
+static unsigned long cpu_util_without(int cpu, struct task_struct *p)
{
struct cfs_rq *cfs_rq;
unsigned int util;
@@ -6231,8 +6286,8 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
cfs_rq = &cpu_rq(cpu)->cfs;
util = READ_ONCE(cfs_rq->avg.util_avg);
- /* Discount task's blocked util from CPU's util */
- util -= min_t(unsigned int, util, task_util(p));
+ /* Discount task's util from CPU's util */
+ lsub_positive(&util, task_util(p));
/*
* Covered cases:
@@ -6240,14 +6295,14 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
* a) if *p is the only task sleeping on this CPU, then:
* cpu_util (== task_util) > util_est (== 0)
* and thus we return:
- * cpu_util_wake = (cpu_util - task_util) = 0
+ * cpu_util_without = (cpu_util - task_util) = 0
*
* b) if other tasks are SLEEPING on this CPU, which is now exiting
* IDLE, then:
* cpu_util >= task_util
* cpu_util > util_est (== 0)
* and thus we discount *p's blocked utilization to return:
- * cpu_util_wake = (cpu_util - task_util) >= 0
+ * cpu_util_without = (cpu_util - task_util) >= 0
*
* c) if other tasks are RUNNABLE on that CPU and
* util_est > cpu_util
@@ -6260,8 +6315,32 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
* covered by the following code when estimated utilization is
* enabled.
*/
- if (sched_feat(UTIL_EST))
- util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued));
+ if (sched_feat(UTIL_EST)) {
+ unsigned int estimated =
+ READ_ONCE(cfs_rq->avg.util_est.enqueued);
+
+ /*
+ * Despite the following checks we still have a small window
+ * for a possible race, when an execl's select_task_rq_fair()
+ * races with LB's detach_task():
+ *
+ * detach_task()
+ * p->on_rq = TASK_ON_RQ_MIGRATING;
+ * ---------------------------------- A
+ * deactivate_task() \
+ * dequeue_task() + RaceTime
+ * util_est_dequeue() /
+ * ---------------------------------- B
+ *
+ * The additional check on "current == p" it's required to
+ * properly fix the execl regression and it helps in further
+ * reducing the chances for the above race.
+ */
+ if (unlikely(task_on_rq_queued(p) || current == p))
+ lsub_positive(&estimated, _task_util_est(p));
+
+ util = max(util, estimated);
+ }
/*
* Utilization (estimated) can exceed the CPU capacity, thus let's
@@ -6299,6 +6378,213 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
}
/*
+ * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued)
+ * to @dst_cpu.
+ */
+static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
+{
+ struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs;
+ unsigned long util_est, util = READ_ONCE(cfs_rq->avg.util_avg);
+
+ /*
+ * If @p migrates from @cpu to another, remove its contribution. Or,
+ * if @p migrates from another CPU to @cpu, add its contribution. In
+ * the other cases, @cpu is not impacted by the migration, so the
+ * util_avg should already be correct.
+ */
+ if (task_cpu(p) == cpu && dst_cpu != cpu)
+ sub_positive(&util, task_util(p));
+ else if (task_cpu(p) != cpu && dst_cpu == cpu)
+ util += task_util(p);
+
+ if (sched_feat(UTIL_EST)) {
+ util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
+
+ /*
+ * During wake-up, the task isn't enqueued yet and doesn't
+ * appear in the cfs_rq->avg.util_est.enqueued of any rq,
+ * so just add it (if needed) to "simulate" what will be
+ * cpu_util() after the task has been enqueued.
+ */
+ if (dst_cpu == cpu)
+ util_est += _task_util_est(p);
+
+ util = max(util, util_est);
+ }
+
+ return min(util, capacity_orig_of(cpu));
+}
+
+/*
+ * compute_energy(): Estimates the energy that would be consumed if @p was
+ * migrated to @dst_cpu. compute_energy() predicts what will be the utilization
+ * landscape of the * CPUs after the task migration, and uses the Energy Model
+ * to compute what would be the energy if we decided to actually migrate that
+ * task.
+ */
+static long
+compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
+{
+ long util, max_util, sum_util, energy = 0;
+ int cpu;
+
+ for (; pd; pd = pd->next) {
+ max_util = sum_util = 0;
+ /*
+ * The capacity state of CPUs of the current rd can be driven by
+ * CPUs of another rd if they belong to the same performance
+ * domain. So, account for the utilization of these CPUs too
+ * by masking pd with cpu_online_mask instead of the rd span.
+ *
+ * If an entire performance domain is outside of the current rd,
+ * it will not appear in its pd list and will not be accounted
+ * by compute_energy().
+ */
+ for_each_cpu_and(cpu, perf_domain_span(pd), cpu_online_mask) {
+ util = cpu_util_next(cpu, p, dst_cpu);
+ util = schedutil_energy_util(cpu, util);
+ max_util = max(util, max_util);
+ sum_util += util;
+ }
+
+ energy += em_pd_energy(pd->em_pd, max_util, sum_util);
+ }
+
+ return energy;
+}
+
+/*
+ * find_energy_efficient_cpu(): Find most energy-efficient target CPU for the
+ * waking task. find_energy_efficient_cpu() looks for the CPU with maximum
+ * spare capacity in each performance domain and uses it as a potential
+ * candidate to execute the task. Then, it uses the Energy Model to figure
+ * out which of the CPU candidates is the most energy-efficient.
+ *
+ * The rationale for this heuristic is as follows. In a performance domain,
+ * all the most energy efficient CPU candidates (according to the Energy
+ * Model) are those for which we'll request a low frequency. When there are
+ * several CPUs for which the frequency request will be the same, we don't
+ * have enough data to break the tie between them, because the Energy Model
+ * only includes active power costs. With this model, if we assume that
+ * frequency requests follow utilization (e.g. using schedutil), the CPU with
+ * the maximum spare capacity in a performance domain is guaranteed to be among
+ * the best candidates of the performance domain.
+ *
+ * In practice, it could be preferable from an energy standpoint to pack
+ * small tasks on a CPU in order to let other CPUs go in deeper idle states,
+ * but that could also hurt our chances to go cluster idle, and we have no
+ * ways to tell with the current Energy Model if this is actually a good
+ * idea or not. So, find_energy_efficient_cpu() basically favors
+ * cluster-packing, and spreading inside a cluster. That should at least be
+ * a good thing for latency, and this is consistent with the idea that most
+ * of the energy savings of EAS come from the asymmetry of the system, and
+ * not so much from breaking the tie between identical CPUs. That's also the
+ * reason why EAS is enabled in the topology code only for systems where
+ * SD_ASYM_CPUCAPACITY is set.
+ *
+ * NOTE: Forkees are not accepted in the energy-aware wake-up path because
+ * they don't have any useful utilization data yet and it's not possible to
+ * forecast their impact on energy consumption. Consequently, they will be
+ * placed by find_idlest_cpu() on the least loaded CPU, which might turn out
+ * to be energy-inefficient in some use-cases. The alternative would be to
+ * bias new tasks towards specific types of CPUs first, or to try to infer
+ * their util_avg from the parent task, but those heuristics could hurt
+ * other use-cases too. So, until someone finds a better way to solve this,
+ * let's keep things simple by re-using the existing slow path.
+ */
+
+static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
+{
+ unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX;
+ struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+ int cpu, best_energy_cpu = prev_cpu;
+ struct perf_domain *head, *pd;
+ unsigned long cpu_cap, util;
+ struct sched_domain *sd;
+
+ rcu_read_lock();
+ pd = rcu_dereference(rd->pd);
+ if (!pd || READ_ONCE(rd->overutilized))
+ goto fail;
+ head = pd;
+
+ /*
+ * Energy-aware wake-up happens on the lowest sched_domain starting
+ * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu.
+ */
+ sd = rcu_dereference(*this_cpu_ptr(&sd_asym_cpucapacity));
+ while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+ sd = sd->parent;
+ if (!sd)
+ goto fail;
+
+ sync_entity_load_avg(&p->se);
+ if (!task_util_est(p))
+ goto unlock;
+
+ for (; pd; pd = pd->next) {
+ unsigned long cur_energy, spare_cap, max_spare_cap = 0;
+ int max_spare_cap_cpu = -1;
+
+ for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
+ if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ continue;
+
+ /* Skip CPUs that will be overutilized. */
+ util = cpu_util_next(cpu, p, cpu);
+ cpu_cap = capacity_of(cpu);
+ if (cpu_cap * 1024 < util * capacity_margin)
+ continue;
+
+ /* Always use prev_cpu as a candidate. */
+ if (cpu == prev_cpu) {
+ prev_energy = compute_energy(p, prev_cpu, head);
+ best_energy = min(best_energy, prev_energy);
+ continue;
+ }
+
+ /*
+ * Find the CPU with the maximum spare capacity in
+ * the performance domain
+ */
+ spare_cap = cpu_cap - util;
+ if (spare_cap > max_spare_cap) {
+ max_spare_cap = spare_cap;
+ max_spare_cap_cpu = cpu;
+ }
+ }
+
+ /* Evaluate the energy impact of using this CPU. */
+ if (max_spare_cap_cpu >= 0) {
+ cur_energy = compute_energy(p, max_spare_cap_cpu, head);
+ if (cur_energy < best_energy) {
+ best_energy = cur_energy;
+ best_energy_cpu = max_spare_cap_cpu;
+ }
+ }
+ }
+unlock:
+ rcu_read_unlock();
+
+ /*
+ * Pick the best CPU if prev_cpu cannot be used, or if it saves at
+ * least 6% of the energy used by prev_cpu.
+ */
+ if (prev_energy == ULONG_MAX)
+ return best_energy_cpu;
+
+ if ((prev_energy - best_energy) > (prev_energy >> 4))
+ return best_energy_cpu;
+
+ return prev_cpu;
+
+fail:
+ rcu_read_unlock();
+
+ return -1;
+}
+
+/*
* select_task_rq_fair: Select target runqueue for the waking task in domains
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
* SD_BALANCE_FORK, or SD_BALANCE_EXEC.
@@ -6321,8 +6607,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
if (sd_flag & SD_BALANCE_WAKE) {
record_wakee(p);
- want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
- && cpumask_test_cpu(cpu, &p->cpus_allowed);
+
+ if (static_branch_unlikely(&sched_energy_present)) {
+ new_cpu = find_energy_efficient_cpu(p, prev_cpu);
+ if (new_cpu >= 0)
+ return new_cpu;
+ new_cpu = prev_cpu;
+ }
+
+ want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
+ cpumask_test_cpu(cpu, &p->cpus_allowed);
}
rcu_read_lock();
@@ -6486,7 +6780,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
static void set_last_buddy(struct sched_entity *se)
{
- if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+ if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
return;
for_each_sched_entity(se) {
@@ -6498,7 +6792,7 @@ static void set_last_buddy(struct sched_entity *se)
static void set_next_buddy(struct sched_entity *se)
{
- if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+ if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
return;
for_each_sched_entity(se) {
@@ -6556,8 +6850,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
return;
/* Idle tasks are by definition preempted by non-idle tasks. */
- if (unlikely(curr->policy == SCHED_IDLE) &&
- likely(p->policy != SCHED_IDLE))
+ if (unlikely(task_has_idle_policy(curr)) &&
+ likely(!task_has_idle_policy(p)))
goto preempt;
/*
@@ -6978,7 +7272,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
if (p->sched_class != &fair_sched_class)
return 0;
- if (unlikely(p->policy == SCHED_IDLE))
+ if (unlikely(task_has_idle_policy(p)))
return 0;
/*
@@ -7862,16 +8156,16 @@ static bool update_nohz_stats(struct rq *rq, bool force)
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
* @env: The load balancing environment.
* @group: sched_group whose statistics are to be updated.
- * @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @local_group: Does group contain this_cpu.
* @sgs: variable to hold the statistics for this group.
- * @overload: Indicate pullable load (e.g. >1 runnable task).
+ * @sg_status: Holds flag indicating the status of the sched_group
*/
static inline void update_sg_lb_stats(struct lb_env *env,
- struct sched_group *group, int load_idx,
- int local_group, struct sg_lb_stats *sgs,
- bool *overload)
+ struct sched_group *group,
+ struct sg_lb_stats *sgs,
+ int *sg_status)
{
+ int local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
+ int load_idx = get_sd_load_idx(env->sd, env->idle);
unsigned long load;
int i, nr_running;
@@ -7895,7 +8189,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
nr_running = rq->nr_running;
if (nr_running > 1)
- *overload = true;
+ *sg_status |= SG_OVERLOAD;
+
+ if (cpu_overutilized(i))
+ *sg_status |= SG_OVERUTILIZED;
#ifdef CONFIG_NUMA_BALANCING
sgs->nr_numa_running += rq->nr_numa_running;
@@ -7911,7 +8208,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
sgs->group_misfit_task_load < rq->misfit_task_load) {
sgs->group_misfit_task_load = rq->misfit_task_load;
- *overload = 1;
+ *sg_status |= SG_OVERLOAD;
}
}
@@ -8056,17 +8353,14 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats *local = &sds->local_stat;
struct sg_lb_stats tmp_sgs;
- int load_idx;
- bool overload = false;
bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
+ int sg_status = 0;
#ifdef CONFIG_NO_HZ_COMMON
if (env->idle == CPU_NEWLY_IDLE && READ_ONCE(nohz.has_blocked))
env->flags |= LBF_NOHZ_STATS;
#endif
- load_idx = get_sd_load_idx(env->sd, env->idle);
-
do {
struct sg_lb_stats *sgs = &tmp_sgs;
int local_group;
@@ -8081,8 +8375,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
update_group_capacity(env->sd, env->dst_cpu);
}
- update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
- &overload);
+ update_sg_lb_stats(env, sg, sgs, &sg_status);
if (local_group)
goto next_group;
@@ -8131,9 +8424,15 @@ next_group:
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
if (!env->sd->parent) {
+ struct root_domain *rd = env->dst_rq->rd;
+
/* update overload indicator if we are at root domain */
- if (READ_ONCE(env->dst_rq->rd->overload) != overload)
- WRITE_ONCE(env->dst_rq->rd->overload, overload);
+ WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD);
+
+ /* Update over-utilization (tipping point, U >= 0) indicator */
+ WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);
+ } else if (sg_status & SG_OVERUTILIZED) {
+ WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED);
}
}
@@ -8360,6 +8659,14 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
* this level.
*/
update_sd_lb_stats(env, &sds);
+
+ if (static_branch_unlikely(&sched_energy_present)) {
+ struct root_domain *rd = env->dst_rq->rd;
+
+ if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized))
+ goto out_balanced;
+ }
+
local = &sds.local_stat;
busiest = &sds.busiest_stat;
@@ -8876,13 +9183,22 @@ out_all_pinned:
sd->nr_balance_failed = 0;
out_one_pinned:
+ ld_moved = 0;
+
+ /*
+ * idle_balance() disregards balance intervals, so we could repeatedly
+ * reach this code, which would lead to balance_interval skyrocketting
+ * in a short amount of time. Skip the balance_interval increase logic
+ * to avoid that.
+ */
+ if (env.idle == CPU_NEWLY_IDLE)
+ goto out;
+
/* tune up the balancing interval */
- if (((env.flags & LBF_ALL_PINNED) &&
- sd->balance_interval < MAX_PINNED_INTERVAL) ||
- (sd->balance_interval < sd->max_interval))
+ if ((env.flags & LBF_ALL_PINNED &&
+ sd->balance_interval < MAX_PINNED_INTERVAL) ||
+ sd->balance_interval < sd->max_interval)
sd->balance_interval *= 2;
-
- ld_moved = 0;
out:
return ld_moved;
}
@@ -9247,7 +9563,7 @@ static void nohz_balancer_kick(struct rq *rq)
}
}
- sd = rcu_dereference(per_cpu(sd_asym, cpu));
+ sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
if (sd) {
for_each_cpu(i, sched_domain_span(sd)) {
if (i == cpu ||
@@ -9499,9 +9815,7 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
return false;
}
- /*
- * barrier, pairs with nohz_balance_enter_idle(), ensures ...
- */
+ /* could be _relaxed() */
flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu));
if (!(flags & NOHZ_KICK_MASK))
return false;
@@ -9751,6 +10065,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
task_tick_numa(rq, curr);
update_misfit_status(curr, rq);
+ update_overutilized_status(task_rq(curr));
}
/*
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index e6802181900f..81faddba9e20 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -8,14 +8,14 @@
*/
#include "sched.h"
-DEFINE_STATIC_KEY_FALSE(housekeeping_overriden);
-EXPORT_SYMBOL_GPL(housekeeping_overriden);
+DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
+EXPORT_SYMBOL_GPL(housekeeping_overridden);
static cpumask_var_t housekeeping_mask;
static unsigned int housekeeping_flags;
int housekeeping_any_cpu(enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
return cpumask_any_and(housekeeping_mask, cpu_online_mask);
return smp_processor_id();
@@ -24,7 +24,7 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
return housekeeping_mask;
return cpu_possible_mask;
@@ -33,7 +33,7 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask);
void housekeeping_affine(struct task_struct *t, enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
set_cpus_allowed_ptr(t, housekeeping_mask);
}
@@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(housekeeping_affine);
bool housekeeping_test_cpu(int cpu, enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
return cpumask_test_cpu(cpu, housekeeping_mask);
return true;
@@ -53,7 +53,7 @@ void __init housekeeping_init(void)
if (!housekeeping_flags)
return;
- static_branch_enable(&housekeeping_overriden);
+ static_branch_enable(&housekeeping_overridden);
if (housekeeping_flags & HK_FLAG_TICK)
sched_tick_offload_init();
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index a171c1258109..28a516575c18 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -91,19 +91,73 @@ long calc_load_fold_active(struct rq *this_rq, long adjust)
return delta;
}
-/*
- * a1 = a0 * e + a * (1 - e)
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x: base of the power
+ * @frac_bits: fractional bits of @x
+ * @n: power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
*/
static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
{
- unsigned long newload;
+ unsigned long result = 1UL << frac_bits;
+
+ if (n) {
+ for (;;) {
+ if (n & 1) {
+ result *= x;
+ result += 1UL << (frac_bits - 1);
+ result >>= frac_bits;
+ }
+ n >>= 1;
+ if (!n)
+ break;
+ x *= x;
+ x += 1UL << (frac_bits - 1);
+ x >>= frac_bits;
+ }
+ }
- newload = load * exp + active * (FIXED_1 - exp);
- if (active >= load)
- newload += FIXED_1-1;
+ return result;
+}
- return newload / FIXED_1;
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ * = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ * ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ * = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ * n 1 - x^(n+1)
+ * S_n := \Sum x^i = -------------
+ * i=0 1 - x
+ */
+unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+ unsigned long active, unsigned int n)
+{
+ return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -225,75 +279,6 @@ static long calc_load_nohz_fold(void)
return delta;
}
-/**
- * fixed_power_int - compute: x^n, in O(log n) time
- *
- * @x: base of the power
- * @frac_bits: fractional bits of @x
- * @n: power to raise @x to.
- *
- * By exploiting the relation between the definition of the natural power
- * function: x^n := x*x*...*x (x multiplied by itself for n times), and
- * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
- * (where: n_i \elem {0, 1}, the binary vector representing n),
- * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
- * of course trivially computable in O(log_2 n), the length of our binary
- * vector.
- */
-static unsigned long
-fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
-{
- unsigned long result = 1UL << frac_bits;
-
- if (n) {
- for (;;) {
- if (n & 1) {
- result *= x;
- result += 1UL << (frac_bits - 1);
- result >>= frac_bits;
- }
- n >>= 1;
- if (!n)
- break;
- x *= x;
- x += 1UL << (frac_bits - 1);
- x >>= frac_bits;
- }
- }
-
- return result;
-}
-
-/*
- * a1 = a0 * e + a * (1 - e)
- *
- * a2 = a1 * e + a * (1 - e)
- * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
- * = a0 * e^2 + a * (1 - e) * (1 + e)
- *
- * a3 = a2 * e + a * (1 - e)
- * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
- * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
- *
- * ...
- *
- * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
- * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
- * = a0 * e^n + a * (1 - e^n)
- *
- * [1] application of the geometric series:
- *
- * n 1 - x^(n+1)
- * S_n := \Sum x^i = -------------
- * i=0 1 - x
- */
-static unsigned long
-calc_load_n(unsigned long load, unsigned long exp,
- unsigned long active, unsigned int n)
-{
- return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
-}
-
/*
* NO_HZ can leave us missing all per-CPU ticks calling
* calc_load_fold_active(), but since a NO_HZ CPU folds its delta into
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 76e0eaf4654e..3cd8a3a795d2 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -210,7 +210,7 @@ static int membarrier_register_global_expedited(void)
* future scheduler executions will observe the new
* thread flag state for this mm.
*/
- synchronize_sched();
+ synchronize_rcu();
}
atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY,
&mm->membarrier_state);
@@ -246,7 +246,7 @@ static int membarrier_register_private_expedited(int flags)
* Ensure all future scheduler executions will observe the
* new thread flag state for this process.
*/
- synchronize_sched();
+ synchronize_rcu();
}
atomic_or(state, &mm->membarrier_state);
@@ -298,7 +298,7 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
if (tick_nohz_full_enabled())
return -EINVAL;
if (num_online_cpus() > 1)
- synchronize_sched();
+ synchronize_rcu();
return 0;
case MEMBARRIER_CMD_GLOBAL_EXPEDITED:
return membarrier_global_expedited();
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
new file mode 100644
index 000000000000..fe24de3fbc93
--- /dev/null
+++ b/kernel/sched/psi.c
@@ -0,0 +1,772 @@
+/*
+ * Pressure stall information for CPU, memory and IO
+ *
+ * Copyright (c) 2018 Facebook, Inc.
+ * Author: Johannes Weiner <hannes@cmpxchg.org>
+ *
+ * When CPU, memory and IO are contended, tasks experience delays that
+ * reduce throughput and introduce latencies into the workload. Memory
+ * and IO contention, in addition, can cause a full loss of forward
+ * progress in which the CPU goes idle.
+ *
+ * This code aggregates individual task delays into resource pressure
+ * metrics that indicate problems with both workload health and
+ * resource utilization.
+ *
+ * Model
+ *
+ * The time in which a task can execute on a CPU is our baseline for
+ * productivity. Pressure expresses the amount of time in which this
+ * potential cannot be realized due to resource contention.
+ *
+ * This concept of productivity has two components: the workload and
+ * the CPU. To measure the impact of pressure on both, we define two
+ * contention states for a resource: SOME and FULL.
+ *
+ * In the SOME state of a given resource, one or more tasks are
+ * delayed on that resource. This affects the workload's ability to
+ * perform work, but the CPU may still be executing other tasks.
+ *
+ * In the FULL state of a given resource, all non-idle tasks are
+ * delayed on that resource such that nobody is advancing and the CPU
+ * goes idle. This leaves both workload and CPU unproductive.
+ *
+ * (Naturally, the FULL state doesn't exist for the CPU resource.)
+ *
+ * SOME = nr_delayed_tasks != 0
+ * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0
+ *
+ * The percentage of wallclock time spent in those compound stall
+ * states gives pressure numbers between 0 and 100 for each resource,
+ * where the SOME percentage indicates workload slowdowns and the FULL
+ * percentage indicates reduced CPU utilization:
+ *
+ * %SOME = time(SOME) / period
+ * %FULL = time(FULL) / period
+ *
+ * Multiple CPUs
+ *
+ * The more tasks and available CPUs there are, the more work can be
+ * performed concurrently. This means that the potential that can go
+ * unrealized due to resource contention *also* scales with non-idle
+ * tasks and CPUs.
+ *
+ * Consider a scenario where 257 number crunching tasks are trying to
+ * run concurrently on 256 CPUs. If we simply aggregated the task
+ * states, we would have to conclude a CPU SOME pressure number of
+ * 100%, since *somebody* is waiting on a runqueue at all
+ * times. However, that is clearly not the amount of contention the
+ * workload is experiencing: only one out of 256 possible exceution
+ * threads will be contended at any given time, or about 0.4%.
+ *
+ * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any
+ * given time *one* of the tasks is delayed due to a lack of memory.
+ * Again, looking purely at the task state would yield a memory FULL
+ * pressure number of 0%, since *somebody* is always making forward
+ * progress. But again this wouldn't capture the amount of execution
+ * potential lost, which is 1 out of 4 CPUs, or 25%.
+ *
+ * To calculate wasted potential (pressure) with multiple processors,
+ * we have to base our calculation on the number of non-idle tasks in
+ * conjunction with the number of available CPUs, which is the number
+ * of potential execution threads. SOME becomes then the proportion of
+ * delayed tasks to possibe threads, and FULL is the share of possible
+ * threads that are unproductive due to delays:
+ *
+ * threads = min(nr_nonidle_tasks, nr_cpus)
+ * SOME = min(nr_delayed_tasks / threads, 1)
+ * FULL = (threads - min(nr_running_tasks, threads)) / threads
+ *
+ * For the 257 number crunchers on 256 CPUs, this yields:
+ *
+ * threads = min(257, 256)
+ * SOME = min(1 / 256, 1) = 0.4%
+ * FULL = (256 - min(257, 256)) / 256 = 0%
+ *
+ * For the 1 out of 4 memory-delayed tasks, this yields:
+ *
+ * threads = min(4, 4)
+ * SOME = min(1 / 4, 1) = 25%
+ * FULL = (4 - min(3, 4)) / 4 = 25%
+ *
+ * [ Substitute nr_cpus with 1, and you can see that it's a natural
+ * extension of the single-CPU model. ]
+ *
+ * Implementation
+ *
+ * To assess the precise time spent in each such state, we would have
+ * to freeze the system on task changes and start/stop the state
+ * clocks accordingly. Obviously that doesn't scale in practice.
+ *
+ * Because the scheduler aims to distribute the compute load evenly
+ * among the available CPUs, we can track task state locally to each
+ * CPU and, at much lower frequency, extrapolate the global state for
+ * the cumulative stall times and the running averages.
+ *
+ * For each runqueue, we track:
+ *
+ * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0)
+ * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu])
+ * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0)
+ *
+ * and then periodically aggregate:
+ *
+ * tNONIDLE = sum(tNONIDLE[i])
+ *
+ * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE
+ * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE
+ *
+ * %SOME = tSOME / period
+ * %FULL = tFULL / period
+ *
+ * This gives us an approximation of pressure that is practical
+ * cost-wise, yet way more sensitive and accurate than periodic
+ * sampling of the aggregate task states would be.
+ */
+
+#include <linux/sched/loadavg.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/seqlock.h>
+#include <linux/cgroup.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/psi.h>
+#include "sched.h"
+
+static int psi_bug __read_mostly;
+
+DEFINE_STATIC_KEY_FALSE(psi_disabled);
+
+#ifdef CONFIG_PSI_DEFAULT_DISABLED
+bool psi_enable;
+#else
+bool psi_enable = true;
+#endif
+static int __init setup_psi(char *str)
+{
+ return kstrtobool(str, &psi_enable) == 0;
+}
+__setup("psi=", setup_psi);
+
+/* Running averages - we need to be higher-res than loadavg */
+#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */
+#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */
+#define EXP_60s 1981 /* 1/exp(2s/60s) */
+#define EXP_300s 2034 /* 1/exp(2s/300s) */
+
+/* Sampling frequency in nanoseconds */
+static u64 psi_period __read_mostly;
+
+/* System-level pressure and stall tracking */
+static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu);
+static struct psi_group psi_system = {
+ .pcpu = &system_group_pcpu,
+};
+
+static void psi_update_work(struct work_struct *work);
+
+static void group_init(struct psi_group *group)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
+ group->next_update = sched_clock() + psi_period;
+ INIT_DELAYED_WORK(&group->clock_work, psi_update_work);
+ mutex_init(&group->stat_lock);
+}
+
+void __init psi_init(void)
+{
+ if (!psi_enable) {
+ static_branch_enable(&psi_disabled);
+ return;
+ }
+
+ psi_period = jiffies_to_nsecs(PSI_FREQ);
+ group_init(&psi_system);
+}
+
+static bool test_state(unsigned int *tasks, enum psi_states state)
+{
+ switch (state) {
+ case PSI_IO_SOME:
+ return tasks[NR_IOWAIT];
+ case PSI_IO_FULL:
+ return tasks[NR_IOWAIT] && !tasks[NR_RUNNING];
+ case PSI_MEM_SOME:
+ return tasks[NR_MEMSTALL];
+ case PSI_MEM_FULL:
+ return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
+ case PSI_CPU_SOME:
+ return tasks[NR_RUNNING] > 1;
+ case PSI_NONIDLE:
+ return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
+ tasks[NR_RUNNING];
+ default:
+ return false;
+ }
+}
+
+static void get_recent_times(struct psi_group *group, int cpu, u32 *times)
+{
+ struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
+ unsigned int tasks[NR_PSI_TASK_COUNTS];
+ u64 now, state_start;
+ unsigned int seq;
+ int s;
+
+ /* Snapshot a coherent view of the CPU state */
+ do {
+ seq = read_seqcount_begin(&groupc->seq);
+ now = cpu_clock(cpu);
+ memcpy(times, groupc->times, sizeof(groupc->times));
+ memcpy(tasks, groupc->tasks, sizeof(groupc->tasks));
+ state_start = groupc->state_start;
+ } while (read_seqcount_retry(&groupc->seq, seq));
+
+ /* Calculate state time deltas against the previous snapshot */
+ for (s = 0; s < NR_PSI_STATES; s++) {
+ u32 delta;
+ /*
+ * In addition to already concluded states, we also
+ * incorporate currently active states on the CPU,
+ * since states may last for many sampling periods.
+ *
+ * This way we keep our delta sampling buckets small
+ * (u32) and our reported pressure close to what's
+ * actually happening.
+ */
+ if (test_state(tasks, s))
+ times[s] += now - state_start;
+
+ delta = times[s] - groupc->times_prev[s];
+ groupc->times_prev[s] = times[s];
+
+ times[s] = delta;
+ }
+}
+
+static void calc_avgs(unsigned long avg[3], int missed_periods,
+ u64 time, u64 period)
+{
+ unsigned long pct;
+
+ /* Fill in zeroes for periods of no activity */
+ if (missed_periods) {
+ avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods);
+ avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods);
+ avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods);
+ }
+
+ /* Sample the most recent active period */
+ pct = div_u64(time * 100, period);
+ pct *= FIXED_1;
+ avg[0] = calc_load(avg[0], EXP_10s, pct);
+ avg[1] = calc_load(avg[1], EXP_60s, pct);
+ avg[2] = calc_load(avg[2], EXP_300s, pct);
+}
+
+static bool update_stats(struct psi_group *group)
+{
+ u64 deltas[NR_PSI_STATES - 1] = { 0, };
+ unsigned long missed_periods = 0;
+ unsigned long nonidle_total = 0;
+ u64 now, expires, period;
+ int cpu;
+ int s;
+
+ mutex_lock(&group->stat_lock);
+
+ /*
+ * Collect the per-cpu time buckets and average them into a
+ * single time sample that is normalized to wallclock time.
+ *
+ * For averaging, each CPU is weighted by its non-idle time in
+ * the sampling period. This eliminates artifacts from uneven
+ * loading, or even entirely idle CPUs.
+ */
+ for_each_possible_cpu(cpu) {
+ u32 times[NR_PSI_STATES];
+ u32 nonidle;
+
+ get_recent_times(group, cpu, times);
+
+ nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]);
+ nonidle_total += nonidle;
+
+ for (s = 0; s < PSI_NONIDLE; s++)
+ deltas[s] += (u64)times[s] * nonidle;
+ }
+
+ /*
+ * Integrate the sample into the running statistics that are
+ * reported to userspace: the cumulative stall times and the
+ * decaying averages.
+ *
+ * Pressure percentages are sampled at PSI_FREQ. We might be
+ * called more often when the user polls more frequently than
+ * that; we might be called less often when there is no task
+ * activity, thus no data, and clock ticks are sporadic. The
+ * below handles both.
+ */
+
+ /* total= */
+ for (s = 0; s < NR_PSI_STATES - 1; s++)
+ group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL));
+
+ /* avgX= */
+ now = sched_clock();
+ expires = group->next_update;
+ if (now < expires)
+ goto out;
+ if (now - expires > psi_period)
+ missed_periods = div_u64(now - expires, psi_period);
+
+ /*
+ * The periodic clock tick can get delayed for various
+ * reasons, especially on loaded systems. To avoid clock
+ * drift, we schedule the clock in fixed psi_period intervals.
+ * But the deltas we sample out of the per-cpu buckets above
+ * are based on the actual time elapsing between clock ticks.
+ */
+ group->next_update = expires + ((1 + missed_periods) * psi_period);
+ period = now - (group->last_update + (missed_periods * psi_period));
+ group->last_update = now;
+
+ for (s = 0; s < NR_PSI_STATES - 1; s++) {
+ u32 sample;
+
+ sample = group->total[s] - group->total_prev[s];
+ /*
+ * Due to the lockless sampling of the time buckets,
+ * recorded time deltas can slip into the next period,
+ * which under full pressure can result in samples in
+ * excess of the period length.
+ *
+ * We don't want to report non-sensical pressures in
+ * excess of 100%, nor do we want to drop such events
+ * on the floor. Instead we punt any overage into the
+ * future until pressure subsides. By doing this we
+ * don't underreport the occurring pressure curve, we
+ * just report it delayed by one period length.
+ *
+ * The error isn't cumulative. As soon as another
+ * delta slips from a period P to P+1, by definition
+ * it frees up its time T in P.
+ */
+ if (sample > period)
+ sample = period;
+ group->total_prev[s] += sample;
+ calc_avgs(group->avg[s], missed_periods, sample, period);
+ }
+out:
+ mutex_unlock(&group->stat_lock);
+ return nonidle_total;
+}
+
+static void psi_update_work(struct work_struct *work)
+{
+ struct delayed_work *dwork;
+ struct psi_group *group;
+ bool nonidle;
+
+ dwork = to_delayed_work(work);
+ group = container_of(dwork, struct psi_group, clock_work);
+
+ /*
+ * If there is task activity, periodically fold the per-cpu
+ * times and feed samples into the running averages. If things
+ * are idle and there is no data to process, stop the clock.
+ * Once restarted, we'll catch up the running averages in one
+ * go - see calc_avgs() and missed_periods.
+ */
+
+ nonidle = update_stats(group);
+
+ if (nonidle) {
+ unsigned long delay = 0;
+ u64 now;
+
+ now = sched_clock();
+ if (group->next_update > now)
+ delay = nsecs_to_jiffies(group->next_update - now) + 1;
+ schedule_delayed_work(dwork, delay);
+ }
+}
+
+static void record_times(struct psi_group_cpu *groupc, int cpu,
+ bool memstall_tick)
+{
+ u32 delta;
+ u64 now;
+
+ now = cpu_clock(cpu);
+ delta = now - groupc->state_start;
+ groupc->state_start = now;
+
+ if (test_state(groupc->tasks, PSI_IO_SOME)) {
+ groupc->times[PSI_IO_SOME] += delta;
+ if (test_state(groupc->tasks, PSI_IO_FULL))
+ groupc->times[PSI_IO_FULL] += delta;
+ }
+
+ if (test_state(groupc->tasks, PSI_MEM_SOME)) {
+ groupc->times[PSI_MEM_SOME] += delta;
+ if (test_state(groupc->tasks, PSI_MEM_FULL))
+ groupc->times[PSI_MEM_FULL] += delta;
+ else if (memstall_tick) {
+ u32 sample;
+ /*
+ * Since we care about lost potential, a
+ * memstall is FULL when there are no other
+ * working tasks, but also when the CPU is
+ * actively reclaiming and nothing productive
+ * could run even if it were runnable.
+ *
+ * When the timer tick sees a reclaiming CPU,
+ * regardless of runnable tasks, sample a FULL
+ * tick (or less if it hasn't been a full tick
+ * since the last state change).
+ */
+ sample = min(delta, (u32)jiffies_to_nsecs(1));
+ groupc->times[PSI_MEM_FULL] += sample;
+ }
+ }
+
+ if (test_state(groupc->tasks, PSI_CPU_SOME))
+ groupc->times[PSI_CPU_SOME] += delta;
+
+ if (test_state(groupc->tasks, PSI_NONIDLE))
+ groupc->times[PSI_NONIDLE] += delta;
+}
+
+static void psi_group_change(struct psi_group *group, int cpu,
+ unsigned int clear, unsigned int set)
+{
+ struct psi_group_cpu *groupc;
+ unsigned int t, m;
+
+ groupc = per_cpu_ptr(group->pcpu, cpu);
+
+ /*
+ * First we assess the aggregate resource states this CPU's
+ * tasks have been in since the last change, and account any
+ * SOME and FULL time these may have resulted in.
+ *
+ * Then we update the task counts according to the state
+ * change requested through the @clear and @set bits.
+ */
+ write_seqcount_begin(&groupc->seq);
+
+ record_times(groupc, cpu, false);
+
+ for (t = 0, m = clear; m; m &= ~(1 << t), t++) {
+ if (!(m & (1 << t)))
+ continue;
+ if (groupc->tasks[t] == 0 && !psi_bug) {
+ printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n",
+ cpu, t, groupc->tasks[0],
+ groupc->tasks[1], groupc->tasks[2],
+ clear, set);
+ psi_bug = 1;
+ }
+ groupc->tasks[t]--;
+ }
+
+ for (t = 0; set; set &= ~(1 << t), t++)
+ if (set & (1 << t))
+ groupc->tasks[t]++;
+
+ write_seqcount_end(&groupc->seq);
+
+ if (!delayed_work_pending(&group->clock_work))
+ schedule_delayed_work(&group->clock_work, PSI_FREQ);
+}
+
+static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
+{
+#ifdef CONFIG_CGROUPS
+ struct cgroup *cgroup = NULL;
+
+ if (!*iter)
+ cgroup = task->cgroups->dfl_cgrp;
+ else if (*iter == &psi_system)
+ return NULL;
+ else
+ cgroup = cgroup_parent(*iter);
+
+ if (cgroup && cgroup_parent(cgroup)) {
+ *iter = cgroup;
+ return cgroup_psi(cgroup);
+ }
+#else
+ if (*iter)
+ return NULL;
+#endif
+ *iter = &psi_system;
+ return &psi_system;
+}
+
+void psi_task_change(struct task_struct *task, int clear, int set)
+{
+ int cpu = task_cpu(task);
+ struct psi_group *group;
+ void *iter = NULL;
+
+ if (!task->pid)
+ return;
+
+ if (((task->psi_flags & set) ||
+ (task->psi_flags & clear) != clear) &&
+ !psi_bug) {
+ printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n",
+ task->pid, task->comm, cpu,
+ task->psi_flags, clear, set);
+ psi_bug = 1;
+ }
+
+ task->psi_flags &= ~clear;
+ task->psi_flags |= set;
+
+ while ((group = iterate_groups(task, &iter)))
+ psi_group_change(group, cpu, clear, set);
+}
+
+void psi_memstall_tick(struct task_struct *task, int cpu)
+{
+ struct psi_group *group;
+ void *iter = NULL;
+
+ while ((group = iterate_groups(task, &iter))) {
+ struct psi_group_cpu *groupc;
+
+ groupc = per_cpu_ptr(group->pcpu, cpu);
+ write_seqcount_begin(&groupc->seq);
+ record_times(groupc, cpu, true);
+ write_seqcount_end(&groupc->seq);
+ }
+}
+
+/**
+ * psi_memstall_enter - mark the beginning of a memory stall section
+ * @flags: flags to handle nested sections
+ *
+ * Marks the calling task as being stalled due to a lack of memory,
+ * such as waiting for a refault or performing reclaim.
+ */
+void psi_memstall_enter(unsigned long *flags)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ *flags = current->flags & PF_MEMSTALL;
+ if (*flags)
+ return;
+ /*
+ * PF_MEMSTALL setting & accounting needs to be atomic wrt
+ * changes to the task's scheduling state, otherwise we can
+ * race with CPU migration.
+ */
+ rq = this_rq_lock_irq(&rf);
+
+ current->flags |= PF_MEMSTALL;
+ psi_task_change(current, 0, TSK_MEMSTALL);
+
+ rq_unlock_irq(rq, &rf);
+}
+
+/**
+ * psi_memstall_leave - mark the end of an memory stall section
+ * @flags: flags to handle nested memdelay sections
+ *
+ * Marks the calling task as no longer stalled due to lack of memory.
+ */
+void psi_memstall_leave(unsigned long *flags)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ if (*flags)
+ return;
+ /*
+ * PF_MEMSTALL clearing & accounting needs to be atomic wrt
+ * changes to the task's scheduling state, otherwise we could
+ * race with CPU migration.
+ */
+ rq = this_rq_lock_irq(&rf);
+
+ current->flags &= ~PF_MEMSTALL;
+ psi_task_change(current, TSK_MEMSTALL, 0);
+
+ rq_unlock_irq(rq, &rf);
+}
+
+#ifdef CONFIG_CGROUPS
+int psi_cgroup_alloc(struct cgroup *cgroup)
+{
+ if (static_branch_likely(&psi_disabled))
+ return 0;
+
+ cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu);
+ if (!cgroup->psi.pcpu)
+ return -ENOMEM;
+ group_init(&cgroup->psi);
+ return 0;
+}
+
+void psi_cgroup_free(struct cgroup *cgroup)
+{
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ cancel_delayed_work_sync(&cgroup->psi.clock_work);
+ free_percpu(cgroup->psi.pcpu);
+}
+
+/**
+ * cgroup_move_task - move task to a different cgroup
+ * @task: the task
+ * @to: the target css_set
+ *
+ * Move task to a new cgroup and safely migrate its associated stall
+ * state between the different groups.
+ *
+ * This function acquires the task's rq lock to lock out concurrent
+ * changes to the task's scheduling state and - in case the task is
+ * running - concurrent changes to its stall state.
+ */
+void cgroup_move_task(struct task_struct *task, struct css_set *to)
+{
+ unsigned int task_flags = 0;
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (static_branch_likely(&psi_disabled)) {
+ /*
+ * Lame to do this here, but the scheduler cannot be locked
+ * from the outside, so we move cgroups from inside sched/.
+ */
+ rcu_assign_pointer(task->cgroups, to);
+ return;
+ }
+
+ rq = task_rq_lock(task, &rf);
+
+ if (task_on_rq_queued(task))
+ task_flags = TSK_RUNNING;
+ else if (task->in_iowait)
+ task_flags = TSK_IOWAIT;
+
+ if (task->flags & PF_MEMSTALL)
+ task_flags |= TSK_MEMSTALL;
+
+ if (task_flags)
+ psi_task_change(task, task_flags, 0);
+
+ /* See comment above */
+ rcu_assign_pointer(task->cgroups, to);
+
+ if (task_flags)
+ psi_task_change(task, 0, task_flags);
+
+ task_rq_unlock(rq, task, &rf);
+}
+#endif /* CONFIG_CGROUPS */
+
+int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
+{
+ int full;
+
+ if (static_branch_likely(&psi_disabled))
+ return -EOPNOTSUPP;
+
+ update_stats(group);
+
+ for (full = 0; full < 2 - (res == PSI_CPU); full++) {
+ unsigned long avg[3];
+ u64 total;
+ int w;
+
+ for (w = 0; w < 3; w++)
+ avg[w] = group->avg[res * 2 + full][w];
+ total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC);
+
+ seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
+ full ? "full" : "some",
+ LOAD_INT(avg[0]), LOAD_FRAC(avg[0]),
+ LOAD_INT(avg[1]), LOAD_FRAC(avg[1]),
+ LOAD_INT(avg[2]), LOAD_FRAC(avg[2]),
+ total);
+ }
+
+ return 0;
+}
+
+static int psi_io_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_IO);
+}
+
+static int psi_memory_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_MEM);
+}
+
+static int psi_cpu_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_CPU);
+}
+
+static int psi_io_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_io_show, NULL);
+}
+
+static int psi_memory_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_memory_show, NULL);
+}
+
+static int psi_cpu_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_cpu_show, NULL);
+}
+
+static const struct file_operations psi_io_fops = {
+ .open = psi_io_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static const struct file_operations psi_memory_fops = {
+ .open = psi_memory_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static const struct file_operations psi_cpu_fops = {
+ .open = psi_cpu_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init psi_proc_init(void)
+{
+ proc_mkdir("pressure", NULL);
+ proc_create("pressure/io", 0, NULL, &psi_io_fops);
+ proc_create("pressure/memory", 0, NULL, &psi_memory_fops);
+ proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops);
+ return 0;
+}
+module_init(psi_proc_init);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 2e2955a8cf8f..e4f398ad9e73 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1498,6 +1498,14 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
#endif
}
+static inline void set_next_task(struct rq *rq, struct task_struct *p)
+{
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* The running task is never eligible for pushing */
+ dequeue_pushable_task(rq, p);
+}
+
static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
struct rt_rq *rt_rq)
{
@@ -1518,7 +1526,6 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
struct sched_rt_entity *rt_se;
- struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
do {
@@ -1527,10 +1534,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
rt_rq = group_rt_rq(rt_se);
} while (rt_rq);
- p = rt_task_of(rt_se);
- p->se.exec_start = rq_clock_task(rq);
-
- return p;
+ return rt_task_of(rt_se);
}
static struct task_struct *
@@ -1561,7 +1565,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
/*
* We may dequeue prev's rt_rq in put_prev_task().
- * So, we update time before rt_nr_running check.
+ * So, we update time before rt_queued check.
*/
if (prev->sched_class == &rt_sched_class)
update_curr_rt(rq);
@@ -1573,8 +1577,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
p = _pick_next_task_rt(rq);
- /* The running task is never eligible for pushing */
- dequeue_pushable_task(rq, p);
+ set_next_task(rq, p);
rt_queue_push_tasks(rq);
@@ -1810,10 +1813,8 @@ static int push_rt_task(struct rq *rq)
return 0;
retry:
- if (unlikely(next_task == rq->curr)) {
- WARN_ON(1);
+ if (WARN_ON(next_task == rq->curr))
return 0;
- }
/*
* It's possible that the next_task slipped in of
@@ -2355,12 +2356,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
static void set_curr_task_rt(struct rq *rq)
{
- struct task_struct *p = rq->curr;
-
- p->se.exec_start = rq_clock_task(rq);
-
- /* The running task is never eligible for pushing */
- dequeue_pushable_task(rq, p);
+ set_next_task(rq, rq->curr);
}
static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b8c007713b3b..0ba08924e017 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -23,6 +23,7 @@
#include <linux/sched/prio.h>
#include <linux/sched/rt.h>
#include <linux/sched/signal.h>
+#include <linux/sched/smt.h>
#include <linux/sched/stat.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/task.h>
@@ -44,6 +45,7 @@
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/delayacct.h>
+#include <linux/energy_model.h>
#include <linux/init_task.h>
#include <linux/kprobes.h>
#include <linux/kthread.h>
@@ -54,6 +56,7 @@
#include <linux/proc_fs.h>
#include <linux/prefetch.h>
#include <linux/profile.h>
+#include <linux/psi.h>
#include <linux/rcupdate_wait.h>
#include <linux/security.h>
#include <linux/stop_machine.h>
@@ -175,6 +178,11 @@ static inline bool valid_policy(int policy)
rt_policy(policy) || dl_policy(policy);
}
+static inline int task_has_idle_policy(struct task_struct *p)
+{
+ return idle_policy(p->policy);
+}
+
static inline int task_has_rt_policy(struct task_struct *p)
{
return rt_policy(p->policy);
@@ -319,6 +327,7 @@ extern bool dl_cpu_busy(unsigned int cpu);
#ifdef CONFIG_CGROUP_SCHED
#include <linux/cgroup.h>
+#include <linux/psi.h>
struct cfs_rq;
struct rt_rq;
@@ -629,7 +638,7 @@ struct dl_rq {
/*
* Deadline values of the currently executing and the
* earliest ready task on this rq. Caching these facilitates
- * the decision wether or not a ready but not running task
+ * the decision whether or not a ready but not running task
* should migrate somewhere else.
*/
struct {
@@ -701,6 +710,16 @@ static inline bool sched_asym_prefer(int a, int b)
return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b);
}
+struct perf_domain {
+ struct em_perf_domain *em_pd;
+ struct perf_domain *next;
+ struct rcu_head rcu;
+};
+
+/* Scheduling group status flags */
+#define SG_OVERLOAD 0x1 /* More than one runnable task on a CPU. */
+#define SG_OVERUTILIZED 0x2 /* One or more CPUs are over-utilized. */
+
/*
* We add the notion of a root-domain which will be used to define per-domain
* variables. Each exclusive cpuset essentially defines an island domain by
@@ -723,6 +742,9 @@ struct root_domain {
*/
int overload;
+ /* Indicate one or more cpus over-utilized (tipping point) */
+ int overutilized;
+
/*
* The bit corresponding to a CPU gets set here if such CPU has more
* than one runnable -deadline task (as it is below for RT tasks).
@@ -753,6 +775,12 @@ struct root_domain {
struct cpupri cpupri;
unsigned long max_cpu_capacity;
+
+ /*
+ * NULL-terminated list of performance domains intersecting with the
+ * CPUs of the rd. Protected by RCU.
+ */
+ struct perf_domain *pd;
};
extern struct root_domain def_root_domain;
@@ -934,9 +962,6 @@ static inline int cpu_of(struct rq *rq)
#ifdef CONFIG_SCHED_SMT
-
-extern struct static_key_false sched_smt_present;
-
extern void __update_idle_core(struct rq *rq);
static inline void update_idle_core(struct rq *rq)
@@ -957,6 +982,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() raw_cpu_ptr(&runqueues)
+extern void update_rq_clock(struct rq *rq);
+
static inline u64 __rq_clock_broken(struct rq *rq)
{
return READ_ONCE(rq->clock);
@@ -1075,6 +1102,98 @@ static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
#endif
}
+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(rq->lock);
+
+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(p->pi_lock)
+ __acquires(rq->lock);
+
+static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+}
+
+static inline void
+task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+ __releases(rq->lock)
+ __releases(p->pi_lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
+}
+
+static inline void
+rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock_irqsave(&rq->lock, rf->flags);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock_irq(&rq->lock);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_relock(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock(&rq->lock);
+ rq_repin_lock(rq, rf);
+}
+
+static inline void
+rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+}
+
+static inline void
+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock_irq(&rq->lock);
+}
+
+static inline void
+rq_unlock(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+}
+
+static inline struct rq *
+this_rq_lock_irq(struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ struct rq *rq;
+
+ local_irq_disable();
+ rq = this_rq();
+ rq_lock(rq, rf);
+ return rq;
+}
+
#ifdef CONFIG_NUMA
enum numa_topology_type {
NUMA_DIRECT,
@@ -1191,7 +1310,8 @@ DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
extern struct static_key_false sched_asym_cpucapacity;
struct sched_group_capacity {
@@ -1335,7 +1455,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
#ifdef CONFIG_SMP
/*
* After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
- * successfuly executed on another CPU. We must ensure that updates of
+ * successfully executed on another CPU. We must ensure that updates of
* per-task data have been completed by this moment.
*/
smp_wmb();
@@ -1700,12 +1820,12 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
rq->nr_running = prev_nr + count;
- if (prev_nr < 2 && rq->nr_running >= 2) {
#ifdef CONFIG_SMP
+ if (prev_nr < 2 && rq->nr_running >= 2) {
if (!READ_ONCE(rq->rd->overload))
WRITE_ONCE(rq->rd->overload, 1);
-#endif
}
+#endif
sched_update_tick_dependency(rq);
}
@@ -1717,8 +1837,6 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
sched_update_tick_dependency(rq);
}
-extern void update_rq_clock(struct rq *rq);
-
extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
@@ -1763,107 +1881,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
#endif
#ifdef CONFIG_SMP
-#ifndef arch_scale_cpu_capacity
-static __always_inline
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
- return sd->smt_gain / sd->span_weight;
-
- return SCHED_CAPACITY_SCALE;
-}
-#endif
-#else
-#ifndef arch_scale_cpu_capacity
-static __always_inline
-unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
-{
- return SCHED_CAPACITY_SCALE;
-}
-#endif
-#endif
-
-struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
- __acquires(rq->lock);
-
-struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
- __acquires(p->pi_lock)
- __acquires(rq->lock);
-
-static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
-}
-
-static inline void
-task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
- __releases(rq->lock)
- __releases(p->pi_lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
- raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
-}
-
-static inline void
-rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock_irqsave(&rq->lock, rf->flags);
- rq_pin_lock(rq, rf);
-}
-
-static inline void
-rq_lock_irq(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock_irq(&rq->lock);
- rq_pin_lock(rq, rf);
-}
-
-static inline void
-rq_lock(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock(&rq->lock);
- rq_pin_lock(rq, rf);
-}
-
-static inline void
-rq_relock(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock(&rq->lock);
- rq_repin_lock(rq, rf);
-}
-
-static inline void
-rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
-}
-
-static inline void
-rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock_irq(&rq->lock);
-}
-
-static inline void
-rq_unlock(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
-}
-
-#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -2195,6 +2212,31 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
+/**
+ * enum schedutil_type - CPU utilization type
+ * @FREQUENCY_UTIL: Utilization used to select frequency
+ * @ENERGY_UTIL: Utilization used during energy calculation
+ *
+ * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
+ * need to be aggregated differently depending on the usage made of them. This
+ * enum is used within schedutil_freq_util() to differentiate the types of
+ * utilization expected by the callers, and adjust the aggregation accordingly.
+ */
+enum schedutil_type {
+ FREQUENCY_UTIL,
+ ENERGY_UTIL,
+};
+
+unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
+ unsigned long max, enum schedutil_type type);
+
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+ unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+
+ return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL);
+}
+
static inline unsigned long cpu_bw_dl(struct rq *rq)
{
return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
@@ -2221,6 +2263,11 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
{
return READ_ONCE(rq->avg_rt.util_avg);
}
+#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+ return cfs;
+}
#endif
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
@@ -2250,3 +2297,13 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned
return util;
}
#endif
+
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+#define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus)))
+#else
+#define perf_domain_span(pd) NULL
+#endif
+
+#ifdef CONFIG_SMP
+extern struct static_key_false sched_energy_present;
+#endif
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 8aea199a39b4..aa0de240fb41 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -55,6 +55,92 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt
# define schedstat_val_or_zero(var) 0
#endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_PSI
+/*
+ * PSI tracks state that persists across sleeps, such as iowaits and
+ * memory stalls. As a result, it has to distinguish between sleeps,
+ * where a task's runnable state changes, and requeues, where a task
+ * and its state are being moved between CPUs and runqueues.
+ */
+static inline void psi_enqueue(struct task_struct *p, bool wakeup)
+{
+ int clear = 0, set = TSK_RUNNING;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ if (!wakeup || p->sched_psi_wake_requeue) {
+ if (p->flags & PF_MEMSTALL)
+ set |= TSK_MEMSTALL;
+ if (p->sched_psi_wake_requeue)
+ p->sched_psi_wake_requeue = 0;
+ } else {
+ if (p->in_iowait)
+ clear |= TSK_IOWAIT;
+ }
+
+ psi_task_change(p, clear, set);
+}
+
+static inline void psi_dequeue(struct task_struct *p, bool sleep)
+{
+ int clear = TSK_RUNNING, set = 0;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ if (!sleep) {
+ if (p->flags & PF_MEMSTALL)
+ clear |= TSK_MEMSTALL;
+ } else {
+ if (p->in_iowait)
+ set |= TSK_IOWAIT;
+ }
+
+ psi_task_change(p, clear, set);
+}
+
+static inline void psi_ttwu_dequeue(struct task_struct *p)
+{
+ if (static_branch_likely(&psi_disabled))
+ return;
+ /*
+ * Is the task being migrated during a wakeup? Make sure to
+ * deregister its sleep-persistent psi states from the old
+ * queue, and let psi_enqueue() know it has to requeue.
+ */
+ if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) {
+ struct rq_flags rf;
+ struct rq *rq;
+ int clear = 0;
+
+ if (p->in_iowait)
+ clear |= TSK_IOWAIT;
+ if (p->flags & PF_MEMSTALL)
+ clear |= TSK_MEMSTALL;
+
+ rq = __task_rq_lock(p, &rf);
+ psi_task_change(p, clear, 0);
+ p->sched_psi_wake_requeue = 1;
+ __task_rq_unlock(rq, &rf);
+ }
+}
+
+static inline void psi_task_tick(struct rq *rq)
+{
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ if (unlikely(rq->curr->flags & PF_MEMSTALL))
+ psi_memstall_tick(rq->curr, cpu_of(rq));
+}
+#else /* CONFIG_PSI */
+static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
+static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
+static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_task_tick(struct rq *rq) {}
+#endif /* CONFIG_PSI */
+
#ifdef CONFIG_SCHED_INFO
static inline void sched_info_reset_dequeued(struct task_struct *t)
{
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 9d74371e4aad..3f35ba1d8fde 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -201,6 +201,199 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
return 1;
}
+DEFINE_STATIC_KEY_FALSE(sched_energy_present);
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+DEFINE_MUTEX(sched_energy_mutex);
+bool sched_energy_update;
+
+static void free_pd(struct perf_domain *pd)
+{
+ struct perf_domain *tmp;
+
+ while (pd) {
+ tmp = pd->next;
+ kfree(pd);
+ pd = tmp;
+ }
+}
+
+static struct perf_domain *find_pd(struct perf_domain *pd, int cpu)
+{
+ while (pd) {
+ if (cpumask_test_cpu(cpu, perf_domain_span(pd)))
+ return pd;
+ pd = pd->next;
+ }
+
+ return NULL;
+}
+
+static struct perf_domain *pd_init(int cpu)
+{
+ struct em_perf_domain *obj = em_cpu_get(cpu);
+ struct perf_domain *pd;
+
+ if (!obj) {
+ if (sched_debug())
+ pr_info("%s: no EM found for CPU%d\n", __func__, cpu);
+ return NULL;
+ }
+
+ pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+ if (!pd)
+ return NULL;
+ pd->em_pd = obj;
+
+ return pd;
+}
+
+static void perf_domain_debug(const struct cpumask *cpu_map,
+ struct perf_domain *pd)
+{
+ if (!sched_debug() || !pd)
+ return;
+
+ printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map));
+
+ while (pd) {
+ printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }",
+ cpumask_first(perf_domain_span(pd)),
+ cpumask_pr_args(perf_domain_span(pd)),
+ em_pd_nr_cap_states(pd->em_pd));
+ pd = pd->next;
+ }
+
+ printk(KERN_CONT "\n");
+}
+
+static void destroy_perf_domain_rcu(struct rcu_head *rp)
+{
+ struct perf_domain *pd;
+
+ pd = container_of(rp, struct perf_domain, rcu);
+ free_pd(pd);
+}
+
+static void sched_energy_set(bool has_eas)
+{
+ if (!has_eas && static_branch_unlikely(&sched_energy_present)) {
+ if (sched_debug())
+ pr_info("%s: stopping EAS\n", __func__);
+ static_branch_disable_cpuslocked(&sched_energy_present);
+ } else if (has_eas && !static_branch_unlikely(&sched_energy_present)) {
+ if (sched_debug())
+ pr_info("%s: starting EAS\n", __func__);
+ static_branch_enable_cpuslocked(&sched_energy_present);
+ }
+}
+
+/*
+ * EAS can be used on a root domain if it meets all the following conditions:
+ * 1. an Energy Model (EM) is available;
+ * 2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
+ * 3. the EM complexity is low enough to keep scheduling overheads low;
+ * 4. schedutil is driving the frequency of all CPUs of the rd;
+ *
+ * The complexity of the Energy Model is defined as:
+ *
+ * C = nr_pd * (nr_cpus + nr_cs)
+ *
+ * with parameters defined as:
+ * - nr_pd: the number of performance domains
+ * - nr_cpus: the number of CPUs
+ * - nr_cs: the sum of the number of capacity states of all performance
+ * domains (for example, on a system with 2 performance domains,
+ * with 10 capacity states each, nr_cs = 2 * 10 = 20).
+ *
+ * It is generally not a good idea to use such a model in the wake-up path on
+ * very complex platforms because of the associated scheduling overheads. The
+ * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
+ * with per-CPU DVFS and less than 8 capacity states each, for example.
+ */
+#define EM_MAX_COMPLEXITY 2048
+
+extern struct cpufreq_governor schedutil_gov;
+static bool build_perf_domains(const struct cpumask *cpu_map)
+{
+ int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
+ struct perf_domain *pd = NULL, *tmp;
+ int cpu = cpumask_first(cpu_map);
+ struct root_domain *rd = cpu_rq(cpu)->rd;
+ struct cpufreq_policy *policy;
+ struct cpufreq_governor *gov;
+
+ /* EAS is enabled for asymmetric CPU capacity topologies. */
+ if (!per_cpu(sd_asym_cpucapacity, cpu)) {
+ if (sched_debug()) {
+ pr_info("rd %*pbl: CPUs do not have asymmetric capacities\n",
+ cpumask_pr_args(cpu_map));
+ }
+ goto free;
+ }
+
+ for_each_cpu(i, cpu_map) {
+ /* Skip already covered CPUs. */
+ if (find_pd(pd, i))
+ continue;
+
+ /* Do not attempt EAS if schedutil is not being used. */
+ policy = cpufreq_cpu_get(i);
+ if (!policy)
+ goto free;
+ gov = policy->governor;
+ cpufreq_cpu_put(policy);
+ if (gov != &schedutil_gov) {
+ if (rd->pd)
+ pr_warn("rd %*pbl: Disabling EAS, schedutil is mandatory\n",
+ cpumask_pr_args(cpu_map));
+ goto free;
+ }
+
+ /* Create the new pd and add it to the local list. */
+ tmp = pd_init(i);
+ if (!tmp)
+ goto free;
+ tmp->next = pd;
+ pd = tmp;
+
+ /*
+ * Count performance domains and capacity states for the
+ * complexity check.
+ */
+ nr_pd++;
+ nr_cs += em_pd_nr_cap_states(pd->em_pd);
+ }
+
+ /* Bail out if the Energy Model complexity is too high. */
+ if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+ WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n",
+ cpumask_pr_args(cpu_map));
+ goto free;
+ }
+
+ perf_domain_debug(cpu_map, pd);
+
+ /* Attach the new list of performance domains to the root domain. */
+ tmp = rd->pd;
+ rcu_assign_pointer(rd->pd, pd);
+ if (tmp)
+ call_rcu(&tmp->rcu, destroy_perf_domain_rcu);
+
+ return !!pd;
+
+free:
+ free_pd(pd);
+ tmp = rd->pd;
+ rcu_assign_pointer(rd->pd, NULL);
+ if (tmp)
+ call_rcu(&tmp->rcu, destroy_perf_domain_rcu);
+
+ return false;
+}
+#else
+static void free_pd(struct perf_domain *pd) { }
+#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL*/
+
static void free_rootdomain(struct rcu_head *rcu)
{
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
@@ -211,6 +404,7 @@ static void free_rootdomain(struct rcu_head *rcu)
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
+ free_pd(rd->pd);
kfree(rd);
}
@@ -397,7 +591,8 @@ DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
static void update_top_cache_domain(int cpu)
@@ -423,7 +618,10 @@ static void update_top_cache_domain(int cpu)
rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
- rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+ rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd);
+
+ sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY);
+ rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd);
}
/*
@@ -1133,7 +1331,6 @@ sd_init(struct sched_domain_topology_level *tl,
.last_balance = jiffies,
.balance_interval = sd_weight,
- .smt_gain = 0,
.max_newidle_lb_cost = 0,
.next_decay_max_lb_cost = jiffies,
.child = child,
@@ -1164,7 +1361,6 @@ sd_init(struct sched_domain_topology_level *tl,
if (sd->flags & SD_SHARE_CPUCAPACITY) {
sd->imbalance_pct = 110;
- sd->smt_gain = 1178; /* ~15% */
} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
sd->imbalance_pct = 117;
@@ -1337,7 +1533,7 @@ void sched_init_numa(void)
int level = 0;
int i, j, k;
- sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
+ sched_domains_numa_distance = kzalloc(sizeof(int) * (nr_node_ids + 1), GFP_KERNEL);
if (!sched_domains_numa_distance)
return;
@@ -1934,6 +2130,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
+ bool __maybe_unused has_eas = false;
int i, j, n;
int new_topology;
@@ -1961,8 +2158,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
/* Destroy deleted domains: */
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(doms_cur[i], doms_new[j])
- && dattrs_equal(dattr_cur, i, dattr_new, j))
+ if (cpumask_equal(doms_cur[i], doms_new[j]) &&
+ dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
/* No match - a current sched domain not in new doms_new[] */
@@ -1982,8 +2179,8 @@ match1:
/* Build new domains: */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(doms_new[i], doms_cur[j])
- && dattrs_equal(dattr_new, i, dattr_cur, j))
+ if (cpumask_equal(doms_new[i], doms_cur[j]) &&
+ dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
/* No match - add a new doms_new */
@@ -1992,6 +2189,24 @@ match2:
;
}
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+ /* Build perf. domains: */
+ for (i = 0; i < ndoms_new; i++) {
+ for (j = 0; j < n && !sched_energy_update; j++) {
+ if (cpumask_equal(doms_new[i], doms_cur[j]) &&
+ cpu_rq(cpumask_first(doms_cur[j]))->rd->pd) {
+ has_eas = true;
+ goto match3;
+ }
+ }
+ /* No match - add perf. domains for a new rd */
+ has_eas |= build_perf_domains(doms_new[i]);
+match3:
+ ;
+ }
+ sched_energy_set(has_eas);
+#endif
+
/* Remember the new sched domains: */
if (doms_cur != &fallback_doms)
free_sched_domains(doms_cur, ndoms_cur);
diff --git a/kernel/signal.c b/kernel/signal.c
index 17565240b1c6..9a32bc2088c9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -892,7 +892,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
/*
* The first thread which returns from do_signal_stop()
* will take ->siglock, notice SIGNAL_CLD_MASK, and
- * notify its parent. See get_signal_to_deliver().
+ * notify its parent. See get_signal().
*/
signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED);
signal->group_stop_count = 0;
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
new file mode 100644
index 000000000000..b193a59fc05b
--- /dev/null
+++ b/kernel/stackleak.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This code fills the used part of the kernel stack with a poison value
+ * before returning to userspace. It's part of the STACKLEAK feature
+ * ported from grsecurity/PaX.
+ *
+ * Author: Alexander Popov <alex.popov@linux.com>
+ *
+ * STACKLEAK reduces the information which kernel stack leak bugs can
+ * reveal and blocks some uninitialized stack variable attacks.
+ */
+
+#include <linux/stackleak.h>
+#include <linux/kprobes.h>
+
+#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
+#include <linux/jump_label.h>
+#include <linux/sysctl.h>
+
+static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
+
+int stack_erasing_sysctl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int ret = 0;
+ int state = !static_branch_unlikely(&stack_erasing_bypass);
+ int prev_state = state;
+
+ table->data = &state;
+ table->maxlen = sizeof(int);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ state = !!state;
+ if (ret || !write || state == prev_state)
+ return ret;
+
+ if (state)
+ static_branch_disable(&stack_erasing_bypass);
+ else
+ static_branch_enable(&stack_erasing_bypass);
+
+ pr_warn("stackleak: kernel stack erasing is %s\n",
+ state ? "enabled" : "disabled");
+ return ret;
+}
+
+#define skip_erasing() static_branch_unlikely(&stack_erasing_bypass)
+#else
+#define skip_erasing() false
+#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */
+
+asmlinkage void notrace stackleak_erase(void)
+{
+ /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */
+ unsigned long kstack_ptr = current->lowest_stack;
+ unsigned long boundary = (unsigned long)end_of_stack(current);
+ unsigned int poison_count = 0;
+ const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
+
+ if (skip_erasing())
+ return;
+
+ /* Check that 'lowest_stack' value is sane */
+ if (unlikely(kstack_ptr - boundary >= THREAD_SIZE))
+ kstack_ptr = boundary;
+
+ /* Search for the poison value in the kernel stack */
+ while (kstack_ptr > boundary && poison_count <= depth) {
+ if (*(unsigned long *)kstack_ptr == STACKLEAK_POISON)
+ poison_count++;
+ else
+ poison_count = 0;
+
+ kstack_ptr -= sizeof(unsigned long);
+ }
+
+ /*
+ * One 'long int' at the bottom of the thread stack is reserved and
+ * should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y).
+ */
+ if (kstack_ptr == boundary)
+ kstack_ptr += sizeof(unsigned long);
+
+#ifdef CONFIG_STACKLEAK_METRICS
+ current->prev_lowest_stack = kstack_ptr;
+#endif
+
+ /*
+ * Now write the poison value to the kernel stack. Start from
+ * 'kstack_ptr' and move up till the new 'boundary'. We assume that
+ * the stack pointer doesn't change when we write poison.
+ */
+ if (on_thread_stack())
+ boundary = current_stack_pointer;
+ else
+ boundary = current_top_of_stack();
+
+ while (kstack_ptr < boundary) {
+ *(unsigned long *)kstack_ptr = STACKLEAK_POISON;
+ kstack_ptr += sizeof(unsigned long);
+ }
+
+ /* Reset the 'lowest_stack' value for the next syscall */
+ current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64;
+}
+NOKPROBE_SYMBOL(stackleak_erase);
+
+void __used notrace stackleak_track_stack(void)
+{
+ /*
+ * N.B. stackleak_erase() fills the kernel stack with the poison value,
+ * which has the register width. That code assumes that the value
+ * of 'lowest_stack' is aligned on the register width boundary.
+ *
+ * That is true for x86 and x86_64 because of the kernel stack
+ * alignment on these platforms (for details, see 'cc_stack_align' in
+ * arch/x86/Makefile). Take care of that when you port STACKLEAK to
+ * new platforms.
+ */
+ unsigned long sp = (unsigned long)&sp;
+
+ /*
+ * Having CONFIG_STACKLEAK_TRACK_MIN_SIZE larger than
+ * STACKLEAK_SEARCH_DEPTH makes the poison search in
+ * stackleak_erase() unreliable. Let's prevent that.
+ */
+ BUILD_BUG_ON(CONFIG_STACKLEAK_TRACK_MIN_SIZE > STACKLEAK_SEARCH_DEPTH);
+
+ if (sp < current->lowest_stack &&
+ sp >= (unsigned long)task_stack_page(current) +
+ sizeof(unsigned long)) {
+ current->lowest_stack = sp;
+ }
+}
+EXPORT_SYMBOL(stackleak_track_stack);
diff --git a/kernel/sys.c b/kernel/sys.c
index 123bd73046ec..64b5a230f38d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -121,6 +121,9 @@
#ifndef SVE_GET_VL
# define SVE_GET_VL() (-EINVAL)
#endif
+#ifndef PAC_RESET_KEYS
+# define PAC_RESET_KEYS(a, b) (-EINVAL)
+#endif
/*
* this is where the system-wide overflow UID and GID are defined, for
@@ -2476,6 +2479,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
break;
+ case PR_PAC_RESET_KEYS:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = PAC_RESET_KEYS(me, arg2);
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index cc02050fd0c4..5fc724e4e454 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -66,7 +66,6 @@
#include <linux/kexec.h>
#include <linux/bpf.h>
#include <linux/mount.h>
-#include <linux/pipe_fs_i.h>
#include <linux/uaccess.h>
#include <asm/processor.h>
@@ -91,7 +90,9 @@
#ifdef CONFIG_CHR_DEV_SG
#include <scsi/sg.h>
#endif
-
+#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
+#include <linux/stackleak.h>
+#endif
#ifdef CONFIG_LOCKUP_DETECTOR
#include <linux/nmi.h>
#endif
@@ -1233,6 +1234,17 @@ static struct ctl_table kern_table[] = {
.extra2 = &one,
},
#endif
+#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
+ {
+ .procname = "stack_erasing",
+ .data = NULL,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = stack_erasing_sysctl,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+#endif
{ }
};
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index fa5de5e8de61..2c97e8c2d29f 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Alarmtimer interface
*
@@ -10,10 +11,6 @@
* Copyright (C) 2010 IBM Corperation
*
* Author: John Stultz <john.stultz@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/time.h>
#include <linux/hrtimer.h>
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 8c0e4092f661..5e77662dd2d9 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/clockevents.c
- *
* This file contains functions which manage clock event devices.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
- *
- * This code is licenced under the GPL version 2. For details see
- * kernel-base/COPYING.
*/
#include <linux/clockchips.h>
@@ -39,10 +35,8 @@ static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
u64 clc = (u64) latch << evt->shift;
u64 rnd;
- if (unlikely(!evt->mult)) {
+ if (WARN_ON(!evt->mult))
evt->mult = 1;
- WARN_ON(1);
- }
rnd = (u64) evt->mult - 1;
/*
@@ -164,10 +158,8 @@ void clockevents_switch_state(struct clock_event_device *dev,
* on it, so fix it up and emit a warning:
*/
if (clockevent_state_oneshot(dev)) {
- if (unlikely(!dev->mult)) {
+ if (WARN_ON(!dev->mult))
dev->mult = 1;
- WARN_ON(1);
- }
}
}
}
@@ -315,10 +307,8 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
int64_t delta;
int rc;
- if (unlikely(expires < 0)) {
- WARN_ON_ONCE(1);
+ if (WARN_ON_ONCE(expires < 0))
return -ETIME;
- }
dev->next_event = expires;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index ffe081623aec..3bcc19ceb073 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -1,26 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * linux/kernel/time/clocksource.c
- *
* This file contains the functions which manage clocksource drivers.
*
* Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
- *
- * 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, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * TODO WishList:
- * o Allow clocksource drivers to be unregistered
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 9cdd74bd2d27..f5cfa1b73d6f 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1,34 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/hrtimer.c
- *
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
*
* High-resolution kernel timers
*
- * In contrast to the low-resolution timeout API implemented in
- * kernel/timer.c, hrtimers provide finer resolution and accuracy
- * depending on system configuration and capabilities.
- *
- * These timers are currently used for:
- * - itimers
- * - POSIX timers
- * - nanosleep
- * - precise in-kernel timing
+ * In contrast to the low-resolution timeout API, aka timer wheel,
+ * hrtimers provide finer resolution and accuracy depending on system
+ * configuration and capabilities.
*
* Started by: Thomas Gleixner and Ingo Molnar
*
* Credits:
- * based on kernel/timer.c
+ * Based on the original timer wheel code
*
* Help, testing, suggestions, bugfixes, improvements were
* provided by:
*
* George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
* et. al.
- *
- * For licencing details see kernel-base/COPYING
*/
#include <linux/cpu.h>
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 9a65713c8309..02068b2d5862 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/itimer.c
- *
* Copyright (C) 1992 Darren Senn
*/
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 497719127bf9..dc1b6f1929f9 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -1,25 +1,9 @@
-/***********************************************************************
-* linux/kernel/time/jiffies.c
-*
-* This file contains the jiffies based clocksource.
-*
-* Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
-*
-* 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, write to the Free Software
-* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-*
-************************************************************************/
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * This file contains the jiffies based clocksource.
+ *
+ * Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
+ */
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/module.h>
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index c5e0cba3b39c..bc3a3c37ec9c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -17,7 +17,6 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/rtc.h>
-#include <linux/math64.h>
#include "ntp_internal.h"
#include "timekeeping_internal.h"
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index fe56c4e06c51..425bbfce6819 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * posix-clock.c - support for dynamic clock devices
+ * Support for dynamic clock devices
*
* Copyright (C) 2010 OMICRON electronics GmbH
- *
- * 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, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/device.h>
#include <linux/export.h>
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index ce32cf741b25..8f0644af40be 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -917,9 +917,6 @@ static void check_process_timers(struct task_struct *tsk,
struct task_cputime cputime;
unsigned long soft;
- if (dl_task(tsk))
- check_dl_overrun(tsk);
-
/*
* If cputimer is not running, then there are no active
* process wide timers (POSIX 1.b, itimers, RLIMIT_CPU).
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 989ccf028bde..a51895486e5e 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Dummy stubs used when CONFIG_POSIX_TIMERS=n
*
* Created by: Nicolas Pitre, July 2016
* Copyright: (C) 2016 Linaro Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/linkage.h>
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index bd62b5eeb5a0..0e84bb72a3da 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1,34 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * linux/kernel/posix-timers.c
- *
- *
* 2002-10-15 Posix Clocks & timers
* by George Anzinger george@mvista.com
- *
* Copyright (C) 2002 2003 by MontaVista Software.
*
* 2004-06-01 Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug.
* Copyright (C) 2004 Boris Hu
*
- * 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, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * MontaVista Software | 1237 East Arques Avenue | Sunnyvale | CA 94085 | USA
- */
-
-/* These are all the functions necessary to implement
- * POSIX clocks & timers
+ * These are all the functions necessary to implement POSIX clocks & timers
*/
#include <linux/mm.h>
#include <linux/interrupt.h>
@@ -289,9 +268,6 @@ static void common_hrtimer_rearm(struct k_itimer *timr)
{
struct hrtimer *timer = &timr->it.real.timer;
- if (!timr->it_interval)
- return;
-
timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
timr->it_interval);
hrtimer_restart(timer);
@@ -317,7 +293,7 @@ void posixtimer_rearm(struct kernel_siginfo *info)
if (!timr)
return;
- if (timr->it_requeue_pending == info->si_sys_private) {
+ if (timr->it_interval && timr->it_requeue_pending == info->si_sys_private) {
timr->kclock->timer_rearm(timr);
timr->it_active = 1;
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index cbc72c2c1fca..094b82ca95e5 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * sched_clock.c: Generic sched_clock() support, to extend low level
- * hardware time counters to full 64-bit ns values.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Generic sched_clock() support, to extend low level hardware time
+ * counters to full 64-bit ns values.
*/
#include <linux/clocksource.h>
#include <linux/init.h>
diff --git a/kernel/time/test_udelay.c b/kernel/time/test_udelay.c
index b0928ab3270f..77c63005dc4e 100644
--- a/kernel/time/test_udelay.c
+++ b/kernel/time/test_udelay.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* udelay() test kernel module
*
@@ -7,15 +8,6 @@
* Specifying usecs of 0 or negative values will run multiples tests.
*
* Copyright (C) 2014 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * 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.
*/
#include <linux/debugfs.h>
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index a59641fb88b6..5be6154e2fd2 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -1,8 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-broadcast-hrtimer.c
- * This file emulates a local clock event device
- * via a pseudo clock device.
+ * Emulate a local clock event device via a pseudo clock device.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index be0aac2b4300..803fa67aace9 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -1,15 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-broadcast.c
- *
* This file contains functions which emulate a local clock-event
* device via a broadcast event source.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
- *
- * This code is licenced under the GPL version 2. For details see
- * kernel-base/COPYING.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 14de3727b18e..529143b4c8d2 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -1,15 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-common.c
- *
* This file contains the base functions to manage periodic tick
* related events.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
- *
- * This code is licenced under the GPL version 2. For details see
- * kernel-base/COPYING.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 6fe615d57ebb..f9745d47425a 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -1,15 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-oneshot.c
- *
* This file contains functions which manage high resolution tick
* related events.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
- *
- * This code is licenced under the GPL version 2. For details see
- * kernel-base/COPYING.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 69e673b88474..6fa52cd6df0b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-sched.c
- *
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
@@ -8,8 +7,6 @@
* No idle tick implementation for low and high resolution timers
*
* Started by: Thomas Gleixner and Ingo Molnar
- *
- * Distribute under GPLv2.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/time.c b/kernel/time/time.c
index e3a7f7fd3abc..5aa0a156e331 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -1,14 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time.c
- *
* Copyright (C) 1991, 1992 Linus Torvalds
*
- * This file contains the interface functions for the various
- * time related system calls: time, stime, gettimeofday, settimeofday,
- * adjtime
- */
-/*
- * Modification history kernel/time.c
+ * This file contains the interface functions for the various time related
+ * system calls: time, stime, gettimeofday, settimeofday, adjtime
+ *
+ * Modification history:
*
* 1993-09-02 Philip Gladstone
* Created file with time related functions from sched/core.c and adjtimex()
@@ -842,7 +839,7 @@ int get_timespec64(struct timespec64 *ts,
ts->tv_sec = kts.tv_sec;
/* Zero out the padding for 32 bit systems or in compat mode */
- if (IS_ENABLED(CONFIG_64BIT_TIME) && (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()))
+ if (IS_ENABLED(CONFIG_64BIT_TIME) && in_compat_syscall())
kts.tv_nsec &= 0xFFFFFFFFUL;
ts->tv_nsec = kts.tv_nsec;
diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc
index f83bbb81600b..7ed0e0fb5831 100644
--- a/kernel/time/timeconst.bc
+++ b/kernel/time/timeconst.bc
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
scale=0
define gcd(a,b) {
diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c
index 7142580ad94f..589e0a552129 100644
--- a/kernel/time/timeconv.c
+++ b/kernel/time/timeconv.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: LGPL-2.0+
/*
* Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
* This file is part of the GNU C Library.
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
index 8afd78932bdf..85b98e727306 100644
--- a/kernel/time/timecounter.c
+++ b/kernel/time/timecounter.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * linux/kernel/time/timecounter.c
- *
- * based on code that migrated away from
- * linux/kernel/time/clocksource.c
- *
- * 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.
+ * Based on clocksource code. See commit 74d23cc704d1
*/
-
#include <linux/export.h>
#include <linux/timecounter.h>
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2d110c948805..c801e25875a3 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/timekeeping.c
- *
- * Kernel timekeeping code and accessor functions
- *
- * This code was moved from linux/kernel/timer.c.
- * Please see that file for copyright and history logs.
- *
+ * Kernel timekeeping code and accessor functions. Based on code from
+ * timer.c, moved in commit 8524070b7982.
*/
-
#include <linux/timekeeper_internal.h>
#include <linux/module.h>
#include <linux/interrupt.h>
@@ -50,7 +45,9 @@ enum timekeeping_adv_mode {
static struct {
seqcount_t seq;
struct timekeeper timekeeper;
-} tk_core ____cacheline_aligned;
+} tk_core ____cacheline_aligned = {
+ .seq = SEQCNT_ZERO(tk_core.seq),
+};
static DEFINE_RAW_SPINLOCK(timekeeper_lock);
static struct timekeeper shadow_timekeeper;
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 238e4be60229..86489950d690 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -1,17 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* debugfs file to track time spent in suspend
*
* Copyright (c) 2011, Google, Inc.
- *
- * 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.
*/
#include <linux/debugfs.h>
@@ -28,7 +19,7 @@
static unsigned int sleep_time_bin[NUM_BINS] = {0};
-static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
+static int tk_debug_sleep_time_show(struct seq_file *s, void *data)
{
unsigned int bin;
seq_puts(s, " time (secs) count\n");
@@ -42,18 +33,7 @@ static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
}
return 0;
}
-
-static int tk_debug_sleep_time_open(struct inode *inode, struct file *file)
-{
- return single_open(file, tk_debug_show_sleep_time, NULL);
-}
-
-static const struct file_operations tk_debug_sleep_time_fops = {
- .open = tk_debug_sleep_time_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(tk_debug_sleep_time);
static int __init tk_debug_sleep_time_init(void)
{
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index fa49cd753dea..444156debfa0 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/timer.c
- *
* Kernel internal timers
*
* Copyright (C) 1991, 1992 Linus Torvalds
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index d647dabdac97..98ba50dcb1b2 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * kernel/time/timer_list.c
- *
* List pending timers
*
* Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/proc_fs.h>
diff --git a/kernel/torture.c b/kernel/torture.c
index 17d91f5fba2a..bbf6d473e50c 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -194,11 +194,23 @@ torture_onoff(void *arg)
int cpu;
int maxcpu = -1;
DEFINE_TORTURE_RANDOM(rand);
+ int ret;
VERBOSE_TOROUT_STRING("torture_onoff task started");
for_each_online_cpu(cpu)
maxcpu = cpu;
WARN_ON(maxcpu < 0);
+ if (!IS_MODULE(CONFIG_TORTURE_TEST))
+ for_each_possible_cpu(cpu) {
+ if (cpu_online(cpu))
+ continue;
+ ret = cpu_up(cpu);
+ if (ret && verbose) {
+ pr_alert("%s" TORTURE_FLAG
+ "%s: Initial online %d: errno %d\n",
+ __func__, torture_type, cpu, ret);
+ }
+ }
if (maxcpu == 0) {
VERBOSE_TOROUT_STRING("Only one CPU, so CPU-hotplug testing is disabled");
@@ -233,16 +245,15 @@ stop:
*/
int torture_onoff_init(long ooholdoff, long oointerval)
{
- int ret = 0;
-
#ifdef CONFIG_HOTPLUG_CPU
onoff_holdoff = ooholdoff;
onoff_interval = oointerval;
if (onoff_interval <= 0)
return 0;
- ret = torture_create_kthread(torture_onoff, NULL, onoff_task);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
- return ret;
+ return torture_create_kthread(torture_onoff, NULL, onoff_task);
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+ return 0;
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
}
EXPORT_SYMBOL_GPL(torture_onoff_init);
@@ -513,15 +524,13 @@ static int torture_shutdown(void *arg)
*/
int torture_shutdown_init(int ssecs, void (*cleanup)(void))
{
- int ret = 0;
-
torture_shutdown_hook = cleanup;
if (ssecs > 0) {
shutdown_time = ktime_add(ktime_get(), ktime_set(ssecs, 0));
- ret = torture_create_kthread(torture_shutdown, NULL,
+ return torture_create_kthread(torture_shutdown, NULL,
shutdown_task);
}
- return ret;
+ return 0;
}
EXPORT_SYMBOL_GPL(torture_shutdown_init);
@@ -620,13 +629,10 @@ static int torture_stutter(void *arg)
/*
* Initialize and kick off the torture_stutter kthread.
*/
-int torture_stutter_init(int s)
+int torture_stutter_init(const int s)
{
- int ret;
-
stutter = s;
- ret = torture_create_kthread(torture_stutter, NULL, stutter_task);
- return ret;
+ return torture_create_kthread(torture_stutter, NULL, stutter_task);
}
EXPORT_SYMBOL_GPL(torture_stutter_init);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index fac0ddf8a8e2..2868d85f1fb1 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -764,9 +764,9 @@ blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
return NULL;
- if (!bio->bi_blkg)
+ if (!bio->bi_css)
return NULL;
- return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup);
+ return cgroup_get_kernfs_id(bio->bi_css->cgroup);
}
#else
static union kernfs_node_id *
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 08fcfe440c63..9864a35c8bb5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -196,11 +196,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
i++;
} else if (fmt[i] == 'p' || fmt[i] == 's') {
mod[fmt_cnt]++;
- i++;
- if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
+ /* disallow any further format extensions */
+ if (fmt[i + 1] != 0 &&
+ !isspace(fmt[i + 1]) &&
+ !ispunct(fmt[i + 1]))
return -EINVAL;
fmt_cnt++;
- if (fmt[i - 1] == 's') {
+ if (fmt[i] == 's') {
if (str_seen)
/* allow only one '%s' per fmt string */
return -EINVAL;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f536f601bd46..f0ff24173a0b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -173,7 +173,7 @@ static void ftrace_sync(struct work_struct *work)
{
/*
* This function is just a stub to implement a hard force
- * of synchronize_sched(). This requires synchronizing
+ * of synchronize_rcu(). This requires synchronizing
* tasks even in userspace and idle.
*
* Yes, function tracing is rude.
@@ -817,7 +817,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static int profile_graph_entry(struct ftrace_graph_ent *trace)
{
- int index = trace->depth;
+ int index = current->curr_ret_stack;
function_profile_call(trace->func, 0, NULL, NULL);
@@ -852,7 +852,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
if (!fgraph_graph_time) {
int index;
- index = trace->depth;
+ index = current->curr_ret_stack;
/* Append this call time to the parent time to subtract */
if (index)
@@ -934,7 +934,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
ftrace_profile_enabled = 0;
/*
* unregister_ftrace_profiler calls stop_machine
- * so this acts like an synchronize_sched.
+ * so this acts like an synchronize_rcu.
*/
unregister_ftrace_profiler();
}
@@ -1086,7 +1086,7 @@ struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr)
/*
* Some of the ops may be dynamically allocated,
- * they are freed after a synchronize_sched().
+ * they are freed after a synchronize_rcu().
*/
preempt_disable_notrace();
@@ -1286,7 +1286,7 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
{
if (!hash || hash == EMPTY_HASH)
return;
- call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
+ call_rcu(&hash->rcu, __free_ftrace_hash_rcu);
}
void ftrace_free_filter(struct ftrace_ops *ops)
@@ -1501,7 +1501,7 @@ static bool hash_contains_ip(unsigned long ip,
* the ip is not in the ops->notrace_hash.
*
* This needs to be called with preemption disabled as
- * the hashes are freed with call_rcu_sched().
+ * the hashes are freed with call_rcu().
*/
static int
ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
@@ -4496,7 +4496,7 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
if (ftrace_enabled && !ftrace_hash_empty(hash))
ftrace_run_modify_code(&probe->ops, FTRACE_UPDATE_CALLS,
&old_hash_ops);
- synchronize_sched();
+ synchronize_rcu();
hlist_for_each_entry_safe(entry, tmp, &hhd, hlist) {
hlist_del(&entry->hlist);
@@ -5314,7 +5314,7 @@ ftrace_graph_release(struct inode *inode, struct file *file)
mutex_unlock(&graph_lock);
/* Wait till all users are no longer using the old hash */
- synchronize_sched();
+ synchronize_rcu();
free_ftrace_hash(old_hash);
}
@@ -5460,6 +5460,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops)
if (ops->flags & FTRACE_OPS_FL_ENABLED)
ftrace_shutdown(ops, 0);
ops->flags |= FTRACE_OPS_FL_DELETED;
+ ftrace_free_filter(ops);
mutex_unlock(&ftrace_lock);
}
@@ -5707,7 +5708,7 @@ void ftrace_release_mod(struct module *mod)
list_for_each_entry_safe(mod_map, n, &ftrace_mod_maps, list) {
if (mod_map->mod == mod) {
list_del_rcu(&mod_map->list);
- call_rcu_sched(&mod_map->rcu, ftrace_free_mod_map);
+ call_rcu(&mod_map->rcu, ftrace_free_mod_map);
break;
}
}
@@ -5927,7 +5928,7 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
struct ftrace_mod_map *mod_map;
const char *ret = NULL;
- /* mod_map is freed via call_rcu_sched() */
+ /* mod_map is freed via call_rcu() */
preempt_disable();
list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
ret = ftrace_func_address_lookup(mod_map, addr, size, off, sym);
@@ -6262,7 +6263,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
/*
* Some of the ops may be dynamically allocated,
- * they must be freed after a synchronize_sched().
+ * they must be freed after a synchronize_rcu().
*/
preempt_disable_notrace();
@@ -6433,7 +6434,7 @@ static void clear_ftrace_pids(struct trace_array *tr)
rcu_assign_pointer(tr->function_pids, NULL);
/* Wait till all users are no longer using pid filtering */
- synchronize_sched();
+ synchronize_rcu();
trace_free_pid_list(pid_list);
}
@@ -6580,7 +6581,7 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf,
rcu_assign_pointer(tr->function_pids, pid_list);
if (filtered_pids) {
- synchronize_sched();
+ synchronize_rcu();
trace_free_pid_list(filtered_pids);
} else if (pid_list) {
/* Register a probe to set whether to ignore the tracing of a task */
@@ -6814,6 +6815,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
atomic_set(&t->tracing_graph_pause, 0);
atomic_set(&t->trace_overrun, 0);
t->curr_ret_stack = -1;
+ t->curr_ret_depth = -1;
/* Make sure the tasks see the -1 first: */
smp_wmb();
t->ret_stack = ret_stack_list[start++];
@@ -7038,6 +7040,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
{
t->curr_ret_stack = -1;
+ t->curr_ret_depth = -1;
/*
* The idle task has no parent, it either has its own
* stack or no stack at all.
@@ -7068,6 +7071,7 @@ void ftrace_graph_init_task(struct task_struct *t)
/* Make sure we do not use the parent ret_stack */
t->ret_stack = NULL;
t->curr_ret_stack = -1;
+ t->curr_ret_depth = -1;
if (ftrace_graph_active) {
struct ftrace_ret_stack *ret_stack;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 65bd4616220d..4f3247a53259 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1834,7 +1834,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
* There could have been a race between checking
* record_disable and incrementing it.
*/
- synchronize_sched();
+ synchronize_rcu();
for_each_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
rb_check_pages(cpu_buffer);
@@ -3151,7 +3151,7 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
* This prevents all writes to the buffer. Any attempt to write
* to the buffer after this will fail and return NULL.
*
- * The caller should call synchronize_sched() after this.
+ * The caller should call synchronize_rcu() after this.
*/
void ring_buffer_record_disable(struct ring_buffer *buffer)
{
@@ -3253,7 +3253,7 @@ bool ring_buffer_record_is_set_on(struct ring_buffer *buffer)
* This prevents all writes to the buffer. Any attempt to write
* to the buffer after this will fail and return NULL.
*
- * The caller should call synchronize_sched() after this.
+ * The caller should call synchronize_rcu() after this.
*/
void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
{
@@ -4191,7 +4191,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
void
ring_buffer_read_prepare_sync(void)
{
- synchronize_sched();
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
@@ -4363,7 +4363,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
atomic_inc(&cpu_buffer->record_disabled);
/* Make sure all commits have finished */
- synchronize_sched();
+ synchronize_rcu();
raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
@@ -4496,7 +4496,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
goto out;
/*
- * We can't do a synchronize_sched here because this
+ * We can't do a synchronize_rcu here because this
* function can be called in atomic context.
* Normally this will be called from the same CPU as cpu.
* If not it's up to the caller to protect this.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bf6f1d70484d..51612b4a603f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1681,7 +1681,7 @@ void tracing_reset(struct trace_buffer *buf, int cpu)
ring_buffer_record_disable(buffer);
/* Make sure all commits have finished */
- synchronize_sched();
+ synchronize_rcu();
ring_buffer_reset_cpu(buffer, cpu);
ring_buffer_record_enable(buffer);
@@ -1698,7 +1698,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf)
ring_buffer_record_disable(buffer);
/* Make sure all commits have finished */
- synchronize_sched();
+ synchronize_rcu();
buf->time_start = buffer_ftrace_now(buf, buf->cpu);
@@ -2250,7 +2250,7 @@ void trace_buffered_event_disable(void)
preempt_enable();
/* Wait for all current users to finish */
- synchronize_sched();
+ synchronize_rcu();
for_each_tracing_cpu(cpu) {
free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
@@ -2727,6 +2727,7 @@ void trace_dump_stack(int skip)
__ftrace_trace_stack(global_trace.trace_buffer.buffer,
flags, skip, preempt_count(), NULL);
}
+EXPORT_SYMBOL_GPL(trace_dump_stack);
static DEFINE_PER_CPU(int, user_stack_count);
@@ -4621,13 +4622,18 @@ static const char readme_msg[] =
"place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n"
#endif
#ifdef CONFIG_UPROBE_EVENTS
- "\t place: <path>:<offset>\n"
+ " place (uprobe): <path>:<offset>[(ref_ctr_offset)]\n"
#endif
"\t args: <name>=fetcharg[:type]\n"
"\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n"
+#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
+ "\t $stack<index>, $stack, $retval, $comm, $arg<N>\n"
+#else
"\t $stack<index>, $stack, $retval, $comm\n"
- "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string,\n"
- "\t b<bit-width>@<bit-offset>/<container-size>\n"
+#endif
+ "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n"
+ "\t b<bit-width>@<bit-offset>/<container-size>,\n"
+ "\t <type>\\[<array-size>\\]\n"
#endif
" events/\t\t- Directory containing all trace event subsystems:\n"
" enable\t\t- Write 0/1 to enable/disable tracing of all events\n"
@@ -5392,7 +5398,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
if (tr->current_trace->reset)
tr->current_trace->reset(tr);
- /* Current trace needs to be nop_trace before synchronize_sched */
+ /* Current trace needs to be nop_trace before synchronize_rcu */
tr->current_trace = &nop_trace;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -5406,7 +5412,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
* The update_max_tr is called from interrupts disabled
* so a synchronized_sched() is sufficient.
*/
- synchronize_sched();
+ synchronize_rcu();
free_snapshot(tr);
}
#endif
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3b8c0e24ab30..447bd96ee658 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -512,12 +512,44 @@ enum {
* can only be modified by current, we can reuse trace_recursion.
*/
TRACE_IRQ_BIT,
+
+ /* Set if the function is in the set_graph_function file */
+ TRACE_GRAPH_BIT,
+
+ /*
+ * In the very unlikely case that an interrupt came in
+ * at a start of graph tracing, and we want to trace
+ * the function in that interrupt, the depth can be greater
+ * than zero, because of the preempted start of a previous
+ * trace. In an even more unlikely case, depth could be 2
+ * if a softirq interrupted the start of graph tracing,
+ * followed by an interrupt preempting a start of graph
+ * tracing in the softirq, and depth can even be 3
+ * if an NMI came in at the start of an interrupt function
+ * that preempted a softirq start of a function that
+ * preempted normal context!!!! Luckily, it can't be
+ * greater than 3, so the next two bits are a mask
+ * of what the depth is when we set TRACE_GRAPH_BIT
+ */
+
+ TRACE_GRAPH_DEPTH_START_BIT,
+ TRACE_GRAPH_DEPTH_END_BIT,
};
#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0)
#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit)))
+#define trace_recursion_depth() \
+ (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3)
+#define trace_recursion_set_depth(depth) \
+ do { \
+ current->trace_recursion &= \
+ ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \
+ current->trace_recursion |= \
+ ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \
+ } while (0)
+
#define TRACE_CONTEXT_BITS 4
#define TRACE_FTRACE_START TRACE_FTRACE_BIT
@@ -843,8 +875,9 @@ extern void __trace_graph_return(struct trace_array *tr,
extern struct ftrace_hash *ftrace_graph_hash;
extern struct ftrace_hash *ftrace_graph_notrace_hash;
-static inline int ftrace_graph_addr(unsigned long addr)
+static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
{
+ unsigned long addr = trace->func;
int ret = 0;
preempt_disable_notrace();
@@ -855,6 +888,14 @@ static inline int ftrace_graph_addr(unsigned long addr)
}
if (ftrace_lookup_ip(ftrace_graph_hash, addr)) {
+
+ /*
+ * This needs to be cleared on the return functions
+ * when the depth is zero.
+ */
+ trace_recursion_set(TRACE_GRAPH_BIT);
+ trace_recursion_set_depth(trace->depth);
+
/*
* If no irqs are to be traced, but a set_graph_function
* is set, and called by an interrupt handler, we still
@@ -872,6 +913,13 @@ out:
return ret;
}
+static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace)
+{
+ if (trace_recursion_test(TRACE_GRAPH_BIT) &&
+ trace->depth == trace_recursion_depth())
+ trace_recursion_clear(TRACE_GRAPH_BIT);
+}
+
static inline int ftrace_graph_notrace_addr(unsigned long addr)
{
int ret = 0;
@@ -885,7 +933,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr)
return ret;
}
#else
-static inline int ftrace_graph_addr(unsigned long addr)
+static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
{
return 1;
}
@@ -894,6 +942,8 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr)
{
return 0;
}
+static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace)
+{ }
#endif /* CONFIG_DYNAMIC_FTRACE */
extern unsigned int fgraph_max_depth;
@@ -901,7 +951,8 @@ extern unsigned int fgraph_max_depth;
static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace)
{
/* trace it when it is-nested-in or is a function enabled. */
- return !(trace->depth || ftrace_graph_addr(trace->func)) ||
+ return !(trace_recursion_test(TRACE_GRAPH_BIT) ||
+ ftrace_graph_addr(trace)) ||
(trace->depth < 0) ||
(fgraph_max_depth && trace->depth >= fgraph_max_depth);
}
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 69a3fe926e8c..76217bbef815 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -290,7 +290,8 @@ void perf_kprobe_destroy(struct perf_event *p_event)
#endif /* CONFIG_KPROBE_EVENTS */
#ifdef CONFIG_UPROBE_EVENTS
-int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe)
+int perf_uprobe_init(struct perf_event *p_event,
+ unsigned long ref_ctr_offset, bool is_retprobe)
{
int ret;
char *path = NULL;
@@ -312,8 +313,8 @@ int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe)
goto out;
}
- tp_event = create_local_trace_uprobe(
- path, p_event->attr.probe_offset, is_retprobe);
+ tp_event = create_local_trace_uprobe(path, p_event->attr.probe_offset,
+ ref_ctr_offset, is_retprobe);
if (IS_ERR(tp_event)) {
ret = PTR_ERR(tp_event);
goto out;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 84a65173b1e9..27821480105e 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -570,11 +570,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
}
}
+ kfree(op_stack);
+ kfree(inverts);
return prog;
out_free:
kfree(op_stack);
- kfree(prog_stack);
kfree(inverts);
+ kfree(prog_stack);
return ERR_PTR(ret);
}
@@ -1614,7 +1616,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
/*
* The calls can still be using the old filters.
- * Do a synchronize_sched() and to ensure all calls are
+ * Do a synchronize_rcu() and to ensure all calls are
* done with them before we free them.
*/
tracepoint_synchronize_unregister();
@@ -1718,6 +1720,7 @@ static int create_filter(struct trace_event_call *call,
err = process_preds(call, filter_string, *filterp, pe);
if (err && set_str)
append_filter_err(pe, *filterp);
+ create_filter_finish(pe);
return err;
}
@@ -1845,7 +1848,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir,
if (filter) {
/*
* No event actually uses the system filter
- * we can free it without synchronize_sched().
+ * we can free it without synchronize_rcu().
*/
__free_filter(system->filter);
system->filter = filter;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index d239004aaf29..eb908ef2ecec 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1063,8 +1063,10 @@ static int create_synth_event(int argc, char **argv)
event = NULL;
ret = -EEXIST;
goto out;
- } else if (delete_event)
+ } else if (delete_event) {
+ ret = -ENOENT;
goto out;
+ }
if (argc < 2) {
ret = -EINVAL;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 2152d1e530cb..cd12ecb66eb9 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -732,8 +732,10 @@ int set_trigger_filter(char *filter_str,
/* The filter is for the 'trigger' event, not the triggered event */
ret = create_event_filter(file->event_call, filter_str, false, &filter);
- if (ret)
- goto out;
+ /*
+ * If create_event_filter() fails, filter still needs to be freed.
+ * Which the calling code will do with data->filter.
+ */
assign:
tmp = rcu_access_pointer(data->filter);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 169b3c44ee97..086af4f5c3e8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -118,8 +118,8 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration,
struct trace_seq *s, u32 flags);
/* Add a function return address to the trace stack on thread info.*/
-int
-ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
+static int
+ftrace_push_return_trace(unsigned long ret, unsigned long func,
unsigned long frame_pointer, unsigned long *retp)
{
unsigned long long calltime;
@@ -177,9 +177,31 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
current->ret_stack[index].retp = retp;
#endif
- *depth = current->curr_ret_stack;
+ return 0;
+}
+
+int function_graph_enter(unsigned long ret, unsigned long func,
+ unsigned long frame_pointer, unsigned long *retp)
+{
+ struct ftrace_graph_ent trace;
+
+ trace.func = func;
+ trace.depth = ++current->curr_ret_depth;
+
+ if (ftrace_push_return_trace(ret, func,
+ frame_pointer, retp))
+ goto out;
+
+ /* Only trace if the calling function expects to */
+ if (!ftrace_graph_entry(&trace))
+ goto out_ret;
return 0;
+ out_ret:
+ current->curr_ret_stack--;
+ out:
+ current->curr_ret_depth--;
+ return -EBUSY;
}
/* Retrieve a function return address to the trace stack on thread info.*/
@@ -241,7 +263,13 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
trace->func = current->ret_stack[index].func;
trace->calltime = current->ret_stack[index].calltime;
trace->overrun = atomic_read(&current->trace_overrun);
- trace->depth = index;
+ trace->depth = current->curr_ret_depth--;
+ /*
+ * We still want to trace interrupts coming in if
+ * max_depth is set to 1. Make sure the decrement is
+ * seen before ftrace_graph_return.
+ */
+ barrier();
}
/*
@@ -255,6 +283,12 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
ftrace_pop_return_trace(&trace, &ret, frame_pointer);
trace.rettime = trace_clock_local();
+ ftrace_graph_return(&trace);
+ /*
+ * The ftrace_graph_return() may still access the current
+ * ret_stack structure, we need to make sure the update of
+ * curr_ret_stack is after that.
+ */
barrier();
current->curr_ret_stack--;
/*
@@ -267,13 +301,6 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
return ret;
}
- /*
- * The trace should run after decrementing the ret counter
- * in case an interrupt were to come in. We don't want to
- * lose the interrupt if max_depth is set.
- */
- ftrace_graph_return(&trace);
-
if (unlikely(!ret)) {
ftrace_graph_stop();
WARN_ON(1);
@@ -482,6 +509,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
int cpu;
int pc;
+ ftrace_graph_addr_finish(trace);
+
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
@@ -505,6 +534,8 @@ void set_graph_array(struct trace_array *tr)
static void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
{
+ ftrace_graph_addr_finish(trace);
+
if (tracing_thresh &&
(trace->rettime - trace->calltime < tracing_thresh))
return;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index b7357f9f82a3..98ea6d28df15 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -208,6 +208,8 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
unsigned long flags;
int pc;
+ ftrace_graph_addr_finish(trace);
+
if (!func_prolog_dec(tr, &data, &flags))
return;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c30032367aab..adc153ab51c0 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -14,6 +14,7 @@
#include "trace_kprobe_selftest.h"
#include "trace_probe.h"
+#include "trace_probe_tmpl.h"
#define KPROBE_EVENT_SYSTEM "kprobes"
#define KRETPROBE_MAXACTIVE_MAX 4096
@@ -61,9 +62,23 @@ static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk,
return strncmp(mod->name, name, len) == 0 && name[len] == ':';
}
-static nokprobe_inline bool trace_kprobe_is_on_module(struct trace_kprobe *tk)
+static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
{
- return !!strchr(trace_kprobe_symbol(tk), ':');
+ char *p;
+ bool ret;
+
+ if (!tk->symbol)
+ return false;
+ p = strchr(tk->symbol, ':');
+ if (!p)
+ return true;
+ *p = '\0';
+ mutex_lock(&module_mutex);
+ ret = !!find_module(tk->symbol);
+ mutex_unlock(&module_mutex);
+ *p = ':';
+
+ return ret;
}
static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
@@ -120,184 +135,6 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
static int kretprobe_dispatcher(struct kretprobe_instance *ri,
struct pt_regs *regs);
-/* Memory fetching by symbol */
-struct symbol_cache {
- char *symbol;
- long offset;
- unsigned long addr;
-};
-
-unsigned long update_symbol_cache(struct symbol_cache *sc)
-{
- sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
-
- if (sc->addr)
- sc->addr += sc->offset;
-
- return sc->addr;
-}
-
-void free_symbol_cache(struct symbol_cache *sc)
-{
- kfree(sc->symbol);
- kfree(sc);
-}
-
-struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
-{
- struct symbol_cache *sc;
-
- if (!sym || strlen(sym) == 0)
- return NULL;
-
- sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
- if (!sc)
- return NULL;
-
- sc->symbol = kstrdup(sym, GFP_KERNEL);
- if (!sc->symbol) {
- kfree(sc);
- return NULL;
- }
- sc->offset = offset;
- update_symbol_cache(sc);
-
- return sc;
-}
-
-/*
- * Kprobes-specific fetch functions
- */
-#define DEFINE_FETCH_stack(type) \
-static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \
- void *offset, void *dest) \
-{ \
- *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \
- (unsigned int)((unsigned long)offset)); \
-} \
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(stack, type));
-
-DEFINE_BASIC_FETCH_FUNCS(stack)
-/* No string on the stack entry */
-#define fetch_stack_string NULL
-#define fetch_stack_string_size NULL
-
-#define DEFINE_FETCH_memory(type) \
-static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \
- void *addr, void *dest) \
-{ \
- type retval; \
- if (probe_kernel_address(addr, retval)) \
- *(type *)dest = 0; \
- else \
- *(type *)dest = retval; \
-} \
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, type));
-
-DEFINE_BASIC_FETCH_FUNCS(memory)
-/*
- * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
- * length and relative data location.
- */
-static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
- void *addr, void *dest)
-{
- int maxlen = get_rloc_len(*(u32 *)dest);
- u8 *dst = get_rloc_data(dest);
- long ret;
-
- if (!maxlen)
- return;
-
- /*
- * Try to get string again, since the string can be changed while
- * probing.
- */
- ret = strncpy_from_unsafe(dst, addr, maxlen);
-
- if (ret < 0) { /* Failed to fetch string */
- dst[0] = '\0';
- *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
- } else {
- *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest));
- }
-}
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string));
-
-/* Return the length of string -- including null terminal byte */
-static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
- void *addr, void *dest)
-{
- mm_segment_t old_fs;
- int ret, len = 0;
- u8 c;
-
- old_fs = get_fs();
- set_fs(KERNEL_DS);
- pagefault_disable();
-
- do {
- ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
- len++;
- } while (c && ret == 0 && len < MAX_STRING_SIZE);
-
- pagefault_enable();
- set_fs(old_fs);
-
- if (ret < 0) /* Failed to check the length */
- *(u32 *)dest = 0;
- else
- *(u32 *)dest = len;
-}
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string_size));
-
-#define DEFINE_FETCH_symbol(type) \
-void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, void *data, void *dest)\
-{ \
- struct symbol_cache *sc = data; \
- if (sc->addr) \
- fetch_memory_##type(regs, (void *)sc->addr, dest); \
- else \
- *(type *)dest = 0; \
-} \
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(symbol, type));
-
-DEFINE_BASIC_FETCH_FUNCS(symbol)
-DEFINE_FETCH_symbol(string)
-DEFINE_FETCH_symbol(string_size)
-
-/* kprobes don't support file_offset fetch methods */
-#define fetch_file_offset_u8 NULL
-#define fetch_file_offset_u16 NULL
-#define fetch_file_offset_u32 NULL
-#define fetch_file_offset_u64 NULL
-#define fetch_file_offset_string NULL
-#define fetch_file_offset_string_size NULL
-
-/* Fetch type information table */
-static const struct fetch_type kprobes_fetch_type_table[] = {
- /* Special types */
- [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
- sizeof(u32), 1, "__data_loc char[]"),
- [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
- string_size, sizeof(u32), 0, "u32"),
- /* Basic types */
- ASSIGN_FETCH_TYPE(u8, u8, 0),
- ASSIGN_FETCH_TYPE(u16, u16, 0),
- ASSIGN_FETCH_TYPE(u32, u32, 0),
- ASSIGN_FETCH_TYPE(u64, u64, 0),
- ASSIGN_FETCH_TYPE(s8, u8, 1),
- ASSIGN_FETCH_TYPE(s16, u16, 1),
- ASSIGN_FETCH_TYPE(s32, u32, 1),
- ASSIGN_FETCH_TYPE(s64, u64, 1),
- ASSIGN_FETCH_TYPE_ALIAS(x8, u8, u8, 0),
- ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0),
- ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0),
- ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0),
-
- ASSIGN_FETCH_TYPE_END
-};
-
/*
* Allocate new trace_probe and initialize it (including kprobes).
*/
@@ -496,7 +333,7 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
* event_call related objects, which will be accessed in
* the kprobe_trace_func/kretprobe_trace_func.
*/
- synchronize_sched();
+ synchronize_rcu();
kfree(link); /* Ignored if link == NULL */
}
@@ -540,8 +377,11 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
return -EINVAL;
}
- for (i = 0; i < tk->tp.nr_args; i++)
- traceprobe_update_arg(&tk->tp.args[i]);
+ for (i = 0; i < tk->tp.nr_args; i++) {
+ ret = traceprobe_update_arg(&tk->tp.args[i]);
+ if (ret)
+ return ret;
+ }
/* Set/clear disabled flag according to tp->flag */
if (trace_probe_is_enabled(&tk->tp))
@@ -554,19 +394,13 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
else
ret = register_kprobe(&tk->rp.kp);
- if (ret == 0)
+ if (ret == 0) {
tk->tp.flags |= TP_FLAG_REGISTERED;
- else {
- if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
- pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
- ret = 0;
- } else if (ret == -EILSEQ) {
- pr_warn("Probing address(0x%p) is not an instruction boundary.\n",
- tk->rp.kp.addr);
- ret = -EINVAL;
- }
+ } else if (ret == -EILSEQ) {
+ pr_warn("Probing address(0x%p) is not an instruction boundary.\n",
+ tk->rp.kp.addr);
+ ret = -EINVAL;
}
-
return ret;
}
@@ -629,6 +463,11 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
/* Register k*probe */
ret = __register_trace_kprobe(tk);
+ if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
+ pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
+ ret = 0;
+ }
+
if (ret < 0)
unregister_kprobe_event(tk);
else
@@ -713,13 +552,15 @@ static int create_trace_kprobe(int argc, char **argv)
long offset = 0;
void *addr = NULL;
char buf[MAX_EVENT_NAME_LEN];
+ unsigned int flags = TPARG_FL_KERNEL;
/* argc must be >= 1 */
if (argv[0][0] == 'p')
is_return = false;
- else if (argv[0][0] == 'r')
+ else if (argv[0][0] == 'r') {
is_return = true;
- else if (argv[0][0] == '-')
+ flags |= TPARG_FL_RETURN;
+ } else if (argv[0][0] == '-')
is_delete = true;
else {
pr_info("Probe definition must be started with 'p', 'r' or"
@@ -749,10 +590,13 @@ static int create_trace_kprobe(int argc, char **argv)
}
if (event) {
- if (strchr(event, '/')) {
+ char *slash;
+
+ slash = strchr(event, '/');
+ if (slash) {
group = event;
- event = strchr(group, '/') + 1;
- event[-1] = '\0';
+ event = slash + 1;
+ slash[0] = '\0';
if (strlen(group) == 0) {
pr_info("Group name is not specified\n");
return -EINVAL;
@@ -802,8 +646,9 @@ static int create_trace_kprobe(int argc, char **argv)
pr_info("Failed to parse either an address or a symbol.\n");
return ret;
}
- if (offset && is_return &&
- !kprobe_on_func_entry(NULL, symbol, offset)) {
+ if (kprobe_on_func_entry(NULL, symbol, offset))
+ flags |= TPARG_FL_FENTRY;
+ if (offset && is_return && !(flags & TPARG_FL_FENTRY)) {
pr_info("Given offset is not valid for return probe.\n");
return -EINVAL;
}
@@ -873,8 +718,7 @@ static int create_trace_kprobe(int argc, char **argv)
/* Parse fetch argument */
ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg,
- is_return, true,
- kprobes_fetch_type_table);
+ flags);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
goto error;
@@ -1028,6 +872,106 @@ static const struct file_operations kprobe_profile_ops = {
.release = seq_release,
};
+/* Kprobe specific fetch functions */
+
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+fetch_store_strlen(unsigned long addr)
+{
+ mm_segment_t old_fs;
+ int ret, len = 0;
+ u8 c;
+
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ pagefault_disable();
+
+ do {
+ ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+ len++;
+ } while (c && ret == 0 && len < MAX_STRING_SIZE);
+
+ pagefault_enable();
+ set_fs(old_fs);
+
+ return (ret < 0) ? ret : len;
+}
+
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
+ * length and relative data location.
+ */
+static nokprobe_inline int
+fetch_store_string(unsigned long addr, void *dest, void *base)
+{
+ int maxlen = get_loc_len(*(u32 *)dest);
+ u8 *dst = get_loc_data(dest, base);
+ long ret;
+
+ if (unlikely(!maxlen))
+ return -ENOMEM;
+ /*
+ * Try to get string again, since the string can be changed while
+ * probing.
+ */
+ ret = strncpy_from_unsafe(dst, (void *)addr, maxlen);
+
+ if (ret >= 0)
+ *(u32 *)dest = make_data_loc(ret, (void *)dst - base);
+ return ret;
+}
+
+static nokprobe_inline int
+probe_mem_read(void *dest, void *src, size_t size)
+{
+ return probe_kernel_read(dest, src, size);
+}
+
+/* Note that we don't verify it, since the code does not come from user space */
+static int
+process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
+ void *base)
+{
+ unsigned long val;
+
+retry:
+ /* 1st stage: get value from context */
+ switch (code->op) {
+ case FETCH_OP_REG:
+ val = regs_get_register(regs, code->param);
+ break;
+ case FETCH_OP_STACK:
+ val = regs_get_kernel_stack_nth(regs, code->param);
+ break;
+ case FETCH_OP_STACKP:
+ val = kernel_stack_pointer(regs);
+ break;
+ case FETCH_OP_RETVAL:
+ val = regs_return_value(regs);
+ break;
+ case FETCH_OP_IMM:
+ val = code->immediate;
+ break;
+ case FETCH_OP_COMM:
+ val = (unsigned long)current->comm;
+ break;
+#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
+ case FETCH_OP_ARG:
+ val = regs_get_kernel_argument(regs, code->param);
+ break;
+#endif
+ case FETCH_NOP_SYMBOL: /* Ignore a place holder */
+ code++;
+ goto retry;
+ default:
+ return -EILSEQ;
+ }
+ code++;
+
+ return process_fetch_insn_bottom(code, val, dest, base);
+}
+NOKPROBE_SYMBOL(process_fetch_insn)
+
/* Kprobe handler */
static nokprobe_inline void
__kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
@@ -1059,7 +1003,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
entry = ring_buffer_event_data(event);
entry->ip = (unsigned long)tk->rp.kp.addr;
- store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
event_trigger_unlock_commit_regs(trace_file, buffer, event,
entry, irq_flags, pc, regs);
@@ -1108,7 +1052,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
entry = ring_buffer_event_data(event);
entry->func = (unsigned long)tk->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
- store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
event_trigger_unlock_commit_regs(trace_file, buffer, event,
entry, irq_flags, pc, regs);
@@ -1133,8 +1077,6 @@ print_kprobe_event(struct trace_iterator *iter, int flags,
struct kprobe_trace_entry_head *field;
struct trace_seq *s = &iter->seq;
struct trace_probe *tp;
- u8 *data;
- int i;
field = (struct kprobe_trace_entry_head *)iter->ent;
tp = container_of(event, struct trace_probe, call.event);
@@ -1146,11 +1088,9 @@ print_kprobe_event(struct trace_iterator *iter, int flags,
trace_seq_putc(s, ')');
- data = (u8 *)&field[1];
- for (i = 0; i < tp->nr_args; i++)
- if (!tp->args[i].type->print(s, tp->args[i].name,
- data + tp->args[i].offset, field))
- goto out;
+ if (print_probe_args(s, tp->args, tp->nr_args,
+ (u8 *)&field[1], field) < 0)
+ goto out;
trace_seq_putc(s, '\n');
out:
@@ -1164,8 +1104,6 @@ print_kretprobe_event(struct trace_iterator *iter, int flags,
struct kretprobe_trace_entry_head *field;
struct trace_seq *s = &iter->seq;
struct trace_probe *tp;
- u8 *data;
- int i;
field = (struct kretprobe_trace_entry_head *)iter->ent;
tp = container_of(event, struct trace_probe, call.event);
@@ -1182,11 +1120,9 @@ print_kretprobe_event(struct trace_iterator *iter, int flags,
trace_seq_putc(s, ')');
- data = (u8 *)&field[1];
- for (i = 0; i < tp->nr_args; i++)
- if (!tp->args[i].type->print(s, tp->args[i].name,
- data + tp->args[i].offset, field))
- goto out;
+ if (print_probe_args(s, tp->args, tp->nr_args,
+ (u8 *)&field[1], field) < 0)
+ goto out;
trace_seq_putc(s, '\n');
@@ -1197,49 +1133,25 @@ print_kretprobe_event(struct trace_iterator *iter, int flags,
static int kprobe_event_define_fields(struct trace_event_call *event_call)
{
- int ret, i;
+ int ret;
struct kprobe_trace_entry_head field;
struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
- /* Set argument names as fields */
- for (i = 0; i < tk->tp.nr_args; i++) {
- struct probe_arg *parg = &tk->tp.args[i];
- ret = trace_define_field(event_call, parg->type->fmttype,
- parg->name,
- sizeof(field) + parg->offset,
- parg->type->size,
- parg->type->is_signed,
- FILTER_OTHER);
- if (ret)
- return ret;
- }
- return 0;
+ return traceprobe_define_arg_fields(event_call, sizeof(field), &tk->tp);
}
static int kretprobe_event_define_fields(struct trace_event_call *event_call)
{
- int ret, i;
+ int ret;
struct kretprobe_trace_entry_head field;
struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
- /* Set argument names as fields */
- for (i = 0; i < tk->tp.nr_args; i++) {
- struct probe_arg *parg = &tk->tp.args[i];
- ret = trace_define_field(event_call, parg->type->fmttype,
- parg->name,
- sizeof(field) + parg->offset,
- parg->type->size,
- parg->type->is_signed,
- FILTER_OTHER);
- if (ret)
- return ret;
- }
- return 0;
+ return traceprobe_define_arg_fields(event_call, sizeof(field), &tk->tp);
}
#ifdef CONFIG_PERF_EVENTS
@@ -1286,7 +1198,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
entry->ip = (unsigned long)tk->rp.kp.addr;
memset(&entry[1], 0, dsize);
- store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
head, NULL);
return 0;
@@ -1322,7 +1234,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
entry->func = (unsigned long)tk->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
- store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
head, NULL);
}
@@ -1457,7 +1369,7 @@ static int register_kprobe_event(struct trace_kprobe *tk)
init_trace_event_call(tk, call);
- if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
+ if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
return -ENOMEM;
ret = register_trace_event(&call->event);
if (!ret) {
@@ -1514,7 +1426,7 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
init_trace_event_call(tk, &tk->tp.call);
- if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) {
+ if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) {
ret = -ENOMEM;
goto error;
}
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index b0875b327f5c..c3fd849d4a8f 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -115,7 +115,7 @@ static int module_trace_bprintk_format_notify(struct notifier_block *self,
* section, then we need to read the link list pointers. The trick is
* we pass the address of the string to the seq function just like
* we do for the kernel core formats. To get back the structure that
- * holds the format, we simply use containerof() and then go to the
+ * holds the format, we simply use container_of() and then go to the
* next format in the list.
*/
static const char **
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index e99c3ce7aa65..bd30e9398d2a 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -26,14 +26,12 @@ const char *reserved_field_names[] = {
/* Printing in basic type function template */
#define DEFINE_BASIC_PRINT_TYPE_FUNC(tname, type, fmt) \
-int PRINT_TYPE_FUNC_NAME(tname)(struct trace_seq *s, const char *name, \
- void *data, void *ent) \
+int PRINT_TYPE_FUNC_NAME(tname)(struct trace_seq *s, void *data, void *ent)\
{ \
- trace_seq_printf(s, " %s=" fmt, name, *(type *)data); \
+ trace_seq_printf(s, fmt, *(type *)data); \
return !trace_seq_has_overflowed(s); \
} \
-const char PRINT_TYPE_FMT_NAME(tname)[] = fmt; \
-NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(tname));
+const char PRINT_TYPE_FMT_NAME(tname)[] = fmt;
DEFINE_BASIC_PRINT_TYPE_FUNC(u8, u8, "%u")
DEFINE_BASIC_PRINT_TYPE_FUNC(u16, u16, "%u")
@@ -48,193 +46,52 @@ DEFINE_BASIC_PRINT_TYPE_FUNC(x16, u16, "0x%x")
DEFINE_BASIC_PRINT_TYPE_FUNC(x32, u32, "0x%x")
DEFINE_BASIC_PRINT_TYPE_FUNC(x64, u64, "0x%Lx")
+int PRINT_TYPE_FUNC_NAME(symbol)(struct trace_seq *s, void *data, void *ent)
+{
+ trace_seq_printf(s, "%pS", (void *)*(unsigned long *)data);
+ return !trace_seq_has_overflowed(s);
+}
+const char PRINT_TYPE_FMT_NAME(symbol)[] = "%pS";
+
/* Print type function for string type */
-int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, const char *name,
- void *data, void *ent)
+int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, void *data, void *ent)
{
int len = *(u32 *)data >> 16;
if (!len)
- trace_seq_printf(s, " %s=(fault)", name);
+ trace_seq_puts(s, "(fault)");
else
- trace_seq_printf(s, " %s=\"%s\"", name,
+ trace_seq_printf(s, "\"%s\"",
(const char *)get_loc_data(data, ent));
return !trace_seq_has_overflowed(s);
}
-NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(string));
const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
-#define CHECK_FETCH_FUNCS(method, fn) \
- (((FETCH_FUNC_NAME(method, u8) == fn) || \
- (FETCH_FUNC_NAME(method, u16) == fn) || \
- (FETCH_FUNC_NAME(method, u32) == fn) || \
- (FETCH_FUNC_NAME(method, u64) == fn) || \
- (FETCH_FUNC_NAME(method, string) == fn) || \
- (FETCH_FUNC_NAME(method, string_size) == fn)) \
- && (fn != NULL))
-
-/* Data fetch function templates */
-#define DEFINE_FETCH_reg(type) \
-void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, void *offset, void *dest) \
-{ \
- *(type *)dest = (type)regs_get_register(regs, \
- (unsigned int)((unsigned long)offset)); \
-} \
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(reg, type));
-DEFINE_BASIC_FETCH_FUNCS(reg)
-/* No string on the register */
-#define fetch_reg_string NULL
-#define fetch_reg_string_size NULL
-
-#define DEFINE_FETCH_retval(type) \
-void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs, \
- void *dummy, void *dest) \
-{ \
- *(type *)dest = (type)regs_return_value(regs); \
-} \
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(retval, type));
-DEFINE_BASIC_FETCH_FUNCS(retval)
-/* No string on the retval */
-#define fetch_retval_string NULL
-#define fetch_retval_string_size NULL
-
-/* Dereference memory access function */
-struct deref_fetch_param {
- struct fetch_param orig;
- long offset;
- fetch_func_t fetch;
- fetch_func_t fetch_size;
+/* Fetch type information table */
+static const struct fetch_type probe_fetch_types[] = {
+ /* Special types */
+ __ASSIGN_FETCH_TYPE("string", string, string, sizeof(u32), 1,
+ "__data_loc char[]"),
+ /* Basic types */
+ ASSIGN_FETCH_TYPE(u8, u8, 0),
+ ASSIGN_FETCH_TYPE(u16, u16, 0),
+ ASSIGN_FETCH_TYPE(u32, u32, 0),
+ ASSIGN_FETCH_TYPE(u64, u64, 0),
+ ASSIGN_FETCH_TYPE(s8, u8, 1),
+ ASSIGN_FETCH_TYPE(s16, u16, 1),
+ ASSIGN_FETCH_TYPE(s32, u32, 1),
+ ASSIGN_FETCH_TYPE(s64, u64, 1),
+ ASSIGN_FETCH_TYPE_ALIAS(x8, u8, u8, 0),
+ ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0),
+ ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0),
+ ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0),
+ ASSIGN_FETCH_TYPE_ALIAS(symbol, ADDR_FETCH_TYPE, ADDR_FETCH_TYPE, 0),
+
+ ASSIGN_FETCH_TYPE_END
};
-#define DEFINE_FETCH_deref(type) \
-void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs, \
- void *data, void *dest) \
-{ \
- struct deref_fetch_param *dprm = data; \
- unsigned long addr; \
- call_fetch(&dprm->orig, regs, &addr); \
- if (addr) { \
- addr += dprm->offset; \
- dprm->fetch(regs, (void *)addr, dest); \
- } else \
- *(type *)dest = 0; \
-} \
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, type));
-DEFINE_BASIC_FETCH_FUNCS(deref)
-DEFINE_FETCH_deref(string)
-
-void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs,
- void *data, void *dest)
-{
- struct deref_fetch_param *dprm = data;
- unsigned long addr;
-
- call_fetch(&dprm->orig, regs, &addr);
- if (addr && dprm->fetch_size) {
- addr += dprm->offset;
- dprm->fetch_size(regs, (void *)addr, dest);
- } else
- *(string_size *)dest = 0;
-}
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, string_size));
-
-static void update_deref_fetch_param(struct deref_fetch_param *data)
-{
- if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
- update_deref_fetch_param(data->orig.data);
- else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
- update_symbol_cache(data->orig.data);
-}
-NOKPROBE_SYMBOL(update_deref_fetch_param);
-
-static void free_deref_fetch_param(struct deref_fetch_param *data)
-{
- if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
- free_deref_fetch_param(data->orig.data);
- else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
- free_symbol_cache(data->orig.data);
- kfree(data);
-}
-NOKPROBE_SYMBOL(free_deref_fetch_param);
-
-/* Bitfield fetch function */
-struct bitfield_fetch_param {
- struct fetch_param orig;
- unsigned char hi_shift;
- unsigned char low_shift;
-};
-
-#define DEFINE_FETCH_bitfield(type) \
-void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs, \
- void *data, void *dest) \
-{ \
- struct bitfield_fetch_param *bprm = data; \
- type buf = 0; \
- call_fetch(&bprm->orig, regs, &buf); \
- if (buf) { \
- buf <<= bprm->hi_shift; \
- buf >>= bprm->low_shift; \
- } \
- *(type *)dest = buf; \
-} \
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(bitfield, type));
-DEFINE_BASIC_FETCH_FUNCS(bitfield)
-#define fetch_bitfield_string NULL
-#define fetch_bitfield_string_size NULL
-
-static void
-update_bitfield_fetch_param(struct bitfield_fetch_param *data)
-{
- /*
- * Don't check the bitfield itself, because this must be the
- * last fetch function.
- */
- if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
- update_deref_fetch_param(data->orig.data);
- else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
- update_symbol_cache(data->orig.data);
-}
-
-static void
-free_bitfield_fetch_param(struct bitfield_fetch_param *data)
-{
- /*
- * Don't check the bitfield itself, because this must be the
- * last fetch function.
- */
- if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
- free_deref_fetch_param(data->orig.data);
- else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
- free_symbol_cache(data->orig.data);
-
- kfree(data);
-}
-
-void FETCH_FUNC_NAME(comm, string)(struct pt_regs *regs,
- void *data, void *dest)
-{
- int maxlen = get_rloc_len(*(u32 *)dest);
- u8 *dst = get_rloc_data(dest);
- long ret;
-
- if (!maxlen)
- return;
-
- ret = strlcpy(dst, current->comm, maxlen);
- *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest));
-}
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string));
-
-void FETCH_FUNC_NAME(comm, string_size)(struct pt_regs *regs,
- void *data, void *dest)
-{
- *(u32 *)dest = strlen(current->comm) + 1;
-}
-NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string_size));
-
-static const struct fetch_type *find_fetch_type(const char *type,
- const struct fetch_type *ftbl)
+static const struct fetch_type *find_fetch_type(const char *type)
{
int i;
@@ -255,58 +112,27 @@ static const struct fetch_type *find_fetch_type(const char *type,
switch (bs) {
case 8:
- return find_fetch_type("u8", ftbl);
+ return find_fetch_type("u8");
case 16:
- return find_fetch_type("u16", ftbl);
+ return find_fetch_type("u16");
case 32:
- return find_fetch_type("u32", ftbl);
+ return find_fetch_type("u32");
case 64:
- return find_fetch_type("u64", ftbl);
+ return find_fetch_type("u64");
default:
goto fail;
}
}
- for (i = 0; ftbl[i].name; i++) {
- if (strcmp(type, ftbl[i].name) == 0)
- return &ftbl[i];
+ for (i = 0; probe_fetch_types[i].name; i++) {
+ if (strcmp(type, probe_fetch_types[i].name) == 0)
+ return &probe_fetch_types[i];
}
fail:
return NULL;
}
-/* Special function : only accept unsigned long */
-static void fetch_kernel_stack_address(struct pt_regs *regs, void *dummy, void *dest)
-{
- *(unsigned long *)dest = kernel_stack_pointer(regs);
-}
-NOKPROBE_SYMBOL(fetch_kernel_stack_address);
-
-static void fetch_user_stack_address(struct pt_regs *regs, void *dummy, void *dest)
-{
- *(unsigned long *)dest = user_stack_pointer(regs);
-}
-NOKPROBE_SYMBOL(fetch_user_stack_address);
-
-static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
- fetch_func_t orig_fn,
- const struct fetch_type *ftbl)
-{
- int i;
-
- if (type != &ftbl[FETCH_TYPE_STRING])
- return NULL; /* Only string type needs size function */
-
- for (i = 0; i < FETCH_MTD_END; i++)
- if (type->fetch[i] == orig_fn)
- return ftbl[FETCH_TYPE_STRSIZE].fetch[i];
-
- WARN_ON(1); /* This should not happen */
-
- return NULL;
-}
-
/* Split symbol and offset. */
int traceprobe_split_symbol_offset(char *symbol, long *offset)
{
@@ -331,41 +157,44 @@ int traceprobe_split_symbol_offset(char *symbol, long *offset)
#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
static int parse_probe_vars(char *arg, const struct fetch_type *t,
- struct fetch_param *f, bool is_return,
- bool is_kprobe)
+ struct fetch_insn *code, unsigned int flags)
{
int ret = 0;
unsigned long param;
if (strcmp(arg, "retval") == 0) {
- if (is_return)
- f->fn = t->fetch[FETCH_MTD_retval];
+ if (flags & TPARG_FL_RETURN)
+ code->op = FETCH_OP_RETVAL;
else
ret = -EINVAL;
} else if (strncmp(arg, "stack", 5) == 0) {
if (arg[5] == '\0') {
- if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR))
- return -EINVAL;
-
- if (is_kprobe)
- f->fn = fetch_kernel_stack_address;
- else
- f->fn = fetch_user_stack_address;
+ code->op = FETCH_OP_STACKP;
} else if (isdigit(arg[5])) {
ret = kstrtoul(arg + 5, 10, &param);
- if (ret || (is_kprobe && param > PARAM_MAX_STACK))
+ if (ret || ((flags & TPARG_FL_KERNEL) &&
+ param > PARAM_MAX_STACK))
ret = -EINVAL;
else {
- f->fn = t->fetch[FETCH_MTD_stack];
- f->data = (void *)param;
+ code->op = FETCH_OP_STACK;
+ code->param = (unsigned int)param;
}
} else
ret = -EINVAL;
} else if (strcmp(arg, "comm") == 0) {
- if (strcmp(t->name, "string") != 0 &&
- strcmp(t->name, "string_size") != 0)
+ code->op = FETCH_OP_COMM;
+#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
+ } else if (((flags & TPARG_FL_MASK) ==
+ (TPARG_FL_KERNEL | TPARG_FL_FENTRY)) &&
+ strncmp(arg, "arg", 3) == 0) {
+ if (!isdigit(arg[3]))
+ return -EINVAL;
+ ret = kstrtoul(arg + 3, 10, &param);
+ if (ret || !param || param > PARAM_MAX_STACK)
return -EINVAL;
- f->fn = t->fetch[FETCH_MTD_comm];
+ code->op = FETCH_OP_ARG;
+ code->param = (unsigned int)param - 1;
+#endif
} else
ret = -EINVAL;
@@ -373,25 +202,27 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
}
/* Recursive argument parser */
-static int parse_probe_arg(char *arg, const struct fetch_type *t,
- struct fetch_param *f, bool is_return, bool is_kprobe,
- const struct fetch_type *ftbl)
+static int
+parse_probe_arg(char *arg, const struct fetch_type *type,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ unsigned int flags)
{
+ struct fetch_insn *code = *pcode;
unsigned long param;
- long offset;
+ long offset = 0;
char *tmp;
int ret = 0;
switch (arg[0]) {
case '$':
- ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe);
+ ret = parse_probe_vars(arg + 1, type, code, flags);
break;
case '%': /* named register */
ret = regs_query_register_offset(arg + 1);
if (ret >= 0) {
- f->fn = t->fetch[FETCH_MTD_reg];
- f->data = (void *)(unsigned long)ret;
+ code->op = FETCH_OP_REG;
+ code->param = (unsigned int)ret;
ret = 0;
}
break;
@@ -401,33 +232,42 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
ret = kstrtoul(arg + 1, 0, &param);
if (ret)
break;
-
- f->fn = t->fetch[FETCH_MTD_memory];
- f->data = (void *)param;
+ /* load address */
+ code->op = FETCH_OP_IMM;
+ code->immediate = param;
} else if (arg[1] == '+') {
/* kprobes don't support file offsets */
- if (is_kprobe)
+ if (flags & TPARG_FL_KERNEL)
return -EINVAL;
ret = kstrtol(arg + 2, 0, &offset);
if (ret)
break;
- f->fn = t->fetch[FETCH_MTD_file_offset];
- f->data = (void *)offset;
+ code->op = FETCH_OP_FOFFS;
+ code->immediate = (unsigned long)offset; // imm64?
} else {
/* uprobes don't support symbols */
- if (!is_kprobe)
+ if (!(flags & TPARG_FL_KERNEL))
return -EINVAL;
- ret = traceprobe_split_symbol_offset(arg + 1, &offset);
- if (ret)
- break;
+ /* Preserve symbol for updating */
+ code->op = FETCH_NOP_SYMBOL;
+ code->data = kstrdup(arg + 1, GFP_KERNEL);
+ if (!code->data)
+ return -ENOMEM;
+ if (++code == end)
+ return -E2BIG;
- f->data = alloc_symbol_cache(arg + 1, offset);
- if (f->data)
- f->fn = t->fetch[FETCH_MTD_symbol];
+ code->op = FETCH_OP_IMM;
+ code->immediate = 0;
}
+ /* These are fetching from memory */
+ if (++code == end)
+ return -E2BIG;
+ *pcode = code;
+ code->op = FETCH_OP_DEREF;
+ code->offset = offset;
break;
case '+': /* deref memory */
@@ -435,11 +275,10 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
case '-':
tmp = strchr(arg, '(');
if (!tmp)
- break;
+ return -EINVAL;
*tmp = '\0';
ret = kstrtol(arg, 0, &offset);
-
if (ret)
break;
@@ -447,36 +286,27 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
tmp = strrchr(arg, ')');
if (tmp) {
- struct deref_fetch_param *dprm;
- const struct fetch_type *t2;
+ const struct fetch_type *t2 = find_fetch_type(NULL);
- t2 = find_fetch_type(NULL, ftbl);
*tmp = '\0';
- dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL);
-
- if (!dprm)
- return -ENOMEM;
-
- dprm->offset = offset;
- dprm->fetch = t->fetch[FETCH_MTD_memory];
- dprm->fetch_size = get_fetch_size_function(t,
- dprm->fetch, ftbl);
- ret = parse_probe_arg(arg, t2, &dprm->orig, is_return,
- is_kprobe, ftbl);
+ ret = parse_probe_arg(arg, t2, &code, end, flags);
if (ret)
- kfree(dprm);
- else {
- f->fn = t->fetch[FETCH_MTD_deref];
- f->data = (void *)dprm;
- }
+ break;
+ if (code->op == FETCH_OP_COMM)
+ return -EINVAL;
+ if (++code == end)
+ return -E2BIG;
+ *pcode = code;
+
+ code->op = FETCH_OP_DEREF;
+ code->offset = offset;
}
break;
}
- if (!ret && !f->fn) { /* Parsed, but do not find fetch method */
- pr_info("%s type has no corresponding fetch method.\n", t->name);
+ if (!ret && code->op == FETCH_OP_NOP) {
+ /* Parsed, but do not find fetch method */
ret = -EINVAL;
}
-
return ret;
}
@@ -485,22 +315,15 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
/* Bitfield type needs to be parsed into a fetch function */
static int __parse_bitfield_probe_arg(const char *bf,
const struct fetch_type *t,
- struct fetch_param *f)
+ struct fetch_insn **pcode)
{
- struct bitfield_fetch_param *bprm;
+ struct fetch_insn *code = *pcode;
unsigned long bw, bo;
char *tail;
if (*bf != 'b')
return 0;
- bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
- if (!bprm)
- return -ENOMEM;
-
- bprm->orig = *f;
- f->fn = t->fetch[FETCH_MTD_bitfield];
- f->data = (void *)bprm;
bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */
if (bw == 0 || *tail != '@')
@@ -511,20 +334,26 @@ static int __parse_bitfield_probe_arg(const char *bf,
if (tail == bf || *tail != '/')
return -EINVAL;
+ code++;
+ if (code->op != FETCH_OP_NOP)
+ return -E2BIG;
+ *pcode = code;
- bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo);
- bprm->low_shift = bprm->hi_shift + bo;
+ code->op = FETCH_OP_MOD_BF;
+ code->lshift = BYTES_TO_BITS(t->size) - (bw + bo);
+ code->rshift = BYTES_TO_BITS(t->size) - bw;
+ code->basesize = t->size;
return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0;
}
/* String length checking wrapper */
int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
- struct probe_arg *parg, bool is_return, bool is_kprobe,
- const struct fetch_type *ftbl)
+ struct probe_arg *parg, unsigned int flags)
{
- const char *t;
- int ret;
+ struct fetch_insn *code, *scode, *tmp = NULL;
+ char *t, *t2;
+ int ret, len;
if (strlen(arg) > MAX_ARGSTR_LEN) {
pr_info("Argument is too long.: %s\n", arg);
@@ -535,36 +364,128 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
pr_info("Failed to allocate memory for command '%s'.\n", arg);
return -ENOMEM;
}
- t = strchr(parg->comm, ':');
+ t = strchr(arg, ':');
if (t) {
- arg[t - parg->comm] = '\0';
- t++;
+ *t = '\0';
+ t2 = strchr(++t, '[');
+ if (t2) {
+ *t2 = '\0';
+ parg->count = simple_strtoul(t2 + 1, &t2, 0);
+ if (strcmp(t2, "]") || parg->count == 0)
+ return -EINVAL;
+ if (parg->count > MAX_ARRAY_LEN)
+ return -E2BIG;
+ }
}
/*
* The default type of $comm should be "string", and it can't be
* dereferenced.
*/
if (!t && strcmp(arg, "$comm") == 0)
- t = "string";
- parg->type = find_fetch_type(t, ftbl);
+ parg->type = find_fetch_type("string");
+ else
+ parg->type = find_fetch_type(t);
if (!parg->type) {
pr_info("Unsupported type: %s\n", t);
return -EINVAL;
}
parg->offset = *size;
- *size += parg->type->size;
- ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return,
- is_kprobe, ftbl);
-
- if (ret >= 0 && t != NULL)
- ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
-
- if (ret >= 0) {
- parg->fetch_size.fn = get_fetch_size_function(parg->type,
- parg->fetch.fn,
- ftbl);
- parg->fetch_size.data = parg->fetch.data;
+ *size += parg->type->size * (parg->count ?: 1);
+
+ if (parg->count) {
+ len = strlen(parg->type->fmttype) + 6;
+ parg->fmt = kmalloc(len, GFP_KERNEL);
+ if (!parg->fmt)
+ return -ENOMEM;
+ snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
+ parg->count);
+ }
+
+ code = tmp = kzalloc(sizeof(*code) * FETCH_INSN_MAX, GFP_KERNEL);
+ if (!code)
+ return -ENOMEM;
+ code[FETCH_INSN_MAX - 1].op = FETCH_OP_END;
+
+ ret = parse_probe_arg(arg, parg->type, &code, &code[FETCH_INSN_MAX - 1],
+ flags);
+ if (ret)
+ goto fail;
+
+ /* Store operation */
+ if (!strcmp(parg->type->name, "string")) {
+ if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_IMM &&
+ code->op != FETCH_OP_COMM) {
+ pr_info("string only accepts memory or address.\n");
+ ret = -EINVAL;
+ goto fail;
+ }
+ if (code->op != FETCH_OP_DEREF || parg->count) {
+ /*
+ * IMM and COMM is pointing actual address, those must
+ * be kept, and if parg->count != 0, this is an array
+ * of string pointers instead of string address itself.
+ */
+ code++;
+ if (code->op != FETCH_OP_NOP) {
+ ret = -E2BIG;
+ goto fail;
+ }
+ }
+ code->op = FETCH_OP_ST_STRING; /* In DEREF case, replace it */
+ code->size = parg->type->size;
+ parg->dynamic = true;
+ } else if (code->op == FETCH_OP_DEREF) {
+ code->op = FETCH_OP_ST_MEM;
+ code->size = parg->type->size;
+ } else {
+ code++;
+ if (code->op != FETCH_OP_NOP) {
+ ret = -E2BIG;
+ goto fail;
+ }
+ code->op = FETCH_OP_ST_RAW;
+ code->size = parg->type->size;
+ }
+ scode = code;
+ /* Modify operation */
+ if (t != NULL) {
+ ret = __parse_bitfield_probe_arg(t, parg->type, &code);
+ if (ret)
+ goto fail;
}
+ /* Loop(Array) operation */
+ if (parg->count) {
+ if (scode->op != FETCH_OP_ST_MEM &&
+ scode->op != FETCH_OP_ST_STRING) {
+ pr_info("array only accepts memory or address\n");
+ ret = -EINVAL;
+ goto fail;
+ }
+ code++;
+ if (code->op != FETCH_OP_NOP) {
+ ret = -E2BIG;
+ goto fail;
+ }
+ code->op = FETCH_OP_LP_ARRAY;
+ code->param = parg->count;
+ }
+ code++;
+ code->op = FETCH_OP_END;
+
+ /* Shrink down the code buffer */
+ parg->code = kzalloc(sizeof(*code) * (code - tmp + 1), GFP_KERNEL);
+ if (!parg->code)
+ ret = -ENOMEM;
+ else
+ memcpy(parg->code, tmp, sizeof(*code) * (code - tmp + 1));
+
+fail:
+ if (ret) {
+ for (code = tmp; code < tmp + FETCH_INSN_MAX; code++)
+ if (code->op == FETCH_NOP_SYMBOL)
+ kfree(code->data);
+ }
+ kfree(tmp);
return ret;
}
@@ -586,35 +507,63 @@ int traceprobe_conflict_field_name(const char *name,
return 0;
}
-void traceprobe_update_arg(struct probe_arg *arg)
-{
- if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
- update_bitfield_fetch_param(arg->fetch.data);
- else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
- update_deref_fetch_param(arg->fetch.data);
- else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
- update_symbol_cache(arg->fetch.data);
-}
-
void traceprobe_free_probe_arg(struct probe_arg *arg)
{
- if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
- free_bitfield_fetch_param(arg->fetch.data);
- else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
- free_deref_fetch_param(arg->fetch.data);
- else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
- free_symbol_cache(arg->fetch.data);
+ struct fetch_insn *code = arg->code;
+ while (code && code->op != FETCH_OP_END) {
+ if (code->op == FETCH_NOP_SYMBOL)
+ kfree(code->data);
+ code++;
+ }
+ kfree(arg->code);
kfree(arg->name);
kfree(arg->comm);
+ kfree(arg->fmt);
}
+int traceprobe_update_arg(struct probe_arg *arg)
+{
+ struct fetch_insn *code = arg->code;
+ long offset;
+ char *tmp;
+ char c;
+ int ret = 0;
+
+ while (code && code->op != FETCH_OP_END) {
+ if (code->op == FETCH_NOP_SYMBOL) {
+ if (code[1].op != FETCH_OP_IMM)
+ return -EINVAL;
+
+ tmp = strpbrk(code->data, "+-");
+ if (tmp)
+ c = *tmp;
+ ret = traceprobe_split_symbol_offset(code->data,
+ &offset);
+ if (ret)
+ return ret;
+
+ code[1].immediate =
+ (unsigned long)kallsyms_lookup_name(code->data);
+ if (tmp)
+ *tmp = c;
+ if (!code[1].immediate)
+ return -ENOENT;
+ code[1].immediate += offset;
+ }
+ code++;
+ }
+ return 0;
+}
+
+/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
bool is_return)
{
- int i;
+ struct probe_arg *parg;
+ int i, j;
int pos = 0;
-
const char *fmt, *arg;
if (!is_return) {
@@ -625,35 +574,51 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
}
- /* When len=0, we just calculate the needed length */
-#define LEN_OR_ZERO (len ? len - pos : 0)
-
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
for (i = 0; i < tp->nr_args; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
- tp->args[i].name, tp->args[i].type->fmt);
+ parg = tp->args + i;
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=", parg->name);
+ if (parg->count) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "{%s",
+ parg->type->fmt);
+ for (j = 1; j < parg->count; j++)
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ",%s",
+ parg->type->fmt);
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "}");
+ } else
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "%s",
+ parg->type->fmt);
}
pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
for (i = 0; i < tp->nr_args; i++) {
- if (strcmp(tp->args[i].type->name, "string") == 0)
+ parg = tp->args + i;
+ if (parg->count) {
+ if (strcmp(parg->type->name, "string") == 0)
+ fmt = ", __get_str(%s[%d])";
+ else
+ fmt = ", REC->%s[%d]";
+ for (j = 0; j < parg->count; j++)
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ fmt, parg->name, j);
+ } else {
+ if (strcmp(parg->type->name, "string") == 0)
+ fmt = ", __get_str(%s)";
+ else
+ fmt = ", REC->%s";
pos += snprintf(buf + pos, LEN_OR_ZERO,
- ", __get_str(%s)",
- tp->args[i].name);
- else
- pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
- tp->args[i].name);
+ fmt, parg->name);
+ }
}
-#undef LEN_OR_ZERO
-
/* return the length of print_fmt */
return pos;
}
+#undef LEN_OR_ZERO
-int set_print_fmt(struct trace_probe *tp, bool is_return)
+int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return)
{
int len;
char *print_fmt;
@@ -670,3 +635,28 @@ int set_print_fmt(struct trace_probe *tp, bool is_return)
return 0;
}
+
+int traceprobe_define_arg_fields(struct trace_event_call *event_call,
+ size_t offset, struct trace_probe *tp)
+{
+ int ret, i;
+
+ /* Set argument names as fields */
+ for (i = 0; i < tp->nr_args; i++) {
+ struct probe_arg *parg = &tp->args[i];
+ const char *fmt = parg->type->fmttype;
+ int size = parg->type->size;
+
+ if (parg->fmt)
+ fmt = parg->fmt;
+ if (parg->count)
+ size *= parg->count;
+ ret = trace_define_field(event_call, fmt, parg->name,
+ offset + parg->offset, size,
+ parg->type->is_signed,
+ FILTER_OTHER);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 5f52668e165d..974afc1a3e73 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -23,6 +23,7 @@
#include <linux/stringify.h>
#include <linux/limits.h>
#include <linux/uaccess.h>
+#include <linux/bitops.h>
#include <asm/bitsperlong.h>
#include "trace.h"
@@ -30,6 +31,7 @@
#define MAX_TRACE_ARGS 128
#define MAX_ARGSTR_LEN 63
+#define MAX_ARRAY_LEN 64
#define MAX_STRING_SIZE PATH_MAX
/* Reserved field names */
@@ -54,50 +56,74 @@
#define TP_FLAG_PROFILE 2
#define TP_FLAG_REGISTERED 4
+/* data_loc: data location, compatible with u32 */
+#define make_data_loc(len, offs) \
+ (((u32)(len) << 16) | ((u32)(offs) & 0xffff))
+#define get_loc_len(dl) ((u32)(dl) >> 16)
+#define get_loc_offs(dl) ((u32)(dl) & 0xffff)
-/* data_rloc: data relative location, compatible with u32 */
-#define make_data_rloc(len, roffs) \
- (((u32)(len) << 16) | ((u32)(roffs) & 0xffff))
-#define get_rloc_len(dl) ((u32)(dl) >> 16)
-#define get_rloc_offs(dl) ((u32)(dl) & 0xffff)
-
-/*
- * Convert data_rloc to data_loc:
- * data_rloc stores the offset from data_rloc itself, but data_loc
- * stores the offset from event entry.
- */
-#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs))
-
-static nokprobe_inline void *get_rloc_data(u32 *dl)
+static nokprobe_inline void *get_loc_data(u32 *dl, void *ent)
{
- return (u8 *)dl + get_rloc_offs(*dl);
+ return (u8 *)ent + get_loc_offs(*dl);
}
-/* For data_loc conversion */
-static nokprobe_inline void *get_loc_data(u32 *dl, void *ent)
+static nokprobe_inline u32 update_data_loc(u32 loc, int consumed)
{
- return (u8 *)ent + get_rloc_offs(*dl);
+ u32 maxlen = get_loc_len(loc);
+ u32 offset = get_loc_offs(loc);
+
+ return make_data_loc(maxlen - consumed, offset + consumed);
}
-/* Data fetch function type */
-typedef void (*fetch_func_t)(struct pt_regs *, void *, void *);
/* Printing function type */
-typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *, void *);
-
-/* Fetch types */
-enum {
- FETCH_MTD_reg = 0,
- FETCH_MTD_stack,
- FETCH_MTD_retval,
- FETCH_MTD_comm,
- FETCH_MTD_memory,
- FETCH_MTD_symbol,
- FETCH_MTD_deref,
- FETCH_MTD_bitfield,
- FETCH_MTD_file_offset,
- FETCH_MTD_END,
+typedef int (*print_type_func_t)(struct trace_seq *, void *, void *);
+
+enum fetch_op {
+ FETCH_OP_NOP = 0,
+ // Stage 1 (load) ops
+ FETCH_OP_REG, /* Register : .param = offset */
+ FETCH_OP_STACK, /* Stack : .param = index */
+ FETCH_OP_STACKP, /* Stack pointer */
+ FETCH_OP_RETVAL, /* Return value */
+ FETCH_OP_IMM, /* Immediate : .immediate */
+ FETCH_OP_COMM, /* Current comm */
+ FETCH_OP_ARG, /* Function argument : .param */
+ FETCH_OP_FOFFS, /* File offset: .immediate */
+ // Stage 2 (dereference) op
+ FETCH_OP_DEREF, /* Dereference: .offset */
+ // Stage 3 (store) ops
+ FETCH_OP_ST_RAW, /* Raw: .size */
+ FETCH_OP_ST_MEM, /* Mem: .offset, .size */
+ FETCH_OP_ST_STRING, /* String: .offset, .size */
+ // Stage 4 (modify) op
+ FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */
+ // Stage 5 (loop) op
+ FETCH_OP_LP_ARRAY, /* Array: .param = loop count */
+ FETCH_OP_END,
+ FETCH_NOP_SYMBOL, /* Unresolved Symbol holder */
};
+struct fetch_insn {
+ enum fetch_op op;
+ union {
+ unsigned int param;
+ struct {
+ unsigned int size;
+ int offset;
+ };
+ struct {
+ unsigned char basesize;
+ unsigned char lshift;
+ unsigned char rshift;
+ };
+ unsigned long immediate;
+ void *data;
+ };
+};
+
+/* fetch + deref*N + store + mod + end <= 16, this allows N=12, enough */
+#define FETCH_INSN_MAX 16
+
/* Fetch type information table */
struct fetch_type {
const char *name; /* Name of type */
@@ -106,13 +132,6 @@ struct fetch_type {
print_type_func_t print; /* Print functions */
const char *fmt; /* Fromat string */
const char *fmttype; /* Name in format file */
- /* Fetch functions */
- fetch_func_t fetch[FETCH_MTD_END];
-};
-
-struct fetch_param {
- fetch_func_t fn;
- void *data;
};
/* For defining macros, define string/string_size types */
@@ -124,8 +143,7 @@ typedef u32 string_size;
/* Printing in basic type function template */
#define DECLARE_BASIC_PRINT_TYPE_FUNC(type) \
-int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name, \
- void *data, void *ent); \
+int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, void *data, void *ent);\
extern const char PRINT_TYPE_FMT_NAME(type)[]
DECLARE_BASIC_PRINT_TYPE_FUNC(u8);
@@ -142,57 +160,7 @@ DECLARE_BASIC_PRINT_TYPE_FUNC(x32);
DECLARE_BASIC_PRINT_TYPE_FUNC(x64);
DECLARE_BASIC_PRINT_TYPE_FUNC(string);
-
-#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type
-
-/* Declare macro for basic types */
-#define DECLARE_FETCH_FUNC(method, type) \
-extern void FETCH_FUNC_NAME(method, type)(struct pt_regs *regs, \
- void *data, void *dest)
-
-#define DECLARE_BASIC_FETCH_FUNCS(method) \
-DECLARE_FETCH_FUNC(method, u8); \
-DECLARE_FETCH_FUNC(method, u16); \
-DECLARE_FETCH_FUNC(method, u32); \
-DECLARE_FETCH_FUNC(method, u64)
-
-DECLARE_BASIC_FETCH_FUNCS(reg);
-#define fetch_reg_string NULL
-#define fetch_reg_string_size NULL
-
-DECLARE_BASIC_FETCH_FUNCS(retval);
-#define fetch_retval_string NULL
-#define fetch_retval_string_size NULL
-
-DECLARE_BASIC_FETCH_FUNCS(symbol);
-DECLARE_FETCH_FUNC(symbol, string);
-DECLARE_FETCH_FUNC(symbol, string_size);
-
-DECLARE_BASIC_FETCH_FUNCS(deref);
-DECLARE_FETCH_FUNC(deref, string);
-DECLARE_FETCH_FUNC(deref, string_size);
-
-DECLARE_BASIC_FETCH_FUNCS(bitfield);
-#define fetch_bitfield_string NULL
-#define fetch_bitfield_string_size NULL
-
-/* comm only makes sense as a string */
-#define fetch_comm_u8 NULL
-#define fetch_comm_u16 NULL
-#define fetch_comm_u32 NULL
-#define fetch_comm_u64 NULL
-DECLARE_FETCH_FUNC(comm, string);
-DECLARE_FETCH_FUNC(comm, string_size);
-
-/*
- * Define macro for basic types - we don't need to define s* types, because
- * we have to care only about bitwidth at recording time.
- */
-#define DEFINE_BASIC_FETCH_FUNCS(method) \
-DEFINE_FETCH_##method(u8) \
-DEFINE_FETCH_##method(u16) \
-DEFINE_FETCH_##method(u32) \
-DEFINE_FETCH_##method(u64)
+DECLARE_BASIC_PRINT_TYPE_FUNC(symbol);
/* Default (unsigned long) fetch type */
#define __DEFAULT_FETCH_TYPE(t) x##t
@@ -200,8 +168,9 @@ DEFINE_FETCH_##method(u64)
#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
-#define ASSIGN_FETCH_FUNC(method, type) \
- [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
+#define __ADDR_FETCH_TYPE(t) u##t
+#define _ADDR_FETCH_TYPE(t) __ADDR_FETCH_TYPE(t)
+#define ADDR_FETCH_TYPE _ADDR_FETCH_TYPE(BITS_PER_LONG)
#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
{.name = _name, \
@@ -210,64 +179,23 @@ DEFINE_FETCH_##method(u64)
.print = PRINT_TYPE_FUNC_NAME(ptype), \
.fmt = PRINT_TYPE_FMT_NAME(ptype), \
.fmttype = _fmttype, \
- .fetch = { \
-ASSIGN_FETCH_FUNC(reg, ftype), \
-ASSIGN_FETCH_FUNC(stack, ftype), \
-ASSIGN_FETCH_FUNC(retval, ftype), \
-ASSIGN_FETCH_FUNC(comm, ftype), \
-ASSIGN_FETCH_FUNC(memory, ftype), \
-ASSIGN_FETCH_FUNC(symbol, ftype), \
-ASSIGN_FETCH_FUNC(deref, ftype), \
-ASSIGN_FETCH_FUNC(bitfield, ftype), \
-ASSIGN_FETCH_FUNC(file_offset, ftype), \
- } \
}
-
+#define _ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
+ __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, #_fmttype)
#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \
- __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
+ _ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, ptype)
/* If ptype is an alias of atype, use this macro (show atype in format) */
#define ASSIGN_FETCH_TYPE_ALIAS(ptype, atype, ftype, sign) \
- __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #atype)
+ _ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, atype)
#define ASSIGN_FETCH_TYPE_END {}
-
-#define FETCH_TYPE_STRING 0
-#define FETCH_TYPE_STRSIZE 1
+#define MAX_ARRAY_LEN 64
#ifdef CONFIG_KPROBE_EVENTS
-struct symbol_cache;
-unsigned long update_symbol_cache(struct symbol_cache *sc);
-void free_symbol_cache(struct symbol_cache *sc);
-struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
bool trace_kprobe_on_func_entry(struct trace_event_call *call);
bool trace_kprobe_error_injectable(struct trace_event_call *call);
#else
-/* uprobes do not support symbol fetch methods */
-#define fetch_symbol_u8 NULL
-#define fetch_symbol_u16 NULL
-#define fetch_symbol_u32 NULL
-#define fetch_symbol_u64 NULL
-#define fetch_symbol_string NULL
-#define fetch_symbol_string_size NULL
-
-struct symbol_cache {
-};
-static inline unsigned long __used update_symbol_cache(struct symbol_cache *sc)
-{
- return 0;
-}
-
-static inline void __used free_symbol_cache(struct symbol_cache *sc)
-{
-}
-
-static inline struct symbol_cache * __used
-alloc_symbol_cache(const char *sym, long offset)
-{
- return NULL;
-}
-
static inline bool trace_kprobe_on_func_entry(struct trace_event_call *call)
{
return false;
@@ -280,11 +208,13 @@ static inline bool trace_kprobe_error_injectable(struct trace_event_call *call)
#endif /* CONFIG_KPROBE_EVENTS */
struct probe_arg {
- struct fetch_param fetch;
- struct fetch_param fetch_size;
+ struct fetch_insn *code;
+ bool dynamic;/* Dynamic array (string) is used */
unsigned int offset; /* Offset from argument entry */
+ unsigned int count; /* Array count */
const char *name; /* Name of this argument */
const char *comm; /* Command of this argument */
+ char *fmt; /* Format string if needed */
const struct fetch_type *type; /* Type of this argument */
};
@@ -313,12 +243,6 @@ static inline bool trace_probe_is_registered(struct trace_probe *tp)
return !!(tp->flags & TP_FLAG_REGISTERED);
}
-static nokprobe_inline void call_fetch(struct fetch_param *fprm,
- struct pt_regs *regs, void *dest)
-{
- return fprm->fn(regs, fprm->data, dest);
-}
-
/* Check the name is good for event/group/fields */
static inline bool is_good_name(const char *name)
{
@@ -343,67 +267,23 @@ find_event_file_link(struct trace_probe *tp, struct trace_event_file *file)
return NULL;
}
+#define TPARG_FL_RETURN BIT(0)
+#define TPARG_FL_KERNEL BIT(1)
+#define TPARG_FL_FENTRY BIT(2)
+#define TPARG_FL_MASK GENMASK(2, 0)
+
extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
- struct probe_arg *parg, bool is_return, bool is_kprobe,
- const struct fetch_type *ftbl);
+ struct probe_arg *parg, unsigned int flags);
extern int traceprobe_conflict_field_name(const char *name,
struct probe_arg *args, int narg);
-extern void traceprobe_update_arg(struct probe_arg *arg);
+extern int traceprobe_update_arg(struct probe_arg *arg);
extern void traceprobe_free_probe_arg(struct probe_arg *arg);
extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
-/* Sum up total data length for dynamic arraies (strings) */
-static nokprobe_inline int
-__get_data_size(struct trace_probe *tp, struct pt_regs *regs)
-{
- int i, ret = 0;
- u32 len;
-
- for (i = 0; i < tp->nr_args; i++)
- if (unlikely(tp->args[i].fetch_size.fn)) {
- call_fetch(&tp->args[i].fetch_size, regs, &len);
- ret += len;
- }
-
- return ret;
-}
-
-/* Store the value of each argument */
-static nokprobe_inline void
-store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs,
- u8 *data, int maxlen)
-{
- int i;
- u32 end = tp->size;
- u32 *dl; /* Data (relative) location */
-
- for (i = 0; i < tp->nr_args; i++) {
- if (unlikely(tp->args[i].fetch_size.fn)) {
- /*
- * First, we set the relative location and
- * maximum data length to *dl
- */
- dl = (u32 *)(data + tp->args[i].offset);
- *dl = make_data_rloc(maxlen, end - tp->args[i].offset);
- /* Then try to fetch string or dynamic array data */
- call_fetch(&tp->args[i].fetch, regs, dl);
- /* Reduce maximum length */
- end += get_rloc_len(*dl);
- maxlen -= get_rloc_len(*dl);
- /* Trick here, convert data_rloc to data_loc */
- *dl = convert_rloc_to_loc(*dl,
- ent_size + tp->args[i].offset);
- } else
- /* Just fetching data normally */
- call_fetch(&tp->args[i].fetch, regs,
- data + tp->args[i].offset);
- }
-}
-
-extern int set_print_fmt(struct trace_probe *tp, bool is_return);
+extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return);
#ifdef CONFIG_PERF_EVENTS
extern struct trace_event_call *
@@ -412,6 +292,9 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
extern void destroy_local_trace_kprobe(struct trace_event_call *event_call);
extern struct trace_event_call *
-create_local_trace_uprobe(char *name, unsigned long offs, bool is_return);
+create_local_trace_uprobe(char *name, unsigned long offs,
+ unsigned long ref_ctr_offset, bool is_return);
extern void destroy_local_trace_uprobe(struct trace_event_call *event_call);
#endif
+extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
+ size_t offset, struct trace_probe *tp);
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
new file mode 100644
index 000000000000..5c56afc17cf8
--- /dev/null
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -0,0 +1,216 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Traceprobe fetch helper inlines
+ */
+
+static nokprobe_inline void
+fetch_store_raw(unsigned long val, struct fetch_insn *code, void *buf)
+{
+ switch (code->size) {
+ case 1:
+ *(u8 *)buf = (u8)val;
+ break;
+ case 2:
+ *(u16 *)buf = (u16)val;
+ break;
+ case 4:
+ *(u32 *)buf = (u32)val;
+ break;
+ case 8:
+ //TBD: 32bit signed
+ *(u64 *)buf = (u64)val;
+ break;
+ default:
+ *(unsigned long *)buf = val;
+ }
+}
+
+static nokprobe_inline void
+fetch_apply_bitfield(struct fetch_insn *code, void *buf)
+{
+ switch (code->basesize) {
+ case 1:
+ *(u8 *)buf <<= code->lshift;
+ *(u8 *)buf >>= code->rshift;
+ break;
+ case 2:
+ *(u16 *)buf <<= code->lshift;
+ *(u16 *)buf >>= code->rshift;
+ break;
+ case 4:
+ *(u32 *)buf <<= code->lshift;
+ *(u32 *)buf >>= code->rshift;
+ break;
+ case 8:
+ *(u64 *)buf <<= code->lshift;
+ *(u64 *)buf >>= code->rshift;
+ break;
+ }
+}
+
+/*
+ * These functions must be defined for each callsite.
+ * Return consumed dynamic data size (>= 0), or error (< 0).
+ * If dest is NULL, don't store result and return required dynamic data size.
+ */
+static int
+process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs,
+ void *dest, void *base);
+static nokprobe_inline int fetch_store_strlen(unsigned long addr);
+static nokprobe_inline int
+fetch_store_string(unsigned long addr, void *dest, void *base);
+static nokprobe_inline int
+probe_mem_read(void *dest, void *src, size_t size);
+
+/* From the 2nd stage, routine is same */
+static nokprobe_inline int
+process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val,
+ void *dest, void *base)
+{
+ struct fetch_insn *s3 = NULL;
+ int total = 0, ret = 0, i = 0;
+ u32 loc = 0;
+ unsigned long lval = val;
+
+stage2:
+ /* 2nd stage: dereference memory if needed */
+ while (code->op == FETCH_OP_DEREF) {
+ lval = val;
+ ret = probe_mem_read(&val, (void *)val + code->offset,
+ sizeof(val));
+ if (ret)
+ return ret;
+ code++;
+ }
+
+ s3 = code;
+stage3:
+ /* 3rd stage: store value to buffer */
+ if (unlikely(!dest)) {
+ if (code->op == FETCH_OP_ST_STRING) {
+ ret += fetch_store_strlen(val + code->offset);
+ code++;
+ goto array;
+ } else
+ return -EILSEQ;
+ }
+
+ switch (code->op) {
+ case FETCH_OP_ST_RAW:
+ fetch_store_raw(val, code, dest);
+ break;
+ case FETCH_OP_ST_MEM:
+ probe_mem_read(dest, (void *)val + code->offset, code->size);
+ break;
+ case FETCH_OP_ST_STRING:
+ loc = *(u32 *)dest;
+ ret = fetch_store_string(val + code->offset, dest, base);
+ break;
+ default:
+ return -EILSEQ;
+ }
+ code++;
+
+ /* 4th stage: modify stored value if needed */
+ if (code->op == FETCH_OP_MOD_BF) {
+ fetch_apply_bitfield(code, dest);
+ code++;
+ }
+
+array:
+ /* the last stage: Loop on array */
+ if (code->op == FETCH_OP_LP_ARRAY) {
+ total += ret;
+ if (++i < code->param) {
+ code = s3;
+ if (s3->op != FETCH_OP_ST_STRING) {
+ dest += s3->size;
+ val += s3->size;
+ goto stage3;
+ }
+ code--;
+ val = lval + sizeof(char *);
+ if (dest) {
+ dest += sizeof(u32);
+ *(u32 *)dest = update_data_loc(loc, ret);
+ }
+ goto stage2;
+ }
+ code++;
+ ret = total;
+ }
+
+ return code->op == FETCH_OP_END ? ret : -EILSEQ;
+}
+
+/* Sum up total data length for dynamic arraies (strings) */
+static nokprobe_inline int
+__get_data_size(struct trace_probe *tp, struct pt_regs *regs)
+{
+ struct probe_arg *arg;
+ int i, len, ret = 0;
+
+ for (i = 0; i < tp->nr_args; i++) {
+ arg = tp->args + i;
+ if (unlikely(arg->dynamic)) {
+ len = process_fetch_insn(arg->code, regs, NULL, NULL);
+ if (len > 0)
+ ret += len;
+ }
+ }
+
+ return ret;
+}
+
+/* Store the value of each argument */
+static nokprobe_inline void
+store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs,
+ int header_size, int maxlen)
+{
+ struct probe_arg *arg;
+ void *base = data - header_size;
+ void *dyndata = data + tp->size;
+ u32 *dl; /* Data location */
+ int ret, i;
+
+ for (i = 0; i < tp->nr_args; i++) {
+ arg = tp->args + i;
+ dl = data + arg->offset;
+ /* Point the dynamic data area if needed */
+ if (unlikely(arg->dynamic))
+ *dl = make_data_loc(maxlen, dyndata - base);
+ ret = process_fetch_insn(arg->code, regs, dl, base);
+ if (unlikely(ret < 0 && arg->dynamic))
+ *dl = make_data_loc(0, dyndata - base);
+ else
+ dyndata += ret;
+ }
+}
+
+static inline int
+print_probe_args(struct trace_seq *s, struct probe_arg *args, int nr_args,
+ u8 *data, void *field)
+{
+ void *p;
+ int i, j;
+
+ for (i = 0; i < nr_args; i++) {
+ struct probe_arg *a = args + i;
+
+ trace_seq_printf(s, " %s=", a->name);
+ if (likely(!a->count)) {
+ if (!a->type->print(s, data + a->offset, field))
+ return -ENOMEM;
+ continue;
+ }
+ trace_seq_putc(s, '{');
+ p = data + a->offset;
+ for (j = 0; j < a->count; j++) {
+ if (!a->type->print(s, p, field))
+ return -ENOMEM;
+ trace_seq_putc(s, j == a->count - 1 ? '}' : ',');
+ p += a->type->size;
+ }
+ }
+ return 0;
+}
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index a86b303e6c67..7d04b9890755 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -270,6 +270,8 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace)
unsigned long flags;
int pc;
+ ftrace_graph_addr_finish(trace);
+
if (!func_prolog_preempt_disable(tr, &data, &pc))
return;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 4237eba4ef20..2b0d1ee3241c 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -111,7 +111,7 @@ check_stack(unsigned long ip, unsigned long *stack)
stack_trace_max_size = this_size;
stack_trace_max.nr_entries = 0;
- stack_trace_max.skip = 3;
+ stack_trace_max.skip = 0;
save_stack_trace(&stack_trace_max);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index e696667da29a..31ea48eceda1 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -15,6 +15,7 @@
#include <linux/rculist.h>
#include "trace_probe.h"
+#include "trace_probe_tmpl.h"
#define UPROBE_EVENT_SYSTEM "uprobes"
@@ -47,6 +48,7 @@ struct trace_uprobe {
struct inode *inode;
char *filename;
unsigned long offset;
+ unsigned long ref_ctr_offset;
unsigned long nhit;
struct trace_probe tp;
};
@@ -98,74 +100,52 @@ static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n)
/*
* Uprobes-specific fetch functions
*/
-#define DEFINE_FETCH_stack(type) \
-static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \
- void *offset, void *dest) \
-{ \
- *(type *)dest = (type)get_user_stack_nth(regs, \
- ((unsigned long)offset)); \
-}
-DEFINE_BASIC_FETCH_FUNCS(stack)
-/* No string on the stack entry */
-#define fetch_stack_string NULL
-#define fetch_stack_string_size NULL
-
-#define DEFINE_FETCH_memory(type) \
-static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \
- void *addr, void *dest) \
-{ \
- type retval; \
- void __user *vaddr = (void __force __user *) addr; \
- \
- if (copy_from_user(&retval, vaddr, sizeof(type))) \
- *(type *)dest = 0; \
- else \
- *(type *) dest = retval; \
+static nokprobe_inline int
+probe_mem_read(void *dest, void *src, size_t size)
+{
+ void __user *vaddr = (void __force __user *)src;
+
+ return copy_from_user(dest, vaddr, size) ? -EFAULT : 0;
}
-DEFINE_BASIC_FETCH_FUNCS(memory)
/*
* Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
* length and relative data location.
*/
-static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
- void *addr, void *dest)
+static nokprobe_inline int
+fetch_store_string(unsigned long addr, void *dest, void *base)
{
long ret;
- u32 rloc = *(u32 *)dest;
- int maxlen = get_rloc_len(rloc);
- u8 *dst = get_rloc_data(dest);
+ u32 loc = *(u32 *)dest;
+ int maxlen = get_loc_len(loc);
+ u8 *dst = get_loc_data(dest, base);
void __user *src = (void __force __user *) addr;
- if (!maxlen)
- return;
+ if (unlikely(!maxlen))
+ return -ENOMEM;
ret = strncpy_from_user(dst, src, maxlen);
- if (ret == maxlen)
- dst[--ret] = '\0';
-
- if (ret < 0) { /* Failed to fetch string */
- ((u8 *)get_rloc_data(dest))[0] = '\0';
- *(u32 *)dest = make_data_rloc(0, get_rloc_offs(rloc));
- } else {
- *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(rloc));
+ if (ret >= 0) {
+ if (ret == maxlen)
+ dst[ret - 1] = '\0';
+ *(u32 *)dest = make_data_loc(ret, (void *)dst - base);
}
+
+ return ret;
}
-static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
- void *addr, void *dest)
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+fetch_store_strlen(unsigned long addr)
{
int len;
void __user *vaddr = (void __force __user *) addr;
len = strnlen_user(vaddr, MAX_STRING_SIZE);
- if (len == 0 || len > MAX_STRING_SIZE) /* Failed to check length */
- *(u32 *)dest = 0;
- else
- *(u32 *)dest = len;
+ return (len > MAX_STRING_SIZE) ? 0 : len;
}
-static unsigned long translate_user_vaddr(void *file_offset)
+static unsigned long translate_user_vaddr(unsigned long file_offset)
{
unsigned long base_addr;
struct uprobe_dispatch_data *udd;
@@ -173,44 +153,44 @@ static unsigned long translate_user_vaddr(void *file_offset)
udd = (void *) current->utask->vaddr;
base_addr = udd->bp_addr - udd->tu->offset;
- return base_addr + (unsigned long)file_offset;
+ return base_addr + file_offset;
}
-#define DEFINE_FETCH_file_offset(type) \
-static void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs, \
- void *offset, void *dest)\
-{ \
- void *vaddr = (void *)translate_user_vaddr(offset); \
- \
- FETCH_FUNC_NAME(memory, type)(regs, vaddr, dest); \
+/* Note that we don't verify it, since the code does not come from user space */
+static int
+process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
+ void *base)
+{
+ unsigned long val;
+
+ /* 1st stage: get value from context */
+ switch (code->op) {
+ case FETCH_OP_REG:
+ val = regs_get_register(regs, code->param);
+ break;
+ case FETCH_OP_STACK:
+ val = get_user_stack_nth(regs, code->param);
+ break;
+ case FETCH_OP_STACKP:
+ val = user_stack_pointer(regs);
+ break;
+ case FETCH_OP_RETVAL:
+ val = regs_return_value(regs);
+ break;
+ case FETCH_OP_IMM:
+ val = code->immediate;
+ break;
+ case FETCH_OP_FOFFS:
+ val = translate_user_vaddr(code->immediate);
+ break;
+ default:
+ return -EILSEQ;
+ }
+ code++;
+
+ return process_fetch_insn_bottom(code, val, dest, base);
}
-DEFINE_BASIC_FETCH_FUNCS(file_offset)
-DEFINE_FETCH_file_offset(string)
-DEFINE_FETCH_file_offset(string_size)
-
-/* Fetch type information table */
-static const struct fetch_type uprobes_fetch_type_table[] = {
- /* Special types */
- [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
- sizeof(u32), 1, "__data_loc char[]"),
- [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
- string_size, sizeof(u32), 0, "u32"),
- /* Basic types */
- ASSIGN_FETCH_TYPE(u8, u8, 0),
- ASSIGN_FETCH_TYPE(u16, u16, 0),
- ASSIGN_FETCH_TYPE(u32, u32, 0),
- ASSIGN_FETCH_TYPE(u64, u64, 0),
- ASSIGN_FETCH_TYPE(s8, u8, 1),
- ASSIGN_FETCH_TYPE(s16, u16, 1),
- ASSIGN_FETCH_TYPE(s32, u32, 1),
- ASSIGN_FETCH_TYPE(s64, u64, 1),
- ASSIGN_FETCH_TYPE_ALIAS(x8, u8, u8, 0),
- ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0),
- ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0),
- ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0),
-
- ASSIGN_FETCH_TYPE_END
-};
+NOKPROBE_SYMBOL(process_fetch_insn)
static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
{
@@ -311,6 +291,35 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu)
return 0;
}
+/*
+ * Uprobe with multiple reference counter is not allowed. i.e.
+ * If inode and offset matches, reference counter offset *must*
+ * match as well. Though, there is one exception: If user is
+ * replacing old trace_uprobe with new one(same group/event),
+ * then we allow same uprobe with new reference counter as far
+ * as the new one does not conflict with any other existing
+ * ones.
+ */
+static struct trace_uprobe *find_old_trace_uprobe(struct trace_uprobe *new)
+{
+ struct trace_uprobe *tmp, *old = NULL;
+ struct inode *new_inode = d_real_inode(new->path.dentry);
+
+ old = find_probe_event(trace_event_name(&new->tp.call),
+ new->tp.call.class->system);
+
+ list_for_each_entry(tmp, &uprobe_list, list) {
+ if ((old ? old != tmp : true) &&
+ new_inode == d_real_inode(tmp->path.dentry) &&
+ new->offset == tmp->offset &&
+ new->ref_ctr_offset != tmp->ref_ctr_offset) {
+ pr_warn("Reference counter offset mismatch.");
+ return ERR_PTR(-EINVAL);
+ }
+ }
+ return old;
+}
+
/* Register a trace_uprobe and probe_event */
static int register_trace_uprobe(struct trace_uprobe *tu)
{
@@ -320,8 +329,12 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
mutex_lock(&uprobe_lock);
/* register as an event */
- old_tu = find_probe_event(trace_event_name(&tu->tp.call),
- tu->tp.call.class->system);
+ old_tu = find_old_trace_uprobe(tu);
+ if (IS_ERR(old_tu)) {
+ ret = PTR_ERR(old_tu);
+ goto end;
+ }
+
if (old_tu) {
/* delete old event */
ret = unregister_trace_uprobe(old_tu);
@@ -352,10 +365,10 @@ end:
static int create_trace_uprobe(int argc, char **argv)
{
struct trace_uprobe *tu;
- char *arg, *event, *group, *filename;
+ char *arg, *event, *group, *filename, *rctr, *rctr_end;
char buf[MAX_EVENT_NAME_LEN];
struct path path;
- unsigned long offset;
+ unsigned long offset, ref_ctr_offset;
bool is_delete, is_return;
int i, ret;
@@ -364,6 +377,7 @@ static int create_trace_uprobe(int argc, char **argv)
is_return = false;
event = NULL;
group = NULL;
+ ref_ctr_offset = 0;
/* argc must be >= 1 */
if (argv[0][0] == '-')
@@ -438,6 +452,26 @@ static int create_trace_uprobe(int argc, char **argv)
goto fail_address_parse;
}
+ /* Parse reference counter offset if specified. */
+ rctr = strchr(arg, '(');
+ if (rctr) {
+ rctr_end = strchr(rctr, ')');
+ if (rctr > rctr_end || *(rctr_end + 1) != 0) {
+ ret = -EINVAL;
+ pr_info("Invalid reference counter offset.\n");
+ goto fail_address_parse;
+ }
+
+ *rctr++ = '\0';
+ *rctr_end = '\0';
+ ret = kstrtoul(rctr, 0, &ref_ctr_offset);
+ if (ret) {
+ pr_info("Invalid reference counter offset.\n");
+ goto fail_address_parse;
+ }
+ }
+
+ /* Parse uprobe offset. */
ret = kstrtoul(arg, 0, &offset);
if (ret)
goto fail_address_parse;
@@ -472,6 +506,7 @@ static int create_trace_uprobe(int argc, char **argv)
goto fail_address_parse;
}
tu->offset = offset;
+ tu->ref_ctr_offset = ref_ctr_offset;
tu->path = path;
tu->filename = kstrdup(filename, GFP_KERNEL);
@@ -522,8 +557,7 @@ static int create_trace_uprobe(int argc, char **argv)
/* Parse fetch argument */
ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg,
- is_return, false,
- uprobes_fetch_type_table);
+ is_return ? TPARG_FL_RETURN : 0);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
goto error;
@@ -590,6 +624,9 @@ static int probes_seq_show(struct seq_file *m, void *v)
trace_event_name(&tu->tp.call), tu->filename,
(int)(sizeof(void *) * 2), tu->offset);
+ if (tu->ref_ctr_offset)
+ seq_printf(m, "(0x%lx)", tu->ref_ctr_offset);
+
for (i = 0; i < tu->tp.nr_args; i++)
seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm);
@@ -833,7 +870,6 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
struct trace_seq *s = &iter->seq;
struct trace_uprobe *tu;
u8 *data;
- int i;
entry = (struct uprobe_trace_entry_head *)iter->ent;
tu = container_of(event, struct trace_uprobe, tp.call.event);
@@ -850,12 +886,8 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
data = DATAOF_TRACE_ENTRY(entry, false);
}
- for (i = 0; i < tu->tp.nr_args; i++) {
- struct probe_arg *parg = &tu->tp.args[i];
-
- if (!parg->type->print(s, parg->name, data + parg->offset, entry))
- goto out;
- }
+ if (print_probe_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0)
+ goto out;
trace_seq_putc(s, '\n');
@@ -905,7 +937,13 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
tu->consumer.filter = filter;
tu->inode = d_real_inode(tu->path.dentry);
- ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+ if (tu->ref_ctr_offset) {
+ ret = uprobe_register_refctr(tu->inode, tu->offset,
+ tu->ref_ctr_offset, &tu->consumer);
+ } else {
+ ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+ }
+
if (ret)
goto err_buffer;
@@ -958,7 +996,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
static int uprobe_event_define_fields(struct trace_event_call *event_call)
{
- int ret, i, size;
+ int ret, size;
struct uprobe_trace_entry_head field;
struct trace_uprobe *tu = event_call->data;
@@ -970,19 +1008,8 @@ static int uprobe_event_define_fields(struct trace_event_call *event_call)
DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0);
size = SIZEOF_TRACE_ENTRY(false);
}
- /* Set argument names as fields */
- for (i = 0; i < tu->tp.nr_args; i++) {
- struct probe_arg *parg = &tu->tp.args[i];
-
- ret = trace_define_field(event_call, parg->type->fmttype,
- parg->name, size + parg->offset,
- parg->type->size, parg->type->is_signed,
- FILTER_OTHER);
- if (ret)
- return ret;
- }
- return 0;
+ return traceprobe_define_arg_fields(event_call, size, &tu->tp);
}
#ifdef CONFIG_PERF_EVENTS
@@ -1233,7 +1260,7 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
ucb = uprobe_buffer_get();
- store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+ store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize);
if (tu->tp.flags & TP_FLAG_TRACE)
ret |= uprobe_trace_func(tu, regs, ucb, dsize);
@@ -1268,7 +1295,7 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
ucb = uprobe_buffer_get();
- store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+ store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize);
if (tu->tp.flags & TP_FLAG_TRACE)
uretprobe_trace_func(tu, func, regs, ucb, dsize);
@@ -1304,7 +1331,7 @@ static int register_uprobe_event(struct trace_uprobe *tu)
init_trace_event_call(tu, call);
- if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
+ if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
return -ENOMEM;
ret = register_trace_event(&call->event);
@@ -1340,7 +1367,8 @@ static int unregister_uprobe_event(struct trace_uprobe *tu)
#ifdef CONFIG_PERF_EVENTS
struct trace_event_call *
-create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
+create_local_trace_uprobe(char *name, unsigned long offs,
+ unsigned long ref_ctr_offset, bool is_return)
{
struct trace_uprobe *tu;
struct path path;
@@ -1372,10 +1400,11 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
tu->offset = offs;
tu->path = path;
+ tu->ref_ctr_offset = ref_ctr_offset;
tu->filename = kstrdup(name, GFP_KERNEL);
init_trace_event_call(tu, &tu->tp.call);
- if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) {
+ if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) {
ret = -ENOMEM;
goto error;
}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index a3be42304485..46f2ab1e08a9 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -92,7 +92,7 @@ static __init int release_early_probes(void)
while (early_probes) {
tmp = early_probes;
early_probes = tmp->next;
- call_rcu_sched(tmp, rcu_free_old_probes);
+ call_rcu(tmp, rcu_free_old_probes);
}
return 0;
@@ -123,7 +123,7 @@ static inline void release_probes(struct tracepoint_func *old)
* cover both cases. So let us chain the SRCU and sched RCU
* callbacks to wait for both grace periods.
*/
- call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes);
+ call_rcu(&tp_probes->rcu, rcu_free_old_probes);
}
}
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index e5222b5fb4fe..923414a246e9 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -974,10 +974,6 @@ static ssize_t map_write(struct file *file, const char __user *buf,
if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
goto out;
- ret = sort_idmaps(&new_map);
- if (ret < 0)
- goto out;
-
ret = -EPERM;
/* Map the lower ids from the parent user namespace to the
* kernel global id space.
@@ -1004,6 +1000,14 @@ static ssize_t map_write(struct file *file, const char __user *buf,
e->lower_first = lower_first;
}
+ /*
+ * If we want to use binary search for lookup, this clones the extent
+ * array and sorts both copies.
+ */
+ ret = sort_idmaps(&new_map);
+ if (ret < 0)
+ goto out;
+
/* Install the map */
if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
memcpy(map->extent, new_map.extent,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0280deac392e..392be4b252f6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3396,7 +3396,7 @@ static void put_unbound_pool(struct worker_pool *pool)
del_timer_sync(&pool->mayday_timer);
/* sched-RCU protected to allow dereferences from get_work_pool() */
- call_rcu_sched(&pool->rcu, rcu_free_pool);
+ call_rcu(&pool->rcu, rcu_free_pool);
}
/**
@@ -3503,14 +3503,14 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
put_unbound_pool(pool);
mutex_unlock(&wq_pool_mutex);
- call_rcu_sched(&pwq->rcu, rcu_free_pwq);
+ call_rcu(&pwq->rcu, rcu_free_pwq);
/*
* If we're the last pwq going away, @wq is already dead and no one
* is gonna access it anymore. Schedule RCU free.
*/
if (is_last)
- call_rcu_sched(&wq->rcu, rcu_free_wq);
+ call_rcu(&wq->rcu, rcu_free_wq);
}
/**
@@ -4195,7 +4195,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
* The base ref is never dropped on per-cpu pwqs. Directly
* schedule RCU free.
*/
- call_rcu_sched(&wq->rcu, rcu_free_wq);
+ call_rcu(&wq->rcu, rcu_free_wq);
} else {
/*
* We're the sole accessor of @wq at this point. Directly