summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/acct.c11
-rw-r--r--kernel/audit_watch.c2
-rw-r--r--kernel/bounds.c7
-rw-r--r--kernel/bpf/bloom_filter.c2
-rw-r--r--kernel/bpf/cgroup_iter.c2
-rw-r--r--kernel/bpf/core.c8
-rw-r--r--kernel/bpf/hashtab.c2
-rw-r--r--kernel/bpf/stackmap.c4
-rw-r--r--kernel/bpf/task_iter.c10
-rw-r--r--kernel/bpf/verifier.c2
-rw-r--r--kernel/cgroup/cgroup-internal.h3
-rw-r--r--kernel/cgroup/cgroup-v1.c6
-rw-r--r--kernel/cgroup/cgroup.c356
-rw-r--r--kernel/cgroup/cpuset.c815
-rw-r--r--kernel/cgroup/legacy_freezer.c23
-rw-r--r--kernel/cgroup/pids.c37
-rw-r--r--kernel/debug/debug_core.c12
-rw-r--r--kernel/delayacct.c13
-rw-r--r--kernel/dma/mapping.c10
-rw-r--r--kernel/dma/swiotlb.c40
-rw-r--r--kernel/entry/common.c5
-rw-r--r--kernel/events/Makefile1
-rw-r--r--kernel/events/core.c91
-rw-r--r--kernel/events/hw_breakpoint.c648
-rw-r--r--kernel/events/hw_breakpoint_test.c333
-rw-r--r--kernel/events/uprobes.c39
-rw-r--r--kernel/exit.c31
-rw-r--r--kernel/fail_function.c26
-rw-r--r--kernel/fork.c99
-rw-r--r--kernel/freezer.c133
-rw-r--r--kernel/futex/waitwake.c8
-rwxr-xr-xkernel/gen_kheaders.sh6
-rw-r--r--kernel/hung_task.c16
-rw-r--r--kernel/irq/irqdesc.c24
-rw-r--r--kernel/kcov.c7
-rw-r--r--kernel/kcsan/selftest.c4
-rw-r--r--kernel/kexec.c11
-rw-r--r--kernel/kexec_core.c36
-rw-r--r--kernel/kexec_file.c4
-rw-r--r--kernel/kexec_internal.h15
-rw-r--r--kernel/ksysfs.c7
-rw-r--r--kernel/kthread.c1
-rw-r--r--kernel/latencytop.c4
-rw-r--r--kernel/livepatch/core.c20
-rw-r--r--kernel/livepatch/transition.c18
-rw-r--r--kernel/locking/Makefile3
-rw-r--r--kernel/locking/lockdep.c6
-rw-r--r--kernel/locking/percpu-rwsem.c6
-rw-r--r--kernel/locking/qrwlock.c4
-rw-r--r--kernel/locking/qspinlock.c2
-rw-r--r--kernel/locking/qspinlock_paravirt.h4
-rw-r--r--kernel/locking/rwsem.c14
-rw-r--r--kernel/locking/semaphore.c12
-rw-r--r--kernel/locking/spinlock.c56
-rw-r--r--kernel/locking/test-ww_mutex.c4
-rw-r--r--kernel/module/decompress.c2
-rw-r--r--kernel/module/internal.h4
-rw-r--r--kernel/module/main.c20
-rw-r--r--kernel/module/tracking.c71
-rw-r--r--kernel/panic.c3
-rw-r--r--kernel/pid.c1
-rw-r--r--kernel/power/hibernate.c35
-rw-r--r--kernel/power/main.c18
-rw-r--r--kernel/power/process.c10
-rw-r--r--kernel/power/suspend.c15
-rw-r--r--kernel/power/user.c24
-rw-r--r--kernel/printk/printk.c19
-rw-r--r--kernel/profile.c32
-rw-r--r--kernel/ptrace.c2
-rw-r--r--kernel/reboot.c17
-rw-r--r--kernel/relay.c5
-rw-r--r--kernel/sched/autogroup.c3
-rw-r--r--kernel/sched/completion.c12
-rw-r--r--kernel/sched/core.c124
-rw-r--r--kernel/sched/core_sched.c4
-rw-r--r--kernel/sched/cpudeadline.c2
-rw-r--r--kernel/sched/cpupri.c2
-rw-r--r--kernel/sched/deadline.c115
-rw-r--r--kernel/sched/debug.c1
-rw-r--r--kernel/sched/fair.c402
-rw-r--r--kernel/sched/psi.c282
-rw-r--r--kernel/sched/rt.c18
-rw-r--r--kernel/sched/sched.h66
-rw-r--r--kernel/sched/stats.h6
-rw-r--r--kernel/sched/stop_task.c11
-rw-r--r--kernel/signal.c17
-rw-r--r--kernel/smp.c6
-rw-r--r--kernel/smpboot.c15
-rw-r--r--kernel/sys.c5
-rw-r--r--kernel/sysctl-test.c43
-rw-r--r--kernel/sysctl.c30
-rw-r--r--kernel/task_work.c16
-rw-r--r--kernel/time/clocksource.c2
-rw-r--r--kernel/time/hrtimer.c4
-rw-r--r--kernel/trace/bpf_trace.c3
-rw-r--r--kernel/trace/ftrace.c39
-rw-r--r--kernel/trace/kprobe_event_gen_test.c49
-rw-r--r--kernel/trace/ring_buffer.c93
-rw-r--r--kernel/trace/rv/monitors/wip/wip.c8
-rw-r--r--kernel/trace/rv/monitors/wwnr/wwnr.c8
-rw-r--r--kernel/trace/trace.c78
-rw-r--r--kernel/trace/trace.h13
-rw-r--r--kernel/trace/trace_benchmark.c2
-rw-r--r--kernel/trace/trace_benchmark.h8
-rw-r--r--kernel/trace/trace_eprobe.c167
-rw-r--r--kernel/trace/trace_events_filter.c239
-rw-r--r--kernel/trace/trace_events_hist.c246
-rw-r--r--kernel/trace/trace_events_synth.c23
-rw-r--r--kernel/trace/trace_events_user.c568
-rw-r--r--kernel/trace/trace_kprobe.c60
-rw-r--r--kernel/trace/trace_osnoise.c3
-rw-r--r--kernel/trace/trace_probe.h3
-rw-r--r--kernel/trace/trace_probe_kernel.h115
-rw-r--r--kernel/trace/tracing_map.c5
-rw-r--r--kernel/tracepoint.c14
-rw-r--r--kernel/ucount.c34
-rw-r--r--kernel/umh.c18
-rw-r--r--kernel/user_namespace.c10
-rw-r--r--kernel/utsname_sysctl.c9
120 files changed, 4467 insertions, 1876 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 318789c728d3..d754e0be1176 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -38,6 +38,7 @@ KCOV_INSTRUMENT_kcov.o := n
KASAN_SANITIZE_kcov.o := n
KCSAN_SANITIZE_kcov.o := n
UBSAN_SANITIZE_kcov.o := n
+KMSAN_SANITIZE_kcov.o := n
CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack) -fno-stack-protector
# Don't instrument error handlers
diff --git a/kernel/acct.c b/kernel/acct.c
index 13706356ec54..62200d799b9b 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -555,15 +555,14 @@ void acct_collect(long exitcode, int group_dead)
unsigned long vsize = 0;
if (group_dead && current->mm) {
+ struct mm_struct *mm = current->mm;
+ VMA_ITERATOR(vmi, mm, 0);
struct vm_area_struct *vma;
- mmap_read_lock(current->mm);
- vma = current->mm->mmap;
- while (vma) {
+ mmap_read_lock(mm);
+ for_each_vma(vmi, vma)
vsize += vma->vm_end - vma->vm_start;
- vma = vma->vm_next;
- }
- mmap_read_unlock(current->mm);
+ mmap_read_unlock(mm);
}
spin_lock_irq(&current->sighand->siglock);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 4b0957aa2cd4..65075f1e4ac8 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -133,7 +133,7 @@ int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev)
}
/* Initialize a parent watch entry. */
-static struct audit_parent *audit_init_parent(struct path *path)
+static struct audit_parent *audit_init_parent(const struct path *path)
{
struct inode *inode = d_backing_inode(path->dentry);
struct audit_parent *parent;
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 9795d75b09b2..b529182e8b04 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -22,6 +22,13 @@ int main(void)
DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
#endif
DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
+#ifdef CONFIG_LRU_GEN
+ DEFINE(LRU_GEN_WIDTH, order_base_2(MAX_NR_GENS + 1));
+ DEFINE(__LRU_REFS_WIDTH, MAX_NR_TIERS - 2);
+#else
+ DEFINE(LRU_GEN_WIDTH, 0);
+ DEFINE(__LRU_REFS_WIDTH, 0);
+#endif
/* End of constants */
return 0;
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
index b9ea539a5561..48ee750849f2 100644
--- a/kernel/bpf/bloom_filter.c
+++ b/kernel/bpf/bloom_filter.c
@@ -158,7 +158,7 @@ static struct bpf_map *bloom_map_alloc(union bpf_attr *attr)
attr->value_size / sizeof(u32);
if (!(attr->map_flags & BPF_F_ZERO_SEED))
- bloom->hash_seed = get_random_int();
+ bloom->hash_seed = get_random_u32();
return &bloom->map;
}
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
index 0d200a993489..9fcf09f2ef00 100644
--- a/kernel/bpf/cgroup_iter.c
+++ b/kernel/bpf/cgroup_iter.c
@@ -196,7 +196,7 @@ static int bpf_iter_attach_cgroup(struct bpf_prog *prog,
return -EINVAL;
if (fd)
- cgrp = cgroup_get_from_fd(fd);
+ cgrp = cgroup_v1v2_get_from_fd(fd);
else if (id)
cgrp = cgroup_get_from_id(id);
else /* walk the entire hierarchy by default. */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 711fd293b6de..25a54e04560e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1032,7 +1032,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
hdr->size = size;
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
- start = (get_random_int() % hole) & ~(alignment - 1);
+ start = prandom_u32_max(hole) & ~(alignment - 1);
/* Leave a random number of instructions before BPF code. */
*image_ptr = &hdr->image[start];
@@ -1094,7 +1094,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
hole = min_t(unsigned int, size - (proglen + sizeof(*ro_header)),
BPF_PROG_CHUNK_SIZE - sizeof(*ro_header));
- start = (get_random_int() % hole) & ~(alignment - 1);
+ start = prandom_u32_max(hole) & ~(alignment - 1);
*image_ptr = &ro_header->image[start];
*rw_image = &(*rw_header)->image[start];
@@ -1216,7 +1216,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
bool emit_zext)
{
struct bpf_insn *to = to_buff;
- u32 imm_rnd = get_random_int();
+ u32 imm_rnd = get_random_u32();
s16 off;
BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG);
@@ -2007,7 +2007,7 @@ out:
static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \
{ \
u64 stack[stack_size / sizeof(u64)]; \
- u64 regs[MAX_BPF_EXT_REG]; \
+ u64 regs[MAX_BPF_EXT_REG] = {}; \
\
FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
ARG1 = (u64) (unsigned long) ctx; \
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index ed3f8a53603b..f39ee3e05589 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -527,7 +527,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
if (htab->map.map_flags & BPF_F_ZERO_SEED)
htab->hashrnd = 0;
else
- htab->hashrnd = get_random_int();
+ htab->hashrnd = get_random_u32();
htab_init_buckets(htab);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 1adbe67cdb95..aecea7451b61 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -338,7 +338,7 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
int ret;
/* perf_sample_data doesn't have callchain, use bpf_get_stackid */
- if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+ if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
return bpf_get_stackid((unsigned long)(ctx->regs),
(unsigned long) map, flags, 0, 0);
@@ -506,7 +506,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
int err = -EINVAL;
__u64 nr_kernel;
- if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+ if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 67e03e1833ba..c2a2182ce570 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -445,8 +445,8 @@ struct bpf_iter_seq_task_vma_info {
};
enum bpf_task_vma_iter_find_op {
- task_vma_iter_first_vma, /* use mm->mmap */
- task_vma_iter_next_vma, /* use curr_vma->vm_next */
+ task_vma_iter_first_vma, /* use find_vma() with addr 0 */
+ task_vma_iter_next_vma, /* use vma_next() with curr_vma */
task_vma_iter_find_vma, /* use find_vma() to find next vma */
};
@@ -544,10 +544,10 @@ again:
switch (op) {
case task_vma_iter_first_vma:
- curr_vma = curr_task->mm->mmap;
+ curr_vma = find_vma(curr_task->mm, 0);
break;
case task_vma_iter_next_vma:
- curr_vma = curr_vma->vm_next;
+ curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
break;
case task_vma_iter_find_vma:
/* We dropped mmap_lock so it is necessary to use find_vma
@@ -561,7 +561,7 @@ again:
if (curr_vma &&
curr_vma->vm_start == info->prev_vm_start &&
curr_vma->vm_end == info->prev_vm_end)
- curr_vma = curr_vma->vm_next;
+ curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
break;
}
if (!curr_vma) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9ab7188d8f68..7f0a9f6cb889 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -13351,7 +13351,7 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
aux[adj_idx].ptr_type == PTR_TO_CTX)
continue;
- imm_rnd = get_random_int();
+ imm_rnd = get_random_u32();
rnd_hi32_patch[0] = insn;
rnd_hi32_patch[1].imm = imm_rnd;
rnd_hi32_patch[3].dst_reg = load_reg;
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 36b740cb3d59..fd4020835ec6 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -164,7 +164,6 @@ struct cgroup_mgctx {
#define DEFINE_CGROUP_MGCTX(name) \
struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
-extern struct mutex cgroup_mutex;
extern spinlock_t css_set_lock;
extern struct cgroup_subsys *cgroup_subsys[];
extern struct list_head cgroup_roots;
@@ -250,6 +249,8 @@ int cgroup_migrate(struct task_struct *leader, bool threadgroup,
int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
bool threadgroup);
+void cgroup_attach_lock(bool lock_threadgroup);
+void cgroup_attach_unlock(bool lock_threadgroup);
struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
bool *locked)
__acquires(&cgroup_threadgroup_rwsem);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index ff6a8099eb2a..52bb5a74a23b 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -59,8 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
int retval = 0;
mutex_lock(&cgroup_mutex);
- cpus_read_lock();
- percpu_down_write(&cgroup_threadgroup_rwsem);
+ cgroup_attach_lock(true);
for_each_root(root) {
struct cgroup *from_cgrp;
@@ -72,8 +71,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
if (retval)
break;
}
- percpu_up_write(&cgroup_threadgroup_rwsem);
- cpus_read_unlock();
+ cgroup_attach_unlock(true);
mutex_unlock(&cgroup_mutex);
return retval;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8ad2c267ff47..2319946715e0 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -217,6 +217,7 @@ struct cgroup_namespace init_cgroup_ns = {
static struct file_system_type cgroup2_fs_type;
static struct cftype cgroup_base_files[];
+static struct cftype cgroup_psi_files[];
/* cgroup optional features */
enum cgroup_opt_features {
@@ -1391,6 +1392,9 @@ static void cgroup_destroy_root(struct cgroup_root *root)
cgroup_free_root(root);
}
+/*
+ * Returned cgroup is without refcount but it's valid as long as cset pins it.
+ */
static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
struct cgroup_root *root)
{
@@ -1402,6 +1406,7 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
res_cgroup = cset->dfl_cgrp;
} else {
struct cgrp_cset_link *link;
+ lockdep_assert_held(&css_set_lock);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
@@ -1413,6 +1418,7 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
}
}
+ BUG_ON(!res_cgroup);
return res_cgroup;
}
@@ -1435,23 +1441,36 @@ current_cgns_cgroup_from_root(struct cgroup_root *root)
rcu_read_unlock();
- BUG_ON(!res);
return res;
}
+/*
+ * Look up cgroup associated with current task's cgroup namespace on the default
+ * hierarchy.
+ *
+ * Unlike current_cgns_cgroup_from_root(), this doesn't need locks:
+ * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu
+ * pointers.
+ * - css_set_lock is not needed because we just read cset->dfl_cgrp.
+ * - As a bonus returned cgrp is pinned with the current because it cannot
+ * switch cgroup_ns asynchronously.
+ */
+static struct cgroup *current_cgns_cgroup_dfl(void)
+{
+ struct css_set *cset;
+
+ cset = current->nsproxy->cgroup_ns->root_cset;
+ return __cset_cgroup_from_root(cset, &cgrp_dfl_root);
+}
+
/* look up cgroup associated with given css_set on the specified hierarchy */
static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
struct cgroup_root *root)
{
- struct cgroup *res = NULL;
-
lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_lock);
- res = __cset_cgroup_from_root(cset, root);
-
- BUG_ON(!res);
- return res;
+ return __cset_cgroup_from_root(cset, root);
}
/*
@@ -1689,12 +1708,16 @@ static void css_clear_dir(struct cgroup_subsys_state *css)
css->flags &= ~CSS_VISIBLE;
if (!css->ss) {
- if (cgroup_on_dfl(cgrp))
- cfts = cgroup_base_files;
- else
- cfts = cgroup1_base_files;
-
- cgroup_addrm_files(css, cgrp, cfts, false);
+ if (cgroup_on_dfl(cgrp)) {
+ cgroup_addrm_files(css, cgrp,
+ cgroup_base_files, false);
+ if (cgroup_psi_enabled())
+ cgroup_addrm_files(css, cgrp,
+ cgroup_psi_files, false);
+ } else {
+ cgroup_addrm_files(css, cgrp,
+ cgroup1_base_files, false);
+ }
} else {
list_for_each_entry(cfts, &css->ss->cfts, node)
cgroup_addrm_files(css, cgrp, cfts, false);
@@ -1717,14 +1740,22 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
return 0;
if (!css->ss) {
- if (cgroup_on_dfl(cgrp))
- cfts = cgroup_base_files;
- else
- cfts = cgroup1_base_files;
-
- ret = cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
- if (ret < 0)
- return ret;
+ if (cgroup_on_dfl(cgrp)) {
+ ret = cgroup_addrm_files(&cgrp->self, cgrp,
+ cgroup_base_files, true);
+ if (ret < 0)
+ return ret;
+
+ if (cgroup_psi_enabled()) {
+ ret = cgroup_addrm_files(&cgrp->self, cgrp,
+ cgroup_psi_files, true);
+ if (ret < 0)
+ return ret;
+ }
+ } else {
+ cgroup_addrm_files(css, cgrp,
+ cgroup1_base_files, true);
+ }
} else {
list_for_each_entry(cfts, &css->ss->cfts, node) {
ret = cgroup_addrm_files(css, cgrp, cfts, true);
@@ -2050,7 +2081,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
}
root_cgrp->kn = kernfs_root_to_node(root->kf_root);
WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1);
- root_cgrp->ancestor_ids[0] = cgroup_id(root_cgrp);
+ root_cgrp->ancestors[0] = root_cgrp;
ret = css_populate_dir(&root_cgrp->self);
if (ret)
@@ -2173,7 +2204,7 @@ static int cgroup_get_tree(struct fs_context *fc)
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
int ret;
- cgrp_dfl_visible = true;
+ WRITE_ONCE(cgrp_dfl_visible, true);
cgroup_get_live(&cgrp_dfl_root.cgrp);
ctx->root = &cgrp_dfl_root;
@@ -2361,7 +2392,7 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
} else {
/* if no hierarchy exists, everyone is in "/" */
- ret = strlcpy(buf, "/", buflen);
+ ret = strscpy(buf, "/", buflen);
}
spin_unlock_irq(&css_set_lock);
@@ -2393,7 +2424,7 @@ EXPORT_SYMBOL_GPL(task_cgroup_path);
* write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
* CPU hotplug is disabled on entry.
*/
-static void cgroup_attach_lock(bool lock_threadgroup)
+void cgroup_attach_lock(bool lock_threadgroup)
{
cpus_read_lock();
if (lock_threadgroup)
@@ -2404,7 +2435,7 @@ static void cgroup_attach_lock(bool lock_threadgroup)
* cgroup_attach_unlock - Undo cgroup_attach_lock()
* @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
*/
-static void cgroup_attach_unlock(bool lock_threadgroup)
+void cgroup_attach_unlock(bool lock_threadgroup)
{
if (lock_threadgroup)
percpu_up_write(&cgroup_threadgroup_rwsem);
@@ -3292,11 +3323,7 @@ static int cgroup_apply_control(struct cgroup *cgrp)
* making the following cgroup_update_dfl_csses() properly update
* css associations of all tasks in the subtree.
*/
- ret = cgroup_update_dfl_csses(cgrp);
- if (ret)
- return ret;
-
- return 0;
+ return cgroup_update_dfl_csses(cgrp);
}
/**
@@ -3689,27 +3716,27 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
- struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+ struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_IO);
}
static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
- struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+ struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_MEM);
}
static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
- struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+ struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_CPU);
}
-static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
- size_t nbytes, enum psi_res res)
+static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, enum psi_res res)
{
struct cgroup_file_ctx *ctx = of->priv;
struct psi_trigger *new;
@@ -3729,7 +3756,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
return -EBUSY;
}
- psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+ psi = cgroup_psi(cgrp);
new = psi_trigger_create(psi, buf, res);
if (IS_ERR(new)) {
cgroup_put(cgrp);
@@ -3746,21 +3773,86 @@ static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
- return cgroup_pressure_write(of, buf, nbytes, PSI_IO);
+ return pressure_write(of, buf, nbytes, PSI_IO);
}
static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
- return cgroup_pressure_write(of, buf, nbytes, PSI_MEM);
+ return pressure_write(of, buf, nbytes, PSI_MEM);
}
static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
- return cgroup_pressure_write(of, buf, nbytes, PSI_CPU);
+ return pressure_write(of, buf, nbytes, PSI_CPU);
+}
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+static int cgroup_irq_pressure_show(struct seq_file *seq, void *v)
+{
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
+ struct psi_group *psi = cgroup_psi(cgrp);
+
+ return psi_show(seq, psi, PSI_IRQ);
+}
+
+static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ return pressure_write(of, buf, nbytes, PSI_IRQ);
+}
+#endif
+
+static int cgroup_pressure_show(struct seq_file *seq, void *v)
+{
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
+ struct psi_group *psi = cgroup_psi(cgrp);
+
+ seq_printf(seq, "%d\n", psi->enabled);
+
+ return 0;
+}
+
+static ssize_t cgroup_pressure_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ ssize_t ret;
+ int enable;
+ struct cgroup *cgrp;
+ struct psi_group *psi;
+
+ ret = kstrtoint(strstrip(buf), 0, &enable);
+ if (ret)
+ return ret;
+
+ if (enable < 0 || enable > 1)
+ return -ERANGE;
+
+ cgrp = cgroup_kn_lock_live(of->kn, false);
+ if (!cgrp)
+ return -ENOENT;
+
+ psi = cgroup_psi(cgrp);
+ if (psi->enabled != enable) {
+ int i;
+
+ /* show or hide {cpu,memory,io,irq}.pressure files */
+ for (i = 0; i < NR_PSI_RESOURCES; i++)
+ cgroup_file_show(&cgrp->psi_files[i], enable);
+
+ psi->enabled = enable;
+ if (enable)
+ psi_cgroup_restart(psi);
+ }
+
+ cgroup_kn_unlock(of->kn);
+
+ return nbytes;
}
static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
@@ -3780,6 +3872,9 @@ static void cgroup_pressure_release(struct kernfs_open_file *of)
bool cgroup_psi_enabled(void)
{
+ if (static_branch_likely(&psi_disabled))
+ return false;
+
return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0;
}
@@ -4132,8 +4227,6 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css,
restart:
for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) {
/* does cft->flags tell us to skip this file on @cgrp? */
- if ((cft->flags & CFTYPE_PRESSURE) && !cgroup_psi_enabled())
- continue;
if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
continue;
if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp))
@@ -4198,21 +4291,25 @@ static void cgroup_exit_cftypes(struct cftype *cfts)
cft->ss = NULL;
/* revert flags set by cgroup core while adding @cfts */
- cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL);
+ cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL |
+ __CFTYPE_ADDED);
}
}
static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
struct cftype *cft;
+ int ret = 0;
for (cft = cfts; cft->name[0] != '\0'; cft++) {
struct kernfs_ops *kf_ops;
WARN_ON(cft->ss || cft->kf_ops);
- if ((cft->flags & CFTYPE_PRESSURE) && !cgroup_psi_enabled())
- continue;
+ if (cft->flags & __CFTYPE_ADDED) {
+ ret = -EBUSY;
+ break;
+ }
if (cft->seq_start)
kf_ops = &cgroup_kf_ops;
@@ -4226,26 +4323,26 @@ static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
if (!kf_ops) {
- cgroup_exit_cftypes(cfts);
- return -ENOMEM;
+ ret = -ENOMEM;
+ break;
}
kf_ops->atomic_write_len = cft->max_write_len;
}
cft->kf_ops = kf_ops;
cft->ss = ss;
+ cft->flags |= __CFTYPE_ADDED;
}
- return 0;
+ if (ret)
+ cgroup_exit_cftypes(cfts);
+ return ret;
}
static int cgroup_rm_cftypes_locked(struct cftype *cfts)
{
lockdep_assert_held(&cgroup_mutex);
- if (!cfts || !cfts[0].ss)
- return -ENOENT;
-
list_del(&cfts->node);
cgroup_apply_cftypes(cfts, false);
cgroup_exit_cftypes(cfts);
@@ -4267,6 +4364,12 @@ int cgroup_rm_cftypes(struct cftype *cfts)
{
int ret;
+ if (!cfts || cfts[0].name[0] == '\0')
+ return 0;
+
+ if (!(cfts[0].flags & __CFTYPE_ADDED))
+ return -ENOENT;
+
mutex_lock(&cgroup_mutex);
ret = cgroup_rm_cftypes_locked(cfts);
mutex_unlock(&cgroup_mutex);
@@ -4372,6 +4475,26 @@ void cgroup_file_notify(struct cgroup_file *cfile)
}
/**
+ * cgroup_file_show - show or hide a hidden cgroup file
+ * @cfile: target cgroup_file obtained by setting cftype->file_offset
+ * @show: whether to show or hide
+ */
+void cgroup_file_show(struct cgroup_file *cfile, bool show)
+{
+ struct kernfs_node *kn;
+
+ spin_lock_irq(&cgroup_file_kn_lock);
+ kn = cfile->kn;
+ kernfs_get(kn);
+ spin_unlock_irq(&cgroup_file_kn_lock);
+
+ if (kn)
+ kernfs_show(kn, show);
+
+ kernfs_put(kn);
+}
+
+/**
* css_next_child - find the next child of a given css
* @pos: the current position (%NULL to initiate traversal)
* @parent: css whose children to walk
@@ -5131,10 +5254,14 @@ static struct cftype cgroup_base_files[] = {
.name = "cpu.stat",
.seq_show = cpu_stat_show,
},
+ { } /* terminate */
+};
+
+static struct cftype cgroup_psi_files[] = {
#ifdef CONFIG_PSI
{
.name = "io.pressure",
- .flags = CFTYPE_PRESSURE,
+ .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
.seq_show = cgroup_io_pressure_show,
.write = cgroup_io_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5142,7 +5269,7 @@ static struct cftype cgroup_base_files[] = {
},
{
.name = "memory.pressure",
- .flags = CFTYPE_PRESSURE,
+ .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
.seq_show = cgroup_memory_pressure_show,
.write = cgroup_memory_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5150,12 +5277,27 @@ static struct cftype cgroup_base_files[] = {
},
{
.name = "cpu.pressure",
- .flags = CFTYPE_PRESSURE,
+ .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
.seq_show = cgroup_cpu_pressure_show,
.write = cgroup_cpu_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
},
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ {
+ .name = "irq.pressure",
+ .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
+ .seq_show = cgroup_irq_pressure_show,
+ .write = cgroup_irq_pressure_write,
+ .poll = cgroup_pressure_poll,
+ .release = cgroup_pressure_release,
+ },
+#endif
+ {
+ .name = "cgroup.pressure",
+ .seq_show = cgroup_pressure_show,
+ .write = cgroup_pressure_write,
+ },
#endif /* CONFIG_PSI */
{ } /* terminate */
};
@@ -5432,8 +5574,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
int ret;
/* allocate the cgroup and its ID, 0 is reserved for the root */
- cgrp = kzalloc(struct_size(cgrp, ancestor_ids, (level + 1)),
- GFP_KERNEL);
+ cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL);
if (!cgrp)
return ERR_PTR(-ENOMEM);
@@ -5485,7 +5626,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
spin_lock_irq(&css_set_lock);
for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
- cgrp->ancestor_ids[tcgrp->level] = cgroup_id(tcgrp);
+ cgrp->ancestors[tcgrp->level] = tcgrp;
if (tcgrp != cgrp) {
tcgrp->nr_descendants++;
@@ -5918,6 +6059,7 @@ int __init cgroup_init(void)
BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
+ BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
cgroup_rstat_boot();
@@ -6038,19 +6180,22 @@ void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
/*
* cgroup_get_from_id : get the cgroup associated with cgroup id
* @id: cgroup id
- * On success return the cgrp, on failure return NULL
+ * On success return the cgrp or ERR_PTR on failure
+ * Only cgroups within current task's cgroup NS are valid.
*/
struct cgroup *cgroup_get_from_id(u64 id)
{
struct kernfs_node *kn;
- struct cgroup *cgrp = NULL;
+ struct cgroup *cgrp, *root_cgrp;
kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id);
if (!kn)
- goto out;
+ return ERR_PTR(-ENOENT);
- if (kernfs_type(kn) != KERNFS_DIR)
- goto put;
+ if (kernfs_type(kn) != KERNFS_DIR) {
+ kernfs_put(kn);
+ return ERR_PTR(-ENOENT);
+ }
rcu_read_lock();
@@ -6059,9 +6204,17 @@ struct cgroup *cgroup_get_from_id(u64 id)
cgrp = NULL;
rcu_read_unlock();
-put:
kernfs_put(kn);
-out:
+
+ if (!cgrp)
+ return ERR_PTR(-ENOENT);
+
+ root_cgrp = current_cgns_cgroup_dfl();
+ if (!cgroup_is_descendant(cgrp, root_cgrp)) {
+ cgroup_put(cgrp);
+ return ERR_PTR(-ENOENT);
+ }
+
return cgrp;
}
EXPORT_SYMBOL_GPL(cgroup_get_from_id);
@@ -6091,7 +6244,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
struct cgroup *cgrp;
int ssid, count = 0;
- if (root == &cgrp_dfl_root && !cgrp_dfl_visible)
+ if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible))
continue;
seq_printf(m, "%d:", root->hierarchy_id);
@@ -6157,16 +6310,42 @@ void cgroup_fork(struct task_struct *child)
INIT_LIST_HEAD(&child->cg_list);
}
-static struct cgroup *cgroup_get_from_file(struct file *f)
+/**
+ * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer
+ * @f: file corresponding to cgroup_dir
+ *
+ * Find the cgroup from a file pointer associated with a cgroup directory.
+ * Returns a pointer to the cgroup on success. ERR_PTR is returned if the
+ * cgroup cannot be found.
+ */
+static struct cgroup *cgroup_v1v2_get_from_file(struct file *f)
{
struct cgroup_subsys_state *css;
- struct cgroup *cgrp;
css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
if (IS_ERR(css))
return ERR_CAST(css);
- cgrp = css->cgroup;
+ return css->cgroup;
+}
+
+/**
+ * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports
+ * cgroup2.
+ * @f: file corresponding to cgroup2_dir
+ */
+static struct cgroup *cgroup_get_from_file(struct file *f)
+{
+ struct cgroup *cgrp = cgroup_v1v2_get_from_file(f);
+
+ if (IS_ERR(cgrp))
+ return ERR_CAST(cgrp);
+
+ if (!cgroup_on_dfl(cgrp)) {
+ cgroup_put(cgrp);
+ return ERR_PTR(-EBADF);
+ }
+
return cgrp;
}
@@ -6633,8 +6812,10 @@ struct cgroup *cgroup_get_from_path(const char *path)
{
struct kernfs_node *kn;
struct cgroup *cgrp = ERR_PTR(-ENOENT);
+ struct cgroup *root_cgrp;
- kn = kernfs_walk_and_get(cgrp_dfl_root.cgrp.kn, path);
+ root_cgrp = current_cgns_cgroup_dfl();
+ kn = kernfs_walk_and_get(root_cgrp->kn, path);
if (!kn)
goto out;
@@ -6659,15 +6840,15 @@ out:
EXPORT_SYMBOL_GPL(cgroup_get_from_path);
/**
- * cgroup_get_from_fd - get a cgroup pointer from a fd
- * @fd: fd obtained by open(cgroup2_dir)
+ * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd
+ * @fd: fd obtained by open(cgroup_dir)
*
* Find the cgroup from a fd which should be obtained
* by opening a cgroup directory. Returns a pointer to the
* cgroup on success. ERR_PTR is returned if the cgroup
* cannot be found.
*/
-struct cgroup *cgroup_get_from_fd(int fd)
+struct cgroup *cgroup_v1v2_get_from_fd(int fd)
{
struct cgroup *cgrp;
struct file *f;
@@ -6676,10 +6857,29 @@ struct cgroup *cgroup_get_from_fd(int fd)
if (!f)
return ERR_PTR(-EBADF);
- cgrp = cgroup_get_from_file(f);
+ cgrp = cgroup_v1v2_get_from_file(f);
fput(f);
return cgrp;
}
+
+/**
+ * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports
+ * cgroup2.
+ * @fd: fd obtained by open(cgroup2_dir)
+ */
+struct cgroup *cgroup_get_from_fd(int fd)
+{
+ struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd);
+
+ if (IS_ERR(cgrp))
+ return ERR_CAST(cgrp);
+
+ if (!cgroup_on_dfl(cgrp)) {
+ cgroup_put(cgrp);
+ return ERR_PTR(-EBADF);
+ }
+ return cgrp;
+}
EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
static u64 power_of_ten(int power)
@@ -6792,9 +6992,6 @@ static ssize_t show_delegatable_files(struct cftype *files, char *buf,
if (!(cft->flags & CFTYPE_NS_DELEGATABLE))
continue;
- if ((cft->flags & CFTYPE_PRESSURE) && !cgroup_psi_enabled())
- continue;
-
if (prefix)
ret += snprintf(buf + ret, size - ret, "%s.", prefix);
@@ -6814,8 +7011,11 @@ static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr,
int ssid;
ssize_t ret = 0;
- ret = show_delegatable_files(cgroup_base_files, buf, PAGE_SIZE - ret,
- NULL);
+ ret = show_delegatable_files(cgroup_base_files, buf + ret,
+ PAGE_SIZE - ret, NULL);
+ if (cgroup_psi_enabled())
+ ret += show_delegatable_files(cgroup_psi_files, buf + ret,
+ PAGE_SIZE - ret, NULL);
for_each_subsys(ss, ssid)
ret += show_delegatable_files(ss->dfl_cftypes, buf + ret,
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 1f3a55297f39..b474289c15b8 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -33,6 +33,7 @@
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
+#include <linux/kthread.h>
#include <linux/list.h>
#include <linux/mempolicy.h>
#include <linux/mm.h>
@@ -85,6 +86,30 @@ struct fmeter {
spinlock_t lock; /* guards read or write of above */
};
+/*
+ * Invalid partition error code
+ */
+enum prs_errcode {
+ PERR_NONE = 0,
+ PERR_INVCPUS,
+ PERR_INVPARENT,
+ PERR_NOTPART,
+ PERR_NOTEXCL,
+ PERR_NOCPUS,
+ PERR_HOTPLUG,
+ PERR_CPUSEMPTY,
+};
+
+static const char * const perr_strings[] = {
+ [PERR_INVCPUS] = "Invalid cpu list in cpuset.cpus",
+ [PERR_INVPARENT] = "Parent is an invalid partition root",
+ [PERR_NOTPART] = "Parent is not a partition root",
+ [PERR_NOTEXCL] = "Cpu list in cpuset.cpus not exclusive",
+ [PERR_NOCPUS] = "Parent unable to distribute cpu downstream",
+ [PERR_HOTPLUG] = "No cpu available due to hotplug",
+ [PERR_CPUSEMPTY] = "cpuset.cpus is empty",
+};
+
struct cpuset {
struct cgroup_subsys_state css;
@@ -168,6 +193,9 @@ struct cpuset {
int use_parent_ecpus;
int child_ecpus_count;
+ /* Invalid partition error code, not lock protected */
+ enum prs_errcode prs_err;
+
/* Handle for cpuset.cpus.partition */
struct cgroup_file partition_file;
};
@@ -175,20 +203,22 @@ struct cpuset {
/*
* Partition root states:
*
- * 0 - not a partition root
- *
+ * 0 - member (not a partition root)
* 1 - partition root
- *
+ * 2 - partition root without load balancing (isolated)
* -1 - invalid partition root
- * None of the cpus in cpus_allowed can be put into the parent's
- * subparts_cpus. In this case, the cpuset is not a real partition
- * root anymore. However, the CPU_EXCLUSIVE bit will still be set
- * and the cpuset can be restored back to a partition root if the
- * parent cpuset can give more CPUs back to this child cpuset.
+ * -2 - invalid isolated partition root
*/
-#define PRS_DISABLED 0
-#define PRS_ENABLED 1
-#define PRS_ERROR -1
+#define PRS_MEMBER 0
+#define PRS_ROOT 1
+#define PRS_ISOLATED 2
+#define PRS_INVALID_ROOT -1
+#define PRS_INVALID_ISOLATED -2
+
+static inline bool is_prs_invalid(int prs_state)
+{
+ return prs_state < 0;
+}
/*
* Temporary cpumasks for working with partitions that are passed among
@@ -268,25 +298,43 @@ static inline int is_spread_slab(const struct cpuset *cs)
return test_bit(CS_SPREAD_SLAB, &cs->flags);
}
-static inline int is_partition_root(const struct cpuset *cs)
+static inline int is_partition_valid(const struct cpuset *cs)
{
return cs->partition_root_state > 0;
}
+static inline int is_partition_invalid(const struct cpuset *cs)
+{
+ return cs->partition_root_state < 0;
+}
+
+/*
+ * Callers should hold callback_lock to modify partition_root_state.
+ */
+static inline void make_partition_invalid(struct cpuset *cs)
+{
+ if (is_partition_valid(cs))
+ cs->partition_root_state = -cs->partition_root_state;
+}
+
/*
* Send notification event of whenever partition_root_state changes.
*/
-static inline void notify_partition_change(struct cpuset *cs,
- int old_prs, int new_prs)
+static inline void notify_partition_change(struct cpuset *cs, int old_prs)
{
- if (old_prs != new_prs)
- cgroup_file_notify(&cs->partition_file);
+ if (old_prs == cs->partition_root_state)
+ return;
+ cgroup_file_notify(&cs->partition_file);
+
+ /* Reset prs_err if not invalid */
+ if (is_partition_valid(cs))
+ WRITE_ONCE(cs->prs_err, PERR_NONE);
}
static struct cpuset top_cpuset = {
.flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) |
(1 << CS_MEM_EXCLUSIVE)),
- .partition_root_state = PRS_ENABLED,
+ .partition_root_state = PRS_ROOT,
};
/**
@@ -404,6 +452,41 @@ static inline bool is_in_v2_mode(void)
(cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
}
+/**
+ * partition_is_populated - check if partition has tasks
+ * @cs: partition root to be checked
+ * @excluded_child: a child cpuset to be excluded in task checking
+ * Return: true if there are tasks, false otherwise
+ *
+ * It is assumed that @cs is a valid partition root. @excluded_child should
+ * be non-NULL when this cpuset is going to become a partition itself.
+ */
+static inline bool partition_is_populated(struct cpuset *cs,
+ struct cpuset *excluded_child)
+{
+ struct cgroup_subsys_state *css;
+ struct cpuset *child;
+
+ if (cs->css.cgroup->nr_populated_csets)
+ return true;
+ if (!excluded_child && !cs->nr_subparts_cpus)
+ return cgroup_is_populated(cs->css.cgroup);
+
+ rcu_read_lock();
+ cpuset_for_each_child(child, css, cs) {
+ if (child == excluded_child)
+ continue;
+ if (is_partition_valid(child))
+ continue;
+ if (cgroup_is_populated(child->css.cgroup)) {
+ rcu_read_unlock();
+ return true;
+ }
+ }
+ rcu_read_unlock();
+ return false;
+}
+
/*
* Return in pmask the portion of a task's cpusets's cpus_allowed that
* are online and are capable of running the task. If none are found,
@@ -659,22 +742,6 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
par = parent_cs(cur);
/*
- * If either I or some sibling (!= me) is exclusive, we can't
- * overlap
- */
- ret = -EINVAL;
- cpuset_for_each_child(c, css, par) {
- if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
- c != cur &&
- cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
- goto out;
- if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
- c != cur &&
- nodes_intersects(trial->mems_allowed, c->mems_allowed))
- goto out;
- }
-
- /*
* Cpusets with tasks - existing or newly being attached - can't
* be changed to have empty cpus_allowed or mems_allowed.
*/
@@ -698,6 +765,22 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
trial->cpus_allowed))
goto out;
+ /*
+ * If either I or some sibling (!= me) is exclusive, we can't
+ * overlap
+ */
+ ret = -EINVAL;
+ cpuset_for_each_child(c, css, par) {
+ if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
+ c != cur &&
+ cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
+ goto out;
+ if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
+ c != cur &&
+ nodes_intersects(trial->mems_allowed, c->mems_allowed))
+ goto out;
+ }
+
ret = 0;
out:
rcu_read_unlock();
@@ -875,7 +958,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
csa[csn++] = cp;
/* skip @cp's subtree if not a partition root */
- if (!is_partition_root(cp))
+ if (!is_partition_valid(cp))
pos_css = css_rightmost_descendant(pos_css);
}
rcu_read_unlock();
@@ -1081,7 +1164,7 @@ static void rebuild_sched_domains_locked(void)
if (top_cpuset.nr_subparts_cpus) {
rcu_read_lock();
cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
- if (!is_partition_root(cs)) {
+ if (!is_partition_valid(cs)) {
pos_css = css_rightmost_descendant(pos_css);
continue;
}
@@ -1127,10 +1210,18 @@ static void update_tasks_cpumask(struct cpuset *cs)
{
struct css_task_iter it;
struct task_struct *task;
+ bool top_cs = cs == &top_cpuset;
css_task_iter_start(&cs->css, 0, &it);
- while ((task = css_task_iter_next(&it)))
+ while ((task = css_task_iter_next(&it))) {
+ /*
+ * Percpu kthreads in top_cpuset are ignored
+ */
+ if (top_cs && (task->flags & PF_KTHREAD) &&
+ kthread_is_per_cpu(task))
+ continue;
set_cpus_allowed_ptr(task, cs->effective_cpus);
+ }
css_task_iter_end(&it);
}
@@ -1165,15 +1256,18 @@ enum subparts_cmd {
partcmd_enable, /* Enable partition root */
partcmd_disable, /* Disable partition root */
partcmd_update, /* Update parent's subparts_cpus */
+ partcmd_invalidate, /* Make partition invalid */
};
+static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
+ int turning_on);
/**
* update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset
* @cpuset: The cpuset that requests change in partition root state
* @cmd: Partition root state change command
* @newmask: Optional new cpumask for partcmd_update
* @tmp: Temporary addmask and delmask
- * Return: 0, 1 or an error code
+ * Return: 0 or a partition root state error code
*
* For partcmd_enable, the cpuset is being transformed from a non-partition
* root to a partition root. The cpus_allowed mask of the given cpuset will
@@ -1184,38 +1278,36 @@ enum subparts_cmd {
* For partcmd_disable, the cpuset is being transformed from a partition
* root back to a non-partition root. Any CPUs in cpus_allowed that are in
* parent's subparts_cpus will be taken away from that cpumask and put back
- * into parent's effective_cpus. 0 should always be returned.
- *
- * For partcmd_update, if the optional newmask is specified, the cpu
- * list is to be changed from cpus_allowed to newmask. Otherwise,
- * cpus_allowed is assumed to remain the same. The cpuset should either
- * be a partition root or an invalid partition root. The partition root
- * state may change if newmask is NULL and none of the requested CPUs can
- * be granted by the parent. The function will return 1 if changes to
- * parent's subparts_cpus and effective_cpus happen or 0 otherwise.
- * Error code should only be returned when newmask is non-NULL.
+ * into parent's effective_cpus. 0 will always be returned.
*
- * The partcmd_enable and partcmd_disable commands are used by
- * update_prstate(). The partcmd_update command is used by
- * update_cpumasks_hier() with newmask NULL and update_cpumask() with
- * newmask set.
+ * For partcmd_update, if the optional newmask is specified, the cpu list is
+ * to be changed from cpus_allowed to newmask. Otherwise, cpus_allowed is
+ * assumed to remain the same. The cpuset should either be a valid or invalid
+ * partition root. The partition root state may change from valid to invalid
+ * or vice versa. An error code will only be returned if transitioning from
+ * invalid to valid violates the exclusivity rule.
*
- * The checking is more strict when enabling partition root than the
- * other two commands.
+ * For partcmd_invalidate, the current partition will be made invalid.
*
- * Because of the implicit cpu exclusive nature of a partition root,
- * cpumask changes that violates the cpu exclusivity rule will not be
- * permitted when checked by validate_change().
+ * The partcmd_enable and partcmd_disable commands are used by
+ * update_prstate(). An error code may be returned and the caller will check
+ * for error.
+ *
+ * The partcmd_update command is used by update_cpumasks_hier() with newmask
+ * NULL and update_cpumask() with newmask set. The partcmd_invalidate is used
+ * by update_cpumask() with NULL newmask. In both cases, the callers won't
+ * check for error and so partition_root_state and prs_error will be updated
+ * directly.
*/
-static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
+static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
struct cpumask *newmask,
struct tmpmasks *tmp)
{
- struct cpuset *parent = parent_cs(cpuset);
+ struct cpuset *parent = parent_cs(cs);
int adding; /* Moving cpus from effective_cpus to subparts_cpus */
int deleting; /* Moving cpus from subparts_cpus to effective_cpus */
int old_prs, new_prs;
- bool part_error = false; /* Partition error? */
+ int part_error = PERR_NONE; /* Partition error? */
percpu_rwsem_assert_held(&cpuset_rwsem);
@@ -1224,126 +1316,165 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
* The new cpumask, if present, or the current cpus_allowed must
* not be empty.
*/
- if (!is_partition_root(parent) ||
- (newmask && cpumask_empty(newmask)) ||
- (!newmask && cpumask_empty(cpuset->cpus_allowed)))
- return -EINVAL;
-
- /*
- * Enabling/disabling partition root is not allowed if there are
- * online children.
- */
- if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css))
- return -EBUSY;
-
- /*
- * Enabling partition root is not allowed if not all the CPUs
- * can be granted from parent's effective_cpus or at least one
- * CPU will be left after that.
- */
- if ((cmd == partcmd_enable) &&
- (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) ||
- cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus)))
- return -EINVAL;
+ if (!is_partition_valid(parent)) {
+ return is_partition_invalid(parent)
+ ? PERR_INVPARENT : PERR_NOTPART;
+ }
+ if ((newmask && cpumask_empty(newmask)) ||
+ (!newmask && cpumask_empty(cs->cpus_allowed)))
+ return PERR_CPUSEMPTY;
/*
- * A cpumask update cannot make parent's effective_cpus become empty.
+ * new_prs will only be changed for the partcmd_update and
+ * partcmd_invalidate commands.
*/
adding = deleting = false;
- old_prs = new_prs = cpuset->partition_root_state;
+ old_prs = new_prs = cs->partition_root_state;
if (cmd == partcmd_enable) {
- cpumask_copy(tmp->addmask, cpuset->cpus_allowed);
+ /*
+ * Enabling partition root is not allowed if cpus_allowed
+ * doesn't overlap parent's cpus_allowed.
+ */
+ if (!cpumask_intersects(cs->cpus_allowed, parent->cpus_allowed))
+ return PERR_INVCPUS;
+
+ /*
+ * A parent can be left with no CPU as long as there is no
+ * task directly associated with the parent partition.
+ */
+ if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) &&
+ partition_is_populated(parent, cs))
+ return PERR_NOCPUS;
+
+ cpumask_copy(tmp->addmask, cs->cpus_allowed);
adding = true;
} else if (cmd == partcmd_disable) {
- deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed,
+ /*
+ * Need to remove cpus from parent's subparts_cpus for valid
+ * partition root.
+ */
+ deleting = !is_prs_invalid(old_prs) &&
+ cpumask_and(tmp->delmask, cs->cpus_allowed,
+ parent->subparts_cpus);
+ } else if (cmd == partcmd_invalidate) {
+ if (is_prs_invalid(old_prs))
+ return 0;
+
+ /*
+ * Make the current partition invalid. It is assumed that
+ * invalidation is caused by violating cpu exclusivity rule.
+ */
+ deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
parent->subparts_cpus);
+ if (old_prs > 0) {
+ new_prs = -old_prs;
+ part_error = PERR_NOTEXCL;
+ }
} else if (newmask) {
/*
* partcmd_update with newmask:
*
+ * Compute add/delete mask to/from subparts_cpus
+ *
* delmask = cpus_allowed & ~newmask & parent->subparts_cpus
- * addmask = newmask & parent->effective_cpus
+ * addmask = newmask & parent->cpus_allowed
* & ~parent->subparts_cpus
*/
- cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask);
+ cpumask_andnot(tmp->delmask, cs->cpus_allowed, newmask);
deleting = cpumask_and(tmp->delmask, tmp->delmask,
parent->subparts_cpus);
- cpumask_and(tmp->addmask, newmask, parent->effective_cpus);
+ cpumask_and(tmp->addmask, newmask, parent->cpus_allowed);
adding = cpumask_andnot(tmp->addmask, tmp->addmask,
parent->subparts_cpus);
/*
- * Return error if the new effective_cpus could become empty.
+ * Make partition invalid if parent's effective_cpus could
+ * become empty and there are tasks in the parent.
*/
if (adding &&
- cpumask_equal(parent->effective_cpus, tmp->addmask)) {
- if (!deleting)
- return -EINVAL;
- /*
- * As some of the CPUs in subparts_cpus might have
- * been offlined, we need to compute the real delmask
- * to confirm that.
- */
- if (!cpumask_and(tmp->addmask, tmp->delmask,
- cpu_active_mask))
- return -EINVAL;
- cpumask_copy(tmp->addmask, parent->effective_cpus);
+ cpumask_subset(parent->effective_cpus, tmp->addmask) &&
+ !cpumask_intersects(tmp->delmask, cpu_active_mask) &&
+ partition_is_populated(parent, cs)) {
+ part_error = PERR_NOCPUS;
+ adding = false;
+ deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
+ parent->subparts_cpus);
}
} else {
/*
* partcmd_update w/o newmask:
*
- * addmask = cpus_allowed & parent->effective_cpus
+ * delmask = cpus_allowed & parent->subparts_cpus
+ * addmask = cpus_allowed & parent->cpus_allowed
+ * & ~parent->subparts_cpus
*
- * Note that parent's subparts_cpus may have been
- * pre-shrunk in case there is a change in the cpu list.
- * So no deletion is needed.
+ * This gets invoked either due to a hotplug event or from
+ * update_cpumasks_hier(). This can cause the state of a
+ * partition root to transition from valid to invalid or vice
+ * versa. So we still need to compute the addmask and delmask.
+
+ * A partition error happens when:
+ * 1) Cpuset is valid partition, but parent does not distribute
+ * out any CPUs.
+ * 2) Parent has tasks and all its effective CPUs will have
+ * to be distributed out.
*/
- adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed,
- parent->effective_cpus);
- part_error = cpumask_equal(tmp->addmask,
- parent->effective_cpus);
+ cpumask_and(tmp->addmask, cs->cpus_allowed,
+ parent->cpus_allowed);
+ adding = cpumask_andnot(tmp->addmask, tmp->addmask,
+ parent->subparts_cpus);
+
+ if ((is_partition_valid(cs) && !parent->nr_subparts_cpus) ||
+ (adding &&
+ cpumask_subset(parent->effective_cpus, tmp->addmask) &&
+ partition_is_populated(parent, cs))) {
+ part_error = PERR_NOCPUS;
+ adding = false;
+ }
+
+ if (part_error && is_partition_valid(cs) &&
+ parent->nr_subparts_cpus)
+ deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
+ parent->subparts_cpus);
}
+ if (part_error)
+ WRITE_ONCE(cs->prs_err, part_error);
if (cmd == partcmd_update) {
- int prev_prs = cpuset->partition_root_state;
-
/*
- * Check for possible transition between PRS_ENABLED
- * and PRS_ERROR.
+ * Check for possible transition between valid and invalid
+ * partition root.
*/
- switch (cpuset->partition_root_state) {
- case PRS_ENABLED:
+ switch (cs->partition_root_state) {
+ case PRS_ROOT:
+ case PRS_ISOLATED:
if (part_error)
- new_prs = PRS_ERROR;
+ new_prs = -old_prs;
break;
- case PRS_ERROR:
+ case PRS_INVALID_ROOT:
+ case PRS_INVALID_ISOLATED:
if (!part_error)
- new_prs = PRS_ENABLED;
+ new_prs = -old_prs;
break;
}
- /*
- * Set part_error if previously in invalid state.
- */
- part_error = (prev_prs == PRS_ERROR);
- }
-
- if (!part_error && (new_prs == PRS_ERROR))
- return 0; /* Nothing need to be done */
-
- if (new_prs == PRS_ERROR) {
- /*
- * Remove all its cpus from parent's subparts_cpus.
- */
- adding = false;
- deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed,
- parent->subparts_cpus);
}
if (!adding && !deleting && (new_prs == old_prs))
return 0;
/*
+ * Transitioning between invalid to valid or vice versa may require
+ * changing CS_CPU_EXCLUSIVE and CS_SCHED_LOAD_BALANCE.
+ */
+ if (old_prs != new_prs) {
+ if (is_prs_invalid(old_prs) && !is_cpu_exclusive(cs) &&
+ (update_flag(CS_CPU_EXCLUSIVE, cs, 1) < 0))
+ return PERR_NOTEXCL;
+ if (is_prs_invalid(new_prs) && is_cpu_exclusive(cs))
+ update_flag(CS_CPU_EXCLUSIVE, cs, 0);
+ }
+
+ /*
* Change the parent's subparts_cpus.
* Newly added CPUs will be removed from effective_cpus and
* newly deleted ones will be added back to effective_cpus.
@@ -1369,18 +1500,32 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);
if (old_prs != new_prs)
- cpuset->partition_root_state = new_prs;
+ cs->partition_root_state = new_prs;
spin_unlock_irq(&callback_lock);
- notify_partition_change(cpuset, old_prs, new_prs);
- return cmd == partcmd_update;
+ if (adding || deleting)
+ update_tasks_cpumask(parent);
+
+ /*
+ * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
+ * rebuild_sched_domains_locked() may be called.
+ */
+ if (old_prs != new_prs) {
+ if (old_prs == PRS_ISOLATED)
+ update_flag(CS_SCHED_LOAD_BALANCE, cs, 1);
+ else if (new_prs == PRS_ISOLATED)
+ update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
+ }
+ notify_partition_change(cs, old_prs);
+ return 0;
}
/*
* update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
* @cs: the cpuset to consider
* @tmp: temp variables for calculating effective_cpus & partition setup
+ * @force: don't skip any descendant cpusets if set
*
* When configured cpumask is changed, the effective cpumasks of this cpuset
* and all its descendants need to be updated.
@@ -1389,7 +1534,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
*
* Called with cpuset_rwsem held
*/
-static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
+static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
+ bool force)
{
struct cpuset *cp;
struct cgroup_subsys_state *pos_css;
@@ -1399,14 +1545,21 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
rcu_read_lock();
cpuset_for_each_descendant_pre(cp, pos_css, cs) {
struct cpuset *parent = parent_cs(cp);
+ bool update_parent = false;
compute_effective_cpumask(tmp->new_cpus, cp, parent);
/*
* If it becomes empty, inherit the effective mask of the
- * parent, which is guaranteed to have some CPUs.
+ * parent, which is guaranteed to have some CPUs unless
+ * it is a partition root that has explicitly distributed
+ * out all its CPUs.
*/
if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) {
+ if (is_partition_valid(cp) &&
+ cpumask_equal(cp->cpus_allowed, cp->subparts_cpus))
+ goto update_parent_subparts;
+
cpumask_copy(tmp->new_cpus, parent->effective_cpus);
if (!cp->use_parent_ecpus) {
cp->use_parent_ecpus = true;
@@ -1420,14 +1573,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
/*
* Skip the whole subtree if the cpumask remains the same
- * and has no partition root state.
+ * and has no partition root state and force flag not set.
*/
- if (!cp->partition_root_state &&
+ if (!cp->partition_root_state && !force &&
cpumask_equal(tmp->new_cpus, cp->effective_cpus)) {
pos_css = css_rightmost_descendant(pos_css);
continue;
}
+update_parent_subparts:
/*
* update_parent_subparts_cpumask() should have been called
* for cs already in update_cpumask(). We should also call
@@ -1437,36 +1591,22 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
old_prs = new_prs = cp->partition_root_state;
if ((cp != cs) && old_prs) {
switch (parent->partition_root_state) {
- case PRS_DISABLED:
- /*
- * If parent is not a partition root or an
- * invalid partition root, clear its state
- * and its CS_CPU_EXCLUSIVE flag.
- */
- WARN_ON_ONCE(cp->partition_root_state
- != PRS_ERROR);
- new_prs = PRS_DISABLED;
-
- /*
- * clear_bit() is an atomic operation and
- * readers aren't interested in the state
- * of CS_CPU_EXCLUSIVE anyway. So we can
- * just update the flag without holding
- * the callback_lock.
- */
- clear_bit(CS_CPU_EXCLUSIVE, &cp->flags);
+ case PRS_ROOT:
+ case PRS_ISOLATED:
+ update_parent = true;
break;
- case PRS_ENABLED:
- if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp))
- update_tasks_cpumask(parent);
- break;
-
- case PRS_ERROR:
+ default:
/*
- * When parent is invalid, it has to be too.
+ * When parent is not a partition root or is
+ * invalid, child partition roots become
+ * invalid too.
*/
- new_prs = PRS_ERROR;
+ if (is_partition_valid(cp))
+ new_prs = -cp->partition_root_state;
+ WRITE_ONCE(cp->prs_err,
+ is_partition_invalid(parent)
+ ? PERR_INVPARENT : PERR_NOTPART);
break;
}
}
@@ -1475,42 +1615,44 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
continue;
rcu_read_unlock();
+ if (update_parent) {
+ update_parent_subparts_cpumask(cp, partcmd_update, NULL,
+ tmp);
+ /*
+ * The cpuset partition_root_state may become
+ * invalid. Capture it.
+ */
+ new_prs = cp->partition_root_state;
+ }
+
spin_lock_irq(&callback_lock);
- cpumask_copy(cp->effective_cpus, tmp->new_cpus);
- if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) {
+ if (cp->nr_subparts_cpus && !is_partition_valid(cp)) {
+ /*
+ * Put all active subparts_cpus back to effective_cpus.
+ */
+ cpumask_or(tmp->new_cpus, tmp->new_cpus,
+ cp->subparts_cpus);
+ cpumask_and(tmp->new_cpus, tmp->new_cpus,
+ cpu_active_mask);
cp->nr_subparts_cpus = 0;
cpumask_clear(cp->subparts_cpus);
- } else if (cp->nr_subparts_cpus) {
+ }
+
+ cpumask_copy(cp->effective_cpus, tmp->new_cpus);
+ if (cp->nr_subparts_cpus) {
/*
* Make sure that effective_cpus & subparts_cpus
* are mutually exclusive.
- *
- * In the unlikely event that effective_cpus
- * becomes empty. we clear cp->nr_subparts_cpus and
- * let its child partition roots to compete for
- * CPUs again.
*/
cpumask_andnot(cp->effective_cpus, cp->effective_cpus,
cp->subparts_cpus);
- if (cpumask_empty(cp->effective_cpus)) {
- cpumask_copy(cp->effective_cpus, tmp->new_cpus);
- cpumask_clear(cp->subparts_cpus);
- cp->nr_subparts_cpus = 0;
- } else if (!cpumask_subset(cp->subparts_cpus,
- tmp->new_cpus)) {
- cpumask_andnot(cp->subparts_cpus,
- cp->subparts_cpus, tmp->new_cpus);
- cp->nr_subparts_cpus
- = cpumask_weight(cp->subparts_cpus);
- }
}
- if (new_prs != old_prs)
- cp->partition_root_state = new_prs;
-
+ cp->partition_root_state = new_prs;
spin_unlock_irq(&callback_lock);
- notify_partition_change(cp, old_prs, new_prs);
+
+ notify_partition_change(cp, old_prs);
WARN_ON(!is_in_v2_mode() &&
!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
@@ -1526,7 +1668,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
if (!cpumask_empty(cp->cpus_allowed) &&
is_sched_load_balance(cp) &&
(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
- is_partition_root(cp)))
+ is_partition_valid(cp)))
need_rebuild_sched_domains = true;
rcu_read_lock();
@@ -1570,7 +1712,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
continue;
rcu_read_unlock();
- update_cpumasks_hier(sibling, tmp);
+ update_cpumasks_hier(sibling, tmp, false);
rcu_read_lock();
css_put(&sibling->css);
}
@@ -1588,6 +1730,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
{
int retval;
struct tmpmasks tmp;
+ bool invalidate = false;
/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
if (cs == &top_cpuset)
@@ -1615,10 +1758,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
return 0;
- retval = validate_change(cs, trialcs);
- if (retval < 0)
- return retval;
-
#ifdef CONFIG_CPUMASK_OFFSTACK
/*
* Use the cpumasks in trialcs for tmpmasks when they are pointers
@@ -1629,28 +1768,70 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
tmp.new_cpus = trialcs->cpus_allowed;
#endif
+ retval = validate_change(cs, trialcs);
+
+ if ((retval == -EINVAL) && cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
+ struct cpuset *cp, *parent;
+ struct cgroup_subsys_state *css;
+
+ /*
+ * The -EINVAL error code indicates that partition sibling
+ * CPU exclusivity rule has been violated. We still allow
+ * the cpumask change to proceed while invalidating the
+ * partition. However, any conflicting sibling partitions
+ * have to be marked as invalid too.
+ */
+ invalidate = true;
+ rcu_read_lock();
+ parent = parent_cs(cs);
+ cpuset_for_each_child(cp, css, parent)
+ if (is_partition_valid(cp) &&
+ cpumask_intersects(trialcs->cpus_allowed, cp->cpus_allowed)) {
+ rcu_read_unlock();
+ update_parent_subparts_cpumask(cp, partcmd_invalidate, NULL, &tmp);
+ rcu_read_lock();
+ }
+ rcu_read_unlock();
+ retval = 0;
+ }
+ if (retval < 0)
+ return retval;
+
if (cs->partition_root_state) {
- /* Cpumask of a partition root cannot be empty */
- if (cpumask_empty(trialcs->cpus_allowed))
- return -EINVAL;
- if (update_parent_subparts_cpumask(cs, partcmd_update,
- trialcs->cpus_allowed, &tmp) < 0)
- return -EINVAL;
+ if (invalidate)
+ update_parent_subparts_cpumask(cs, partcmd_invalidate,
+ NULL, &tmp);
+ else
+ update_parent_subparts_cpumask(cs, partcmd_update,
+ trialcs->cpus_allowed, &tmp);
}
+ compute_effective_cpumask(trialcs->effective_cpus, trialcs,
+ parent_cs(cs));
spin_lock_irq(&callback_lock);
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
/*
- * Make sure that subparts_cpus is a subset of cpus_allowed.
+ * Make sure that subparts_cpus, if not empty, is a subset of
+ * cpus_allowed. Clear subparts_cpus if partition not valid or
+ * empty effective cpus with tasks.
*/
if (cs->nr_subparts_cpus) {
- cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed);
- cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
+ if (!is_partition_valid(cs) ||
+ (cpumask_subset(trialcs->effective_cpus, cs->subparts_cpus) &&
+ partition_is_populated(cs, NULL))) {
+ cs->nr_subparts_cpus = 0;
+ cpumask_clear(cs->subparts_cpus);
+ } else {
+ cpumask_and(cs->subparts_cpus, cs->subparts_cpus,
+ cs->cpus_allowed);
+ cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
+ }
}
spin_unlock_irq(&callback_lock);
- update_cpumasks_hier(cs, &tmp);
+ /* effective_cpus will be updated here */
+ update_cpumasks_hier(cs, &tmp, false);
if (cs->partition_root_state) {
struct cpuset *parent = parent_cs(cs);
@@ -2026,16 +2207,18 @@ out:
return err;
}
-/*
+/**
* update_prstate - update partition_root_state
- * cs: the cpuset to update
- * new_prs: new partition root state
+ * @cs: the cpuset to update
+ * @new_prs: new partition root state
+ * Return: 0 if successful, != 0 if error
*
* Call with cpuset_rwsem held.
*/
static int update_prstate(struct cpuset *cs, int new_prs)
{
- int err, old_prs = cs->partition_root_state;
+ int err = PERR_NONE, old_prs = cs->partition_root_state;
+ bool sched_domain_rebuilt = false;
struct cpuset *parent = parent_cs(cs);
struct tmpmasks tmpmask;
@@ -2043,28 +2226,33 @@ static int update_prstate(struct cpuset *cs, int new_prs)
return 0;
/*
- * Cannot force a partial or invalid partition root to a full
- * partition root.
+ * For a previously invalid partition root, leave it at being
+ * invalid if new_prs is not "member".
*/
- if (new_prs && (old_prs == PRS_ERROR))
- return -EINVAL;
+ if (new_prs && is_prs_invalid(old_prs)) {
+ cs->partition_root_state = -new_prs;
+ return 0;
+ }
if (alloc_cpumasks(NULL, &tmpmask))
return -ENOMEM;
- err = -EINVAL;
if (!old_prs) {
/*
* Turning on partition root requires setting the
* CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed
- * cannot be NULL.
+ * cannot be empty.
*/
- if (cpumask_empty(cs->cpus_allowed))
+ if (cpumask_empty(cs->cpus_allowed)) {
+ err = PERR_CPUSEMPTY;
goto out;
+ }
err = update_flag(CS_CPU_EXCLUSIVE, cs, 1);
- if (err)
+ if (err) {
+ err = PERR_NOTEXCL;
goto out;
+ }
err = update_parent_subparts_cpumask(cs, partcmd_enable,
NULL, &tmpmask);
@@ -2072,47 +2260,77 @@ static int update_prstate(struct cpuset *cs, int new_prs)
update_flag(CS_CPU_EXCLUSIVE, cs, 0);
goto out;
}
+
+ if (new_prs == PRS_ISOLATED) {
+ /*
+ * Disable the load balance flag should not return an
+ * error unless the system is running out of memory.
+ */
+ update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
+ sched_domain_rebuilt = true;
+ }
+ } else if (old_prs && new_prs) {
+ /*
+ * A change in load balance state only, no change in cpumasks.
+ */
+ update_flag(CS_SCHED_LOAD_BALANCE, cs, (new_prs != PRS_ISOLATED));
+ sched_domain_rebuilt = true;
+ goto out; /* Sched domain is rebuilt in update_flag() */
} else {
/*
- * Turning off partition root will clear the
- * CS_CPU_EXCLUSIVE bit.
+ * Switching back to member is always allowed even if it
+ * disables child partitions.
*/
- if (old_prs == PRS_ERROR) {
- update_flag(CS_CPU_EXCLUSIVE, cs, 0);
- err = 0;
- goto out;
- }
+ update_parent_subparts_cpumask(cs, partcmd_disable, NULL,
+ &tmpmask);
- err = update_parent_subparts_cpumask(cs, partcmd_disable,
- NULL, &tmpmask);
- if (err)
- goto out;
+ /*
+ * If there are child partitions, they will all become invalid.
+ */
+ if (unlikely(cs->nr_subparts_cpus)) {
+ spin_lock_irq(&callback_lock);
+ cs->nr_subparts_cpus = 0;
+ cpumask_clear(cs->subparts_cpus);
+ compute_effective_cpumask(cs->effective_cpus, cs, parent);
+ spin_unlock_irq(&callback_lock);
+ }
/* Turning off CS_CPU_EXCLUSIVE will not return error */
update_flag(CS_CPU_EXCLUSIVE, cs, 0);
+
+ if (!is_sched_load_balance(cs)) {
+ /* Make sure load balance is on */
+ update_flag(CS_SCHED_LOAD_BALANCE, cs, 1);
+ sched_domain_rebuilt = true;
+ }
}
- /*
- * Update cpumask of parent's tasks except when it is the top
- * cpuset as some system daemons cannot be mapped to other CPUs.
- */
- if (parent != &top_cpuset)
- update_tasks_cpumask(parent);
+ update_tasks_cpumask(parent);
if (parent->child_ecpus_count)
update_sibling_cpumasks(parent, cs, &tmpmask);
- rebuild_sched_domains_locked();
+ if (!sched_domain_rebuilt)
+ rebuild_sched_domains_locked();
out:
- if (!err) {
- spin_lock_irq(&callback_lock);
- cs->partition_root_state = new_prs;
- spin_unlock_irq(&callback_lock);
- notify_partition_change(cs, old_prs, new_prs);
- }
+ /*
+ * Make partition invalid if an error happen
+ */
+ if (err)
+ new_prs = -new_prs;
+ spin_lock_irq(&callback_lock);
+ cs->partition_root_state = new_prs;
+ spin_unlock_irq(&callback_lock);
+ /*
+ * Update child cpusets, if present.
+ * Force update if switching back to member.
+ */
+ if (!list_empty(&cs->css.children))
+ update_cpumasks_hier(cs, &tmpmask, !new_prs);
+ notify_partition_change(cs, old_prs);
free_cpumasks(NULL, &tmpmask);
- return err;
+ return 0;
}
/*
@@ -2238,6 +2456,12 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
(cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
goto out_unlock;
+ /*
+ * Task cannot be moved to a cpuset with empty effective cpus.
+ */
+ if (cpumask_empty(cs->effective_cpus))
+ goto out_unlock;
+
cgroup_taskset_for_each(task, css, tset) {
ret = task_can_attach(task, cs->effective_cpus);
if (ret)
@@ -2598,16 +2822,29 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
static int sched_partition_show(struct seq_file *seq, void *v)
{
struct cpuset *cs = css_cs(seq_css(seq));
+ const char *err, *type = NULL;
switch (cs->partition_root_state) {
- case PRS_ENABLED:
+ case PRS_ROOT:
seq_puts(seq, "root\n");
break;
- case PRS_DISABLED:
+ case PRS_ISOLATED:
+ seq_puts(seq, "isolated\n");
+ break;
+ case PRS_MEMBER:
seq_puts(seq, "member\n");
break;
- case PRS_ERROR:
- seq_puts(seq, "root invalid\n");
+ case PRS_INVALID_ROOT:
+ type = "root";
+ fallthrough;
+ case PRS_INVALID_ISOLATED:
+ if (!type)
+ type = "isolated";
+ err = perr_strings[READ_ONCE(cs->prs_err)];
+ if (err)
+ seq_printf(seq, "%s invalid (%s)\n", type, err);
+ else
+ seq_printf(seq, "%s invalid\n", type);
break;
}
return 0;
@@ -2626,9 +2863,11 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
* Convert "root" to ENABLED, and convert "member" to DISABLED.
*/
if (!strcmp(buf, "root"))
- val = PRS_ENABLED;
+ val = PRS_ROOT;
else if (!strcmp(buf, "member"))
- val = PRS_DISABLED;
+ val = PRS_MEMBER;
+ else if (!strcmp(buf, "isolated"))
+ val = PRS_ISOLATED;
else
return -EINVAL;
@@ -2927,7 +3166,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
cpus_read_lock();
percpu_down_write(&cpuset_rwsem);
- if (is_partition_root(cs))
+ if (is_partition_valid(cs))
update_prstate(cs, 0);
if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
@@ -3103,7 +3342,8 @@ hotplug_update_tasks(struct cpuset *cs,
struct cpumask *new_cpus, nodemask_t *new_mems,
bool cpus_updated, bool mems_updated)
{
- if (cpumask_empty(new_cpus))
+ /* A partition root is allowed to have empty effective cpus */
+ if (cpumask_empty(new_cpus) && !is_partition_valid(cs))
cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus);
if (nodes_empty(*new_mems))
*new_mems = parent_cs(cs)->effective_mems;
@@ -3172,11 +3412,31 @@ retry:
/*
* In the unlikely event that a partition root has empty
- * effective_cpus or its parent becomes erroneous, we have to
- * transition it to the erroneous state.
+ * effective_cpus with tasks, we will have to invalidate child
+ * partitions, if present, by setting nr_subparts_cpus to 0 to
+ * reclaim their cpus.
*/
- if (is_partition_root(cs) && (cpumask_empty(&new_cpus) ||
- (parent->partition_root_state == PRS_ERROR))) {
+ if (cs->nr_subparts_cpus && is_partition_valid(cs) &&
+ cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) {
+ spin_lock_irq(&callback_lock);
+ cs->nr_subparts_cpus = 0;
+ cpumask_clear(cs->subparts_cpus);
+ spin_unlock_irq(&callback_lock);
+ compute_effective_cpumask(&new_cpus, cs, parent);
+ }
+
+ /*
+ * Force the partition to become invalid if either one of
+ * the following conditions hold:
+ * 1) empty effective cpus but not valid empty partition.
+ * 2) parent is invalid or doesn't grant any cpus to child
+ * partitions.
+ */
+ if (is_partition_valid(cs) && (!parent->nr_subparts_cpus ||
+ (cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)))) {
+ int old_prs, parent_prs;
+
+ update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp);
if (cs->nr_subparts_cpus) {
spin_lock_irq(&callback_lock);
cs->nr_subparts_cpus = 0;
@@ -3185,39 +3445,32 @@ retry:
compute_effective_cpumask(&new_cpus, cs, parent);
}
- /*
- * If the effective_cpus is empty because the child
- * partitions take away all the CPUs, we can keep
- * the current partition and let the child partitions
- * fight for available CPUs.
- */
- if ((parent->partition_root_state == PRS_ERROR) ||
- cpumask_empty(&new_cpus)) {
- int old_prs;
-
- update_parent_subparts_cpumask(cs, partcmd_disable,
- NULL, tmp);
- old_prs = cs->partition_root_state;
- if (old_prs != PRS_ERROR) {
- spin_lock_irq(&callback_lock);
- cs->partition_root_state = PRS_ERROR;
- spin_unlock_irq(&callback_lock);
- notify_partition_change(cs, old_prs, PRS_ERROR);
- }
+ old_prs = cs->partition_root_state;
+ parent_prs = parent->partition_root_state;
+ if (is_partition_valid(cs)) {
+ spin_lock_irq(&callback_lock);
+ make_partition_invalid(cs);
+ spin_unlock_irq(&callback_lock);
+ if (is_prs_invalid(parent_prs))
+ WRITE_ONCE(cs->prs_err, PERR_INVPARENT);
+ else if (!parent_prs)
+ WRITE_ONCE(cs->prs_err, PERR_NOTPART);
+ else
+ WRITE_ONCE(cs->prs_err, PERR_HOTPLUG);
+ notify_partition_change(cs, old_prs);
}
cpuset_force_rebuild();
}
/*
- * On the other hand, an erroneous partition root may be transitioned
- * back to a regular one or a partition root with no CPU allocated
- * from the parent may change to erroneous.
+ * On the other hand, an invalid partition root may be transitioned
+ * back to a regular one.
*/
- if (is_partition_root(parent) &&
- ((cs->partition_root_state == PRS_ERROR) ||
- !cpumask_intersects(&new_cpus, parent->subparts_cpus)) &&
- update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp))
- cpuset_force_rebuild();
+ else if (is_partition_valid(parent) && is_partition_invalid(cs)) {
+ update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp);
+ if (is_partition_valid(cs))
+ cpuset_force_rebuild();
+ }
update_tasks:
cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 08236798d173..1b6b21851e9d 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -113,7 +113,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
if (parent && (parent->state & CGROUP_FREEZING)) {
freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN;
- atomic_inc(&system_freezing_cnt);
+ static_branch_inc(&freezer_active);
}
mutex_unlock(&freezer_mutex);
@@ -134,7 +134,7 @@ static void freezer_css_offline(struct cgroup_subsys_state *css)
mutex_lock(&freezer_mutex);
if (freezer->state & CGROUP_FREEZING)
- atomic_dec(&system_freezing_cnt);
+ static_branch_dec(&freezer_active);
freezer->state = 0;
@@ -179,6 +179,7 @@ static void freezer_attach(struct cgroup_taskset *tset)
__thaw_task(task);
} else {
freeze_task(task);
+
/* clear FROZEN and propagate upwards */
while (freezer && (freezer->state & CGROUP_FROZEN)) {
freezer->state &= ~CGROUP_FROZEN;
@@ -271,16 +272,8 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
css_task_iter_start(css, 0, &it);
while ((task = css_task_iter_next(&it))) {
- if (freezing(task)) {
- /*
- * freezer_should_skip() indicates that the task
- * should be skipped when determining freezing
- * completion. Consider it frozen in addition to
- * the usual frozen condition.
- */
- if (!frozen(task) && !freezer_should_skip(task))
- goto out_iter_end;
- }
+ if (freezing(task) && !frozen(task))
+ goto out_iter_end;
}
freezer->state |= CGROUP_FROZEN;
@@ -357,7 +350,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze,
if (freeze) {
if (!(freezer->state & CGROUP_FREEZING))
- atomic_inc(&system_freezing_cnt);
+ static_branch_inc(&freezer_active);
freezer->state |= state;
freeze_cgroup(freezer);
} else {
@@ -366,9 +359,9 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze,
freezer->state &= ~state;
if (!(freezer->state & CGROUP_FREEZING)) {
- if (was_freezing)
- atomic_dec(&system_freezing_cnt);
freezer->state &= ~CGROUP_FROZEN;
+ if (was_freezing)
+ static_branch_dec(&freezer_active);
unfreeze_cgroup(freezer);
}
}
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index 511af87f685e..7695e60bcb40 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -47,6 +47,7 @@ struct pids_cgroup {
*/
atomic64_t counter;
atomic64_t limit;
+ int64_t watermark;
/* Handle for "pids.events" */
struct cgroup_file events_file;
@@ -85,6 +86,16 @@ static void pids_css_free(struct cgroup_subsys_state *css)
kfree(css_pids(css));
}
+static void pids_update_watermark(struct pids_cgroup *p, int64_t nr_pids)
+{
+ /*
+ * This is racy, but we don't need perfectly accurate tallying of
+ * the watermark, and this lets us avoid extra atomic overhead.
+ */
+ if (nr_pids > READ_ONCE(p->watermark))
+ WRITE_ONCE(p->watermark, nr_pids);
+}
+
/**
* pids_cancel - uncharge the local pid count
* @pids: the pid cgroup state
@@ -128,8 +139,11 @@ static void pids_charge(struct pids_cgroup *pids, int num)
{
struct pids_cgroup *p;
- for (p = pids; parent_pids(p); p = parent_pids(p))
- atomic64_add(num, &p->counter);
+ for (p = pids; parent_pids(p); p = parent_pids(p)) {
+ int64_t new = atomic64_add_return(num, &p->counter);
+
+ pids_update_watermark(p, new);
+ }
}
/**
@@ -156,6 +170,12 @@ static int pids_try_charge(struct pids_cgroup *pids, int num)
*/
if (new > limit)
goto revert;
+
+ /*
+ * Not technically accurate if we go over limit somewhere up
+ * the hierarchy, but that's tolerable for the watermark.
+ */
+ pids_update_watermark(p, new);
}
return 0;
@@ -311,6 +331,14 @@ static s64 pids_current_read(struct cgroup_subsys_state *css,
return atomic64_read(&pids->counter);
}
+static s64 pids_peak_read(struct cgroup_subsys_state *css,
+ struct cftype *cft)
+{
+ struct pids_cgroup *pids = css_pids(css);
+
+ return READ_ONCE(pids->watermark);
+}
+
static int pids_events_show(struct seq_file *sf, void *v)
{
struct pids_cgroup *pids = css_pids(seq_css(sf));
@@ -332,6 +360,11 @@ static struct cftype pids_files[] = {
.flags = CFTYPE_NOT_ON_ROOT,
},
{
+ .name = "peak",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .read_s64 = pids_peak_read,
+ },
+ {
.name = "events",
.seq_show = pids_events_show,
.file_offset = offsetof(struct pids_cgroup, events_file),
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 7beceb447211..d5e9ccde3ab8 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -50,7 +50,6 @@
#include <linux/pid.h>
#include <linux/smp.h>
#include <linux/mm.h>
-#include <linux/vmacache.h>
#include <linux/rcupdate.h>
#include <linux/irq.h>
#include <linux/security.h>
@@ -283,17 +282,6 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
if (!CACHE_FLUSH_IS_SAFE)
return;
- if (current->mm) {
- int i;
-
- for (i = 0; i < VMACACHE_SIZE; i++) {
- if (!current->vmacache.vmas[i])
- continue;
- flush_cache_range(current->vmacache.vmas[i],
- addr, addr + BREAK_INSTR_SIZE);
- }
- }
-
/* Force flush instruction cache if it was outside the mm */
flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
}
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 164ed9ef77a3..e39cb696cfbd 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -214,13 +214,22 @@ void __delayacct_freepages_end(void)
&current->delays->freepages_count);
}
-void __delayacct_thrashing_start(void)
+void __delayacct_thrashing_start(bool *in_thrashing)
{
+ *in_thrashing = !!current->in_thrashing;
+ if (*in_thrashing)
+ return;
+
+ current->in_thrashing = 1;
current->delays->thrashing_start = local_clock();
}
-void __delayacct_thrashing_end(void)
+void __delayacct_thrashing_end(bool *in_thrashing)
{
+ if (*in_thrashing)
+ return;
+
+ current->in_thrashing = 0;
delayacct_end(&current->delays->lock,
&current->delays->thrashing_start,
&current->delays->thrashing_delay,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 27f272381cf2..33437d620644 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -10,6 +10,7 @@
#include <linux/dma-map-ops.h>
#include <linux/export.h>
#include <linux/gfp.h>
+#include <linux/kmsan.h>
#include <linux/of_device.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
@@ -156,6 +157,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
else
addr = ops->map_page(dev, page, offset, size, dir, attrs);
+ kmsan_handle_dma(page, offset, size, dir);
debug_dma_map_page(dev, page, offset, size, dir, addr, attrs);
return addr;
@@ -194,11 +196,13 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
else
ents = ops->map_sg(dev, sg, nents, dir, attrs);
- if (ents > 0)
+ if (ents > 0) {
+ kmsan_handle_dma_sg(sg, nents, dir);
debug_dma_map_sg(dev, sg, nents, ents, dir, attrs);
- else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM &&
- ents != -EIO && ents != -EREMOTEIO))
+ } else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM &&
+ ents != -EIO && ents != -EREMOTEIO)) {
return -EIO;
+ }
return ents;
}
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 0ef6b12f961d..339a990554e7 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -346,22 +346,27 @@ retry:
memblock_free(tlb, PAGE_ALIGN(bytes));
nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
- if (nslabs < IO_TLB_MIN_SLABS)
- panic("%s: Failed to remap %zu bytes\n",
- __func__, bytes);
- goto retry;
+ if (nslabs >= IO_TLB_MIN_SLABS)
+ goto retry;
+
+ pr_warn("%s: Failed to remap %zu bytes\n", __func__, bytes);
+ return;
}
alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
- if (!mem->slots)
- panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
- __func__, alloc_size, PAGE_SIZE);
+ if (!mem->slots) {
+ pr_warn("%s: Failed to allocate %zu bytes align=0x%lx\n",
+ __func__, alloc_size, PAGE_SIZE);
+ return;
+ }
mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
default_nareas), SMP_CACHE_BYTES);
- if (!mem->areas)
- panic("%s: Failed to allocate mem->areas.\n", __func__);
+ if (!mem->areas) {
+ pr_warn("%s: Failed to allocate mem->areas.\n", __func__);
+ return;
+ }
swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false,
default_nareas);
@@ -545,9 +550,8 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
}
if (PageHighMem(pfn_to_page(pfn))) {
- /* The buffer does not have a mapping. Map it in and copy */
unsigned int offset = orig_addr & ~PAGE_MASK;
- char *buffer;
+ struct page *page;
unsigned int sz = 0;
unsigned long flags;
@@ -555,12 +559,11 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
sz = min_t(size_t, PAGE_SIZE - offset, size);
local_irq_save(flags);
- buffer = kmap_atomic(pfn_to_page(pfn));
+ page = pfn_to_page(pfn);
if (dir == DMA_TO_DEVICE)
- memcpy(vaddr, buffer + offset, sz);
+ memcpy_from_page(vaddr, page, offset, sz);
else
- memcpy(buffer + offset, vaddr, sz);
- kunmap_atomic(buffer);
+ memcpy_to_page(page, offset, vaddr, sz);
local_irq_restore(flags);
size -= sz;
@@ -731,8 +734,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
int index;
phys_addr_t tlb_addr;
- if (!mem || !mem->nslabs)
- panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+ if (!mem || !mem->nslabs) {
+ dev_warn_ratelimited(dev,
+ "Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+ }
if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 063068a9ea9b..846add8394c4 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -5,6 +5,7 @@
#include <linux/resume_user_mode.h>
#include <linux/highmem.h>
#include <linux/jump_label.h>
+#include <linux/kmsan.h>
#include <linux/livepatch.h>
#include <linux/audit.h>
#include <linux/tick.h>
@@ -24,6 +25,7 @@ static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
user_exit_irqoff();
instrumentation_begin();
+ kmsan_unpoison_entry_regs(regs);
trace_hardirqs_off_finish();
instrumentation_end();
}
@@ -352,6 +354,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
lockdep_hardirqs_off(CALLER_ADDR0);
ct_irq_enter();
instrumentation_begin();
+ kmsan_unpoison_entry_regs(regs);
trace_hardirqs_off_finish();
instrumentation_end();
@@ -367,6 +370,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
*/
lockdep_hardirqs_off(CALLER_ADDR0);
instrumentation_begin();
+ kmsan_unpoison_entry_regs(regs);
rcu_irq_enter_check_tick();
trace_hardirqs_off_finish();
instrumentation_end();
@@ -452,6 +456,7 @@ irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
ct_nmi_enter();
instrumentation_begin();
+ kmsan_unpoison_entry_regs(regs);
trace_hardirqs_off_finish();
ftrace_nmi_enter();
instrumentation_end();
diff --git a/kernel/events/Makefile b/kernel/events/Makefile
index 8591c180b52b..91a62f566743 100644
--- a/kernel/events/Makefile
+++ b/kernel/events/Makefile
@@ -2,4 +2,5 @@
obj-y := core.o ring_buffer.o callchain.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
+obj-$(CONFIG_HW_BREAKPOINT_KUNIT_TEST) += hw_breakpoint_test.o
obj-$(CONFIG_UPROBES) += uprobes.o
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ff4bffc502c6..aefc1e08e015 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1468,6 +1468,8 @@ static void __update_context_time(struct perf_event_context *ctx, bool adv)
{
u64 now = perf_clock();
+ lockdep_assert_held(&ctx->lock);
+
if (adv)
ctx->time += now - ctx->timestamp;
ctx->timestamp = now;
@@ -2224,16 +2226,22 @@ static inline int __pmu_filter_match(struct perf_event *event)
static inline int pmu_filter_match(struct perf_event *event)
{
struct perf_event *sibling;
+ unsigned long flags;
+ int ret = 1;
if (!__pmu_filter_match(event))
return 0;
+ local_irq_save(flags);
for_each_sibling_event(sibling, event) {
- if (!__pmu_filter_match(sibling))
- return 0;
+ if (!__pmu_filter_match(sibling)) {
+ ret = 0;
+ break;
+ }
}
+ local_irq_restore(flags);
- return 1;
+ return ret;
}
static inline int
@@ -6794,11 +6802,10 @@ out_put:
static void __perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
- struct perf_event *event)
+ struct perf_event *event,
+ u64 sample_type)
{
- u64 sample_type = event->attr.sample_type;
-
- data->type = sample_type;
+ data->type = event->attr.sample_type;
header->size += event->id_header_size;
if (sample_type & PERF_SAMPLE_TID) {
@@ -6827,7 +6834,7 @@ void perf_event_header__init_id(struct perf_event_header *header,
struct perf_event *event)
{
if (event->attr.sample_id_all)
- __perf_event_header__init_id(header, data, event);
+ __perf_event_header__init_id(header, data, event, event->attr.sample_type);
}
static void __perf_event__output_id_sample(struct perf_output_handle *handle,
@@ -6976,11 +6983,6 @@ static void perf_output_read(struct perf_output_handle *handle,
perf_output_read_one(handle, event, enabled, running);
}
-static inline bool perf_sample_save_hw_index(struct perf_event *event)
-{
- return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
-}
-
void perf_output_sample(struct perf_output_handle *handle,
struct perf_event_header *header,
struct perf_sample_data *data,
@@ -7062,14 +7064,14 @@ void perf_output_sample(struct perf_output_handle *handle,
}
if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
- if (data->br_stack) {
+ if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
size_t size;
size = data->br_stack->nr
* sizeof(struct perf_branch_entry);
perf_output_put(handle, data->br_stack->nr);
- if (perf_sample_save_hw_index(event))
+ if (branch_sample_hw_index(event))
perf_output_put(handle, data->br_stack->hw_idx);
perf_output_copy(handle, data->br_stack->entries, size);
} else {
@@ -7312,6 +7314,7 @@ void perf_prepare_sample(struct perf_event_header *header,
struct pt_regs *regs)
{
u64 sample_type = event->attr.sample_type;
+ u64 filtered_sample_type;
header->type = PERF_RECORD_SAMPLE;
header->size = sizeof(*header) + event->header_size;
@@ -7319,7 +7322,12 @@ void perf_prepare_sample(struct perf_event_header *header,
header->misc = 0;
header->misc |= perf_misc_flags(regs);
- __perf_event_header__init_id(header, data, event);
+ /*
+ * Clear the sample flags that have already been done by the
+ * PMU driver.
+ */
+ filtered_sample_type = sample_type & ~data->sample_flags;
+ __perf_event_header__init_id(header, data, event, filtered_sample_type);
if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
data->ip = perf_instruction_pointer(regs);
@@ -7327,7 +7335,7 @@ void perf_prepare_sample(struct perf_event_header *header,
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
int size = 1;
- if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+ if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN)
data->callchain = perf_callchain(event, regs);
size += data->callchain->nr;
@@ -7339,7 +7347,7 @@ void perf_prepare_sample(struct perf_event_header *header,
struct perf_raw_record *raw = data->raw;
int size;
- if (raw) {
+ if (raw && (data->sample_flags & PERF_SAMPLE_RAW)) {
struct perf_raw_frag *frag = &raw->frag;
u32 sum = 0;
@@ -7355,6 +7363,7 @@ void perf_prepare_sample(struct perf_event_header *header,
frag->pad = raw->size - sum;
} else {
size = sizeof(u64);
+ data->raw = NULL;
}
header->size += size;
@@ -7362,8 +7371,8 @@ void perf_prepare_sample(struct perf_event_header *header,
if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
int size = sizeof(u64); /* nr */
- if (data->br_stack) {
- if (perf_sample_save_hw_index(event))
+ if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
+ if (branch_sample_hw_index(event))
size += sizeof(u64);
size += data->br_stack->nr
@@ -7412,6 +7421,20 @@ void perf_prepare_sample(struct perf_event_header *header,
header->size += size;
}
+ if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+ data->weight.full = 0;
+
+ if (filtered_sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = PERF_MEM_NA;
+
+ if (filtered_sample_type & PERF_SAMPLE_TRANSACTION)
+ data->txn = 0;
+
+ if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_DATA_PAGE_SIZE)) {
+ if (filtered_sample_type & PERF_SAMPLE_ADDR)
+ data->addr = 0;
+ }
+
if (sample_type & PERF_SAMPLE_REGS_INTR) {
/* regs dump ABI info */
int size = sizeof(u64);
@@ -7427,7 +7450,8 @@ void perf_prepare_sample(struct perf_event_header *header,
header->size += size;
}
- if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+ if (sample_type & PERF_SAMPLE_PHYS_ADDR &&
+ filtered_sample_type & PERF_SAMPLE_PHYS_ADDR)
data->phys_addr = perf_virt_to_phys(data->addr);
#ifdef CONFIG_CGROUP_PERF
@@ -9998,8 +10022,16 @@ static void bpf_overflow_handler(struct perf_event *event,
goto out;
rcu_read_lock();
prog = READ_ONCE(event->prog);
- if (prog)
+ if (prog) {
+ if (prog->call_get_stack &&
+ (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
+ !(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) {
+ data->callchain = perf_callchain(event, regs);
+ data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
+ }
+
ret = bpf_prog_run(prog, &ctx);
+ }
rcu_read_unlock();
out:
__this_cpu_dec(bpf_prog_active);
@@ -10025,7 +10057,7 @@ static int perf_event_set_bpf_handler(struct perf_event *event,
if (event->attr.precise_ip &&
prog->call_get_stack &&
- (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY) ||
+ (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) ||
event->attr.exclude_callchain_kernel ||
event->attr.exclude_callchain_user)) {
/*
@@ -10238,8 +10270,9 @@ static void perf_addr_filter_apply(struct perf_addr_filter *filter,
struct perf_addr_filter_range *fr)
{
struct vm_area_struct *vma;
+ VMA_ITERATOR(vmi, mm, 0);
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ for_each_vma(vmi, vma) {
if (!vma->vm_file)
continue;
@@ -10942,7 +10975,7 @@ static ssize_t nr_addr_filters_show(struct device *dev,
{
struct pmu *pmu = dev_get_drvdata(dev);
- return snprintf(page, PAGE_SIZE - 1, "%d\n", pmu->nr_addr_filters);
+ return scnprintf(page, PAGE_SIZE - 1, "%d\n", pmu->nr_addr_filters);
}
DEVICE_ATTR_RO(nr_addr_filters);
@@ -10953,7 +10986,7 @@ type_show(struct device *dev, struct device_attribute *attr, char *page)
{
struct pmu *pmu = dev_get_drvdata(dev);
- return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->type);
+ return scnprintf(page, PAGE_SIZE - 1, "%d\n", pmu->type);
}
static DEVICE_ATTR_RO(type);
@@ -10964,7 +10997,7 @@ perf_event_mux_interval_ms_show(struct device *dev,
{
struct pmu *pmu = dev_get_drvdata(dev);
- return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
+ return scnprintf(page, PAGE_SIZE - 1, "%d\n", pmu->hrtimer_interval_ms);
}
static DEFINE_MUTEX(mux_interval_mutex);
@@ -11718,11 +11751,9 @@ err_pmu:
event->destroy(event);
module_put(pmu->module);
err_ns:
- if (event->ns)
- put_pid_ns(event->ns);
if (event->hw.target)
put_task_struct(event->hw.target);
- kmem_cache_free(perf_event_cache, event);
+ call_rcu(&event->rcu_head, free_event_rcu);
return ERR_PTR(err);
}
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index f32320ac02fd..c3797701339c 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -17,61 +17,276 @@
* This file contains the arch-independent routines.
*/
+#include <linux/hw_breakpoint.h>
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/cpu.h>
+#include <linux/export.h>
+#include <linux/init.h>
#include <linux/irqflags.h>
-#include <linux/kallsyms.h>
-#include <linux/notifier.h>
-#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/percpu-rwsem.h>
#include <linux/percpu.h>
+#include <linux/rhashtable.h>
#include <linux/sched.h>
-#include <linux/init.h>
#include <linux/slab.h>
-#include <linux/list.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/bug.h>
-#include <linux/hw_breakpoint.h>
/*
- * Constraints data
+ * Datastructure to track the total uses of N slots across tasks or CPUs;
+ * bp_slots_histogram::count[N] is the number of assigned N+1 breakpoint slots.
+ */
+struct bp_slots_histogram {
+#ifdef hw_breakpoint_slots
+ atomic_t count[hw_breakpoint_slots(0)];
+#else
+ atomic_t *count;
+#endif
+};
+
+/*
+ * Per-CPU constraints data.
*/
struct bp_cpuinfo {
- /* Number of pinned cpu breakpoints in a cpu */
- unsigned int cpu_pinned;
- /* tsk_pinned[n] is the number of tasks having n+1 breakpoints */
- unsigned int *tsk_pinned;
- /* Number of non-pinned cpu/task breakpoints in a cpu */
- unsigned int flexible; /* XXX: placeholder, see fetch_this_slot() */
+ /* Number of pinned CPU breakpoints in a CPU. */
+ unsigned int cpu_pinned;
+ /* Histogram of pinned task breakpoints in a CPU. */
+ struct bp_slots_histogram tsk_pinned;
};
static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]);
-static int nr_slots[TYPE_MAX];
static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type)
{
return per_cpu_ptr(bp_cpuinfo + type, cpu);
}
+/* Number of pinned CPU breakpoints globally. */
+static struct bp_slots_histogram cpu_pinned[TYPE_MAX];
+/* Number of pinned CPU-independent task breakpoints. */
+static struct bp_slots_histogram tsk_pinned_all[TYPE_MAX];
+
/* Keep track of the breakpoints attached to tasks */
-static LIST_HEAD(bp_task_head);
+static struct rhltable task_bps_ht;
+static const struct rhashtable_params task_bps_ht_params = {
+ .head_offset = offsetof(struct hw_perf_event, bp_list),
+ .key_offset = offsetof(struct hw_perf_event, target),
+ .key_len = sizeof_field(struct hw_perf_event, target),
+ .automatic_shrinking = true,
+};
-static int constraints_initialized;
+static bool constraints_initialized __ro_after_init;
-/* Gather the number of total pinned and un-pinned bp in a cpuset */
-struct bp_busy_slots {
- unsigned int pinned;
- unsigned int flexible;
-};
+/*
+ * Synchronizes accesses to the per-CPU constraints; the locking rules are:
+ *
+ * 1. Atomic updates to bp_cpuinfo::tsk_pinned only require a held read-lock
+ * (due to bp_slots_histogram::count being atomic, no update are lost).
+ *
+ * 2. Holding a write-lock is required for computations that require a
+ * stable snapshot of all bp_cpuinfo::tsk_pinned.
+ *
+ * 3. In all other cases, non-atomic accesses require the appropriately held
+ * lock (read-lock for read-only accesses; write-lock for reads/writes).
+ */
+DEFINE_STATIC_PERCPU_RWSEM(bp_cpuinfo_sem);
-/* Serialize accesses to the above constraints */
-static DEFINE_MUTEX(nr_bp_mutex);
+/*
+ * Return mutex to serialize accesses to per-task lists in task_bps_ht. Since
+ * rhltable synchronizes concurrent insertions/deletions, independent tasks may
+ * insert/delete concurrently; therefore, a mutex per task is sufficient.
+ *
+ * Uses task_struct::perf_event_mutex, to avoid extending task_struct with a
+ * hw_breakpoint-only mutex, which may be infrequently used. The caveat here is
+ * that hw_breakpoint may contend with per-task perf event list management. The
+ * assumption is that perf usecases involving hw_breakpoints are very unlikely
+ * to result in unnecessary contention.
+ */
+static inline struct mutex *get_task_bps_mutex(struct perf_event *bp)
+{
+ struct task_struct *tsk = bp->hw.target;
-__weak int hw_breakpoint_weight(struct perf_event *bp)
+ return tsk ? &tsk->perf_event_mutex : NULL;
+}
+
+static struct mutex *bp_constraints_lock(struct perf_event *bp)
+{
+ struct mutex *tsk_mtx = get_task_bps_mutex(bp);
+
+ if (tsk_mtx) {
+ /*
+ * Fully analogous to the perf_try_init_event() nesting
+ * argument in the comment near perf_event_ctx_lock_nested();
+ * this child->perf_event_mutex cannot ever deadlock against
+ * the parent->perf_event_mutex usage from
+ * perf_event_task_{en,dis}able().
+ *
+ * Specifically, inherited events will never occur on
+ * ->perf_event_list.
+ */
+ mutex_lock_nested(tsk_mtx, SINGLE_DEPTH_NESTING);
+ percpu_down_read(&bp_cpuinfo_sem);
+ } else {
+ percpu_down_write(&bp_cpuinfo_sem);
+ }
+
+ return tsk_mtx;
+}
+
+static void bp_constraints_unlock(struct mutex *tsk_mtx)
+{
+ if (tsk_mtx) {
+ percpu_up_read(&bp_cpuinfo_sem);
+ mutex_unlock(tsk_mtx);
+ } else {
+ percpu_up_write(&bp_cpuinfo_sem);
+ }
+}
+
+static bool bp_constraints_is_locked(struct perf_event *bp)
+{
+ struct mutex *tsk_mtx = get_task_bps_mutex(bp);
+
+ return percpu_is_write_locked(&bp_cpuinfo_sem) ||
+ (tsk_mtx ? mutex_is_locked(tsk_mtx) :
+ percpu_is_read_locked(&bp_cpuinfo_sem));
+}
+
+static inline void assert_bp_constraints_lock_held(struct perf_event *bp)
+{
+ struct mutex *tsk_mtx = get_task_bps_mutex(bp);
+
+ if (tsk_mtx)
+ lockdep_assert_held(tsk_mtx);
+ lockdep_assert_held(&bp_cpuinfo_sem);
+}
+
+#ifdef hw_breakpoint_slots
+/*
+ * Number of breakpoint slots is constant, and the same for all types.
+ */
+static_assert(hw_breakpoint_slots(TYPE_INST) == hw_breakpoint_slots(TYPE_DATA));
+static inline int hw_breakpoint_slots_cached(int type) { return hw_breakpoint_slots(type); }
+static inline int init_breakpoint_slots(void) { return 0; }
+#else
+/*
+ * Dynamic number of breakpoint slots.
+ */
+static int __nr_bp_slots[TYPE_MAX] __ro_after_init;
+
+static inline int hw_breakpoint_slots_cached(int type)
+{
+ return __nr_bp_slots[type];
+}
+
+static __init bool
+bp_slots_histogram_alloc(struct bp_slots_histogram *hist, enum bp_type_idx type)
+{
+ hist->count = kcalloc(hw_breakpoint_slots_cached(type), sizeof(*hist->count), GFP_KERNEL);
+ return hist->count;
+}
+
+static __init void bp_slots_histogram_free(struct bp_slots_histogram *hist)
+{
+ kfree(hist->count);
+}
+
+static __init int init_breakpoint_slots(void)
+{
+ int i, cpu, err_cpu;
+
+ for (i = 0; i < TYPE_MAX; i++)
+ __nr_bp_slots[i] = hw_breakpoint_slots(i);
+
+ for_each_possible_cpu(cpu) {
+ for (i = 0; i < TYPE_MAX; i++) {
+ struct bp_cpuinfo *info = get_bp_info(cpu, i);
+
+ if (!bp_slots_histogram_alloc(&info->tsk_pinned, i))
+ goto err;
+ }
+ }
+ for (i = 0; i < TYPE_MAX; i++) {
+ if (!bp_slots_histogram_alloc(&cpu_pinned[i], i))
+ goto err;
+ if (!bp_slots_histogram_alloc(&tsk_pinned_all[i], i))
+ goto err;
+ }
+
+ return 0;
+err:
+ for_each_possible_cpu(err_cpu) {
+ for (i = 0; i < TYPE_MAX; i++)
+ bp_slots_histogram_free(&get_bp_info(err_cpu, i)->tsk_pinned);
+ if (err_cpu == cpu)
+ break;
+ }
+ for (i = 0; i < TYPE_MAX; i++) {
+ bp_slots_histogram_free(&cpu_pinned[i]);
+ bp_slots_histogram_free(&tsk_pinned_all[i]);
+ }
+
+ return -ENOMEM;
+}
+#endif
+
+static inline void
+bp_slots_histogram_add(struct bp_slots_histogram *hist, int old, int val)
+{
+ const int old_idx = old - 1;
+ const int new_idx = old_idx + val;
+
+ if (old_idx >= 0)
+ WARN_ON(atomic_dec_return_relaxed(&hist->count[old_idx]) < 0);
+ if (new_idx >= 0)
+ WARN_ON(atomic_inc_return_relaxed(&hist->count[new_idx]) < 0);
+}
+
+static int
+bp_slots_histogram_max(struct bp_slots_histogram *hist, enum bp_type_idx type)
+{
+ for (int i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) {
+ const int count = atomic_read(&hist->count[i]);
+
+ /* Catch unexpected writers; we want a stable snapshot. */
+ ASSERT_EXCLUSIVE_WRITER(hist->count[i]);
+ if (count > 0)
+ return i + 1;
+ WARN(count < 0, "inconsistent breakpoint slots histogram");
+ }
+
+ return 0;
+}
+
+static int
+bp_slots_histogram_max_merge(struct bp_slots_histogram *hist1, struct bp_slots_histogram *hist2,
+ enum bp_type_idx type)
+{
+ for (int i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) {
+ const int count1 = atomic_read(&hist1->count[i]);
+ const int count2 = atomic_read(&hist2->count[i]);
+
+ /* Catch unexpected writers; we want a stable snapshot. */
+ ASSERT_EXCLUSIVE_WRITER(hist1->count[i]);
+ ASSERT_EXCLUSIVE_WRITER(hist2->count[i]);
+ if (count1 + count2 > 0)
+ return i + 1;
+ WARN(count1 < 0, "inconsistent breakpoint slots histogram");
+ WARN(count2 < 0, "inconsistent breakpoint slots histogram");
+ }
+
+ return 0;
+}
+
+#ifndef hw_breakpoint_weight
+static inline int hw_breakpoint_weight(struct perf_event *bp)
{
return 1;
}
+#endif
static inline enum bp_type_idx find_slot_idx(u64 bp_type)
{
@@ -82,39 +297,61 @@ static inline enum bp_type_idx find_slot_idx(u64 bp_type)
}
/*
- * Report the maximum number of pinned breakpoints a task
- * have in this cpu
+ * Return the maximum number of pinned breakpoints a task has in this CPU.
*/
static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
{
- unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
- int i;
+ struct bp_slots_histogram *tsk_pinned = &get_bp_info(cpu, type)->tsk_pinned;
- for (i = nr_slots[type] - 1; i >= 0; i--) {
- if (tsk_pinned[i] > 0)
- return i + 1;
- }
-
- return 0;
+ /*
+ * At this point we want to have acquired the bp_cpuinfo_sem as a
+ * writer to ensure that there are no concurrent writers in
+ * toggle_bp_task_slot() to tsk_pinned, and we get a stable snapshot.
+ */
+ lockdep_assert_held_write(&bp_cpuinfo_sem);
+ return bp_slots_histogram_max_merge(tsk_pinned, &tsk_pinned_all[type], type);
}
/*
* Count the number of breakpoints of the same type and same task.
* The given event must be not on the list.
+ *
+ * If @cpu is -1, but the result of task_bp_pinned() is not CPU-independent,
+ * returns a negative value.
*/
static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type)
{
- struct task_struct *tsk = bp->hw.target;
+ struct rhlist_head *head, *pos;
struct perf_event *iter;
int count = 0;
- list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
- if (iter->hw.target == tsk &&
- find_slot_idx(iter->attr.bp_type) == type &&
- (iter->cpu < 0 || cpu == iter->cpu))
- count += hw_breakpoint_weight(iter);
+ /*
+ * We need a stable snapshot of the per-task breakpoint list.
+ */
+ assert_bp_constraints_lock_held(bp);
+
+ rcu_read_lock();
+ head = rhltable_lookup(&task_bps_ht, &bp->hw.target, task_bps_ht_params);
+ if (!head)
+ goto out;
+
+ rhl_for_each_entry_rcu(iter, pos, head, hw.bp_list) {
+ if (find_slot_idx(iter->attr.bp_type) != type)
+ continue;
+
+ if (iter->cpu >= 0) {
+ if (cpu == -1) {
+ count = -1;
+ goto out;
+ } else if (cpu != iter->cpu)
+ continue;
+ }
+
+ count += hw_breakpoint_weight(iter);
}
+out:
+ rcu_read_unlock();
return count;
}
@@ -126,16 +363,29 @@ static const struct cpumask *cpumask_of_bp(struct perf_event *bp)
}
/*
- * Report the number of pinned/un-pinned breakpoints we have in
- * a given cpu (cpu > -1) or in all of them (cpu = -1).
+ * Returns the max pinned breakpoint slots in a given
+ * CPU (cpu > -1) or across all of them (cpu = -1).
*/
-static void
-fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
- enum bp_type_idx type)
+static int
+max_bp_pinned_slots(struct perf_event *bp, enum bp_type_idx type)
{
const struct cpumask *cpumask = cpumask_of_bp(bp);
+ int pinned_slots = 0;
int cpu;
+ if (bp->hw.target && bp->cpu < 0) {
+ int max_pinned = task_bp_pinned(-1, bp, type);
+
+ if (max_pinned >= 0) {
+ /*
+ * Fast path: task_bp_pinned() is CPU-independent and
+ * returns the same value for any CPU.
+ */
+ max_pinned += bp_slots_histogram_max(&cpu_pinned[type], type);
+ return max_pinned;
+ }
+ }
+
for_each_cpu(cpu, cpumask) {
struct bp_cpuinfo *info = get_bp_info(cpu, type);
int nr;
@@ -146,71 +396,131 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
else
nr += task_bp_pinned(cpu, bp, type);
- if (nr > slots->pinned)
- slots->pinned = nr;
-
- nr = info->flexible;
- if (nr > slots->flexible)
- slots->flexible = nr;
+ pinned_slots = max(nr, pinned_slots);
}
-}
-/*
- * For now, continue to consider flexible as pinned, until we can
- * ensure no flexible event can ever be scheduled before a pinned event
- * in a same cpu.
- */
-static void
-fetch_this_slot(struct bp_busy_slots *slots, int weight)
-{
- slots->pinned += weight;
-}
-
-/*
- * Add a pinned breakpoint for the given task in our constraint table
- */
-static void toggle_bp_task_slot(struct perf_event *bp, int cpu,
- enum bp_type_idx type, int weight)
-{
- unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
- int old_idx, new_idx;
-
- old_idx = task_bp_pinned(cpu, bp, type) - 1;
- new_idx = old_idx + weight;
-
- if (old_idx >= 0)
- tsk_pinned[old_idx]--;
- if (new_idx >= 0)
- tsk_pinned[new_idx]++;
+ return pinned_slots;
}
/*
* Add/remove the given breakpoint in our constraint table
*/
-static void
-toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
- int weight)
+static int
+toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, int weight)
{
- const struct cpumask *cpumask = cpumask_of_bp(bp);
- int cpu;
+ int cpu, next_tsk_pinned;
if (!enable)
weight = -weight;
- /* Pinned counter cpu profiling */
if (!bp->hw.target) {
- get_bp_info(bp->cpu, type)->cpu_pinned += weight;
- return;
+ /*
+ * Update the pinned CPU slots, in per-CPU bp_cpuinfo and in the
+ * global histogram.
+ */
+ struct bp_cpuinfo *info = get_bp_info(bp->cpu, type);
+
+ lockdep_assert_held_write(&bp_cpuinfo_sem);
+ bp_slots_histogram_add(&cpu_pinned[type], info->cpu_pinned, weight);
+ info->cpu_pinned += weight;
+ return 0;
+ }
+
+ /*
+ * If bp->hw.target, tsk_pinned is only modified, but not used
+ * otherwise. We can permit concurrent updates as long as there are no
+ * other uses: having acquired bp_cpuinfo_sem as a reader allows
+ * concurrent updates here. Uses of tsk_pinned will require acquiring
+ * bp_cpuinfo_sem as a writer to stabilize tsk_pinned's value.
+ */
+ lockdep_assert_held_read(&bp_cpuinfo_sem);
+
+ /*
+ * Update the pinned task slots, in per-CPU bp_cpuinfo and in the global
+ * histogram. We need to take care of 4 cases:
+ *
+ * 1. This breakpoint targets all CPUs (cpu < 0), and there may only
+ * exist other task breakpoints targeting all CPUs. In this case we
+ * can simply update the global slots histogram.
+ *
+ * 2. This breakpoint targets a specific CPU (cpu >= 0), but there may
+ * only exist other task breakpoints targeting all CPUs.
+ *
+ * a. On enable: remove the existing breakpoints from the global
+ * slots histogram and use the per-CPU histogram.
+ *
+ * b. On disable: re-insert the existing breakpoints into the global
+ * slots histogram and remove from per-CPU histogram.
+ *
+ * 3. Some other existing task breakpoints target specific CPUs. Only
+ * update the per-CPU slots histogram.
+ */
+
+ if (!enable) {
+ /*
+ * Remove before updating histograms so we can determine if this
+ * was the last task breakpoint for a specific CPU.
+ */
+ int ret = rhltable_remove(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params);
+
+ if (ret)
+ return ret;
+ }
+ /*
+ * Note: If !enable, next_tsk_pinned will not count the to-be-removed breakpoint.
+ */
+ next_tsk_pinned = task_bp_pinned(-1, bp, type);
+
+ if (next_tsk_pinned >= 0) {
+ if (bp->cpu < 0) { /* Case 1: fast path */
+ if (!enable)
+ next_tsk_pinned += hw_breakpoint_weight(bp);
+ bp_slots_histogram_add(&tsk_pinned_all[type], next_tsk_pinned, weight);
+ } else if (enable) { /* Case 2.a: slow path */
+ /* Add existing to per-CPU histograms. */
+ for_each_possible_cpu(cpu) {
+ bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned,
+ 0, next_tsk_pinned);
+ }
+ /* Add this first CPU-pinned task breakpoint. */
+ bp_slots_histogram_add(&get_bp_info(bp->cpu, type)->tsk_pinned,
+ next_tsk_pinned, weight);
+ /* Rebalance global task pinned histogram. */
+ bp_slots_histogram_add(&tsk_pinned_all[type], next_tsk_pinned,
+ -next_tsk_pinned);
+ } else { /* Case 2.b: slow path */
+ /* Remove this last CPU-pinned task breakpoint. */
+ bp_slots_histogram_add(&get_bp_info(bp->cpu, type)->tsk_pinned,
+ next_tsk_pinned + hw_breakpoint_weight(bp), weight);
+ /* Remove all from per-CPU histograms. */
+ for_each_possible_cpu(cpu) {
+ bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned,
+ next_tsk_pinned, -next_tsk_pinned);
+ }
+ /* Rebalance global task pinned histogram. */
+ bp_slots_histogram_add(&tsk_pinned_all[type], 0, next_tsk_pinned);
+ }
+ } else { /* Case 3: slow path */
+ const struct cpumask *cpumask = cpumask_of_bp(bp);
+
+ for_each_cpu(cpu, cpumask) {
+ next_tsk_pinned = task_bp_pinned(cpu, bp, type);
+ if (!enable)
+ next_tsk_pinned += hw_breakpoint_weight(bp);
+ bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned,
+ next_tsk_pinned, weight);
+ }
}
- /* Pinned counter task profiling */
- for_each_cpu(cpu, cpumask)
- toggle_bp_task_slot(bp, cpu, type, weight);
+ /*
+ * Readers want a stable snapshot of the per-task breakpoint list.
+ */
+ assert_bp_constraints_lock_held(bp);
if (enable)
- list_add_tail(&bp->hw.bp_list, &bp_task_head);
- else
- list_del(&bp->hw.bp_list);
+ return rhltable_insert(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params);
+
+ return 0;
}
__weak int arch_reserve_bp_slot(struct perf_event *bp)
@@ -234,7 +544,12 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
}
/*
- * Constraints to check before allowing this new breakpoint counter:
+ * Constraints to check before allowing this new breakpoint counter.
+ *
+ * Note: Flexible breakpoints are currently unimplemented, but outlined in the
+ * below algorithm for completeness. The implementation treats flexible as
+ * pinned due to no guarantee that we currently always schedule flexible events
+ * before a pinned event in a same CPU.
*
* == Non-pinned counter == (Considered as pinned for now)
*
@@ -276,8 +591,8 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
*/
static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
{
- struct bp_busy_slots slots = {0};
enum bp_type_idx type;
+ int max_pinned_slots;
int weight;
int ret;
@@ -293,36 +608,24 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
type = find_slot_idx(bp_type);
weight = hw_breakpoint_weight(bp);
- fetch_bp_busy_slots(&slots, bp, type);
- /*
- * Simulate the addition of this breakpoint to the constraints
- * and see the result.
- */
- fetch_this_slot(&slots, weight);
-
- /* Flexible counters need to keep at least one slot */
- if (slots.pinned + (!!slots.flexible) > nr_slots[type])
+ /* Check if this new breakpoint can be satisfied across all CPUs. */
+ max_pinned_slots = max_bp_pinned_slots(bp, type) + weight;
+ if (max_pinned_slots > hw_breakpoint_slots_cached(type))
return -ENOSPC;
ret = arch_reserve_bp_slot(bp);
if (ret)
return ret;
- toggle_bp_slot(bp, true, type, weight);
-
- return 0;
+ return toggle_bp_slot(bp, true, type, weight);
}
int reserve_bp_slot(struct perf_event *bp)
{
- int ret;
-
- mutex_lock(&nr_bp_mutex);
-
- ret = __reserve_bp_slot(bp, bp->attr.bp_type);
-
- mutex_unlock(&nr_bp_mutex);
+ struct mutex *mtx = bp_constraints_lock(bp);
+ int ret = __reserve_bp_slot(bp, bp->attr.bp_type);
+ bp_constraints_unlock(mtx);
return ret;
}
@@ -335,17 +638,16 @@ static void __release_bp_slot(struct perf_event *bp, u64 bp_type)
type = find_slot_idx(bp_type);
weight = hw_breakpoint_weight(bp);
- toggle_bp_slot(bp, false, type, weight);
+ WARN_ON(toggle_bp_slot(bp, false, type, weight));
}
void release_bp_slot(struct perf_event *bp)
{
- mutex_lock(&nr_bp_mutex);
+ struct mutex *mtx = bp_constraints_lock(bp);
arch_unregister_hw_breakpoint(bp);
__release_bp_slot(bp, bp->attr.bp_type);
-
- mutex_unlock(&nr_bp_mutex);
+ bp_constraints_unlock(mtx);
}
static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
@@ -372,11 +674,10 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
{
- int ret;
+ struct mutex *mtx = bp_constraints_lock(bp);
+ int ret = __modify_bp_slot(bp, old_type, new_type);
- mutex_lock(&nr_bp_mutex);
- ret = __modify_bp_slot(bp, old_type, new_type);
- mutex_unlock(&nr_bp_mutex);
+ bp_constraints_unlock(mtx);
return ret;
}
@@ -387,18 +688,28 @@ static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
*/
int dbg_reserve_bp_slot(struct perf_event *bp)
{
- if (mutex_is_locked(&nr_bp_mutex))
+ int ret;
+
+ if (bp_constraints_is_locked(bp))
return -1;
- return __reserve_bp_slot(bp, bp->attr.bp_type);
+ /* Locks aren't held; disable lockdep assert checking. */
+ lockdep_off();
+ ret = __reserve_bp_slot(bp, bp->attr.bp_type);
+ lockdep_on();
+
+ return ret;
}
int dbg_release_bp_slot(struct perf_event *bp)
{
- if (mutex_is_locked(&nr_bp_mutex))
+ if (bp_constraints_is_locked(bp))
return -1;
+ /* Locks aren't held; disable lockdep assert checking. */
+ lockdep_off();
__release_bp_slot(bp, bp->attr.bp_type);
+ lockdep_on();
return 0;
}
@@ -604,6 +915,50 @@ void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)
}
EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint);
+/**
+ * hw_breakpoint_is_used - check if breakpoints are currently used
+ *
+ * Returns: true if breakpoints are used, false otherwise.
+ */
+bool hw_breakpoint_is_used(void)
+{
+ int cpu;
+
+ if (!constraints_initialized)
+ return false;
+
+ for_each_possible_cpu(cpu) {
+ for (int type = 0; type < TYPE_MAX; ++type) {
+ struct bp_cpuinfo *info = get_bp_info(cpu, type);
+
+ if (info->cpu_pinned)
+ return true;
+
+ for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) {
+ if (atomic_read(&info->tsk_pinned.count[slot]))
+ return true;
+ }
+ }
+ }
+
+ for (int type = 0; type < TYPE_MAX; ++type) {
+ for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) {
+ /*
+ * Warn, because if there are CPU pinned counters,
+ * should never get here; bp_cpuinfo::cpu_pinned should
+ * be consistent with the global cpu_pinned histogram.
+ */
+ if (WARN_ON(atomic_read(&cpu_pinned[type].count[slot])))
+ return true;
+
+ if (atomic_read(&tsk_pinned_all[type].count[slot]))
+ return true;
+ }
+ }
+
+ return false;
+}
+
static struct notifier_block hw_breakpoint_exceptions_nb = {
.notifier_call = hw_breakpoint_exceptions_notify,
/* we need to be notified first */
@@ -678,38 +1033,19 @@ static struct pmu perf_breakpoint = {
int __init init_hw_breakpoint(void)
{
- int cpu, err_cpu;
- int i;
-
- for (i = 0; i < TYPE_MAX; i++)
- nr_slots[i] = hw_breakpoint_slots(i);
+ int ret;
- for_each_possible_cpu(cpu) {
- for (i = 0; i < TYPE_MAX; i++) {
- struct bp_cpuinfo *info = get_bp_info(cpu, i);
+ ret = rhltable_init(&task_bps_ht, &task_bps_ht_params);
+ if (ret)
+ return ret;
- info->tsk_pinned = kcalloc(nr_slots[i], sizeof(int),
- GFP_KERNEL);
- if (!info->tsk_pinned)
- goto err_alloc;
- }
- }
+ ret = init_breakpoint_slots();
+ if (ret)
+ return ret;
- constraints_initialized = 1;
+ constraints_initialized = true;
perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT);
return register_die_notifier(&hw_breakpoint_exceptions_nb);
-
- err_alloc:
- for_each_possible_cpu(err_cpu) {
- for (i = 0; i < TYPE_MAX; i++)
- kfree(get_bp_info(err_cpu, i)->tsk_pinned);
- if (err_cpu == cpu)
- break;
- }
-
- return -ENOMEM;
}
-
-
diff --git a/kernel/events/hw_breakpoint_test.c b/kernel/events/hw_breakpoint_test.c
new file mode 100644
index 000000000000..5ced822df788
--- /dev/null
+++ b/kernel/events/hw_breakpoint_test.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test for hw_breakpoint constraints accounting logic.
+ *
+ * Copyright (C) 2022, Google LLC.
+ */
+
+#include <kunit/test.h>
+#include <linux/cpumask.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/kthread.h>
+#include <linux/perf_event.h>
+#include <asm/hw_breakpoint.h>
+
+#define TEST_REQUIRES_BP_SLOTS(test, slots) \
+ do { \
+ if ((slots) > get_test_bp_slots()) { \
+ kunit_skip((test), "Requires breakpoint slots: %d > %d", slots, \
+ get_test_bp_slots()); \
+ } \
+ } while (0)
+
+#define TEST_EXPECT_NOSPC(expr) KUNIT_EXPECT_EQ(test, -ENOSPC, PTR_ERR(expr))
+
+#define MAX_TEST_BREAKPOINTS 512
+
+static char break_vars[MAX_TEST_BREAKPOINTS];
+static struct perf_event *test_bps[MAX_TEST_BREAKPOINTS];
+static struct task_struct *__other_task;
+
+static struct perf_event *register_test_bp(int cpu, struct task_struct *tsk, int idx)
+{
+ struct perf_event_attr attr = {};
+
+ if (WARN_ON(idx < 0 || idx >= MAX_TEST_BREAKPOINTS))
+ return NULL;
+
+ hw_breakpoint_init(&attr);
+ attr.bp_addr = (unsigned long)&break_vars[idx];
+ attr.bp_len = HW_BREAKPOINT_LEN_1;
+ attr.bp_type = HW_BREAKPOINT_RW;
+ return perf_event_create_kernel_counter(&attr, cpu, tsk, NULL, NULL);
+}
+
+static void unregister_test_bp(struct perf_event **bp)
+{
+ if (WARN_ON(IS_ERR(*bp)))
+ return;
+ if (WARN_ON(!*bp))
+ return;
+ unregister_hw_breakpoint(*bp);
+ *bp = NULL;
+}
+
+static int get_test_bp_slots(void)
+{
+ static int slots;
+
+ if (!slots)
+ slots = hw_breakpoint_slots(TYPE_DATA);
+
+ return slots;
+}
+
+static void fill_one_bp_slot(struct kunit *test, int *id, int cpu, struct task_struct *tsk)
+{
+ struct perf_event *bp = register_test_bp(cpu, tsk, *id);
+
+ KUNIT_ASSERT_NOT_NULL(test, bp);
+ KUNIT_ASSERT_FALSE(test, IS_ERR(bp));
+ KUNIT_ASSERT_NULL(test, test_bps[*id]);
+ test_bps[(*id)++] = bp;
+}
+
+/*
+ * Fills up the given @cpu/@tsk with breakpoints, only leaving @skip slots free.
+ *
+ * Returns true if this can be called again, continuing at @id.
+ */
+static bool fill_bp_slots(struct kunit *test, int *id, int cpu, struct task_struct *tsk, int skip)
+{
+ for (int i = 0; i < get_test_bp_slots() - skip; ++i)
+ fill_one_bp_slot(test, id, cpu, tsk);
+
+ return *id + get_test_bp_slots() <= MAX_TEST_BREAKPOINTS;
+}
+
+static int dummy_kthread(void *arg)
+{
+ return 0;
+}
+
+static struct task_struct *get_other_task(struct kunit *test)
+{
+ struct task_struct *tsk;
+
+ if (__other_task)
+ return __other_task;
+
+ tsk = kthread_create(dummy_kthread, NULL, "hw_breakpoint_dummy_task");
+ KUNIT_ASSERT_FALSE(test, IS_ERR(tsk));
+ __other_task = tsk;
+ return __other_task;
+}
+
+static int get_test_cpu(int num)
+{
+ int cpu;
+
+ WARN_ON(num < 0);
+
+ for_each_online_cpu(cpu) {
+ if (num-- <= 0)
+ break;
+ }
+
+ return cpu;
+}
+
+/* ===== Test cases ===== */
+
+static void test_one_cpu(struct kunit *test)
+{
+ int idx = 0;
+
+ fill_bp_slots(test, &idx, get_test_cpu(0), NULL, 0);
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+}
+
+static void test_many_cpus(struct kunit *test)
+{
+ int idx = 0;
+ int cpu;
+
+ /* Test that CPUs are independent. */
+ for_each_online_cpu(cpu) {
+ bool do_continue = fill_bp_slots(test, &idx, cpu, NULL, 0);
+
+ TEST_EXPECT_NOSPC(register_test_bp(cpu, NULL, idx));
+ if (!do_continue)
+ break;
+ }
+}
+
+static void test_one_task_on_all_cpus(struct kunit *test)
+{
+ int idx = 0;
+
+ fill_bp_slots(test, &idx, -1, current, 0);
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+ /* Remove one and adding back CPU-target should work. */
+ unregister_test_bp(&test_bps[0]);
+ fill_one_bp_slot(test, &idx, get_test_cpu(0), NULL);
+}
+
+static void test_two_tasks_on_all_cpus(struct kunit *test)
+{
+ int idx = 0;
+
+ /* Test that tasks are independent. */
+ fill_bp_slots(test, &idx, -1, current, 0);
+ fill_bp_slots(test, &idx, -1, get_other_task(test), 0);
+
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(-1, get_other_task(test), idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), get_other_task(test), idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+ /* Remove one from first task and adding back CPU-target should not work. */
+ unregister_test_bp(&test_bps[0]);
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+}
+
+static void test_one_task_on_one_cpu(struct kunit *test)
+{
+ int idx = 0;
+
+ fill_bp_slots(test, &idx, get_test_cpu(0), current, 0);
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+ /*
+ * Remove one and adding back CPU-target should work; this case is
+ * special vs. above because the task's constraints are CPU-dependent.
+ */
+ unregister_test_bp(&test_bps[0]);
+ fill_one_bp_slot(test, &idx, get_test_cpu(0), NULL);
+}
+
+static void test_one_task_mixed(struct kunit *test)
+{
+ int idx = 0;
+
+ TEST_REQUIRES_BP_SLOTS(test, 3);
+
+ fill_one_bp_slot(test, &idx, get_test_cpu(0), current);
+ fill_bp_slots(test, &idx, -1, current, 1);
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+
+ /* Transition from CPU-dependent pinned count to CPU-independent. */
+ unregister_test_bp(&test_bps[0]);
+ unregister_test_bp(&test_bps[1]);
+ fill_one_bp_slot(test, &idx, get_test_cpu(0), NULL);
+ fill_one_bp_slot(test, &idx, get_test_cpu(0), NULL);
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+}
+
+static void test_two_tasks_on_one_cpu(struct kunit *test)
+{
+ int idx = 0;
+
+ fill_bp_slots(test, &idx, get_test_cpu(0), current, 0);
+ fill_bp_slots(test, &idx, get_test_cpu(0), get_other_task(test), 0);
+
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(-1, get_other_task(test), idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), get_other_task(test), idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+ /* Can still create breakpoints on some other CPU. */
+ fill_bp_slots(test, &idx, get_test_cpu(1), NULL, 0);
+}
+
+static void test_two_tasks_on_one_all_cpus(struct kunit *test)
+{
+ int idx = 0;
+
+ fill_bp_slots(test, &idx, get_test_cpu(0), current, 0);
+ fill_bp_slots(test, &idx, -1, get_other_task(test), 0);
+
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(-1, get_other_task(test), idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), get_other_task(test), idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+ /* Cannot create breakpoints on some other CPU either. */
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(1), NULL, idx));
+}
+
+static void test_task_on_all_and_one_cpu(struct kunit *test)
+{
+ int tsk_on_cpu_idx, cpu_idx;
+ int idx = 0;
+
+ TEST_REQUIRES_BP_SLOTS(test, 3);
+
+ fill_bp_slots(test, &idx, -1, current, 2);
+ /* Transitioning from only all CPU breakpoints to mixed. */
+ tsk_on_cpu_idx = idx;
+ fill_one_bp_slot(test, &idx, get_test_cpu(0), current);
+ fill_one_bp_slot(test, &idx, -1, current);
+
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+
+ /* We should still be able to use up another CPU's slots. */
+ cpu_idx = idx;
+ fill_one_bp_slot(test, &idx, get_test_cpu(1), NULL);
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(1), NULL, idx));
+
+ /* Transitioning back to task target on all CPUs. */
+ unregister_test_bp(&test_bps[tsk_on_cpu_idx]);
+ /* Still have a CPU target breakpoint in get_test_cpu(1). */
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ /* Remove it and try again. */
+ unregister_test_bp(&test_bps[cpu_idx]);
+ fill_one_bp_slot(test, &idx, -1, current);
+
+ TEST_EXPECT_NOSPC(register_test_bp(-1, current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), current, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(0), NULL, idx));
+ TEST_EXPECT_NOSPC(register_test_bp(get_test_cpu(1), NULL, idx));
+}
+
+static struct kunit_case hw_breakpoint_test_cases[] = {
+ KUNIT_CASE(test_one_cpu),
+ KUNIT_CASE(test_many_cpus),
+ KUNIT_CASE(test_one_task_on_all_cpus),
+ KUNIT_CASE(test_two_tasks_on_all_cpus),
+ KUNIT_CASE(test_one_task_on_one_cpu),
+ KUNIT_CASE(test_one_task_mixed),
+ KUNIT_CASE(test_two_tasks_on_one_cpu),
+ KUNIT_CASE(test_two_tasks_on_one_all_cpus),
+ KUNIT_CASE(test_task_on_all_and_one_cpu),
+ {},
+};
+
+static int test_init(struct kunit *test)
+{
+ /* Most test cases want 2 distinct CPUs. */
+ if (num_online_cpus() < 2)
+ return -EINVAL;
+
+ /* Want the system to not use breakpoints elsewhere. */
+ if (hw_breakpoint_is_used())
+ return -EBUSY;
+
+ return 0;
+}
+
+static void test_exit(struct kunit *test)
+{
+ for (int i = 0; i < MAX_TEST_BREAKPOINTS; ++i) {
+ if (test_bps[i])
+ unregister_test_bp(&test_bps[i]);
+ }
+
+ if (__other_task) {
+ kthread_stop(__other_task);
+ __other_task = NULL;
+ }
+
+ /* Verify that internal state agrees that no breakpoints are in use. */
+ KUNIT_EXPECT_FALSE(test, hw_breakpoint_is_used());
+}
+
+static struct kunit_suite hw_breakpoint_test_suite = {
+ .name = "hw_breakpoint",
+ .test_cases = hw_breakpoint_test_cases,
+ .init = test_init,
+ .exit = test_exit,
+};
+
+kunit_test_suites(&hw_breakpoint_test_suite);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Marco Elver <elver@google.com>");
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2eaa327f8158..d9e357b7e17c 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -19,7 +19,7 @@
#include <linux/export.h>
#include <linux/rmap.h> /* anon_vma_prepare */
#include <linux/mmu_notifier.h> /* set_pte_at_notify */
-#include <linux/swap.h> /* try_to_free_swap */
+#include <linux/swap.h> /* folio_free_swap */
#include <linux/ptrace.h> /* user_enable_single_step */
#include <linux/kdebug.h> /* notifier mechanism */
#include "../../mm/internal.h" /* munlock_vma_page */
@@ -154,8 +154,10 @@ static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
struct page *old_page, struct page *new_page)
{
+ struct folio *old_folio = page_folio(old_page);
+ struct folio *new_folio;
struct mm_struct *mm = vma->vm_mm;
- DEFINE_FOLIO_VMA_WALK(pvmw, page_folio(old_page), vma, addr, 0);
+ DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0);
int err;
struct mmu_notifier_range range;
@@ -163,14 +165,14 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
addr + PAGE_SIZE);
if (new_page) {
- err = mem_cgroup_charge(page_folio(new_page), vma->vm_mm,
- GFP_KERNEL);
+ new_folio = page_folio(new_page);
+ err = mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL);
if (err)
return err;
}
- /* For try_to_free_swap() below */
- lock_page(old_page);
+ /* For folio_free_swap() below */
+ folio_lock(old_folio);
mmu_notifier_invalidate_range_start(&range);
err = -EAGAIN;
@@ -179,14 +181,14 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
if (new_page) {
- get_page(new_page);
+ folio_get(new_folio);
page_add_new_anon_rmap(new_page, vma, addr);
- lru_cache_add_inactive_or_unevictable(new_page, vma);
+ folio_add_lru_vma(new_folio, vma);
} else
/* no new page, just dec_mm_counter for old_page */
dec_mm_counter(mm, MM_ANONPAGES);
- if (!PageAnon(old_page)) {
+ if (!folio_test_anon(old_folio)) {
dec_mm_counter(mm, mm_counter_file(old_page));
inc_mm_counter(mm, MM_ANONPAGES);
}
@@ -198,15 +200,15 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
mk_pte(new_page, vma->vm_page_prot));
page_remove_rmap(old_page, vma, false);
- if (!page_mapped(old_page))
- try_to_free_swap(old_page);
+ if (!folio_mapped(old_folio))
+ folio_free_swap(old_folio);
page_vma_mapped_walk_done(&pvmw);
- put_page(old_page);
+ folio_put(old_folio);
err = 0;
unlock:
mmu_notifier_invalidate_range_end(&range);
- unlock_page(old_page);
+ folio_unlock(old_folio);
return err;
}
@@ -349,9 +351,10 @@ static bool valid_ref_ctr_vma(struct uprobe *uprobe,
static struct vm_area_struct *
find_ref_ctr_vma(struct uprobe *uprobe, struct mm_struct *mm)
{
+ VMA_ITERATOR(vmi, mm, 0);
struct vm_area_struct *tmp;
- for (tmp = mm->mmap; tmp; tmp = tmp->vm_next)
+ for_each_vma(vmi, tmp)
if (valid_ref_ctr_vma(uprobe, tmp))
return tmp;
@@ -552,7 +555,7 @@ put_old:
/* try collapse pmd for compound page */
if (!ret && orig_page_huge)
- collapse_pte_mapped_thp(mm, vaddr);
+ collapse_pte_mapped_thp(mm, vaddr, false);
return ret;
}
@@ -1231,11 +1234,12 @@ int uprobe_apply(struct inode *inode, loff_t offset,
static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
{
+ VMA_ITERATOR(vmi, mm, 0);
struct vm_area_struct *vma;
int err = 0;
mmap_read_lock(mm);
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ for_each_vma(vmi, vma) {
unsigned long vaddr;
loff_t offset;
@@ -1983,9 +1987,10 @@ bool uprobe_deny_signal(void)
static void mmf_recalc_uprobes(struct mm_struct *mm)
{
+ VMA_ITERATOR(vmi, mm, 0);
struct vm_area_struct *vma;
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ for_each_vma(vmi, vma) {
if (!valid_vma(vma, false))
continue;
/*
diff --git a/kernel/exit.c b/kernel/exit.c
index 84021b24f79e..35e0a31a0315 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -60,6 +60,7 @@
#include <linux/writeback.h>
#include <linux/shm.h>
#include <linux/kcov.h>
+#include <linux/kmsan.h>
#include <linux/random.h>
#include <linux/rcuwait.h>
#include <linux/compat.h>
@@ -183,6 +184,10 @@ void put_task_struct_rcu_user(struct task_struct *task)
call_rcu(&task->rcu, delayed_put_task_struct);
}
+void __weak release_thread(struct task_struct *dead_task)
+{
+}
+
void release_task(struct task_struct *p)
{
struct task_struct *leader;
@@ -374,10 +379,10 @@ static void coredump_task_exit(struct task_struct *tsk)
complete(&core_state->startup);
for (;;) {
- set_current_state(TASK_UNINTERRUPTIBLE);
+ set_current_state(TASK_UNINTERRUPTIBLE|TASK_FREEZABLE);
if (!self.task) /* see coredump_finish() */
break;
- freezable_schedule();
+ schedule();
}
__set_current_state(TASK_RUNNING);
}
@@ -466,6 +471,7 @@ assign_new_owner:
goto retry;
}
WRITE_ONCE(mm->owner, c);
+ lru_gen_migrate_mm(mm);
task_unlock(c);
put_task_struct(c);
}
@@ -733,14 +739,33 @@ static void check_stack_usage(void)
static inline void check_stack_usage(void) {}
#endif
+static void synchronize_group_exit(struct task_struct *tsk, long code)
+{
+ struct sighand_struct *sighand = tsk->sighand;
+ struct signal_struct *signal = tsk->signal;
+
+ spin_lock_irq(&sighand->siglock);
+ signal->quick_threads--;
+ if ((signal->quick_threads == 0) &&
+ !(signal->flags & SIGNAL_GROUP_EXIT)) {
+ signal->flags = SIGNAL_GROUP_EXIT;
+ signal->group_exit_code = code;
+ signal->group_stop_count = 0;
+ }
+ spin_unlock_irq(&sighand->siglock);
+}
+
void __noreturn do_exit(long code)
{
struct task_struct *tsk = current;
int group_dead;
+ synchronize_group_exit(tsk, code);
+
WARN_ON(tsk->plug);
kcov_task_exit(tsk);
+ kmsan_task_exit(tsk);
coredump_task_exit(tsk);
ptrace_event(PTRACE_EVENT_EXIT, code);
@@ -905,7 +930,7 @@ do_group_exit(int exit_code)
exit_code = sig->group_exit_code;
else if (sig->group_exec_task)
exit_code = 0;
- else if (!thread_group_empty(current)) {
+ else {
struct sighand_struct *const sighand = current->sighand;
spin_lock_irq(&sighand->siglock);
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 60dc825ecc2b..a7ccd2930c5f 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -247,15 +247,11 @@ static ssize_t fei_write(struct file *file, const char __user *buffer,
/* cut off if it is too long */
if (count > KSYM_NAME_LEN)
count = KSYM_NAME_LEN;
- buf = kmalloc(count + 1, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
- if (copy_from_user(buf, buffer, count)) {
- ret = -EFAULT;
- goto out_free;
- }
- buf[count] = '\0';
+ buf = memdup_user_nul(buffer, count);
+ if (IS_ERR(buf))
+ return PTR_ERR(buf);
+
sym = strstrip(buf);
mutex_lock(&fei_lock);
@@ -298,17 +294,15 @@ static ssize_t fei_write(struct file *file, const char __user *buffer,
}
ret = register_kprobe(&attr->kp);
- if (!ret)
- fei_debugfs_add_attr(attr);
- if (ret < 0)
- fei_attr_remove(attr);
- else {
- list_add_tail(&attr->list, &fei_attr_list);
- ret = count;
+ if (ret) {
+ fei_attr_free(attr);
+ goto out;
}
+ fei_debugfs_add_attr(attr);
+ list_add_tail(&attr->list, &fei_attr_list);
+ ret = count;
out:
mutex_unlock(&fei_lock);
-out_free:
kfree(buf);
return ret;
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 2b6bd511c6ed..08969f5aa38d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -37,13 +37,13 @@
#include <linux/fdtable.h>
#include <linux/iocontext.h>
#include <linux/key.h>
+#include <linux/kmsan.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
-#include <linux/vmacache.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
@@ -97,7 +97,6 @@
#include <linux/scs.h>
#include <linux/io_uring.h>
#include <linux/bpf.h>
-#include <linux/sched/mm.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
@@ -475,7 +474,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
*/
*new = data_race(*orig);
INIT_LIST_HEAD(&new->anon_vma_chain);
- new->vm_next = new->vm_prev = NULL;
dup_anon_vma_name(orig, new);
}
return new;
@@ -580,11 +578,12 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
static __latent_entropy int dup_mmap(struct mm_struct *mm,
struct mm_struct *oldmm)
{
- struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
- struct rb_node **rb_link, *rb_parent;
+ struct vm_area_struct *mpnt, *tmp;
int retval;
- unsigned long charge;
+ unsigned long charge = 0;
LIST_HEAD(uf);
+ MA_STATE(old_mas, &oldmm->mm_mt, 0, 0);
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
uprobe_start_dup_mmap();
if (mmap_write_lock_killable(oldmm)) {
@@ -606,16 +605,16 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
mm->exec_vm = oldmm->exec_vm;
mm->stack_vm = oldmm->stack_vm;
- rb_link = &mm->mm_rb.rb_node;
- rb_parent = NULL;
- pprev = &mm->mmap;
retval = ksm_fork(mm, oldmm);
if (retval)
goto out;
khugepaged_fork(mm, oldmm);
- prev = NULL;
- for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
+ retval = mas_expected_entries(&mas, oldmm->map_count);
+ if (retval)
+ goto out;
+
+ mas_for_each(&old_mas, mpnt, ULONG_MAX) {
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
@@ -629,7 +628,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
*/
if (fatal_signal_pending(current)) {
retval = -EINTR;
- goto out;
+ goto loop_out;
}
if (mpnt->vm_flags & VM_ACCOUNT) {
unsigned long len = vma_pages(mpnt);
@@ -675,24 +674,17 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
}
/*
- * Clear hugetlb-related page reserves for children. This only
- * affects MAP_PRIVATE mappings. Faults generated by the child
- * are not guaranteed to succeed, even if read-only
+ * Copy/update hugetlb private vma information.
*/
if (is_vm_hugetlb_page(tmp))
- reset_vma_resv_huge_pages(tmp);
-
- /*
- * Link in the new vma and copy the page table entries.
- */
- *pprev = tmp;
- pprev = &tmp->vm_next;
- tmp->vm_prev = prev;
- prev = tmp;
+ hugetlb_dup_vma_private(tmp);
- __vma_link_rb(mm, tmp, rb_link, rb_parent);
- rb_link = &tmp->vm_rb.rb_right;
- rb_parent = &tmp->vm_rb;
+ /* Link the vma into the MT */
+ mas.index = tmp->vm_start;
+ mas.last = tmp->vm_end - 1;
+ mas_store(&mas, tmp);
+ if (mas_is_err(&mas))
+ goto fail_nomem_mas_store;
mm->map_count++;
if (!(tmp->vm_flags & VM_WIPEONFORK))
@@ -702,10 +694,12 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
tmp->vm_ops->open(tmp);
if (retval)
- goto out;
+ goto loop_out;
}
/* a new mm has just been created */
retval = arch_dup_mmap(oldmm, mm);
+loop_out:
+ mas_destroy(&mas);
out:
mmap_write_unlock(mm);
flush_tlb_mm(oldmm);
@@ -714,6 +708,9 @@ out:
fail_uprobe_end:
uprobe_end_dup_mmap();
return retval;
+
+fail_nomem_mas_store:
+ unlink_anon_vmas(tmp);
fail_nomem_anon_vma_fork:
mpol_put(vma_policy(tmp));
fail_nomem_policy:
@@ -721,7 +718,7 @@ fail_nomem_policy:
fail_nomem:
retval = -ENOMEM;
vm_unacct_memory(charge);
- goto out;
+ goto loop_out;
}
static inline int mm_alloc_pgd(struct mm_struct *mm)
@@ -925,13 +922,13 @@ void __init fork_init(void)
init_task.signal->rlim[RLIMIT_SIGPENDING] =
init_task.signal->rlim[RLIMIT_NPROC];
- for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++)
+ for (i = 0; i < UCOUNT_COUNTS; i++)
init_user_ns.ucount_max[i] = max_threads/2;
- set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY);
- set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY);
- set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY);
- set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY);
+ set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY);
+ set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY);
+ set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY);
+ set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY);
#ifdef CONFIG_VMAP_STACK
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
@@ -1026,6 +1023,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
tsk->worker_private = NULL;
kcov_task_init(tsk);
+ kmsan_task_create(tsk);
kmap_local_fork(tsk);
#ifdef CONFIG_FAULT_INJECTION
@@ -1109,9 +1107,8 @@ static void mm_init_uprobes_state(struct mm_struct *mm)
static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
struct user_namespace *user_ns)
{
- mm->mmap = NULL;
- mm->mm_rb = RB_ROOT;
- mm->vmacache_seqnum = 0;
+ mt_init_flags(&mm->mm_mt, MM_MT_FLAGS);
+ mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock);
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
seqcount_init(&mm->write_protect_seq);
@@ -1152,6 +1149,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
goto fail_nocontext;
mm->user_ns = get_user_ns(user_ns);
+ lru_gen_init_mm(mm);
return mm;
fail_nocontext:
@@ -1194,6 +1192,7 @@ static inline void __mmput(struct mm_struct *mm)
}
if (mm->binfmt)
module_put(mm->binfmt->module);
+ lru_gen_del_mm(mm);
mmdrop(mm);
}
@@ -1285,13 +1284,16 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
/* Forbid mm->exe_file change if old file still mapped. */
old_exe_file = get_mm_exe_file(mm);
if (old_exe_file) {
+ VMA_ITERATOR(vmi, mm, 0);
mmap_read_lock(mm);
- for (vma = mm->mmap; vma && !ret; vma = vma->vm_next) {
+ for_each_vma(vmi, vma) {
if (!vma->vm_file)
continue;
if (path_equal(&vma->vm_file->f_path,
- &old_exe_file->f_path))
+ &old_exe_file->f_path)) {
ret = -EBUSY;
+ break;
+ }
}
mmap_read_unlock(mm);
fput(old_exe_file);
@@ -1421,13 +1423,12 @@ static void complete_vfork_done(struct task_struct *tsk)
static int wait_for_vfork_done(struct task_struct *child,
struct completion *vfork)
{
+ unsigned int state = TASK_UNINTERRUPTIBLE|TASK_KILLABLE|TASK_FREEZABLE;
int killed;
- freezer_do_not_count();
cgroup_enter_frozen();
- killed = wait_for_completion_killable(vfork);
+ killed = wait_for_completion_state(vfork, state);
cgroup_leave_frozen(false);
- freezer_count();
if (killed) {
task_lock(child);
@@ -1567,9 +1568,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
if (!oldmm)
return 0;
- /* initialize the new vmacache entries */
- vmacache_flush(tsk);
-
if (clone_flags & CLONE_VM) {
mmget(oldmm);
mm = oldmm;
@@ -1693,6 +1691,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
return -ENOMEM;
sig->nr_threads = 1;
+ sig->quick_threads = 1;
atomic_set(&sig->live, 1);
refcount_set(&sig->sigcnt, 1);
@@ -2116,7 +2115,7 @@ static __latent_entropy struct task_struct *copy_process(
goto bad_fork_free;
retval = -EAGAIN;
- if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
+ if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
if (p->real_cred->user != INIT_USER &&
!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
goto bad_fork_cleanup_count;
@@ -2460,6 +2459,7 @@ static __latent_entropy struct task_struct *copy_process(
__this_cpu_inc(process_counts);
} else {
current->signal->nr_threads++;
+ current->signal->quick_threads++;
atomic_inc(&current->signal->live);
refcount_inc(&current->signal->sigcnt);
task_join_group_stop(p);
@@ -2692,6 +2692,13 @@ pid_t kernel_clone(struct kernel_clone_args *args)
get_task_struct(p);
}
+ if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
+ /* lock the task to synchronize with memcg migration */
+ task_lock(p);
+ lru_gen_add_mm(p->mm);
+ task_unlock(p);
+ }
+
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 45ab36ffd0e7..4fad0e6fca64 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -13,10 +13,11 @@
#include <linux/kthread.h>
/* total number of freezing conditions in effect */
-atomic_t system_freezing_cnt = ATOMIC_INIT(0);
-EXPORT_SYMBOL(system_freezing_cnt);
+DEFINE_STATIC_KEY_FALSE(freezer_active);
+EXPORT_SYMBOL(freezer_active);
-/* indicate whether PM freezing is in effect, protected by
+/*
+ * indicate whether PM freezing is in effect, protected by
* system_transition_mutex
*/
bool pm_freezing;
@@ -29,7 +30,7 @@ static DEFINE_SPINLOCK(freezer_lock);
* freezing_slow_path - slow path for testing whether a task needs to be frozen
* @p: task to be tested
*
- * This function is called by freezing() if system_freezing_cnt isn't zero
+ * This function is called by freezing() if freezer_active isn't zero
* and tests whether @p needs to enter and stay in frozen state. Can be
* called under any context. The freezers are responsible for ensuring the
* target tasks see the updated state.
@@ -52,41 +53,40 @@ bool freezing_slow_path(struct task_struct *p)
}
EXPORT_SYMBOL(freezing_slow_path);
+bool frozen(struct task_struct *p)
+{
+ return READ_ONCE(p->__state) & TASK_FROZEN;
+}
+
/* Refrigerator is place where frozen processes are stored :-). */
bool __refrigerator(bool check_kthr_stop)
{
- /* Hmm, should we be allowed to suspend when there are realtime
- processes around? */
+ unsigned int state = get_current_state();
bool was_frozen = false;
- unsigned int save = get_current_state();
pr_debug("%s entered refrigerator\n", current->comm);
+ WARN_ON_ONCE(state && !(state & TASK_NORMAL));
+
for (;;) {
- set_current_state(TASK_UNINTERRUPTIBLE);
+ bool freeze;
+
+ set_current_state(TASK_FROZEN);
spin_lock_irq(&freezer_lock);
- current->flags |= PF_FROZEN;
- if (!freezing(current) ||
- (check_kthr_stop && kthread_should_stop()))
- current->flags &= ~PF_FROZEN;
+ freeze = freezing(current) && !(check_kthr_stop && kthread_should_stop());
spin_unlock_irq(&freezer_lock);
- if (!(current->flags & PF_FROZEN))
+ if (!freeze)
break;
+
was_frozen = true;
schedule();
}
+ __set_current_state(TASK_RUNNING);
pr_debug("%s left refrigerator\n", current->comm);
- /*
- * Restore saved task state before returning. The mb'd version
- * needs to be used; otherwise, it might silently break
- * synchronization which depends on ordered task state change.
- */
- set_current_state(save);
-
return was_frozen;
}
EXPORT_SYMBOL(__refrigerator);
@@ -101,6 +101,44 @@ static void fake_signal_wake_up(struct task_struct *p)
}
}
+static int __set_task_frozen(struct task_struct *p, void *arg)
+{
+ unsigned int state = READ_ONCE(p->__state);
+
+ if (p->on_rq)
+ return 0;
+
+ if (p != current && task_curr(p))
+ return 0;
+
+ if (!(state & (TASK_FREEZABLE | __TASK_STOPPED | __TASK_TRACED)))
+ return 0;
+
+ /*
+ * Only TASK_NORMAL can be augmented with TASK_FREEZABLE, since they
+ * can suffer spurious wakeups.
+ */
+ if (state & TASK_FREEZABLE)
+ WARN_ON_ONCE(!(state & TASK_NORMAL));
+
+#ifdef CONFIG_LOCKDEP
+ /*
+ * It's dangerous to freeze with locks held; there be dragons there.
+ */
+ if (!(state & __TASK_FREEZABLE_UNSAFE))
+ WARN_ON_ONCE(debug_locks && p->lockdep_depth);
+#endif
+
+ WRITE_ONCE(p->__state, TASK_FROZEN);
+ return TASK_FROZEN;
+}
+
+static bool __freeze_task(struct task_struct *p)
+{
+ /* TASK_FREEZABLE|TASK_STOPPED|TASK_TRACED -> TASK_FROZEN */
+ return task_call_func(p, __set_task_frozen, NULL);
+}
+
/**
* freeze_task - send a freeze request to given task
* @p: task to send the request to
@@ -116,20 +154,8 @@ bool freeze_task(struct task_struct *p)
{
unsigned long flags;
- /*
- * This check can race with freezer_do_not_count, but worst case that
- * will result in an extra wakeup being sent to the task. It does not
- * race with freezer_count(), the barriers in freezer_count() and
- * freezer_should_skip() ensure that either freezer_count() sees
- * freezing == true in try_to_freeze() and freezes, or
- * freezer_should_skip() sees !PF_FREEZE_SKIP and freezes the task
- * normally.
- */
- if (freezer_should_skip(p))
- return false;
-
spin_lock_irqsave(&freezer_lock, flags);
- if (!freezing(p) || frozen(p)) {
+ if (!freezing(p) || frozen(p) || __freeze_task(p)) {
spin_unlock_irqrestore(&freezer_lock, flags);
return false;
}
@@ -137,19 +163,52 @@ bool freeze_task(struct task_struct *p)
if (!(p->flags & PF_KTHREAD))
fake_signal_wake_up(p);
else
- wake_up_state(p, TASK_INTERRUPTIBLE);
+ wake_up_state(p, TASK_NORMAL);
spin_unlock_irqrestore(&freezer_lock, flags);
return true;
}
+/*
+ * The special task states (TASK_STOPPED, TASK_TRACED) keep their canonical
+ * state in p->jobctl. If either of them got a wakeup that was missed because
+ * TASK_FROZEN, then their canonical state reflects that and the below will
+ * refuse to restore the special state and instead issue the wakeup.
+ */
+static int __set_task_special(struct task_struct *p, void *arg)
+{
+ unsigned int state = 0;
+
+ if (p->jobctl & JOBCTL_TRACED)
+ state = TASK_TRACED;
+
+ else if (p->jobctl & JOBCTL_STOPPED)
+ state = TASK_STOPPED;
+
+ if (state)
+ WRITE_ONCE(p->__state, state);
+
+ return state;
+}
+
void __thaw_task(struct task_struct *p)
{
- unsigned long flags;
+ unsigned long flags, flags2;
spin_lock_irqsave(&freezer_lock, flags);
- if (frozen(p))
- wake_up_process(p);
+ if (WARN_ON_ONCE(freezing(p)))
+ goto unlock;
+
+ if (lock_task_sighand(p, &flags2)) {
+ /* TASK_FROZEN -> TASK_{STOPPED,TRACED} */
+ bool ret = task_call_func(p, __set_task_special, NULL);
+ unlock_task_sighand(p, &flags2);
+ if (ret)
+ goto unlock;
+ }
+
+ wake_up_state(p, TASK_FROZEN);
+unlock:
spin_unlock_irqrestore(&freezer_lock, flags);
}
diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c
index 4ce0923f1ce3..ba01b9408203 100644
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -334,7 +334,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
* futex_queue() calls spin_unlock() upon completion, both serializing
* access to the hash list and forcing another memory barrier.
*/
- set_current_state(TASK_INTERRUPTIBLE);
+ set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
futex_queue(q, hb);
/* Arm the timer */
@@ -352,7 +352,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
* is no timeout, or if it has yet to expire.
*/
if (!timeout || timeout->task)
- freezable_schedule();
+ schedule();
}
__set_current_state(TASK_RUNNING);
}
@@ -430,7 +430,7 @@ retry:
return ret;
}
- set_current_state(TASK_INTERRUPTIBLE);
+ set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
for (i = 0; i < count; i++) {
u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr;
@@ -504,7 +504,7 @@ static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count,
return;
}
- freezable_schedule();
+ schedule();
}
/**
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 0c78e64f747d..473036b43c83 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -31,8 +31,8 @@ if [ "$building_out_of_srctree" ]; then
fi
all_dirs="$all_dirs $dir_list"
-# include/generated/compile.h is ignored because it is touched even when none
-# of the source files changed.
+# include/generated/utsversion.h is ignored because it is generated after this
+# script is executed. (utsversion.h is unneeded for kheaders)
#
# When Kconfig regenerates include/generated/autoconf.h, its timestamp is
# updated, but the contents might be still the same. When any CONFIG option is
@@ -42,7 +42,7 @@ all_dirs="$all_dirs $dir_list"
#
# Ignore them for md5 calculation to avoid pointless regeneration.
headers_md5="$(find $all_dirs -name "*.h" |
- grep -v "include/generated/compile.h" |
+ grep -v "include/generated/utsversion.h" |
grep -v "include/generated/autoconf.h" |
xargs ls -l | md5sum | cut -d ' ' -f1)"
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index bb2354f73ded..c71889f3f3fc 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -95,8 +95,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
* Ensure the task is not frozen.
* Also, skip vfork and any other user process that freezer should skip.
*/
- if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP)))
- return;
+ if (unlikely(READ_ONCE(t->__state) & TASK_FROZEN))
+ return;
/*
* When a freshly created task is scheduled once, changes its state to
@@ -191,6 +191,8 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
hung_task_show_lock = false;
rcu_read_lock();
for_each_process_thread(g, t) {
+ unsigned int state;
+
if (!max_count--)
goto unlock;
if (time_after(jiffies, last_break + HUNG_TASK_LOCK_BREAK)) {
@@ -198,8 +200,14 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
goto unlock;
last_break = jiffies;
}
- /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
- if (READ_ONCE(t->__state) == TASK_UNINTERRUPTIBLE)
+ /*
+ * skip the TASK_KILLABLE tasks -- these can be killed
+ * skip the TASK_IDLE tasks -- those are genuinely idle
+ */
+ state = READ_ONCE(t->__state);
+ if ((state & TASK_UNINTERRUPTIBLE) &&
+ !(state & TASK_WAKEKILL) &&
+ !(state & TASK_NOLOAD))
check_hung_task(t, timeout);
}
unlock:
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 5db0230aa6b5..a91f9001103c 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -705,6 +705,30 @@ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq)
}
EXPORT_SYMBOL_GPL(generic_handle_domain_irq);
+ /**
+ * generic_handle_irq_safe - Invoke the handler for a HW irq belonging
+ * to a domain from any context.
+ * @domain: The domain where to perform the lookup
+ * @hwirq: The HW irq number to convert to a logical one
+ *
+ * Returns: 0 on success, a negative value on error.
+ *
+ * This function can be called from any context (IRQ or process
+ * context). If the interrupt is marked as 'enforce IRQ-context only' then
+ * the function must be invoked from hard interrupt context.
+ */
+int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq)
+{
+ unsigned long flags;
+ int ret;
+
+ local_irq_save(flags);
+ ret = handle_irq_desc(irq_resolve_mapping(domain, hwirq));
+ local_irq_restore(flags);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(generic_handle_domain_irq_safe);
+
/**
* generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging
* to a domain.
diff --git a/kernel/kcov.c b/kernel/kcov.c
index e19c84b02452..e5cd09fd8a05 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -11,6 +11,7 @@
#include <linux/fs.h>
#include <linux/hashtable.h>
#include <linux/init.h>
+#include <linux/kmsan-checks.h>
#include <linux/mm.h>
#include <linux/preempt.h>
#include <linux/printk.h>
@@ -152,6 +153,12 @@ static void kcov_remote_area_put(struct kcov_remote_area *area,
INIT_LIST_HEAD(&area->list);
area->size = size;
list_add(&area->list, &kcov_remote_areas);
+ /*
+ * KMSAN doesn't instrument this file, so it may not know area->list
+ * is initialized. Unpoison it explicitly to avoid reports in
+ * kcov_remote_area_get().
+ */
+ kmsan_unpoison_memory(&area->list, sizeof(area->list));
}
static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c
index 75712959c84e..00cdf8fa5693 100644
--- a/kernel/kcsan/selftest.c
+++ b/kernel/kcsan/selftest.c
@@ -26,7 +26,7 @@
static bool __init test_requires(void)
{
/* random should be initialized for the below tests */
- return prandom_u32() + prandom_u32() != 0;
+ return get_random_u32() + get_random_u32() != 0;
}
/*
@@ -46,7 +46,7 @@ static bool __init test_encode_decode(void)
unsigned long addr;
size_t verif_size;
- prandom_bytes(&addr, sizeof(addr));
+ get_random_bytes(&addr, sizeof(addr));
if (addr < PAGE_SIZE)
addr = PAGE_SIZE;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index b5e40f069768..cb8e6e6f983c 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -93,13 +93,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
/*
* Because we write directly to the reserved memory region when loading
- * crash kernels we need a mutex here to prevent multiple crash kernels
- * from attempting to load simultaneously, and to prevent a crash kernel
- * from loading over the top of a in use crash kernel.
- *
- * KISS: always take the mutex.
+ * crash kernels we need a serialization here to prevent multiple crash
+ * kernels from attempting to load simultaneously.
*/
- if (!mutex_trylock(&kexec_mutex))
+ if (!kexec_trylock())
return -EBUSY;
if (flags & KEXEC_ON_CRASH) {
@@ -165,7 +162,7 @@ out:
kimage_free(image);
out_unlock:
- mutex_unlock(&kexec_mutex);
+ kexec_unlock();
return ret;
}
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index acd029b307e4..ca2743f9c634 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -46,7 +46,7 @@
#include <crypto/hash.h>
#include "kexec_internal.h"
-DEFINE_MUTEX(kexec_mutex);
+atomic_t __kexec_lock = ATOMIC_INIT(0);
/* Per cpu memory for storing cpu states in case of system crash. */
note_buf_t __percpu *crash_notes;
@@ -809,7 +809,7 @@ static int kimage_load_normal_segment(struct kimage *image,
if (result < 0)
goto out;
- ptr = kmap(page);
+ ptr = kmap_local_page(page);
/* Start with a clear page */
clear_page(ptr);
ptr += maddr & ~PAGE_MASK;
@@ -822,7 +822,7 @@ static int kimage_load_normal_segment(struct kimage *image,
memcpy(ptr, kbuf, uchunk);
else
result = copy_from_user(ptr, buf, uchunk);
- kunmap(page);
+ kunmap_local(ptr);
if (result) {
result = -EFAULT;
goto out;
@@ -873,7 +873,7 @@ static int kimage_load_crash_segment(struct kimage *image,
goto out;
}
arch_kexec_post_alloc_pages(page_address(page), 1, 0);
- ptr = kmap(page);
+ ptr = kmap_local_page(page);
ptr += maddr & ~PAGE_MASK;
mchunk = min_t(size_t, mbytes,
PAGE_SIZE - (maddr & ~PAGE_MASK));
@@ -889,7 +889,7 @@ static int kimage_load_crash_segment(struct kimage *image,
else
result = copy_from_user(ptr, buf, uchunk);
kexec_flush_icache_page(page);
- kunmap(page);
+ kunmap_local(ptr);
arch_kexec_pre_free_pages(page_address(page), 1);
if (result) {
result = -EFAULT;
@@ -959,7 +959,7 @@ late_initcall(kexec_core_sysctl_init);
*/
void __noclone __crash_kexec(struct pt_regs *regs)
{
- /* Take the kexec_mutex here to prevent sys_kexec_load
+ /* Take the kexec_lock here to prevent sys_kexec_load
* running on one cpu from replacing the crash kernel
* we are using after a panic on a different cpu.
*
@@ -967,7 +967,7 @@ void __noclone __crash_kexec(struct pt_regs *regs)
* of memory the xchg(&kexec_crash_image) would be
* sufficient. But since I reuse the memory...
*/
- if (mutex_trylock(&kexec_mutex)) {
+ if (kexec_trylock()) {
if (kexec_crash_image) {
struct pt_regs fixed_regs;
@@ -976,7 +976,7 @@ void __noclone __crash_kexec(struct pt_regs *regs)
machine_crash_shutdown(&fixed_regs);
machine_kexec(kexec_crash_image);
}
- mutex_unlock(&kexec_mutex);
+ kexec_unlock();
}
}
STACK_FRAME_NON_STANDARD(__crash_kexec);
@@ -1004,14 +1004,17 @@ void crash_kexec(struct pt_regs *regs)
}
}
-size_t crash_get_memory_size(void)
+ssize_t crash_get_memory_size(void)
{
- size_t size = 0;
+ ssize_t size = 0;
+
+ if (!kexec_trylock())
+ return -EBUSY;
- mutex_lock(&kexec_mutex);
if (crashk_res.end != crashk_res.start)
size = resource_size(&crashk_res);
- mutex_unlock(&kexec_mutex);
+
+ kexec_unlock();
return size;
}
@@ -1022,7 +1025,8 @@ int crash_shrink_memory(unsigned long new_size)
unsigned long old_size;
struct resource *ram_res;
- mutex_lock(&kexec_mutex);
+ if (!kexec_trylock())
+ return -EBUSY;
if (kexec_crash_image) {
ret = -ENOENT;
@@ -1060,7 +1064,7 @@ int crash_shrink_memory(unsigned long new_size)
insert_resource(&iomem_resource, ram_res);
unlock:
- mutex_unlock(&kexec_mutex);
+ kexec_unlock();
return ret;
}
@@ -1132,7 +1136,7 @@ int kernel_kexec(void)
{
int error = 0;
- if (!mutex_trylock(&kexec_mutex))
+ if (!kexec_trylock())
return -EBUSY;
if (!kexec_image) {
error = -EINVAL;
@@ -1208,6 +1212,6 @@ int kernel_kexec(void)
#endif
Unlock:
- mutex_unlock(&kexec_mutex);
+ kexec_unlock();
return error;
}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 1d546dc97c50..45637511e0de 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -339,7 +339,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
image = NULL;
- if (!mutex_trylock(&kexec_mutex))
+ if (!kexec_trylock())
return -EBUSY;
dest_image = &kexec_image;
@@ -411,7 +411,7 @@ out:
if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
arch_kexec_protect_crashkres();
- mutex_unlock(&kexec_mutex);
+ kexec_unlock();
kimage_free(image);
return ret;
}
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 48aaf2ac0d0d..74da1409cd14 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -13,7 +13,20 @@ void kimage_terminate(struct kimage *image);
int kimage_is_destination_range(struct kimage *image,
unsigned long start, unsigned long end);
-extern struct mutex kexec_mutex;
+/*
+ * Whatever is used to serialize accesses to the kexec_crash_image needs to be
+ * NMI safe, as __crash_kexec() can happen during nmi_panic(), so here we use a
+ * "simple" atomic variable that is acquired with a cmpxchg().
+ */
+extern atomic_t __kexec_lock;
+static inline bool kexec_trylock(void)
+{
+ return atomic_cmpxchg_acquire(&__kexec_lock, 0, 1) == 0;
+}
+static inline void kexec_unlock(void)
+{
+ atomic_set_release(&__kexec_lock, 0);
+}
#ifdef CONFIG_KEXEC_FILE
#include <linux/purgatory.h>
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index b1292a57c2a5..65dba9076f31 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -105,7 +105,12 @@ KERNEL_ATTR_RO(kexec_crash_loaded);
static ssize_t kexec_crash_size_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
- return sprintf(buf, "%zu\n", crash_get_memory_size());
+ ssize_t size = crash_get_memory_size();
+
+ if (size < 0)
+ return size;
+
+ return sprintf(buf, "%zd\n", size);
}
static ssize_t kexec_crash_size_store(struct kobject *kobj,
struct kobj_attribute *attr,
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 28a6b7ab4a0f..f97fd01a2932 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -704,6 +704,7 @@ int kthread_stop(struct task_struct *k)
kthread = to_kthread(k);
set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
kthread_unpark(k);
+ set_tsk_thread_flag(k, TIF_NOTIFY_SIGNAL);
wake_up_process(k);
wait_for_completion(&kthread->exited);
ret = kthread->result;
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 76166df011a4..781249098cb6 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -112,7 +112,7 @@ static void __sched
account_global_scheduler_latency(struct task_struct *tsk,
struct latency_record *lat)
{
- int firstnonnull = MAXLR + 1;
+ int firstnonnull = MAXLR;
int i;
/* skip kernel threads for now */
@@ -150,7 +150,7 @@ account_global_scheduler_latency(struct task_struct *tsk,
}
i = firstnonnull;
- if (i >= MAXLR - 1)
+ if (i >= MAXLR)
return;
/* Allocted a new one: */
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index ec06ce59d728..9ada0bc5247b 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -325,6 +325,7 @@ int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs,
* /sys/kernel/livepatch/<patch>/transition
* /sys/kernel/livepatch/<patch>/force
* /sys/kernel/livepatch/<patch>/<object>
+ * /sys/kernel/livepatch/<patch>/<object>/patched
* /sys/kernel/livepatch/<patch>/<object>/<function,sympos>
*/
static int __klp_disable_patch(struct klp_patch *patch);
@@ -431,6 +432,22 @@ static struct attribute *klp_patch_attrs[] = {
};
ATTRIBUTE_GROUPS(klp_patch);
+static ssize_t patched_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct klp_object *obj;
+
+ obj = container_of(kobj, struct klp_object, kobj);
+ return sysfs_emit(buf, "%d\n", obj->patched);
+}
+
+static struct kobj_attribute patched_kobj_attr = __ATTR_RO(patched);
+static struct attribute *klp_object_attrs[] = {
+ &patched_kobj_attr.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(klp_object);
+
static void klp_free_object_dynamic(struct klp_object *obj)
{
kfree(obj->name);
@@ -576,6 +593,7 @@ static void klp_kobj_release_object(struct kobject *kobj)
static struct kobj_type klp_ktype_object = {
.release = klp_kobj_release_object,
.sysfs_ops = &kobj_sysfs_ops,
+ .default_groups = klp_object_groups,
};
static void klp_kobj_release_func(struct kobject *kobj)
@@ -1171,7 +1189,7 @@ int klp_module_coming(struct module *mod)
return -EINVAL;
if (!strcmp(mod->name, "vmlinux")) {
- pr_err("vmlinux.ko: invalid module name");
+ pr_err("vmlinux.ko: invalid module name\n");
return -EINVAL;
}
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 5d03a2ad1066..30187b1d8275 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -610,9 +610,23 @@ void klp_reverse_transition(void)
/* Called from copy_process() during fork */
void klp_copy_process(struct task_struct *child)
{
- child->patch_state = current->patch_state;
- /* TIF_PATCH_PENDING gets copied in setup_thread_stack() */
+ /*
+ * The parent process may have gone through a KLP transition since
+ * the thread flag was copied in setup_thread_stack earlier. Bring
+ * the task flag up to date with the parent here.
+ *
+ * The operation is serialized against all klp_*_transition()
+ * operations by the tasklist_lock. The only exception is
+ * klp_update_patch_state(current), but we cannot race with
+ * that because we are current.
+ */
+ if (test_tsk_thread_flag(current, TIF_PATCH_PENDING))
+ set_tsk_thread_flag(child, TIF_PATCH_PENDING);
+ else
+ clear_tsk_thread_flag(child, TIF_PATCH_PENDING);
+
+ child->patch_state = current->patch_state;
}
/*
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index d51cabf28f38..ea925731fa40 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -5,8 +5,9 @@ KCOV_INSTRUMENT := n
obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
-# Avoid recursion lockdep -> KCSAN -> ... -> lockdep.
+# Avoid recursion lockdep -> sanitizer -> ... -> lockdep.
KCSAN_SANITIZE_lockdep.o := n
+KMSAN_SANITIZE_lockdep.o := n
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 64a13eb56078..e3375bc40dad 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -934,8 +934,10 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
* Huh! same key, different name? Did someone trample
* on some memory? We're most confused.
*/
- WARN_ON_ONCE(class->name != lock->name &&
- lock->key != &__lockdep_no_validate__);
+ WARN_ONCE(class->name != lock->name &&
+ lock->key != &__lockdep_no_validate__,
+ "Looking for class \"%s\" with key %ps, but found a different class \"%s\" with the same key\n",
+ lock->name, lock->key, class->name);
return class;
}
}
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 5fe4c5495ba3..185bd1c906b0 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -192,6 +192,12 @@ EXPORT_SYMBOL_GPL(__percpu_down_read);
__sum; \
})
+bool percpu_is_read_locked(struct percpu_rw_semaphore *sem)
+{
+ return per_cpu_sum(*sem->read_count) != 0 && !atomic_read(&sem->block);
+}
+EXPORT_SYMBOL_GPL(percpu_is_read_locked);
+
/*
* Return true if the modular sum of the sem->read_count per-CPU variable is
* zero. If this sum is zero, then it is stable due to the fact that if any
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index 2e1600906c9f..d2ef312a8611 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -18,7 +18,7 @@
* queued_read_lock_slowpath - acquire read lock of a queued rwlock
* @lock: Pointer to queued rwlock structure
*/
-void queued_read_lock_slowpath(struct qrwlock *lock)
+void __lockfunc queued_read_lock_slowpath(struct qrwlock *lock)
{
/*
* Readers come here when they cannot get the lock without waiting
@@ -63,7 +63,7 @@ EXPORT_SYMBOL(queued_read_lock_slowpath);
* queued_write_lock_slowpath - acquire write lock of a queued rwlock
* @lock : Pointer to queued rwlock structure
*/
-void queued_write_lock_slowpath(struct qrwlock *lock)
+void __lockfunc queued_write_lock_slowpath(struct qrwlock *lock)
{
int cnts;
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 65a9a10caa6f..2b23378775fe 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -313,7 +313,7 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
* contended : (*,x,y) +--> (*,0,0) ---> (*,0,1) -' :
* queue : ^--' :
*/
-void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
{
struct mcs_spinlock *prev, *next, *node;
u32 old, tail;
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index e84d21aa0722..6afc249ce697 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -489,7 +489,7 @@ gotlock:
* PV versions of the unlock fastpath and slowpath functions to be used
* instead of queued_spin_unlock().
*/
-__visible void
+__visible __lockfunc void
__pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
{
struct pv_node *node;
@@ -544,7 +544,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
#include <asm/qspinlock_paravirt.h>
#ifndef __pv_queued_spin_unlock
-__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+__visible __lockfunc void __pv_queued_spin_unlock(struct qspinlock *lock)
{
u8 locked;
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 65f0262f635e..44873594de03 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -133,14 +133,19 @@
* the owner value concurrently without lock. Read from owner, however,
* may not need READ_ONCE() as long as the pointer value is only used
* for comparison and isn't being dereferenced.
+ *
+ * Both rwsem_{set,clear}_owner() functions should be in the same
+ * preempt disable section as the atomic op that changes sem->count.
*/
static inline void rwsem_set_owner(struct rw_semaphore *sem)
{
+ lockdep_assert_preemption_disabled();
atomic_long_set(&sem->owner, (long)current);
}
static inline void rwsem_clear_owner(struct rw_semaphore *sem)
{
+ lockdep_assert_preemption_disabled();
atomic_long_set(&sem->owner, 0);
}
@@ -251,13 +256,16 @@ static inline bool rwsem_read_trylock(struct rw_semaphore *sem, long *cntp)
static inline bool rwsem_write_trylock(struct rw_semaphore *sem)
{
long tmp = RWSEM_UNLOCKED_VALUE;
+ bool ret = false;
+ preempt_disable();
if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, RWSEM_WRITER_LOCKED)) {
rwsem_set_owner(sem);
- return true;
+ ret = true;
}
- return false;
+ preempt_enable();
+ return ret;
}
/*
@@ -1352,8 +1360,10 @@ static inline void __up_write(struct rw_semaphore *sem)
DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) &&
!rwsem_test_oflags(sem, RWSEM_NONSPINNABLE), sem);
+ preempt_disable();
rwsem_clear_owner(sem);
tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
+ preempt_enable();
if (unlikely(tmp & RWSEM_FLAG_WAITERS))
rwsem_wake(sem);
}
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index f2654d2fe43a..34bfae72f295 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -51,7 +51,7 @@ static noinline void __up(struct semaphore *sem);
* Use of this function is deprecated, please use down_interruptible() or
* down_killable() instead.
*/
-void down(struct semaphore *sem)
+void __sched down(struct semaphore *sem)
{
unsigned long flags;
@@ -74,7 +74,7 @@ EXPORT_SYMBOL(down);
* If the sleep is interrupted by a signal, this function will return -EINTR.
* If the semaphore is successfully acquired, this function returns 0.
*/
-int down_interruptible(struct semaphore *sem)
+int __sched down_interruptible(struct semaphore *sem)
{
unsigned long flags;
int result = 0;
@@ -101,7 +101,7 @@ EXPORT_SYMBOL(down_interruptible);
* -EINTR. If the semaphore is successfully acquired, this function returns
* 0.
*/
-int down_killable(struct semaphore *sem)
+int __sched down_killable(struct semaphore *sem)
{
unsigned long flags;
int result = 0;
@@ -131,7 +131,7 @@ EXPORT_SYMBOL(down_killable);
* Unlike mutex_trylock, this function can be used from interrupt context,
* and the semaphore can be released by any task or interrupt.
*/
-int down_trylock(struct semaphore *sem)
+int __sched down_trylock(struct semaphore *sem)
{
unsigned long flags;
int count;
@@ -156,7 +156,7 @@ EXPORT_SYMBOL(down_trylock);
* If the semaphore is not released within the specified number of jiffies,
* this function returns -ETIME. It returns 0 if the semaphore was acquired.
*/
-int down_timeout(struct semaphore *sem, long timeout)
+int __sched down_timeout(struct semaphore *sem, long timeout)
{
unsigned long flags;
int result = 0;
@@ -180,7 +180,7 @@ EXPORT_SYMBOL(down_timeout);
* Release the semaphore. Unlike mutexes, up() may be called from any
* context and even by tasks which have never called down().
*/
-void up(struct semaphore *sem)
+void __sched up(struct semaphore *sem)
{
unsigned long flags;
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 7f49baaa4979..8475a0794f8c 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -133,7 +133,7 @@ BUILD_LOCK_OPS(write, rwlock);
#endif
#ifndef CONFIG_INLINE_SPIN_TRYLOCK
-int __lockfunc _raw_spin_trylock(raw_spinlock_t *lock)
+noinline int __lockfunc _raw_spin_trylock(raw_spinlock_t *lock)
{
return __raw_spin_trylock(lock);
}
@@ -141,7 +141,7 @@ EXPORT_SYMBOL(_raw_spin_trylock);
#endif
#ifndef CONFIG_INLINE_SPIN_TRYLOCK_BH
-int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock)
+noinline int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock)
{
return __raw_spin_trylock_bh(lock);
}
@@ -149,7 +149,7 @@ EXPORT_SYMBOL(_raw_spin_trylock_bh);
#endif
#ifndef CONFIG_INLINE_SPIN_LOCK
-void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)
{
__raw_spin_lock(lock);
}
@@ -157,7 +157,7 @@ EXPORT_SYMBOL(_raw_spin_lock);
#endif
#ifndef CONFIG_INLINE_SPIN_LOCK_IRQSAVE
-unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock)
+noinline unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock)
{
return __raw_spin_lock_irqsave(lock);
}
@@ -165,7 +165,7 @@ EXPORT_SYMBOL(_raw_spin_lock_irqsave);
#endif
#ifndef CONFIG_INLINE_SPIN_LOCK_IRQ
-void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock)
{
__raw_spin_lock_irq(lock);
}
@@ -173,7 +173,7 @@ EXPORT_SYMBOL(_raw_spin_lock_irq);
#endif
#ifndef CONFIG_INLINE_SPIN_LOCK_BH
-void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)
{
__raw_spin_lock_bh(lock);
}
@@ -181,7 +181,7 @@ EXPORT_SYMBOL(_raw_spin_lock_bh);
#endif
#ifdef CONFIG_UNINLINE_SPIN_UNLOCK
-void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)
{
__raw_spin_unlock(lock);
}
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(_raw_spin_unlock);
#endif
#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE
-void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
+noinline void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
{
__raw_spin_unlock_irqrestore(lock, flags);
}
@@ -197,7 +197,7 @@ EXPORT_SYMBOL(_raw_spin_unlock_irqrestore);
#endif
#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ
-void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock)
{
__raw_spin_unlock_irq(lock);
}
@@ -205,7 +205,7 @@ EXPORT_SYMBOL(_raw_spin_unlock_irq);
#endif
#ifndef CONFIG_INLINE_SPIN_UNLOCK_BH
-void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
{
__raw_spin_unlock_bh(lock);
}
@@ -215,7 +215,7 @@ EXPORT_SYMBOL(_raw_spin_unlock_bh);
#ifndef CONFIG_PREEMPT_RT
#ifndef CONFIG_INLINE_READ_TRYLOCK
-int __lockfunc _raw_read_trylock(rwlock_t *lock)
+noinline int __lockfunc _raw_read_trylock(rwlock_t *lock)
{
return __raw_read_trylock(lock);
}
@@ -223,7 +223,7 @@ EXPORT_SYMBOL(_raw_read_trylock);
#endif
#ifndef CONFIG_INLINE_READ_LOCK
-void __lockfunc _raw_read_lock(rwlock_t *lock)
+noinline void __lockfunc _raw_read_lock(rwlock_t *lock)
{
__raw_read_lock(lock);
}
@@ -231,7 +231,7 @@ EXPORT_SYMBOL(_raw_read_lock);
#endif
#ifndef CONFIG_INLINE_READ_LOCK_IRQSAVE
-unsigned long __lockfunc _raw_read_lock_irqsave(rwlock_t *lock)
+noinline unsigned long __lockfunc _raw_read_lock_irqsave(rwlock_t *lock)
{
return __raw_read_lock_irqsave(lock);
}
@@ -239,7 +239,7 @@ EXPORT_SYMBOL(_raw_read_lock_irqsave);
#endif
#ifndef CONFIG_INLINE_READ_LOCK_IRQ
-void __lockfunc _raw_read_lock_irq(rwlock_t *lock)
+noinline void __lockfunc _raw_read_lock_irq(rwlock_t *lock)
{
__raw_read_lock_irq(lock);
}
@@ -247,7 +247,7 @@ EXPORT_SYMBOL(_raw_read_lock_irq);
#endif
#ifndef CONFIG_INLINE_READ_LOCK_BH
-void __lockfunc _raw_read_lock_bh(rwlock_t *lock)
+noinline void __lockfunc _raw_read_lock_bh(rwlock_t *lock)
{
__raw_read_lock_bh(lock);
}
@@ -255,7 +255,7 @@ EXPORT_SYMBOL(_raw_read_lock_bh);
#endif
#ifndef CONFIG_INLINE_READ_UNLOCK
-void __lockfunc _raw_read_unlock(rwlock_t *lock)
+noinline void __lockfunc _raw_read_unlock(rwlock_t *lock)
{
__raw_read_unlock(lock);
}
@@ -263,7 +263,7 @@ EXPORT_SYMBOL(_raw_read_unlock);
#endif
#ifndef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE
-void __lockfunc _raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+noinline void __lockfunc _raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
{
__raw_read_unlock_irqrestore(lock, flags);
}
@@ -271,7 +271,7 @@ EXPORT_SYMBOL(_raw_read_unlock_irqrestore);
#endif
#ifndef CONFIG_INLINE_READ_UNLOCK_IRQ
-void __lockfunc _raw_read_unlock_irq(rwlock_t *lock)
+noinline void __lockfunc _raw_read_unlock_irq(rwlock_t *lock)
{
__raw_read_unlock_irq(lock);
}
@@ -279,7 +279,7 @@ EXPORT_SYMBOL(_raw_read_unlock_irq);
#endif
#ifndef CONFIG_INLINE_READ_UNLOCK_BH
-void __lockfunc _raw_read_unlock_bh(rwlock_t *lock)
+noinline void __lockfunc _raw_read_unlock_bh(rwlock_t *lock)
{
__raw_read_unlock_bh(lock);
}
@@ -287,7 +287,7 @@ EXPORT_SYMBOL(_raw_read_unlock_bh);
#endif
#ifndef CONFIG_INLINE_WRITE_TRYLOCK
-int __lockfunc _raw_write_trylock(rwlock_t *lock)
+noinline int __lockfunc _raw_write_trylock(rwlock_t *lock)
{
return __raw_write_trylock(lock);
}
@@ -295,7 +295,7 @@ EXPORT_SYMBOL(_raw_write_trylock);
#endif
#ifndef CONFIG_INLINE_WRITE_LOCK
-void __lockfunc _raw_write_lock(rwlock_t *lock)
+noinline void __lockfunc _raw_write_lock(rwlock_t *lock)
{
__raw_write_lock(lock);
}
@@ -313,7 +313,7 @@ EXPORT_SYMBOL(_raw_write_lock_nested);
#endif
#ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE
-unsigned long __lockfunc _raw_write_lock_irqsave(rwlock_t *lock)
+noinline unsigned long __lockfunc _raw_write_lock_irqsave(rwlock_t *lock)
{
return __raw_write_lock_irqsave(lock);
}
@@ -321,7 +321,7 @@ EXPORT_SYMBOL(_raw_write_lock_irqsave);
#endif
#ifndef CONFIG_INLINE_WRITE_LOCK_IRQ
-void __lockfunc _raw_write_lock_irq(rwlock_t *lock)
+noinline void __lockfunc _raw_write_lock_irq(rwlock_t *lock)
{
__raw_write_lock_irq(lock);
}
@@ -329,7 +329,7 @@ EXPORT_SYMBOL(_raw_write_lock_irq);
#endif
#ifndef CONFIG_INLINE_WRITE_LOCK_BH
-void __lockfunc _raw_write_lock_bh(rwlock_t *lock)
+noinline void __lockfunc _raw_write_lock_bh(rwlock_t *lock)
{
__raw_write_lock_bh(lock);
}
@@ -337,7 +337,7 @@ EXPORT_SYMBOL(_raw_write_lock_bh);
#endif
#ifndef CONFIG_INLINE_WRITE_UNLOCK
-void __lockfunc _raw_write_unlock(rwlock_t *lock)
+noinline void __lockfunc _raw_write_unlock(rwlock_t *lock)
{
__raw_write_unlock(lock);
}
@@ -345,7 +345,7 @@ EXPORT_SYMBOL(_raw_write_unlock);
#endif
#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE
-void __lockfunc _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+noinline void __lockfunc _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
{
__raw_write_unlock_irqrestore(lock, flags);
}
@@ -353,7 +353,7 @@ EXPORT_SYMBOL(_raw_write_unlock_irqrestore);
#endif
#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQ
-void __lockfunc _raw_write_unlock_irq(rwlock_t *lock)
+noinline void __lockfunc _raw_write_unlock_irq(rwlock_t *lock)
{
__raw_write_unlock_irq(lock);
}
@@ -361,7 +361,7 @@ EXPORT_SYMBOL(_raw_write_unlock_irq);
#endif
#ifndef CONFIG_INLINE_WRITE_UNLOCK_BH
-void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
+noinline void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
{
__raw_write_unlock_bh(lock);
}
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 353004155d65..43efb2a04160 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -399,7 +399,7 @@ static int *get_random_order(int count)
order[n] = n;
for (n = count - 1; n > 1; n--) {
- r = get_random_int() % (n + 1);
+ r = prandom_u32_max(n + 1);
if (r != n) {
tmp = order[n];
order[n] = order[r];
@@ -538,7 +538,7 @@ static void stress_one_work(struct work_struct *work)
{
struct stress *stress = container_of(work, typeof(*stress), work);
const int nlocks = stress->nlocks;
- struct ww_mutex *lock = stress->locks + (get_random_int() % nlocks);
+ struct ww_mutex *lock = stress->locks + prandom_u32_max(nlocks);
int err;
do {
diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c
index 4d0bcb3d9e44..c033572d83f0 100644
--- a/kernel/module/decompress.c
+++ b/kernel/module/decompress.c
@@ -256,7 +256,7 @@ void module_decompress_cleanup(struct load_info *info)
static ssize_t compression_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
- return sysfs_emit(buf, "%s\n", __stringify(MODULE_COMPRESSION));
+ return sysfs_emit(buf, __stringify(MODULE_COMPRESSION) "\n");
}
static struct kobj_attribute module_compression_attr = __ATTR_RO(compression);
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index 680d980a4fb2..2e2bf236f558 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -53,6 +53,7 @@ extern const struct kernel_symbol __stop___ksymtab_gpl[];
extern const s32 __start___kcrctab[];
extern const s32 __start___kcrctab_gpl[];
+#include <linux/dynamic_debug.h>
struct load_info {
const char *name;
/* pointer to module in temporary copy, freed at end of load_module() */
@@ -62,8 +63,7 @@ struct load_info {
Elf_Shdr *sechdrs;
char *secstrings, *strtab;
unsigned long symoffs, stroffs, init_typeoffs, core_typeoffs;
- struct _ddebug *debug;
- unsigned int num_debug;
+ struct _ddebug_info dyndbg;
bool sig_ok;
#ifdef CONFIG_KALLSYMS
unsigned long mod_kallsyms_init_off;
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 70c0b2c6fef8..d02d39c7174e 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1594,16 +1594,16 @@ static void free_modinfo(struct module *mod)
}
}
-static void dynamic_debug_setup(struct module *mod, struct _ddebug *debug, unsigned int num)
+static void dynamic_debug_setup(struct module *mod, struct _ddebug_info *dyndbg)
{
- if (!debug)
+ if (!dyndbg->num_descs)
return;
- ddebug_add_module(debug, num, mod->name);
+ ddebug_add_module(dyndbg, mod->name);
}
-static void dynamic_debug_remove(struct module *mod, struct _ddebug *debug)
+static void dynamic_debug_remove(struct module *mod, struct _ddebug_info *dyndbg)
{
- if (debug)
+ if (dyndbg->num_descs)
ddebug_remove_module(mod->name);
}
@@ -2107,8 +2107,10 @@ static int find_module_sections(struct module *mod, struct load_info *info)
if (section_addr(info, "__obsparm"))
pr_warn("%s: Ignoring obsolete parameters\n", mod->name);
- info->debug = section_objs(info, "__dyndbg",
- sizeof(*info->debug), &info->num_debug);
+ info->dyndbg.descs = section_objs(info, "__dyndbg",
+ sizeof(*info->dyndbg.descs), &info->dyndbg.num_descs);
+ info->dyndbg.classes = section_objs(info, "__dyndbg_classes",
+ sizeof(*info->dyndbg.classes), &info->dyndbg.num_classes);
return 0;
}
@@ -2799,7 +2801,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
}
init_build_id(mod, info);
- dynamic_debug_setup(mod, info->debug, info->num_debug);
+ dynamic_debug_setup(mod, &info->dyndbg);
/* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
ftrace_module_init(mod);
@@ -2863,7 +2865,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
ddebug_cleanup:
ftrace_release_mod(mod);
- dynamic_debug_remove(mod, info->debug);
+ dynamic_debug_remove(mod, &info->dyndbg);
synchronize_rcu();
kfree(mod->args);
free_arch_cleanup:
diff --git a/kernel/module/tracking.c b/kernel/module/tracking.c
index 7f8133044d09..26d812e07615 100644
--- a/kernel/module/tracking.c
+++ b/kernel/module/tracking.c
@@ -10,6 +10,7 @@
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/list.h>
+#include <linux/debugfs.h>
#include <linux/rculist.h>
#include "internal.h"
@@ -21,6 +22,9 @@ int try_add_tainted_module(struct module *mod)
module_assert_mutex_or_preempt();
+ if (!mod->taints)
+ goto out;
+
list_for_each_entry_rcu(mod_taint, &unloaded_tainted_modules, list,
lockdep_is_held(&module_mutex)) {
if (!strcmp(mod_taint->name, mod->name) &&
@@ -59,3 +63,70 @@ void print_unloaded_tainted_modules(void)
}
}
}
+
+#ifdef CONFIG_DEBUG_FS
+static void *unloaded_tainted_modules_seq_start(struct seq_file *m, loff_t *pos)
+ __acquires(rcu)
+{
+ rcu_read_lock();
+ return seq_list_start_rcu(&unloaded_tainted_modules, *pos);
+}
+
+static void *unloaded_tainted_modules_seq_next(struct seq_file *m, void *p, loff_t *pos)
+{
+ return seq_list_next_rcu(p, &unloaded_tainted_modules, pos);
+}
+
+static void unloaded_tainted_modules_seq_stop(struct seq_file *m, void *p)
+ __releases(rcu)
+{
+ rcu_read_unlock();
+}
+
+static int unloaded_tainted_modules_seq_show(struct seq_file *m, void *p)
+{
+ struct mod_unload_taint *mod_taint;
+ char buf[MODULE_FLAGS_BUF_SIZE];
+ size_t l;
+
+ mod_taint = list_entry(p, struct mod_unload_taint, list);
+ l = module_flags_taint(mod_taint->taints, buf);
+ buf[l++] = '\0';
+
+ seq_printf(m, "%s (%s) %llu", mod_taint->name, buf, mod_taint->count);
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+static const struct seq_operations unloaded_tainted_modules_seq_ops = {
+ .start = unloaded_tainted_modules_seq_start,
+ .next = unloaded_tainted_modules_seq_next,
+ .stop = unloaded_tainted_modules_seq_stop,
+ .show = unloaded_tainted_modules_seq_show,
+};
+
+static int unloaded_tainted_modules_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &unloaded_tainted_modules_seq_ops);
+}
+
+static const struct file_operations unloaded_tainted_modules_fops = {
+ .open = unloaded_tainted_modules_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static int __init unloaded_tainted_modules_init(void)
+{
+ struct dentry *dir;
+
+ dir = debugfs_create_dir("modules", NULL);
+ debugfs_create_file("unloaded_tainted", 0444, dir, NULL,
+ &unloaded_tainted_modules_fops);
+
+ return 0;
+}
+module_init(unloaded_tainted_modules_init);
+#endif /* CONFIG_DEBUG_FS */
diff --git a/kernel/panic.c b/kernel/panic.c
index c6eb8f8db0c0..da323209f583 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -329,9 +329,6 @@ void panic(const char *fmt, ...)
if (_crash_kexec_post_notifiers)
__crash_kexec(NULL);
-#ifdef CONFIG_VT
- unblank_screen();
-#endif
console_unblank();
/*
diff --git a/kernel/pid.c b/kernel/pid.c
index 2fc0a16ec77b..3fbc5e46b721 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -519,6 +519,7 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{
return idr_get_next(&ns->idr, &nr);
}
+EXPORT_SYMBOL_GPL(find_ge_pid);
struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
{
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 89c71fce225d..f58a0aa92310 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -92,20 +92,24 @@ bool hibernation_available(void)
*/
void hibernation_set_ops(const struct platform_hibernation_ops *ops)
{
+ unsigned int sleep_flags;
+
if (ops && !(ops->begin && ops->end && ops->pre_snapshot
&& ops->prepare && ops->finish && ops->enter && ops->pre_restore
&& ops->restore_cleanup && ops->leave)) {
WARN_ON(1);
return;
}
- lock_system_sleep();
+
+ sleep_flags = lock_system_sleep();
+
hibernation_ops = ops;
if (ops)
hibernation_mode = HIBERNATION_PLATFORM;
else if (hibernation_mode == HIBERNATION_PLATFORM)
hibernation_mode = HIBERNATION_SHUTDOWN;
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
}
EXPORT_SYMBOL_GPL(hibernation_set_ops);
@@ -713,6 +717,7 @@ static int load_image_and_restore(void)
int hibernate(void)
{
bool snapshot_test = false;
+ unsigned int sleep_flags;
int error;
if (!hibernation_available()) {
@@ -720,7 +725,7 @@ int hibernate(void)
return -EPERM;
}
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
/* The snapshot device should not be opened while we're running */
if (!hibernate_acquire()) {
error = -EBUSY;
@@ -794,7 +799,7 @@ int hibernate(void)
pm_restore_console();
hibernate_release();
Unlock:
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
pr_info("hibernation exit\n");
return error;
@@ -809,9 +814,10 @@ int hibernate(void)
*/
int hibernate_quiet_exec(int (*func)(void *data), void *data)
{
+ unsigned int sleep_flags;
int error;
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
if (!hibernate_acquire()) {
error = -EBUSY;
@@ -891,7 +897,7 @@ restore:
hibernate_release();
unlock:
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
return error;
}
@@ -1100,11 +1106,12 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t n)
{
+ int mode = HIBERNATION_INVALID;
+ unsigned int sleep_flags;
int error = 0;
- int i;
int len;
char *p;
- int mode = HIBERNATION_INVALID;
+ int i;
if (!hibernation_available())
return -EPERM;
@@ -1112,7 +1119,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
p = memchr(buf, '\n', n);
len = p ? p - buf : n;
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
if (len == strlen(hibernation_modes[i])
&& !strncmp(buf, hibernation_modes[i], len)) {
@@ -1142,7 +1149,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
if (!error)
pm_pr_dbg("Hibernation mode set to '%s'\n",
hibernation_modes[mode]);
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
return error ? error : n;
}
@@ -1158,9 +1165,10 @@ static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr,
static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t n)
{
- dev_t res;
+ unsigned int sleep_flags;
int len = n;
char *name;
+ dev_t res;
if (len && buf[len-1] == '\n')
len--;
@@ -1173,9 +1181,10 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
if (!res)
return -EINVAL;
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
swsusp_resume_device = res;
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
+
pm_pr_dbg("Configured hibernation resume from disk to %u\n",
swsusp_resume_device);
noresume = 0;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index e3694034b753..31ec4a9b9d70 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -21,14 +21,16 @@
#ifdef CONFIG_PM_SLEEP
-void lock_system_sleep(void)
+unsigned int lock_system_sleep(void)
{
- current->flags |= PF_FREEZER_SKIP;
+ unsigned int flags = current->flags;
+ current->flags |= PF_NOFREEZE;
mutex_lock(&system_transition_mutex);
+ return flags;
}
EXPORT_SYMBOL_GPL(lock_system_sleep);
-void unlock_system_sleep(void)
+void unlock_system_sleep(unsigned int flags)
{
/*
* Don't use freezer_count() because we don't want the call to
@@ -46,7 +48,8 @@ void unlock_system_sleep(void)
* Which means, if we use try_to_freeze() here, it would make them
* enter the refrigerator, thus causing hibernation to lockup.
*/
- current->flags &= ~PF_FREEZER_SKIP;
+ if (!(flags & PF_NOFREEZE))
+ current->flags &= ~PF_NOFREEZE;
mutex_unlock(&system_transition_mutex);
}
EXPORT_SYMBOL_GPL(unlock_system_sleep);
@@ -263,16 +266,17 @@ static ssize_t pm_test_show(struct kobject *kobj, struct kobj_attribute *attr,
static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t n)
{
+ unsigned int sleep_flags;
const char * const *s;
+ int error = -EINVAL;
int level;
char *p;
int len;
- int error = -EINVAL;
p = memchr(buf, '\n', n);
len = p ? p - buf : n;
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
level = TEST_FIRST;
for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++)
@@ -282,7 +286,7 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
break;
}
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
return error ? error : n;
}
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 3068601e585a..ddd9988327fe 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -50,8 +50,7 @@ static int try_to_freeze_tasks(bool user_only)
if (p == current || !freeze_task(p))
continue;
- if (!freezer_should_skip(p))
- todo++;
+ todo++;
}
read_unlock(&tasklist_lock);
@@ -96,8 +95,7 @@ static int try_to_freeze_tasks(bool user_only)
if (!wakeup || pm_debug_messages_on) {
read_lock(&tasklist_lock);
for_each_process_thread(g, p) {
- if (p != current && !freezer_should_skip(p)
- && freezing(p) && !frozen(p))
+ if (p != current && freezing(p) && !frozen(p))
sched_show_task(p);
}
read_unlock(&tasklist_lock);
@@ -129,7 +127,7 @@ int freeze_processes(void)
current->flags |= PF_SUSPEND_TASK;
if (!pm_freezing)
- atomic_inc(&system_freezing_cnt);
+ static_branch_inc(&freezer_active);
pm_wakeup_clear(0);
pr_info("Freezing user space processes ... ");
@@ -190,7 +188,7 @@ void thaw_processes(void)
trace_suspend_resume(TPS("thaw_processes"), 0, true);
if (pm_freezing)
- atomic_dec(&system_freezing_cnt);
+ static_branch_dec(&freezer_active);
pm_freezing = false;
pm_nosig_freezing = false;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 827075944d28..fa3bf161d13f 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -75,9 +75,11 @@ EXPORT_SYMBOL_GPL(pm_suspend_default_s2idle);
void s2idle_set_ops(const struct platform_s2idle_ops *ops)
{
- lock_system_sleep();
+ unsigned int sleep_flags;
+
+ sleep_flags = lock_system_sleep();
s2idle_ops = ops;
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
}
static void s2idle_begin(void)
@@ -136,6 +138,9 @@ static void s2idle_loop(void)
break;
}
+ if (s2idle_ops && s2idle_ops->check)
+ s2idle_ops->check();
+
s2idle_enter();
}
@@ -200,7 +205,9 @@ __setup("mem_sleep_default=", mem_sleep_default_setup);
*/
void suspend_set_ops(const struct platform_suspend_ops *ops)
{
- lock_system_sleep();
+ unsigned int sleep_flags;
+
+ sleep_flags = lock_system_sleep();
suspend_ops = ops;
@@ -216,7 +223,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops)
mem_sleep_current = PM_SUSPEND_MEM;
}
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
}
EXPORT_SYMBOL_GPL(suspend_set_ops);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index d43c2aa583b2..3a4e70366f35 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -47,12 +47,13 @@ int is_hibernate_resume_dev(dev_t dev)
static int snapshot_open(struct inode *inode, struct file *filp)
{
struct snapshot_data *data;
+ unsigned int sleep_flags;
int error;
if (!hibernation_available())
return -EPERM;
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
if (!hibernate_acquire()) {
error = -EBUSY;
@@ -98,7 +99,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
data->dev = 0;
Unlock:
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
return error;
}
@@ -106,8 +107,9 @@ static int snapshot_open(struct inode *inode, struct file *filp)
static int snapshot_release(struct inode *inode, struct file *filp)
{
struct snapshot_data *data;
+ unsigned int sleep_flags;
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
swsusp_free();
data = filp->private_data;
@@ -124,7 +126,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
PM_POST_HIBERNATION : PM_POST_RESTORE);
hibernate_release();
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
return 0;
}
@@ -132,11 +134,12 @@ static int snapshot_release(struct inode *inode, struct file *filp)
static ssize_t snapshot_read(struct file *filp, char __user *buf,
size_t count, loff_t *offp)
{
+ loff_t pg_offp = *offp & ~PAGE_MASK;
struct snapshot_data *data;
+ unsigned int sleep_flags;
ssize_t res;
- loff_t pg_offp = *offp & ~PAGE_MASK;
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
data = filp->private_data;
if (!data->ready) {
@@ -157,7 +160,7 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
*offp += res;
Unlock:
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
return res;
}
@@ -165,16 +168,17 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
static ssize_t snapshot_write(struct file *filp, const char __user *buf,
size_t count, loff_t *offp)
{
+ loff_t pg_offp = *offp & ~PAGE_MASK;
struct snapshot_data *data;
+ unsigned long sleep_flags;
ssize_t res;
- loff_t pg_offp = *offp & ~PAGE_MASK;
if (need_wait) {
wait_for_device_probe();
need_wait = false;
}
- lock_system_sleep();
+ sleep_flags = lock_system_sleep();
data = filp->private_data;
@@ -196,7 +200,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
if (res > 0)
*offp += res;
unlock:
- unlock_system_sleep();
+ unlock_system_sleep(sleep_flags);
return res;
}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a1a81fd9889b..e4f1e7478b52 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -220,9 +220,6 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
}
#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */
-/* Number of registered extended console drivers. */
-static int nr_ext_console_drivers;
-
/*
* Helper macros to handle lockdep when locking/unlocking console_sem. We use
* macros instead of functions so that _RET_IP_ contains useful information.
@@ -433,7 +430,7 @@ static struct printk_ringbuffer *prb = &printk_rb_static;
* per_cpu_areas are initialised. This variable is set to true when
* it's safe to access per-CPU data.
*/
-static bool __printk_percpu_data_ready __read_mostly;
+static bool __printk_percpu_data_ready __ro_after_init;
bool printk_percpu_data_ready(void)
{
@@ -2296,6 +2293,7 @@ asmlinkage __visible int _printk(const char *fmt, ...)
}
EXPORT_SYMBOL(_printk);
+static bool pr_flush(int timeout_ms, bool reset_on_progress);
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress);
#else /* CONFIG_PRINTK */
@@ -2330,6 +2328,7 @@ static void call_console_driver(struct console *con, const char *text, size_t le
{
}
static bool suppress_message_printing(int level) { return false; }
+static bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; }
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }
#endif /* CONFIG_PRINTK */
@@ -3186,9 +3185,6 @@ void register_console(struct console *newcon)
console_drivers->next = newcon;
}
- if (newcon->flags & CON_EXTENDED)
- nr_ext_console_drivers++;
-
newcon->dropped = 0;
if (newcon->flags & CON_PRINTBUFFER) {
/* Get a consistent copy of @syslog_seq. */
@@ -3213,9 +3209,6 @@ void register_console(struct console *newcon)
if (bootcon_enabled &&
((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) &&
!keep_bootcon) {
- /* We need to iterate through all boot consoles, to make
- * sure we print everything out, before we unregister them.
- */
for_each_console(con)
if (con->flags & CON_BOOT)
unregister_console(con);
@@ -3254,9 +3247,6 @@ int unregister_console(struct console *console)
if (res)
goto out_disable_unlock;
- if (console->flags & CON_EXTENDED)
- nr_ext_console_drivers--;
-
/*
* If this isn't the last console and it has CON_CONSDEV set, we
* need to set it on the next preferred console.
@@ -3438,11 +3428,10 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
* Context: Process context. May sleep while acquiring console lock.
* Return: true if all enabled printers are caught up.
*/
-bool pr_flush(int timeout_ms, bool reset_on_progress)
+static bool pr_flush(int timeout_ms, bool reset_on_progress)
{
return __pr_flush(NULL, timeout_ms, reset_on_progress);
}
-EXPORT_SYMBOL(pr_flush);
/*
* Delayed printk version, for scheduler-internal messages:
diff --git a/kernel/profile.c b/kernel/profile.c
index 7ea01ba30e75..8a77769bc4b4 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -59,43 +59,39 @@ int profile_setup(char *str)
static const char schedstr[] = "schedule";
static const char sleepstr[] = "sleep";
static const char kvmstr[] = "kvm";
+ const char *select = NULL;
int par;
if (!strncmp(str, sleepstr, strlen(sleepstr))) {
#ifdef CONFIG_SCHEDSTATS
force_schedstat_enabled();
prof_on = SLEEP_PROFILING;
- if (str[strlen(sleepstr)] == ',')
- str += strlen(sleepstr) + 1;
- if (get_option(&str, &par))
- prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
- pr_info("kernel sleep profiling enabled (shift: %u)\n",
- prof_shift);
+ select = sleepstr;
#else
pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
#endif /* CONFIG_SCHEDSTATS */
} else if (!strncmp(str, schedstr, strlen(schedstr))) {
prof_on = SCHED_PROFILING;
- if (str[strlen(schedstr)] == ',')
- str += strlen(schedstr) + 1;
- if (get_option(&str, &par))
- prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
- pr_info("kernel schedule profiling enabled (shift: %u)\n",
- prof_shift);
+ select = schedstr;
} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
prof_on = KVM_PROFILING;
- if (str[strlen(kvmstr)] == ',')
- str += strlen(kvmstr) + 1;
- if (get_option(&str, &par))
- prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
- pr_info("kernel KVM profiling enabled (shift: %u)\n",
- prof_shift);
+ select = kvmstr;
} else if (get_option(&str, &par)) {
prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
prof_on = CPU_PROFILING;
pr_info("kernel profiling enabled (shift: %u)\n",
prof_shift);
}
+
+ if (select) {
+ if (str[strlen(select)] == ',')
+ str += strlen(select) + 1;
+ if (get_option(&str, &par))
+ prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
+ pr_info("kernel %s profiling enabled (shift: %u)\n",
+ select, prof_shift);
+ }
+
return 1;
}
__setup("profile=", profile_setup);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1893d909e45c..54482193e1ed 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -269,7 +269,7 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
read_unlock(&tasklist_lock);
if (!ret && !ignore_state &&
- WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED)))
+ WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED|TASK_FROZEN)))
ret = -ESRCH;
return ret;
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 3c35445bf5ad..3bba88c7ffc6 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -243,6 +243,17 @@ void migrate_to_reboot_cpu(void)
set_cpus_allowed_ptr(current, cpumask_of(cpu));
}
+/*
+ * Notifier list for kernel code which wants to be called
+ * to prepare system for restart.
+ */
+static BLOCKING_NOTIFIER_HEAD(restart_prep_handler_list);
+
+static void do_kernel_restart_prepare(void)
+{
+ blocking_notifier_call_chain(&restart_prep_handler_list, 0, NULL);
+}
+
/**
* kernel_restart - reboot the system
* @cmd: pointer to buffer containing command to execute for restart
@@ -254,6 +265,7 @@ void migrate_to_reboot_cpu(void)
void kernel_restart(char *cmd)
{
kernel_restart_prepare(cmd);
+ do_kernel_restart_prepare();
migrate_to_reboot_cpu();
syscore_shutdown();
if (!cmd)
@@ -396,6 +408,11 @@ register_sys_off_handler(enum sys_off_mode mode,
handler->list = &power_off_handler_list;
break;
+ case SYS_OFF_MODE_RESTART_PREPARE:
+ handler->list = &restart_prep_handler_list;
+ handler->blocking = true;
+ break;
+
case SYS_OFF_MODE_RESTART:
handler->list = &restart_handler_list;
break;
diff --git a/kernel/relay.c b/kernel/relay.c
index 6a611e779e95..d7edc934c56d 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -60,10 +60,7 @@ static const struct vm_operations_struct relay_file_mmap_ops = {
*/
static struct page **relay_alloc_page_array(unsigned int n_pages)
{
- const size_t pa_size = n_pages * sizeof(struct page *);
- if (pa_size > PAGE_SIZE)
- return vzalloc(pa_size);
- return kzalloc(pa_size, GFP_KERNEL);
+ return kvcalloc(n_pages, sizeof(struct page *), GFP_KERNEL);
}
/*
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 4ebaf97f7bd8..991fc9002535 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -161,7 +161,8 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
struct task_struct *t;
unsigned long flags;
- BUG_ON(!lock_task_sighand(p, &flags));
+ if (WARN_ON_ONCE(!lock_task_sighand(p, &flags)))
+ return;
prev = p->signal->autogroup;
if (prev == ag) {
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 35f15c26ed54..d57a5c1c1cd9 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -204,6 +204,7 @@ EXPORT_SYMBOL(wait_for_completion_io_timeout);
int __sched wait_for_completion_interruptible(struct completion *x)
{
long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+
if (t == -ERESTARTSYS)
return t;
return 0;
@@ -241,12 +242,23 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
int __sched wait_for_completion_killable(struct completion *x)
{
long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
+
if (t == -ERESTARTSYS)
return t;
return 0;
}
EXPORT_SYMBOL(wait_for_completion_killable);
+int __sched wait_for_completion_state(struct completion *x, unsigned int state)
+{
+ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, state);
+
+ if (t == -ERESTARTSYS)
+ return t;
+ return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_state);
+
/**
* wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
* @x: holds the state of this particular completion
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 60fdc0faf1c9..5800b0623ff3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -143,11 +143,7 @@ __read_mostly int sysctl_resched_latency_warn_once = 1;
* Number of tasks to iterate in a single balance run.
* Limited because this is done with IRQs disabled.
*/
-#ifdef CONFIG_PREEMPT_RT
-const_debug unsigned int sysctl_sched_nr_migrate = 8;
-#else
-const_debug unsigned int sysctl_sched_nr_migrate = 32;
-#endif
+const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
__read_mostly int scheduler_running;
@@ -361,10 +357,7 @@ static void __sched_core_flip(bool enabled)
/*
* Toggle the offline CPUs.
*/
- cpumask_copy(&sched_core_mask, cpu_possible_mask);
- cpumask_andnot(&sched_core_mask, &sched_core_mask, cpu_online_mask);
-
- for_each_cpu(cpu, &sched_core_mask)
+ for_each_cpu_andnot(cpu, cpu_possible_mask, cpu_online_mask)
cpu_rq(cpu)->core_enabled = enabled;
cpus_read_unlock();
@@ -482,8 +475,7 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
* p->se.load, p->rt_priority,
* p->dl.dl_{runtime, deadline, period, flags, bw, density}
* - sched_setnuma(): p->numa_preferred_nid
- * - sched_move_task()/
- * cpu_cgroup_fork(): p->sched_task_group
+ * - sched_move_task(): p->sched_task_group
* - uclamp_update_active() p->uclamp*
*
* p->state <- TASK_*:
@@ -709,6 +701,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
rq->prev_irq_time += irq_delta;
delta -= irq_delta;
+ psi_account_irqtime(rq->curr, irq_delta);
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
if (static_key_false((&paravirt_steal_rq_enabled))) {
@@ -2329,7 +2322,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
rq = cpu_rq(new_cpu);
rq_lock(rq, rf);
- BUG_ON(task_cpu(p) != new_cpu);
+ WARN_ON_ONCE(task_cpu(p) != new_cpu);
activate_task(rq, p, 0);
check_preempt_curr(rq, p, 0);
@@ -2779,7 +2772,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
return -EINVAL;
}
- if (task_running(rq, p) || READ_ONCE(p->__state) == TASK_WAKING) {
+ if (task_on_cpu(rq, p) || READ_ONCE(p->__state) == TASK_WAKING) {
/*
* MIGRATE_ENABLE gets here because 'p == current', but for
* anything else we cannot do is_migration_disabled(), punt
@@ -3255,12 +3248,12 @@ out:
/*
* wait_task_inactive - wait for a thread to unschedule.
*
- * If @match_state is nonzero, it's the @p->state value just checked and
- * not expected to change. If it changes, i.e. @p might have woken up,
- * then return zero. When we succeed in waiting for @p to be off its CPU,
- * we return a positive number (its total switch count). If a second call
- * a short while later returns the same number, the caller can be sure that
- * @p has remained unscheduled the whole time.
+ * Wait for the thread to block in any of the states set in @match_state.
+ * If it changes, i.e. @p might have woken up, then return zero. When we
+ * succeed in waiting for @p to be off its CPU, we return a positive number
+ * (its total switch count). If a second call a short while later returns the
+ * same number, the caller can be sure that @p has remained unscheduled the
+ * whole time.
*
* The caller must ensure that the task *will* unschedule sometime soon,
* else this function might spin for a *long* time. This function can't
@@ -3291,12 +3284,12 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
*
* NOTE! Since we don't hold any locks, it's not
* even sure that "rq" stays as the right runqueue!
- * But we don't care, since "task_running()" will
+ * But we don't care, since "task_on_cpu()" will
* return false if the runqueue has changed and p
* is actually now running somewhere else!
*/
- while (task_running(rq, p)) {
- if (match_state && unlikely(READ_ONCE(p->__state) != match_state))
+ while (task_on_cpu(rq, p)) {
+ if (!(READ_ONCE(p->__state) & match_state))
return 0;
cpu_relax();
}
@@ -3308,10 +3301,10 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
*/
rq = task_rq_lock(p, &rf);
trace_sched_wait_task(p);
- running = task_running(rq, p);
+ running = task_on_cpu(rq, p);
queued = task_on_rq_queued(p);
ncsw = 0;
- if (!match_state || READ_ONCE(p->__state) == match_state)
+ if (READ_ONCE(p->__state) & match_state)
ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
task_rq_unlock(rq, p, &rf);
@@ -4397,6 +4390,17 @@ void set_numabalancing_state(bool enabled)
}
#ifdef CONFIG_PROC_SYSCTL
+static void reset_memory_tiering(void)
+{
+ struct pglist_data *pgdat;
+
+ for_each_online_pgdat(pgdat) {
+ pgdat->nbp_threshold = 0;
+ pgdat->nbp_th_nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+ pgdat->nbp_th_start = jiffies_to_msecs(jiffies);
+ }
+}
+
int sysctl_numa_balancing(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
@@ -4413,6 +4417,9 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
if (err < 0)
return err;
if (write) {
+ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
+ (state & NUMA_BALANCING_MEMORY_TIERING))
+ reset_memory_tiering();
sysctl_numa_balancing_mode = state;
__set_numabalancing_state(state);
}
@@ -5167,6 +5174,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
* finish_task_switch()'s mmdrop().
*/
switch_mm_irqs_off(prev->active_mm, next->mm, next);
+ lru_gen_use_mm(next->mm);
if (!prev->mm) { // from kernel
/* will mmdrop() in finish_task_switch(). */
@@ -6430,7 +6438,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
prev->sched_contributes_to_load =
(prev_state & TASK_UNINTERRUPTIBLE) &&
!(prev_state & TASK_NOLOAD) &&
- !(prev->flags & PF_FROZEN);
+ !(prev_state & TASK_FROZEN);
if (prev->sched_contributes_to_load)
rq->nr_uninterruptible++;
@@ -8650,7 +8658,7 @@ again:
if (curr->sched_class != p->sched_class)
goto out_unlock;
- if (task_running(p_rq, p) || !task_is_running(p))
+ if (task_on_cpu(p_rq, p) || !task_is_running(p))
goto out_unlock;
yielded = curr->sched_class->yield_to_task(rq, p);
@@ -8862,7 +8870,7 @@ void sched_show_task(struct task_struct *p)
if (pid_alive(p))
ppid = task_pid_nr(rcu_dereference(p->real_parent));
rcu_read_unlock();
- pr_cont(" stack:%5lu pid:%5d ppid:%6d flags:0x%08lx\n",
+ pr_cont(" stack:%-5lu pid:%-5d ppid:%-6d flags:0x%08lx\n",
free, task_pid_nr(p), ppid,
read_task_thread_flags(p));
@@ -8890,7 +8898,7 @@ state_filter_match(unsigned long state_filter, struct task_struct *p)
* When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
* TASK_KILLABLE).
*/
- if (state_filter == TASK_UNINTERRUPTIBLE && state == TASK_IDLE)
+ if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD))
return false;
return true;
@@ -9602,9 +9610,6 @@ LIST_HEAD(task_groups);
static struct kmem_cache *task_group_cache __read_mostly;
#endif
-DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
-DECLARE_PER_CPU(cpumask_var_t, select_rq_mask);
-
void __init sched_init(void)
{
unsigned long ptr = 0;
@@ -9648,14 +9653,6 @@ void __init sched_init(void)
#endif /* CONFIG_RT_GROUP_SCHED */
}
-#ifdef CONFIG_CPUMASK_OFFSTACK
- for_each_possible_cpu(i) {
- per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
- cpumask_size(), GFP_KERNEL, cpu_to_node(i));
- per_cpu(select_rq_mask, i) = (cpumask_var_t)kzalloc_node(
- cpumask_size(), GFP_KERNEL, cpu_to_node(i));
- }
-#endif /* CONFIG_CPUMASK_OFFSTACK */
init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
@@ -10164,7 +10161,7 @@ void sched_release_group(struct task_group *tg)
spin_unlock_irqrestore(&task_group_lock, flags);
}
-static void sched_change_group(struct task_struct *tsk, int type)
+static void sched_change_group(struct task_struct *tsk)
{
struct task_group *tg;
@@ -10180,7 +10177,7 @@ static void sched_change_group(struct task_struct *tsk, int type)
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->task_change_group)
- tsk->sched_class->task_change_group(tsk, type);
+ tsk->sched_class->task_change_group(tsk);
else
#endif
set_task_rq(tsk, task_cpu(tsk));
@@ -10211,7 +10208,7 @@ void sched_move_task(struct task_struct *tsk)
if (running)
put_prev_task(rq, tsk);
- sched_change_group(tsk, TASK_MOVE_GROUP);
+ sched_change_group(tsk);
if (queued)
enqueue_task(rq, tsk, queue_flags);
@@ -10289,53 +10286,19 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
sched_unregister_group(tg);
}
-/*
- * This is called before wake_up_new_task(), therefore we really only
- * have to set its group bits, all the other stuff does not apply.
- */
-static void cpu_cgroup_fork(struct task_struct *task)
-{
- struct rq_flags rf;
- struct rq *rq;
-
- rq = task_rq_lock(task, &rf);
-
- update_rq_clock(rq);
- sched_change_group(task, TASK_SET_GROUP);
-
- task_rq_unlock(rq, task, &rf);
-}
-
+#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{
struct task_struct *task;
struct cgroup_subsys_state *css;
- int ret = 0;
cgroup_taskset_for_each(task, css, tset) {
-#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(css_tg(css), task))
return -EINVAL;
-#endif
- /*
- * Serialize against wake_up_new_task() such that if it's
- * running, we're sure to observe its full state.
- */
- raw_spin_lock_irq(&task->pi_lock);
- /*
- * Avoid calling sched_move_task() before wake_up_new_task()
- * has happened. This would lead to problems with PELT, due to
- * move wanting to detach+attach while we're not attached yet.
- */
- if (READ_ONCE(task->__state) == TASK_NEW)
- ret = -EINVAL;
- raw_spin_unlock_irq(&task->pi_lock);
-
- if (ret)
- break;
}
- return ret;
+ return 0;
}
+#endif
static void cpu_cgroup_attach(struct cgroup_taskset *tset)
{
@@ -11171,8 +11134,9 @@ struct cgroup_subsys cpu_cgrp_subsys = {
.css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
.css_extra_stat_show = cpu_extra_stat_show,
- .fork = cpu_cgroup_fork,
+#ifdef CONFIG_RT_GROUP_SCHED
.can_attach = cpu_cgroup_can_attach,
+#endif
.attach = cpu_cgroup_attach,
.legacy_cftypes = cpu_legacy_files,
.dfl_cftypes = cpu_files,
diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c
index 93878cb2a46d..a57fd8f27498 100644
--- a/kernel/sched/core_sched.c
+++ b/kernel/sched/core_sched.c
@@ -88,7 +88,7 @@ static unsigned long sched_core_update_cookie(struct task_struct *p,
* core has now entered/left forced idle state. Defer accounting to the
* next scheduling edge, rather than always forcing a reschedule here.
*/
- if (task_running(rq, p))
+ if (task_on_cpu(rq, p))
resched_curr(rq);
task_rq_unlock(rq, p, &rf);
@@ -205,7 +205,7 @@ int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type,
default:
err = -EINVAL;
goto out;
- };
+ }
if (type == PIDTYPE_PID) {
__sched_core_set(task, cookie);
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 02d970a879ed..57c92d751bcd 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -123,7 +123,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
unsigned long cap, max_cap = 0;
int cpu, max_cpu = -1;
- if (!static_branch_unlikely(&sched_asym_cpucapacity))
+ if (!sched_asym_cpucap_active())
return 1;
/* Ensure the capacity of the CPUs fits the task. */
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index fa9ce9d83683..a286e726eb4b 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -147,7 +147,7 @@ int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
int task_pri = convert_prio(p->prio);
int idx, cpu;
- BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
+ WARN_ON_ONCE(task_pri >= CPUPRI_NR_PRIORITIES);
for (idx = 0; idx < task_pri; idx++) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0ab79d819a0d..86dea6a05267 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -124,15 +124,12 @@ static inline int dl_bw_cpus(int i)
return cpus;
}
-static inline unsigned long __dl_bw_capacity(int i)
+static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
{
- struct root_domain *rd = cpu_rq(i)->rd;
unsigned long cap = 0;
+ int i;
- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
- "sched RCU must be held");
-
- for_each_cpu_and(i, rd->span, cpu_active_mask)
+ for_each_cpu_and(i, mask, cpu_active_mask)
cap += capacity_orig_of(i);
return cap;
@@ -144,11 +141,14 @@ static inline unsigned long __dl_bw_capacity(int i)
*/
static inline unsigned long dl_bw_capacity(int i)
{
- if (!static_branch_unlikely(&sched_asym_cpucapacity) &&
+ if (!sched_asym_cpucap_active() &&
capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
} else {
- return __dl_bw_capacity(i);
+ RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+ "sched RCU must be held");
+
+ return __dl_bw_capacity(cpu_rq(i)->rd->span);
}
}
@@ -310,7 +310,7 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
{
struct rq *rq;
- BUG_ON(p->dl.flags & SCHED_FLAG_SUGOV);
+ WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
if (task_on_rq_queued(p))
return;
@@ -431,8 +431,8 @@ static void task_non_contending(struct task_struct *p)
sub_rq_bw(&p->dl, &rq->dl);
raw_spin_lock(&dl_b->lock);
__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
- __dl_clear_params(p);
raw_spin_unlock(&dl_b->lock);
+ __dl_clear_params(p);
}
return;
@@ -607,7 +607,7 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
{
struct rb_node *leftmost;
- BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+ WARN_ON_ONCE(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
leftmost = rb_add_cached(&p->pushable_dl_tasks,
&rq->dl.pushable_dl_tasks_root,
@@ -684,7 +684,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
* Failed to find any suitable CPU.
* The task will never come back!
*/
- BUG_ON(dl_bandwidth_enabled());
+ WARN_ON_ONCE(dl_bandwidth_enabled());
/*
* If admission control is disabled we
@@ -770,6 +770,14 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, int flags);
+static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
+ struct rq *rq)
+{
+ /* for non-boosted task, pi_of(dl_se) == dl_se */
+ dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+ dl_se->runtime = pi_of(dl_se)->dl_runtime;
+}
+
/*
* We are being explicitly informed that a new instance is starting,
* and this means that:
@@ -803,8 +811,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
* future; in fact, we must consider execution overheads (time
* spent on hardirq context, etc.).
*/
- dl_se->deadline = rq_clock(rq) + dl_se->dl_deadline;
- dl_se->runtime = dl_se->dl_runtime;
+ replenish_dl_new_period(dl_se, rq);
}
/*
@@ -830,16 +837,14 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
- BUG_ON(pi_of(dl_se)->dl_runtime <= 0);
+ WARN_ON_ONCE(pi_of(dl_se)->dl_runtime <= 0);
/*
* This could be the case for a !-dl task that is boosted.
* Just go with full inherited parameters.
*/
- if (dl_se->dl_deadline == 0) {
- dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
- dl_se->runtime = pi_of(dl_se)->dl_runtime;
- }
+ if (dl_se->dl_deadline == 0)
+ replenish_dl_new_period(dl_se, rq);
if (dl_se->dl_yielded && dl_se->runtime > 0)
dl_se->runtime = 0;
@@ -866,8 +871,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
*/
if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
printk_deferred_once("sched: DL replenish lagged too much\n");
- dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
- dl_se->runtime = pi_of(dl_se)->dl_runtime;
+ replenish_dl_new_period(dl_se, rq);
}
if (dl_se->dl_yielded)
@@ -1024,8 +1028,7 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
return;
}
- dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
- dl_se->runtime = pi_of(dl_se)->dl_runtime;
+ replenish_dl_new_period(dl_se, rq);
}
}
@@ -1333,11 +1336,7 @@ static void update_curr_dl(struct rq *rq)
trace_sched_stat_runtime(curr, delta_exec, 0);
- curr->se.sum_exec_runtime += delta_exec;
- account_group_exec_runtime(curr, delta_exec);
-
- curr->se.exec_start = now;
- cgroup_account_cputime(curr, delta_exec);
+ update_current_exec_runtime(curr, now, delta_exec);
if (dl_entity_is_special(dl_se))
return;
@@ -1616,7 +1615,7 @@ static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
- BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node));
+ WARN_ON_ONCE(!RB_EMPTY_NODE(&dl_se->rb_node));
rb_add_cached(&dl_se->rb_node, &dl_rq->root, __dl_less);
@@ -1640,7 +1639,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
static void
enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
{
- BUG_ON(on_dl_rq(dl_se));
+ WARN_ON_ONCE(on_dl_rq(dl_se));
update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags);
@@ -1814,6 +1813,14 @@ static void yield_task_dl(struct rq *rq)
#ifdef CONFIG_SMP
+static inline bool dl_task_is_earliest_deadline(struct task_struct *p,
+ struct rq *rq)
+{
+ return (!rq->dl.dl_nr_running ||
+ dl_time_before(p->dl.deadline,
+ rq->dl.earliest_dl.curr));
+}
+
static int find_later_rq(struct task_struct *task);
static int
@@ -1849,16 +1856,14 @@ select_task_rq_dl(struct task_struct *p, int cpu, int flags)
* Take the capacity of the CPU into account to
* ensure it fits the requirement of the task.
*/
- if (static_branch_unlikely(&sched_asym_cpucapacity))
+ if (sched_asym_cpucap_active())
select_rq |= !dl_task_fits_capacity(p, cpu);
if (select_rq) {
int target = find_later_rq(p);
if (target != -1 &&
- (dl_time_before(p->dl.deadline,
- cpu_rq(target)->dl.earliest_dl.curr) ||
- (cpu_rq(target)->dl.dl_nr_running == 0)))
+ dl_task_is_earliest_deadline(p, cpu_rq(target)))
cpu = target;
}
rcu_read_unlock();
@@ -2017,7 +2022,7 @@ static struct task_struct *pick_task_dl(struct rq *rq)
return NULL;
dl_se = pick_next_dl_entity(dl_rq);
- BUG_ON(!dl_se);
+ WARN_ON_ONCE(!dl_se);
p = dl_task_of(dl_se);
return p;
@@ -2087,7 +2092,7 @@ static void task_fork_dl(struct task_struct *p)
static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
{
- if (!task_running(rq, p) &&
+ if (!task_on_cpu(rq, p) &&
cpumask_test_cpu(cpu, &p->cpus_mask))
return 1;
return 0;
@@ -2225,9 +2230,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
later_rq = cpu_rq(cpu);
- if (later_rq->dl.dl_nr_running &&
- !dl_time_before(task->dl.deadline,
- later_rq->dl.earliest_dl.curr)) {
+ if (!dl_task_is_earliest_deadline(task, later_rq)) {
/*
* Target rq has tasks of equal or earlier deadline,
* retrying does not release any lock and is unlikely
@@ -2241,7 +2244,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
if (double_lock_balance(rq, later_rq)) {
if (unlikely(task_rq(task) != rq ||
!cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
- task_running(rq, task) ||
+ task_on_cpu(rq, task) ||
!dl_task(task) ||
!task_on_rq_queued(task))) {
double_unlock_balance(rq, later_rq);
@@ -2255,9 +2258,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
* its earliest one has a later deadline than our
* task, the rq is a good one.
*/
- if (!later_rq->dl.dl_nr_running ||
- dl_time_before(task->dl.deadline,
- later_rq->dl.earliest_dl.curr))
+ if (dl_task_is_earliest_deadline(task, later_rq))
break;
/* Otherwise we try again. */
@@ -2277,12 +2278,12 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
p = __node_2_pdl(rb_first_cached(&rq->dl.pushable_dl_tasks_root));
- BUG_ON(rq->cpu != task_cpu(p));
- BUG_ON(task_current(rq, p));
- BUG_ON(p->nr_cpus_allowed <= 1);
+ WARN_ON_ONCE(rq->cpu != task_cpu(p));
+ WARN_ON_ONCE(task_current(rq, p));
+ WARN_ON_ONCE(p->nr_cpus_allowed <= 1);
- BUG_ON(!task_on_rq_queued(p));
- BUG_ON(!dl_task(p));
+ WARN_ON_ONCE(!task_on_rq_queued(p));
+ WARN_ON_ONCE(!dl_task(p));
return p;
}
@@ -2428,9 +2429,7 @@ static void pull_dl_task(struct rq *this_rq)
* - it will preempt the last one we pulled (if any).
*/
if (p && dl_time_before(p->dl.deadline, dmin) &&
- (!this_rq->dl.dl_nr_running ||
- dl_time_before(p->dl.deadline,
- this_rq->dl.earliest_dl.curr))) {
+ dl_task_is_earliest_deadline(p, this_rq)) {
WARN_ON(p == src_rq->curr);
WARN_ON(!task_on_rq_queued(p));
@@ -2475,7 +2474,7 @@ skip:
*/
static void task_woken_dl(struct rq *rq, struct task_struct *p)
{
- if (!task_running(rq, p) &&
+ if (!task_on_cpu(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
p->nr_cpus_allowed > 1 &&
dl_task(rq->curr) &&
@@ -2492,7 +2491,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
struct root_domain *src_rd;
struct rq *rq;
- BUG_ON(!dl_task(p));
+ WARN_ON_ONCE(!dl_task(p));
rq = task_rq(p);
src_rd = rq->rd;
@@ -3007,17 +3006,15 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
const struct cpumask *trial)
{
- int ret = 1, trial_cpus;
+ unsigned long flags, cap;
struct dl_bw *cur_dl_b;
- unsigned long flags;
+ int ret = 1;
rcu_read_lock_sched();
cur_dl_b = dl_bw_of(cpumask_any(cur));
- trial_cpus = cpumask_weight(trial);
-
+ cap = __dl_bw_capacity(trial);
raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
- if (cur_dl_b->bw != -1 &&
- cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
+ if (__dl_overflow(cur_dl_b, cap, 0, 0))
ret = 0;
raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
rcu_read_unlock_sched();
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 667876da8382..1637b65ba07a 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -333,6 +333,7 @@ static __init int sched_init_debug(void)
debugfs_create_u32("scan_period_min_ms", 0644, numa, &sysctl_numa_balancing_scan_period_min);
debugfs_create_u32("scan_period_max_ms", 0644, numa, &sysctl_numa_balancing_scan_period_max);
debugfs_create_u32("scan_size_mb", 0644, numa, &sysctl_numa_balancing_scan_size);
+ debugfs_create_u32("hot_threshold_ms", 0644, numa, &sysctl_numa_balancing_hot_threshold);
#endif
debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 914096c5b1ae..e4a0b8bd941c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -40,6 +40,7 @@
#include <linux/cpuidle.h>
#include <linux/interrupt.h>
+#include <linux/memory-tiers.h>
#include <linux/mempolicy.h>
#include <linux/mutex_api.h>
#include <linux/profile.h>
@@ -799,8 +800,6 @@ void init_entity_runnable_average(struct sched_entity *se)
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}
-static void attach_entity_cfs_rq(struct sched_entity *se);
-
/*
* With new tasks being created, their initial util_avgs are extrapolated
* based on the cfs_rq's current util_avg:
@@ -835,20 +834,6 @@ void post_init_entity_util_avg(struct task_struct *p)
long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)));
long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
- if (cap > 0) {
- if (cfs_rq->avg.util_avg != 0) {
- sa->util_avg = cfs_rq->avg.util_avg * se->load.weight;
- sa->util_avg /= (cfs_rq->avg.load_avg + 1);
-
- if (sa->util_avg > cap)
- sa->util_avg = cap;
- } else {
- sa->util_avg = cap;
- }
- }
-
- sa->runnable_avg = sa->util_avg;
-
if (p->sched_class != &fair_sched_class) {
/*
* For !fair tasks do:
@@ -864,7 +849,19 @@ void post_init_entity_util_avg(struct task_struct *p)
return;
}
- attach_entity_cfs_rq(se);
+ if (cap > 0) {
+ if (cfs_rq->avg.util_avg != 0) {
+ sa->util_avg = cfs_rq->avg.util_avg * se->load.weight;
+ sa->util_avg /= (cfs_rq->avg.load_avg + 1);
+
+ if (sa->util_avg > cap)
+ sa->util_avg = cap;
+ } else {
+ sa->util_avg = cap;
+ }
+ }
+
+ sa->runnable_avg = sa->util_avg;
}
#else /* !CONFIG_SMP */
@@ -1094,6 +1091,12 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
unsigned int sysctl_numa_balancing_scan_delay = 1000;
+/* The page with hint page fault latency < threshold in ms is considered hot */
+unsigned int sysctl_numa_balancing_hot_threshold = MSEC_PER_SEC;
+
+/* Restrict the NUMA promotion throughput (MB/s) for each target node. */
+unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
+
struct numa_group {
refcount_t refcount;
@@ -1436,6 +1439,120 @@ static inline unsigned long group_weight(struct task_struct *p, int nid,
return 1000 * faults / total_faults;
}
+/*
+ * If memory tiering mode is enabled, cpupid of slow memory page is
+ * used to record scan time instead of CPU and PID. When tiering mode
+ * is disabled at run time, the scan time (in cpupid) will be
+ * interpreted as CPU and PID. So CPU needs to be checked to avoid to
+ * access out of array bound.
+ */
+static inline bool cpupid_valid(int cpupid)
+{
+ return cpupid_to_cpu(cpupid) < nr_cpu_ids;
+}
+
+/*
+ * For memory tiering mode, if there are enough free pages (more than
+ * enough watermark defined here) in fast memory node, to take full
+ * advantage of fast memory capacity, all recently accessed slow
+ * memory pages will be migrated to fast memory node without
+ * considering hot threshold.
+ */
+static bool pgdat_free_space_enough(struct pglist_data *pgdat)
+{
+ int z;
+ unsigned long enough_wmark;
+
+ enough_wmark = max(1UL * 1024 * 1024 * 1024 >> PAGE_SHIFT,
+ pgdat->node_present_pages >> 4);
+ for (z = pgdat->nr_zones - 1; z >= 0; z--) {
+ struct zone *zone = pgdat->node_zones + z;
+
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone_watermark_ok(zone, 0,
+ wmark_pages(zone, WMARK_PROMO) + enough_wmark,
+ ZONE_MOVABLE, 0))
+ return true;
+ }
+ return false;
+}
+
+/*
+ * For memory tiering mode, when page tables are scanned, the scan
+ * time will be recorded in struct page in addition to make page
+ * PROT_NONE for slow memory page. So when the page is accessed, in
+ * hint page fault handler, the hint page fault latency is calculated
+ * via,
+ *
+ * hint page fault latency = hint page fault time - scan time
+ *
+ * The smaller the hint page fault latency, the higher the possibility
+ * for the page to be hot.
+ */
+static int numa_hint_fault_latency(struct page *page)
+{
+ int last_time, time;
+
+ time = jiffies_to_msecs(jiffies);
+ last_time = xchg_page_access_time(page, time);
+
+ return (time - last_time) & PAGE_ACCESS_TIME_MASK;
+}
+
+/*
+ * For memory tiering mode, too high promotion/demotion throughput may
+ * hurt application latency. So we provide a mechanism to rate limit
+ * the number of pages that are tried to be promoted.
+ */
+static bool numa_promotion_rate_limit(struct pglist_data *pgdat,
+ unsigned long rate_limit, int nr)
+{
+ unsigned long nr_cand;
+ unsigned int now, start;
+
+ now = jiffies_to_msecs(jiffies);
+ mod_node_page_state(pgdat, PGPROMOTE_CANDIDATE, nr);
+ nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+ start = pgdat->nbp_rl_start;
+ if (now - start > MSEC_PER_SEC &&
+ cmpxchg(&pgdat->nbp_rl_start, start, now) == start)
+ pgdat->nbp_rl_nr_cand = nr_cand;
+ if (nr_cand - pgdat->nbp_rl_nr_cand >= rate_limit)
+ return true;
+ return false;
+}
+
+#define NUMA_MIGRATION_ADJUST_STEPS 16
+
+static void numa_promotion_adjust_threshold(struct pglist_data *pgdat,
+ unsigned long rate_limit,
+ unsigned int ref_th)
+{
+ unsigned int now, start, th_period, unit_th, th;
+ unsigned long nr_cand, ref_cand, diff_cand;
+
+ now = jiffies_to_msecs(jiffies);
+ th_period = sysctl_numa_balancing_scan_period_max;
+ start = pgdat->nbp_th_start;
+ if (now - start > th_period &&
+ cmpxchg(&pgdat->nbp_th_start, start, now) == start) {
+ ref_cand = rate_limit *
+ sysctl_numa_balancing_scan_period_max / MSEC_PER_SEC;
+ nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+ diff_cand = nr_cand - pgdat->nbp_th_nr_cand;
+ unit_th = ref_th * 2 / NUMA_MIGRATION_ADJUST_STEPS;
+ th = pgdat->nbp_threshold ? : ref_th;
+ if (diff_cand > ref_cand * 11 / 10)
+ th = max(th - unit_th, unit_th);
+ else if (diff_cand < ref_cand * 9 / 10)
+ th = min(th + unit_th, ref_th * 2);
+ pgdat->nbp_th_nr_cand = nr_cand;
+ pgdat->nbp_threshold = th;
+ }
+}
+
bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
int src_nid, int dst_cpu)
{
@@ -1443,9 +1560,44 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
int dst_nid = cpu_to_node(dst_cpu);
int last_cpupid, this_cpupid;
+ /*
+ * The pages in slow memory node should be migrated according
+ * to hot/cold instead of private/shared.
+ */
+ if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
+ !node_is_toptier(src_nid)) {
+ struct pglist_data *pgdat;
+ unsigned long rate_limit;
+ unsigned int latency, th, def_th;
+
+ pgdat = NODE_DATA(dst_nid);
+ if (pgdat_free_space_enough(pgdat)) {
+ /* workload changed, reset hot threshold */
+ pgdat->nbp_threshold = 0;
+ return true;
+ }
+
+ def_th = sysctl_numa_balancing_hot_threshold;
+ rate_limit = sysctl_numa_balancing_promote_rate_limit << \
+ (20 - PAGE_SHIFT);
+ numa_promotion_adjust_threshold(pgdat, rate_limit, def_th);
+
+ th = pgdat->nbp_threshold ? : def_th;
+ latency = numa_hint_fault_latency(page);
+ if (latency >= th)
+ return false;
+
+ return !numa_promotion_rate_limit(pgdat, rate_limit,
+ thp_nr_pages(page));
+ }
+
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
+ !node_is_toptier(src_nid) && !cpupid_valid(last_cpupid))
+ return false;
+
/*
* Allow first faults or private faults to migrate immediately early in
* the lifetime of a task. The magic number 4 is based on waiting for
@@ -1592,11 +1744,11 @@ numa_type numa_classify(unsigned int imbalance_pct,
#ifdef CONFIG_SCHED_SMT
/* Forward declarations of select_idle_sibling helpers */
-static inline bool test_idle_cores(int cpu, bool def);
+static inline bool test_idle_cores(int cpu);
static inline int numa_idle_core(int idle_core, int cpu)
{
if (!static_branch_likely(&sched_smt_present) ||
- idle_core >= 0 || !test_idle_cores(cpu, false))
+ idle_core >= 0 || !test_idle_cores(cpu))
return idle_core;
/*
@@ -2600,7 +2752,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
if (!join)
return;
- BUG_ON(irqs_disabled());
+ WARN_ON_ONCE(irqs_disabled());
double_lock_irq(&my_grp->lock, &grp->lock);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
@@ -2685,6 +2837,15 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
if (!p->mm)
return;
+ /*
+ * NUMA faults statistics are unnecessary for the slow memory
+ * node for memory tiering mode.
+ */
+ if (!node_is_toptier(mem_node) &&
+ (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ||
+ !cpupid_valid(last_cpupid)))
+ return;
+
/* Allocate buffer to track faults on a per-node basis */
if (unlikely(!p->numa_faults)) {
int size = sizeof(*p->numa_faults) *
@@ -2765,6 +2926,7 @@ static void task_numa_work(struct callback_head *work)
struct task_struct *p = current;
struct mm_struct *mm = p->mm;
u64 runtime = p->se.sum_exec_runtime;
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
struct vm_area_struct *vma;
unsigned long start, end;
unsigned long nr_pte_updates = 0;
@@ -2821,13 +2983,16 @@ static void task_numa_work(struct callback_head *work)
if (!mmap_read_trylock(mm))
return;
- vma = find_vma(mm, start);
+ mas_set(&mas, start);
+ vma = mas_find(&mas, ULONG_MAX);
if (!vma) {
reset_ptenuma_scan(p);
start = 0;
- vma = mm->mmap;
+ mas_set(&mas, start);
+ vma = mas_find(&mas, ULONG_MAX);
}
- for (; vma; vma = vma->vm_next) {
+
+ for (; vma; vma = mas_find(&mas, ULONG_MAX)) {
if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
continue;
@@ -3838,8 +4003,7 @@ static void migrate_se_pelt_lag(struct sched_entity *se) {}
* @cfs_rq: cfs_rq to update
*
* The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
- * avg. The immediate corollary is that all (fair) tasks must be attached, see
- * post_init_entity_util_avg().
+ * avg. The immediate corollary is that all (fair) tasks must be attached.
*
* cfs_rq->avg is used for task_h_load() and update_cfs_share() for example.
*
@@ -4003,6 +4167,7 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
#define UPDATE_TG 0x1
#define SKIP_AGE_LOAD 0x2
#define DO_ATTACH 0x4
+#define DO_DETACH 0x8
/* Update task and its cfs_rq load average */
static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
@@ -4032,6 +4197,13 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
attach_entity_load_avg(cfs_rq, se);
update_tg_load_avg(cfs_rq);
+ } else if (flags & DO_DETACH) {
+ /*
+ * DO_DETACH means we're here from dequeue_entity()
+ * and we are migrating task out of the CPU.
+ */
+ detach_entity_load_avg(cfs_rq, se);
+ update_tg_load_avg(cfs_rq);
} else if (decayed) {
cfs_rq_util_change(cfs_rq, 0);
@@ -4064,8 +4236,8 @@ static void remove_entity_load_avg(struct sched_entity *se)
/*
* tasks cannot exit without having gone through wake_up_new_task() ->
- * post_init_entity_util_avg() which will have added things to the
- * cfs_rq, so we can remove unconditionally.
+ * enqueue_task_fair() which will have added things to the cfs_rq,
+ * so we can remove unconditionally.
*/
sync_entity_load_avg(se);
@@ -4262,7 +4434,7 @@ static inline int task_fits_capacity(struct task_struct *p,
static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
{
- if (!static_branch_unlikely(&sched_asym_cpucapacity))
+ if (!sched_asym_cpucap_active())
return;
if (!p || p->nr_cpus_allowed == 1) {
@@ -4292,6 +4464,7 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
#define UPDATE_TG 0x0
#define SKIP_AGE_LOAD 0x0
#define DO_ATTACH 0x0
+#define DO_DETACH 0x0
static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int not_used1)
{
@@ -4434,7 +4607,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
/*
* When enqueuing a sched_entity, we must:
* - Update loads to have both entity and cfs_rq synced with now.
- * - Add its load to cfs_rq->runnable_avg
+ * - For group_entity, update its runnable_weight to reflect the new
+ * h_nr_running of its group cfs_rq.
* - For group_entity, update its weight to reflect the new share of
* its group cfs_rq
* - Add its new weight to cfs_rq->load.weight
@@ -4511,6 +4685,11 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
+ int action = UPDATE_TG;
+
+ if (entity_is_task(se) && task_on_rq_migrating(task_of(se)))
+ action |= DO_DETACH;
+
/*
* Update run-time statistics of the 'current'.
*/
@@ -4519,12 +4698,13 @@ 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.
- * - Subtract its load from the cfs_rq->runnable_avg.
+ * - For group_entity, update its runnable_weight to reflect the new
+ * h_nr_running of its group cfs_rq.
* - 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.
*/
- update_load_avg(cfs_rq, se, UPDATE_TG);
+ update_load_avg(cfs_rq, se, action);
se_update_runnable(se);
update_stats_dequeue_fair(cfs_rq, se, flags);
@@ -5893,8 +6073,8 @@ dequeue_throttle:
#ifdef CONFIG_SMP
/* Working cpumask for: load_balance, load_balance_newidle. */
-DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
-DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
+static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
+static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
#ifdef CONFIG_NO_HZ_COMMON
@@ -6260,7 +6440,7 @@ static inline void set_idle_cores(int cpu, int val)
WRITE_ONCE(sds->has_idle_cores, val);
}
-static inline bool test_idle_cores(int cpu, bool def)
+static inline bool test_idle_cores(int cpu)
{
struct sched_domain_shared *sds;
@@ -6268,7 +6448,7 @@ static inline bool test_idle_cores(int cpu, bool def)
if (sds)
return READ_ONCE(sds->has_idle_cores);
- return def;
+ return false;
}
/*
@@ -6284,7 +6464,7 @@ void __update_idle_core(struct rq *rq)
int cpu;
rcu_read_lock();
- if (test_idle_cores(core, true))
+ if (test_idle_cores(core))
goto unlock;
for_each_cpu(cpu, cpu_smt_mask(core)) {
@@ -6310,9 +6490,6 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
bool idle = true;
int cpu;
- if (!static_branch_likely(&sched_smt_present))
- return __select_idle_cpu(core, p);
-
for_each_cpu(cpu, cpu_smt_mask(core)) {
if (!available_idle_cpu(cpu)) {
idle = false;
@@ -6339,13 +6516,12 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
/*
* Scan the local SMT mask for idle CPUs.
*/
-static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
+static int select_idle_smt(struct task_struct *p, int target)
{
int cpu;
- for_each_cpu(cpu, cpu_smt_mask(target)) {
- if (!cpumask_test_cpu(cpu, p->cpus_ptr) ||
- !cpumask_test_cpu(cpu, sched_domain_span(sd)))
+ for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) {
+ if (cpu == target)
continue;
if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
return cpu;
@@ -6360,9 +6536,9 @@ static inline void set_idle_cores(int cpu, int val)
{
}
-static inline bool test_idle_cores(int cpu, bool def)
+static inline bool test_idle_cores(int cpu)
{
- return def;
+ return false;
}
static inline int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu)
@@ -6370,7 +6546,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma
return __select_idle_cpu(core, p);
}
-static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
+static inline int select_idle_smt(struct task_struct *p, int target)
{
return -1;
}
@@ -6389,19 +6565,19 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
struct sched_domain_shared *sd_share;
struct rq *this_rq = this_rq();
int this = smp_processor_id();
- struct sched_domain *this_sd;
+ struct sched_domain *this_sd = NULL;
u64 time = 0;
- this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
- if (!this_sd)
- return -1;
-
cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
if (sched_feat(SIS_PROP) && !has_idle_core) {
u64 avg_cost, avg_idle, span_avg;
unsigned long now = jiffies;
+ this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
+ if (!this_sd)
+ return -1;
+
/*
* If we're busy, the assumption that the last idle period
* predicts the future is flawed; age away the remaining
@@ -6455,7 +6631,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
if (has_idle_core)
set_idle_cores(target, false);
- if (sched_feat(SIS_PROP) && !has_idle_core) {
+ if (sched_feat(SIS_PROP) && this_sd && !has_idle_core) {
time = cpu_clock(this) - time;
/*
@@ -6506,7 +6682,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
static inline bool asym_fits_capacity(unsigned long task_util, int cpu)
{
- if (static_branch_unlikely(&sched_asym_cpucapacity))
+ if (sched_asym_cpucap_active())
return fits_capacity(task_util, capacity_of(cpu));
return true;
@@ -6526,7 +6702,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
* On asymmetric system, update task utilization because we will check
* that the task fits with cpu's capacity.
*/
- if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+ if (sched_asym_cpucap_active()) {
sync_entity_load_avg(&p->se);
task_util = uclamp_task_util(p);
}
@@ -6580,7 +6756,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
* For asymmetric CPU capacity systems, our domain of interest is
* sd_asym_cpucapacity rather than sd_llc.
*/
- if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+ if (sched_asym_cpucap_active()) {
sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
/*
* On an asymmetric CPU capacity system where an exclusive
@@ -6601,10 +6777,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
return target;
if (sched_smt_active()) {
- has_idle_core = test_idle_cores(target, false);
+ has_idle_core = test_idle_cores(target);
if (!has_idle_core && cpus_share_cache(prev, target)) {
- i = select_idle_smt(p, sd, prev);
+ i = select_idle_smt(p, prev);
if ((unsigned int)i < nr_cpumask_bits)
return i;
}
@@ -7076,8 +7252,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
return new_cpu;
}
-static void detach_entity_cfs_rq(struct sched_entity *se);
-
/*
* Called immediately before a task is migrated to a new CPU; task_cpu(p) and
* cfs_rq_of(p) references at time of call are still valid and identify the
@@ -7099,15 +7273,7 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
}
- if (p->on_rq == TASK_ON_RQ_MIGRATING) {
- /*
- * In case of TASK_ON_RQ_MIGRATING we in fact hold the 'old'
- * rq->lock and can modify state directly.
- */
- lockdep_assert_rq_held(task_rq(p));
- detach_entity_cfs_rq(se);
-
- } else {
+ if (!task_on_rq_migrating(p)) {
remove_entity_load_avg(se);
/*
@@ -7279,7 +7445,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
return;
find_matching_se(&se, &pse);
- BUG_ON(!pse);
+ WARN_ON_ONCE(!pse);
cse_is_idle = se_is_idle(se);
pse_is_idle = se_is_idle(pse);
@@ -7938,7 +8104,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
/* Record that we found at least one task that could run on dst_cpu */
env->flags &= ~LBF_ALL_PINNED;
- if (task_running(env->src_rq, p)) {
+ if (task_on_cpu(env->src_rq, p)) {
schedstat_inc(p->stats.nr_failed_migrations_running);
return 0;
}
@@ -8012,8 +8178,6 @@ static struct task_struct *detach_one_task(struct lb_env *env)
return NULL;
}
-static const unsigned int sched_nr_migrate_break = 32;
-
/*
* detach_tasks() -- tries to detach up to imbalance load/util/tasks from
* busiest_rq, as part of a balancing operation within domain "sd".
@@ -8049,20 +8213,24 @@ static int detach_tasks(struct lb_env *env)
if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1)
break;
- p = list_last_entry(tasks, struct task_struct, se.group_node);
-
env->loop++;
- /* We've more or less seen every task there is, call it quits */
- if (env->loop > env->loop_max)
+ /*
+ * We've more or less seen every task there is, call it quits
+ * unless we haven't found any movable task yet.
+ */
+ if (env->loop > env->loop_max &&
+ !(env->flags & LBF_ALL_PINNED))
break;
/* take a breather every nr_migrate tasks */
if (env->loop > env->loop_break) {
- env->loop_break += sched_nr_migrate_break;
+ env->loop_break += SCHED_NR_MIGRATE_BREAK;
env->flags |= LBF_NEED_BREAK;
break;
}
+ p = list_last_entry(tasks, struct task_struct, se.group_node);
+
if (!can_migrate_task(p, env))
goto next;
@@ -8159,7 +8327,7 @@ static void attach_task(struct rq *rq, struct task_struct *p)
{
lockdep_assert_rq_held(rq);
- BUG_ON(task_rq(p) != rq);
+ WARN_ON_ONCE(task_rq(p) != rq);
activate_task(rq, p, ENQUEUE_NOCLOCK);
check_preempt_curr(rq, p, 0);
}
@@ -10099,14 +10267,13 @@ static int load_balance(int this_cpu, struct rq *this_rq,
struct rq *busiest;
struct rq_flags rf;
struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
-
struct lb_env env = {
.sd = sd,
.dst_cpu = this_cpu,
.dst_rq = this_rq,
.dst_grpmask = sched_group_span(sd->groups),
.idle = idle,
- .loop_break = sched_nr_migrate_break,
+ .loop_break = SCHED_NR_MIGRATE_BREAK,
.cpus = cpus,
.fbq_type = all,
.tasks = LIST_HEAD_INIT(env.tasks),
@@ -10134,7 +10301,7 @@ redo:
goto out_balanced;
}
- BUG_ON(busiest == env.dst_rq);
+ WARN_ON_ONCE(busiest == env.dst_rq);
schedstat_add(sd->lb_imbalance[idle], env.imbalance);
@@ -10182,7 +10349,9 @@ more_balance:
if (env.flags & LBF_NEED_BREAK) {
env.flags &= ~LBF_NEED_BREAK;
- goto more_balance;
+ /* Stop if we tried all running tasks */
+ if (env.loop < busiest->nr_running)
+ goto more_balance;
}
/*
@@ -10213,7 +10382,7 @@ more_balance:
env.dst_cpu = env.new_dst_cpu;
env.flags &= ~LBF_DST_PINNED;
env.loop = 0;
- env.loop_break = sched_nr_migrate_break;
+ env.loop_break = SCHED_NR_MIGRATE_BREAK;
/*
* Go back to "more_balance" rather than "redo" since we
@@ -10245,7 +10414,7 @@ more_balance:
*/
if (!cpumask_subset(cpus, env.dst_grpmask)) {
env.loop = 0;
- env.loop_break = sched_nr_migrate_break;
+ env.loop_break = SCHED_NR_MIGRATE_BREAK;
goto redo;
}
goto out_all_pinned;
@@ -10430,7 +10599,7 @@ static int active_load_balance_cpu_stop(void *data)
* we need to fix it. Originally reported by
* Bjorn Helgaas on a 128-CPU setup.
*/
- BUG_ON(busiest_rq == target_rq);
+ WARN_ON_ONCE(busiest_rq == target_rq);
/* Search for an sd spanning us and the target CPU. */
rcu_read_lock();
@@ -10916,8 +11085,7 @@ static bool update_nohz_stats(struct rq *rq)
* can be a simple update of blocked load or a complete load balance with
* tasks movement depending of flags.
*/
-static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
- enum cpu_idle_type idle)
+static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags)
{
/* Earliest time when we have to do rebalance again */
unsigned long now = jiffies;
@@ -11032,7 +11200,7 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
if (idle != CPU_IDLE)
return false;
- _nohz_idle_balance(this_rq, flags, idle);
+ _nohz_idle_balance(this_rq, flags);
return true;
}
@@ -11052,7 +11220,7 @@ void nohz_run_idle_balance(int cpu)
* (ie NOHZ_STATS_KICK set) and will do the same.
*/
if ((flags == NOHZ_NEWILB_KICK) && !need_resched())
- _nohz_idle_balance(cpu_rq(cpu), NOHZ_STATS_KICK, CPU_IDLE);
+ _nohz_idle_balance(cpu_rq(cpu), NOHZ_STATS_KICK);
}
static void nohz_newidle_balance(struct rq *this_rq)
@@ -11552,6 +11720,17 @@ static void detach_entity_cfs_rq(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
+#ifdef CONFIG_SMP
+ /*
+ * In case the task sched_avg hasn't been attached:
+ * - A forked task which hasn't been woken up by wake_up_new_task().
+ * - A task which has been woken up by try_to_wake_up() but is
+ * waiting for actually being woken up by sched_ttwu_pending().
+ */
+ if (!se->avg.last_update_time)
+ return;
+#endif
+
/* Catch up with the cfs_rq and remove our load when we leave */
update_load_avg(cfs_rq, se, 0);
detach_entity_load_avg(cfs_rq, se);
@@ -11563,14 +11742,6 @@ static void attach_entity_cfs_rq(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
-#ifdef CONFIG_FAIR_GROUP_SCHED
- /*
- * Since the real-depth could have been changed (only FAIR
- * class maintain depth value), reset depth properly.
- */
- se->depth = se->parent ? se->parent->depth + 1 : 0;
-#endif
-
/* Synchronize entity with its cfs_rq */
update_load_avg(cfs_rq, se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
attach_entity_load_avg(cfs_rq, se);
@@ -11666,39 +11837,25 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-static void task_set_group_fair(struct task_struct *p)
+static void task_change_group_fair(struct task_struct *p)
{
- struct sched_entity *se = &p->se;
-
- set_task_rq(p, task_cpu(p));
- se->depth = se->parent ? se->parent->depth + 1 : 0;
-}
+ /*
+ * We couldn't detach or attach a forked task which
+ * hasn't been woken up by wake_up_new_task().
+ */
+ if (READ_ONCE(p->__state) == TASK_NEW)
+ return;
-static void task_move_group_fair(struct task_struct *p)
-{
detach_task_cfs_rq(p);
- set_task_rq(p, task_cpu(p));
#ifdef CONFIG_SMP
/* Tell se's cfs_rq has been changed -- migrated */
p->se.avg.last_update_time = 0;
#endif
+ set_task_rq(p, task_cpu(p));
attach_task_cfs_rq(p);
}
-static void task_change_group_fair(struct task_struct *p, int type)
-{
- switch (type) {
- case TASK_SET_GROUP:
- task_set_group_fair(p);
- break;
-
- case TASK_MOVE_GROUP:
- task_move_group_fair(p);
- break;
- }
-}
-
void free_fair_sched_group(struct task_group *tg)
{
int i;
@@ -12075,6 +12232,13 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m)
__init void init_sched_fair_class(void)
{
#ifdef CONFIG_SMP
+ int i;
+
+ for_each_possible_cpu(i) {
+ zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i));
+ zalloc_cpumask_var_node(&per_cpu(select_rq_mask, i), GFP_KERNEL, cpu_to_node(i));
+ }
+
open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
#ifdef CONFIG_NO_HZ_COMMON
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ecb4b4ff4ce0..ee2ecc081422 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -181,6 +181,7 @@ static void group_init(struct psi_group *group)
{
int cpu;
+ group->enabled = true;
for_each_possible_cpu(cpu)
seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
group->avg_last_update = sched_clock();
@@ -201,6 +202,7 @@ void __init psi_init(void)
{
if (!psi_enable) {
static_branch_enable(&psi_disabled);
+ static_branch_disable(&psi_cgroups_enabled);
return;
}
@@ -211,7 +213,7 @@ void __init psi_init(void)
group_init(&psi_system);
}
-static bool test_state(unsigned int *tasks, enum psi_states state)
+static bool test_state(unsigned int *tasks, enum psi_states state, bool oncpu)
{
switch (state) {
case PSI_IO_SOME:
@@ -224,9 +226,9 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
return unlikely(tasks[NR_MEMSTALL] &&
tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]);
case PSI_CPU_SOME:
- return unlikely(tasks[NR_RUNNING] > tasks[NR_ONCPU]);
+ return unlikely(tasks[NR_RUNNING] > oncpu);
case PSI_CPU_FULL:
- return unlikely(tasks[NR_RUNNING] && !tasks[NR_ONCPU]);
+ return unlikely(tasks[NR_RUNNING] && !oncpu);
case PSI_NONIDLE:
return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
tasks[NR_RUNNING];
@@ -688,35 +690,53 @@ static void psi_group_change(struct psi_group *group, int cpu,
bool wake_clock)
{
struct psi_group_cpu *groupc;
- u32 state_mask = 0;
unsigned int t, m;
enum psi_states s;
+ u32 state_mask;
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
+ * First we update the task counts according to the state
* change requested through the @clear and @set bits.
+ *
+ * Then if the cgroup PSI stats accounting enabled, 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.
*/
write_seqcount_begin(&groupc->seq);
- record_times(groupc, now);
+ /*
+ * Start with TSK_ONCPU, which doesn't have a corresponding
+ * task count - it's just a boolean flag directly encoded in
+ * the state mask. Clear, set, or carry the current state if
+ * no changes are requested.
+ */
+ if (unlikely(clear & TSK_ONCPU)) {
+ state_mask = 0;
+ clear &= ~TSK_ONCPU;
+ } else if (unlikely(set & TSK_ONCPU)) {
+ state_mask = PSI_ONCPU;
+ set &= ~TSK_ONCPU;
+ } else {
+ state_mask = groupc->state_mask & PSI_ONCPU;
+ }
+ /*
+ * The rest of the state mask is calculated based on the task
+ * counts. Update those first, then construct the mask.
+ */
for (t = 0, m = clear; m; m &= ~(1 << t), t++) {
if (!(m & (1 << t)))
continue;
if (groupc->tasks[t]) {
groupc->tasks[t]--;
} else if (!psi_bug) {
- printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u %u] clear=%x set=%x\n",
+ printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n",
cpu, t, groupc->tasks[0],
groupc->tasks[1], groupc->tasks[2],
- groupc->tasks[3], groupc->tasks[4],
- clear, set);
+ groupc->tasks[3], clear, set);
psi_bug = 1;
}
}
@@ -725,9 +745,25 @@ static void psi_group_change(struct psi_group *group, int cpu,
if (set & (1 << t))
groupc->tasks[t]++;
- /* Calculate state mask representing active states */
+ if (!group->enabled) {
+ /*
+ * On the first group change after disabling PSI, conclude
+ * the current state and flush its time. This is unlikely
+ * to matter to the user, but aggregation (get_recent_times)
+ * may have already incorporated the live state into times_prev;
+ * avoid a delta sample underflow when PSI is later re-enabled.
+ */
+ if (unlikely(groupc->state_mask & (1 << PSI_NONIDLE)))
+ record_times(groupc, now);
+
+ groupc->state_mask = state_mask;
+
+ write_seqcount_end(&groupc->seq);
+ return;
+ }
+
for (s = 0; s < NR_PSI_STATES; s++) {
- if (test_state(groupc->tasks, s))
+ if (test_state(groupc->tasks, s, state_mask & PSI_ONCPU))
state_mask |= (1 << s);
}
@@ -739,9 +775,11 @@ static void psi_group_change(struct psi_group *group, int cpu,
* task in a cgroup is in_memstall, the corresponding groupc
* on that cpu is in PSI_MEM_FULL state.
*/
- if (unlikely(groupc->tasks[NR_ONCPU] && cpu_curr(cpu)->in_memstall))
+ if (unlikely((state_mask & PSI_ONCPU) && cpu_curr(cpu)->in_memstall))
state_mask |= (1 << PSI_MEM_FULL);
+ record_times(groupc, now);
+
groupc->state_mask = state_mask;
write_seqcount_end(&groupc->seq);
@@ -753,27 +791,12 @@ static void psi_group_change(struct psi_group *group, int cpu,
schedule_delayed_work(&group->avgs_work, PSI_FREQ);
}
-static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
+static inline struct psi_group *task_psi_group(struct task_struct *task)
{
- if (*iter == &psi_system)
- return NULL;
-
#ifdef CONFIG_CGROUPS
- if (static_branch_likely(&psi_cgroups_enabled)) {
- struct cgroup *cgroup = NULL;
-
- if (!*iter)
- cgroup = task->cgroups->dfl_cgrp;
- else
- cgroup = cgroup_parent(*iter);
-
- if (cgroup && cgroup_parent(cgroup)) {
- *iter = cgroup;
- return cgroup_psi(cgroup);
- }
- }
+ if (static_branch_likely(&psi_cgroups_enabled))
+ return cgroup_psi(task_dfl_cgroup(task));
#endif
- *iter = &psi_system;
return &psi_system;
}
@@ -796,8 +819,6 @@ void psi_task_change(struct task_struct *task, int clear, int set)
{
int cpu = task_cpu(task);
struct psi_group *group;
- bool wake_clock = true;
- void *iter = NULL;
u64 now;
if (!task->pid)
@@ -806,19 +827,11 @@ void psi_task_change(struct task_struct *task, int clear, int set)
psi_flags_change(task, clear, set);
now = cpu_clock(cpu);
- /*
- * Periodic aggregation shuts off if there is a period of no
- * task changes, so we wake it back up if necessary. However,
- * don't do this if the task change is the aggregation worker
- * itself going to sleep, or we'll ping-pong forever.
- */
- if (unlikely((clear & TSK_RUNNING) &&
- (task->flags & PF_WQ_WORKER) &&
- wq_worker_last_func(task) == psi_avgs_work))
- wake_clock = false;
- while ((group = iterate_groups(task, &iter)))
- psi_group_change(group, cpu, clear, set, now, wake_clock);
+ group = task_psi_group(task);
+ do {
+ psi_group_change(group, cpu, clear, set, now, true);
+ } while ((group = group->parent));
}
void psi_task_switch(struct task_struct *prev, struct task_struct *next,
@@ -826,34 +839,30 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
{
struct psi_group *group, *common = NULL;
int cpu = task_cpu(prev);
- void *iter;
u64 now = cpu_clock(cpu);
if (next->pid) {
- bool identical_state;
-
psi_flags_change(next, 0, TSK_ONCPU);
/*
- * When switching between tasks that have an identical
- * runtime state, the cgroup that contains both tasks
- * we reach the first common ancestor. Iterate @next's
- * ancestors only until we encounter @prev's ONCPU.
+ * Set TSK_ONCPU on @next's cgroups. If @next shares any
+ * ancestors with @prev, those will already have @prev's
+ * TSK_ONCPU bit set, and we can stop the iteration there.
*/
- identical_state = prev->psi_flags == next->psi_flags;
- iter = NULL;
- while ((group = iterate_groups(next, &iter))) {
- if (identical_state &&
- per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
+ group = task_psi_group(next);
+ do {
+ if (per_cpu_ptr(group->pcpu, cpu)->state_mask &
+ PSI_ONCPU) {
common = group;
break;
}
psi_group_change(group, cpu, 0, TSK_ONCPU, now, true);
- }
+ } while ((group = group->parent));
}
if (prev->pid) {
int clear = TSK_ONCPU, set = 0;
+ bool wake_clock = true;
/*
* When we're going to sleep, psi_dequeue() lets us
@@ -867,26 +876,74 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
clear |= TSK_MEMSTALL_RUNNING;
if (prev->in_iowait)
set |= TSK_IOWAIT;
+
+ /*
+ * Periodic aggregation shuts off if there is a period of no
+ * task changes, so we wake it back up if necessary. However,
+ * don't do this if the task change is the aggregation worker
+ * itself going to sleep, or we'll ping-pong forever.
+ */
+ if (unlikely((prev->flags & PF_WQ_WORKER) &&
+ wq_worker_last_func(prev) == psi_avgs_work))
+ wake_clock = false;
}
psi_flags_change(prev, clear, set);
- iter = NULL;
- while ((group = iterate_groups(prev, &iter)) && group != common)
- psi_group_change(group, cpu, clear, set, now, true);
+ group = task_psi_group(prev);
+ do {
+ if (group == common)
+ break;
+ psi_group_change(group, cpu, clear, set, now, wake_clock);
+ } while ((group = group->parent));
/*
- * TSK_ONCPU is handled up to the common ancestor. If we're tasked
- * with dequeuing too, finish that for the rest of the hierarchy.
+ * TSK_ONCPU is handled up to the common ancestor. If there are
+ * any other differences between the two tasks (e.g. prev goes
+ * to sleep, or only one task is memstall), finish propagating
+ * those differences all the way up to the root.
*/
- if (sleep) {
+ if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) {
clear &= ~TSK_ONCPU;
- for (; group; group = iterate_groups(prev, &iter))
- psi_group_change(group, cpu, clear, set, now, true);
+ for (; group; group = group->parent)
+ psi_group_change(group, cpu, clear, set, now, wake_clock);
}
}
}
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+void psi_account_irqtime(struct task_struct *task, u32 delta)
+{
+ int cpu = task_cpu(task);
+ struct psi_group *group;
+ struct psi_group_cpu *groupc;
+ u64 now;
+
+ if (!task->pid)
+ return;
+
+ now = cpu_clock(cpu);
+
+ group = task_psi_group(task);
+ do {
+ if (!group->enabled)
+ continue;
+
+ groupc = per_cpu_ptr(group->pcpu, cpu);
+
+ write_seqcount_begin(&groupc->seq);
+
+ record_times(groupc, now);
+ groupc->times[PSI_IRQ_FULL] += delta;
+
+ write_seqcount_end(&groupc->seq);
+
+ if (group->poll_states & (1 << PSI_IRQ_FULL))
+ psi_schedule_poll_work(group, 1);
+ } while ((group = group->parent));
+}
+#endif
+
/**
* psi_memstall_enter - mark the beginning of a memory stall section
* @flags: flags to handle nested sections
@@ -917,6 +974,7 @@ void psi_memstall_enter(unsigned long *flags)
rq_unlock_irq(rq, &rf);
}
+EXPORT_SYMBOL_GPL(psi_memstall_enter);
/**
* psi_memstall_leave - mark the end of an memory stall section
@@ -946,11 +1004,12 @@ void psi_memstall_leave(unsigned long *flags)
rq_unlock_irq(rq, &rf);
}
+EXPORT_SYMBOL_GPL(psi_memstall_leave);
#ifdef CONFIG_CGROUPS
int psi_cgroup_alloc(struct cgroup *cgroup)
{
- if (static_branch_likely(&psi_disabled))
+ if (!static_branch_likely(&psi_cgroups_enabled))
return 0;
cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL);
@@ -963,12 +1022,13 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
return -ENOMEM;
}
group_init(cgroup->psi);
+ cgroup->psi->parent = cgroup_psi(cgroup_parent(cgroup));
return 0;
}
void psi_cgroup_free(struct cgroup *cgroup)
{
- if (static_branch_likely(&psi_disabled))
+ if (!static_branch_likely(&psi_cgroups_enabled))
return;
cancel_delayed_work_sync(&cgroup->psi->avgs_work);
@@ -996,7 +1056,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
struct rq_flags rf;
struct rq *rq;
- if (static_branch_likely(&psi_disabled)) {
+ if (!static_branch_likely(&psi_cgroups_enabled)) {
/*
* Lame to do this here, but the scheduler cannot be locked
* from the outside, so we move cgroups from inside sched/.
@@ -1044,10 +1104,45 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
task_rq_unlock(rq, task, &rf);
}
+
+void psi_cgroup_restart(struct psi_group *group)
+{
+ int cpu;
+
+ /*
+ * After we disable psi_group->enabled, we don't actually
+ * stop percpu tasks accounting in each psi_group_cpu,
+ * instead only stop test_state() loop, record_times()
+ * and averaging worker, see psi_group_change() for details.
+ *
+ * When disable cgroup PSI, this function has nothing to sync
+ * since cgroup pressure files are hidden and percpu psi_group_cpu
+ * would see !psi_group->enabled and only do task accounting.
+ *
+ * When re-enable cgroup PSI, this function use psi_group_change()
+ * to get correct state mask from test_state() loop on tasks[],
+ * and restart groupc->state_start from now, use .clear = .set = 0
+ * here since no task status really changed.
+ */
+ if (!group->enabled)
+ return;
+
+ for_each_possible_cpu(cpu) {
+ struct rq *rq = cpu_rq(cpu);
+ struct rq_flags rf;
+ u64 now;
+
+ rq_lock_irq(rq, &rf);
+ now = cpu_clock(cpu);
+ psi_group_change(group, cpu, 0, 0, now, true);
+ rq_unlock_irq(rq, &rf);
+ }
+}
#endif /* CONFIG_CGROUPS */
int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
{
+ bool only_full = false;
int full;
u64 now;
@@ -1062,7 +1157,11 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
group->avg_next_update = update_averages(group, now);
mutex_unlock(&group->avgs_lock);
- for (full = 0; full < 2; full++) {
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ only_full = res == PSI_IRQ;
+#endif
+
+ for (full = 0; full < 2 - only_full; full++) {
unsigned long avg[3] = { 0, };
u64 total = 0;
int w;
@@ -1076,7 +1175,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
}
seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
- full ? "full" : "some",
+ full || only_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]),
@@ -1104,6 +1203,11 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
else
return ERR_PTR(-EINVAL);
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ if (res == PSI_IRQ && --state != PSI_IRQ_FULL)
+ return ERR_PTR(-EINVAL);
+#endif
+
if (state >= PSI_NONIDLE)
return ERR_PTR(-EINVAL);
@@ -1388,6 +1492,33 @@ static const struct proc_ops psi_cpu_proc_ops = {
.proc_release = psi_fop_release,
};
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+static int psi_irq_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_IRQ);
+}
+
+static int psi_irq_open(struct inode *inode, struct file *file)
+{
+ return psi_open(file, psi_irq_show);
+}
+
+static ssize_t psi_irq_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_IRQ);
+}
+
+static const struct proc_ops psi_irq_proc_ops = {
+ .proc_open = psi_irq_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = psi_irq_write,
+ .proc_poll = psi_fop_poll,
+ .proc_release = psi_fop_release,
+};
+#endif
+
static int __init psi_proc_init(void)
{
if (psi_enable) {
@@ -1395,6 +1526,9 @@ static int __init psi_proc_init(void)
proc_create("pressure/io", 0666, NULL, &psi_io_proc_ops);
proc_create("pressure/memory", 0666, NULL, &psi_memory_proc_ops);
proc_create("pressure/cpu", 0666, NULL, &psi_cpu_proc_ops);
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ proc_create("pressure/irq", 0666, NULL, &psi_irq_proc_ops);
+#endif
}
return 0;
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 55f39c8f4203..d869bcf898cc 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -509,7 +509,7 @@ static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
unsigned int cpu_cap;
/* Only heterogeneous systems can benefit from this check */
- if (!static_branch_unlikely(&sched_asym_cpucapacity))
+ if (!sched_asym_cpucap_active())
return true;
min_cap = uclamp_eff_value(p, UCLAMP_MIN);
@@ -843,7 +843,7 @@ static void __disable_runtime(struct rq *rq)
* We cannot be left wanting - that would mean some runtime
* leaked out of the system.
*/
- BUG_ON(want);
+ WARN_ON_ONCE(want);
balanced:
/*
* Disable all the borrow logic by pretending we have inf
@@ -1062,11 +1062,7 @@ static void update_curr_rt(struct rq *rq)
trace_sched_stat_runtime(curr, delta_exec, 0);
- curr->se.sum_exec_runtime += delta_exec;
- account_group_exec_runtime(curr, delta_exec);
-
- curr->se.exec_start = now;
- cgroup_account_cputime(curr, delta_exec);
+ update_current_exec_runtime(curr, now, delta_exec);
if (!rt_bandwidth_enabled())
return;
@@ -1849,7 +1845,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
{
- if (!task_running(rq, p) &&
+ if (!task_on_cpu(rq, p) &&
cpumask_test_cpu(cpu, &p->cpus_mask))
return 1;
@@ -1897,7 +1893,7 @@ static int find_lowest_rq(struct task_struct *task)
* If we're on asym system ensure we consider the different capacities
* of the CPUs when searching for the lowest_mask.
*/
- if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+ if (sched_asym_cpucap_active()) {
ret = cpupri_find_fitness(&task_rq(task)->rd->cpupri,
task, lowest_mask,
@@ -2004,7 +2000,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
*/
if (unlikely(task_rq(task) != rq ||
!cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
- task_running(rq, task) ||
+ task_on_cpu(rq, task) ||
!rt_task(task) ||
!task_on_rq_queued(task))) {
@@ -2462,7 +2458,7 @@ skip:
*/
static void task_woken_rt(struct rq *rq, struct task_struct *p)
{
- bool need_to_push = !task_running(rq, p) &&
+ bool need_to_push = !task_on_cpu(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
p->nr_cpus_allowed > 1 &&
(dl_task(rq->curr) || rt_task(rq->curr)) &&
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e26688d387ae..1644242ecd11 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -321,21 +321,6 @@ struct dl_bw {
u64 total_bw;
};
-/*
- * Verify the fitness of task @p to run on @cpu taking into account the
- * CPU original capacity and the runtime/deadline ratio of the task.
- *
- * The function will return true if the CPU original capacity of the
- * @cpu scaled by SCHED_CAPACITY_SCALE >= runtime/deadline ratio of the
- * task and false otherwise.
- */
-static inline bool dl_task_fits_capacity(struct task_struct *p, int cpu)
-{
- unsigned long cap = arch_scale_cpu_capacity(cpu);
-
- return cap_scale(p->dl.dl_deadline, cap) >= p->dl.dl_runtime;
-}
-
extern void init_dl_bw(struct dl_bw *dl_b);
extern int sched_dl_global_validate(void);
extern void sched_dl_do_global(void);
@@ -1815,6 +1800,11 @@ DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
extern struct static_key_false sched_asym_cpucapacity;
+static __always_inline bool sched_asym_cpucap_active(void)
+{
+ return static_branch_unlikely(&sched_asym_cpucapacity);
+}
+
struct sched_group_capacity {
atomic_t ref;
/*
@@ -1942,6 +1932,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
p->se.cfs_rq = tg->cfs_rq[cpu];
p->se.parent = tg->se[cpu];
+ p->se.depth = tg->se[cpu] ? tg->se[cpu]->depth + 1 : 0;
#endif
#ifdef CONFIG_RT_GROUP_SCHED
@@ -2060,7 +2051,7 @@ static inline int task_current(struct rq *rq, struct task_struct *p)
return rq->curr == p;
}
-static inline int task_running(struct rq *rq, struct task_struct *p)
+static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
return p->on_cpu;
@@ -2204,11 +2195,8 @@ struct sched_class {
void (*update_curr)(struct rq *rq);
-#define TASK_SET_GROUP 0
-#define TASK_MOVE_GROUP 1
-
#ifdef CONFIG_FAIR_GROUP_SCHED
- void (*task_change_group)(struct task_struct *p, int type);
+ void (*task_change_group)(struct task_struct *p);
#endif
};
@@ -2435,6 +2423,12 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
+#ifdef CONFIG_PREEMPT_RT
+#define SCHED_NR_MIGRATE_BREAK 8
+#else
+#define SCHED_NR_MIGRATE_BREAK 32
+#endif
+
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;
@@ -2452,6 +2446,7 @@ extern unsigned int sysctl_numa_balancing_scan_delay;
extern unsigned int sysctl_numa_balancing_scan_period_min;
extern unsigned int sysctl_numa_balancing_scan_period_max;
extern unsigned int sysctl_numa_balancing_scan_size;
+extern unsigned int sysctl_numa_balancing_hot_threshold;
#endif
#ifdef CONFIG_SCHED_HRTICK
@@ -2709,8 +2704,8 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
__acquires(rq1->lock)
__acquires(rq2->lock)
{
- BUG_ON(!irqs_disabled());
- BUG_ON(rq1 != rq2);
+ WARN_ON_ONCE(!irqs_disabled());
+ WARN_ON_ONCE(rq1 != rq2);
raw_spin_rq_lock(rq1);
__acquire(rq2->lock); /* Fake it out ;) */
double_rq_clock_clear_update(rq1, rq2);
@@ -2726,7 +2721,7 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__releases(rq1->lock)
__releases(rq2->lock)
{
- BUG_ON(rq1 != rq2);
+ WARN_ON_ONCE(rq1 != rq2);
raw_spin_rq_unlock(rq1);
__release(rq2->lock);
}
@@ -2896,6 +2891,21 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
enum cpu_util_type type,
struct task_struct *p);
+/*
+ * Verify the fitness of task @p to run on @cpu taking into account the
+ * CPU original capacity and the runtime/deadline ratio of the task.
+ *
+ * The function will return true if the original capacity of @cpu is
+ * greater than or equal to task's deadline density right shifted by
+ * (BW_SHIFT - SCHED_CAPACITY_SHIFT) and false otherwise.
+ */
+static inline bool dl_task_fits_capacity(struct task_struct *p, int cpu)
+{
+ unsigned long cap = arch_scale_cpu_capacity(cpu);
+
+ return cap >= p->dl.dl_density >> (BW_SHIFT - SCHED_CAPACITY_SHIFT);
+}
+
static inline unsigned long cpu_bw_dl(struct rq *rq)
{
return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
@@ -3157,4 +3167,14 @@ extern int sched_dynamic_mode(const char *str);
extern void sched_dynamic_update(int mode);
#endif
+static inline void update_current_exec_runtime(struct task_struct *curr,
+ u64 now, u64 delta_exec)
+{
+ curr->se.sum_exec_runtime += delta_exec;
+ account_group_exec_runtime(curr, delta_exec);
+
+ curr->se.exec_start = now;
+ cgroup_account_cputime(curr, delta_exec);
+}
+
#endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index baa839c1ba96..84a188913cc9 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -107,6 +107,11 @@ __schedstats_from_se(struct sched_entity *se)
}
#ifdef CONFIG_PSI
+void psi_task_change(struct task_struct *task, int clear, int set);
+void psi_task_switch(struct task_struct *prev, struct task_struct *next,
+ bool sleep);
+void psi_account_irqtime(struct task_struct *task, u32 delta);
+
/*
* PSI tracks state that persists across sleeps, such as iowaits and
* memory stalls. As a result, it has to distinguish between sleeps,
@@ -201,6 +206,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {}
static inline void psi_sched_switch(struct task_struct *prev,
struct task_struct *next,
bool sleep) {}
+static inline void psi_account_irqtime(struct task_struct *task, u32 delta) {}
#endif /* CONFIG_PSI */
#ifdef CONFIG_SCHED_INFO
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index d04073a93eb4..85590599b4d6 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -71,20 +71,17 @@ static void yield_task_stop(struct rq *rq)
static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
{
struct task_struct *curr = rq->curr;
- u64 delta_exec;
+ u64 now, delta_exec;
- delta_exec = rq_clock_task(rq) - curr->se.exec_start;
+ now = rq_clock_task(rq);
+ delta_exec = now - curr->se.exec_start;
if (unlikely((s64)delta_exec < 0))
delta_exec = 0;
schedstat_set(curr->stats.exec_max,
max(curr->stats.exec_max, delta_exec));
- curr->se.sum_exec_runtime += delta_exec;
- account_group_exec_runtime(curr, delta_exec);
-
- curr->se.exec_start = rq_clock_task(rq);
- cgroup_account_cputime(curr, delta_exec);
+ update_current_exec_runtime(curr, now, delta_exec);
}
/*
diff --git a/kernel/signal.c b/kernel/signal.c
index 6f86fda5e432..d140672185a4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -913,8 +913,9 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
if (signal->core_state)
return sig == SIGKILL;
/*
- * The process is in the middle of dying, nothing to do.
+ * The process is in the middle of dying, drop the signal.
*/
+ return false;
} else if (sig_kernel_stop(sig)) {
/*
* This is a stop signal. Remove SIGCONT from all queues.
@@ -2304,7 +2305,7 @@ static int ptrace_stop(int exit_code, int why, unsigned long message,
read_unlock(&tasklist_lock);
cgroup_enter_frozen();
preempt_enable_no_resched();
- freezable_schedule();
+ schedule();
cgroup_leave_frozen(true);
/*
@@ -2473,7 +2474,7 @@ static bool do_signal_stop(int signr)
/* Now we don't run again until woken by SIGCONT or SIGKILL */
cgroup_enter_frozen();
- freezable_schedule();
+ schedule();
return true;
} else {
/*
@@ -2548,11 +2549,11 @@ static void do_freezer_trap(void)
* immediately (if there is a non-fatal signal pending), and
* put the task into sleep.
*/
- __set_current_state(TASK_INTERRUPTIBLE);
+ __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
clear_thread_flag(TIF_SIGPENDING);
spin_unlock_irq(&current->sighand->siglock);
cgroup_enter_frozen();
- freezable_schedule();
+ schedule();
}
static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type)
@@ -3600,9 +3601,9 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info,
recalc_sigpending();
spin_unlock_irq(&tsk->sighand->siglock);
- __set_current_state(TASK_INTERRUPTIBLE);
- ret = freezable_schedule_hrtimeout_range(to, tsk->timer_slack_ns,
- HRTIMER_MODE_REL);
+ __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
+ ret = schedule_hrtimeout_range(to, tsk->timer_slack_ns,
+ HRTIMER_MODE_REL);
spin_lock_irq(&tsk->sighand->siglock);
__set_task_blocked(tsk, &tsk->real_blocked);
sigemptyset(&tsk->real_blocked);
diff --git a/kernel/smp.c b/kernel/smp.c
index e8cdc025a046..06a413987a14 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -1069,7 +1069,7 @@ static int __init nrcpus(char *str)
int nr_cpus;
if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids)
- nr_cpu_ids = nr_cpus;
+ set_nr_cpu_ids(nr_cpus);
return 0;
}
@@ -1087,14 +1087,16 @@ static int __init maxcpus(char *str)
early_param("maxcpus", maxcpus);
+#if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS)
/* Setup number of possible processor ids */
unsigned int nr_cpu_ids __read_mostly = NR_CPUS;
EXPORT_SYMBOL(nr_cpu_ids);
+#endif
/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
void __init setup_nr_cpu_ids(void)
{
- nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
+ set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1);
}
/* Called by boot processor to activate the rest. */
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index b9f54544e749..2c7396da470c 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -433,7 +433,7 @@ bool cpu_wait_death(unsigned int cpu, int seconds)
/* The outgoing CPU will normally get done quite quickly. */
if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD)
- goto update_state;
+ goto update_state_early;
udelay(5);
/* But if the outgoing CPU dawdles, wait increasingly long times. */
@@ -444,16 +444,17 @@ bool cpu_wait_death(unsigned int cpu, int seconds)
break;
sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10);
}
-update_state:
+update_state_early:
oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
+update_state:
if (oldstate == CPU_DEAD) {
/* Outgoing CPU died normally, update state. */
smp_mb(); /* atomic_read() before update. */
atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD);
} else {
/* Outgoing CPU still hasn't died, set state accordingly. */
- if (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
- oldstate, CPU_BROKEN) != oldstate)
+ if (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
+ &oldstate, CPU_BROKEN))
goto update_state;
ret = false;
}
@@ -475,14 +476,14 @@ bool cpu_report_death(void)
int newstate;
int cpu = smp_processor_id();
+ oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
do {
- oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
if (oldstate != CPU_BROKEN)
newstate = CPU_DEAD;
else
newstate = CPU_DEAD_FROZEN;
- } while (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
- oldstate, newstate) != oldstate);
+ } while (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
+ &oldstate, newstate));
return newstate == CPU_DEAD;
}
diff --git a/kernel/sys.c b/kernel/sys.c
index b911fa6d81ab..5fd54bf0e886 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -25,6 +25,7 @@
#include <linux/times.h>
#include <linux/posix-timers.h>
#include <linux/security.h>
+#include <linux/random.h>
#include <linux/suspend.h>
#include <linux/tty.h>
#include <linux/signal.h>
@@ -496,7 +497,7 @@ static void flag_nproc_exceeded(struct cred *new)
* for programs doing set*uid()+execve() by harmlessly deferring the
* failure to the execve() stage.
*/
- if (is_ucounts_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
+ if (is_rlimit_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
new->user != INIT_USER)
current->flags |= PF_NPROC_EXCEEDED;
else
@@ -1366,6 +1367,7 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
if (!copy_from_user(tmp, name, len)) {
struct new_utsname *u;
+ add_device_randomness(tmp, len);
down_write(&uts_sem);
u = utsname();
memcpy(u->nodename, tmp, len);
@@ -1419,6 +1421,7 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
if (!copy_from_user(tmp, name, len)) {
struct new_utsname *u;
+ add_device_randomness(tmp, len);
down_write(&uts_sem);
u = utsname();
memcpy(u->domainname, tmp, len);
diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c
index 664ded05dd7a..6ef887c19c48 100644
--- a/kernel/sysctl-test.c
+++ b/kernel/sysctl-test.c
@@ -9,9 +9,6 @@
#define KUNIT_PROC_READ 0
#define KUNIT_PROC_WRITE 1
-static int i_zero;
-static int i_one_hundred = 100;
-
/*
* Test that proc_dointvec will not try to use a NULL .data field even when the
* length is non-zero.
@@ -29,8 +26,8 @@ static void sysctl_test_api_dointvec_null_tbl_data(struct kunit *test)
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
/*
* proc_dointvec expects a buffer in user space, so we allocate one. We
@@ -79,8 +76,8 @@ static void sysctl_test_api_dointvec_table_maxlen_unset(struct kunit *test)
.maxlen = 0,
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int),
GFP_USER);
@@ -122,8 +119,8 @@ static void sysctl_test_api_dointvec_table_len_is_zero(struct kunit *test)
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int),
GFP_USER);
@@ -156,8 +153,8 @@ static void sysctl_test_api_dointvec_table_read_but_position_set(
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int),
GFP_USER);
@@ -191,8 +188,8 @@ static void sysctl_test_dointvec_read_happy_single_positive(struct kunit *test)
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
size_t len = 4;
loff_t pos = 0;
@@ -222,8 +219,8 @@ static void sysctl_test_dointvec_read_happy_single_negative(struct kunit *test)
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
size_t len = 5;
loff_t pos = 0;
@@ -251,8 +248,8 @@ static void sysctl_test_dointvec_write_happy_single_positive(struct kunit *test)
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
char input[] = "9";
size_t len = sizeof(input) - 1;
@@ -281,8 +278,8 @@ static void sysctl_test_dointvec_write_happy_single_negative(struct kunit *test)
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
char input[] = "-9";
size_t len = sizeof(input) - 1;
@@ -313,8 +310,8 @@ static void sysctl_test_api_dointvec_write_single_less_int_min(
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
size_t max_len = 32, len = max_len;
loff_t pos = 0;
@@ -351,8 +348,8 @@ static void sysctl_test_api_dointvec_write_single_greater_int_max(
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
- .extra1 = &i_zero,
- .extra2 = &i_one_hundred,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
};
size_t max_len = 32, len = max_len;
loff_t pos = 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 205d605cacc5..188c305aeb8b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -82,9 +82,16 @@
#include <linux/rtmutex.h>
#endif
+/* shared constants to be used in various sysctls */
+const int sysctl_vals[] = { 0, 1, 2, 3, 4, 100, 200, 1000, 3000, INT_MAX, 65535, -1 };
+EXPORT_SYMBOL(sysctl_vals);
+
+const unsigned long sysctl_long_vals[] = { 0, 1, LONG_MAX };
+EXPORT_SYMBOL_GPL(sysctl_long_vals);
+
#if defined(CONFIG_SYSCTL)
-/* Constants used for minimum and maximum */
+/* Constants used for minimum and maximum */
#ifdef CONFIG_PERF_EVENTS
static const int six_hundred_forty_kb = 640 * 1024;
@@ -129,11 +136,6 @@ static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT;
int sysctl_legacy_va_layout;
#endif
-#ifdef CONFIG_COMPACTION
-/* min_extfrag_threshold is SYSCTL_ZERO */;
-static const int max_extfrag_threshold = 1000;
-#endif
-
#endif /* CONFIG_SYSCTL */
/*
@@ -1052,9 +1054,9 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table,
return 0;
}
- i = (unsigned long *) data;
- min = (unsigned long *) table->extra1;
- max = (unsigned long *) table->extra2;
+ i = data;
+ min = table->extra1;
+ max = table->extra2;
vleft = table->maxlen / sizeof(unsigned long);
left = *lenp;
@@ -1641,6 +1643,14 @@ static struct ctl_table kern_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_FOUR,
},
+ {
+ .procname = "numa_balancing_promote_rate_limit_MBps",
+ .data = &sysctl_numa_balancing_promote_rate_limit,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ },
#endif /* CONFIG_NUMA_BALANCING */
{
.procname = "panic",
@@ -2216,7 +2226,7 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
- .extra2 = (void *)&max_extfrag_threshold,
+ .extra2 = SYSCTL_ONE_THOUSAND,
},
{
.procname = "compact_unevictable_allowed",
diff --git a/kernel/task_work.c b/kernel/task_work.c
index dff75bcde151..065e1ef8fc8d 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -47,12 +47,12 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
/* record the work call stack in order to print it in KASAN reports */
kasan_record_aux_stack(work);
+ head = READ_ONCE(task->task_works);
do {
- head = READ_ONCE(task->task_works);
if (unlikely(head == &work_exited))
return -ESRCH;
work->next = head;
- } while (cmpxchg(&task->task_works, head, work) != head);
+ } while (!try_cmpxchg(&task->task_works, &head, work));
switch (notify) {
case TWA_NONE:
@@ -100,10 +100,12 @@ task_work_cancel_match(struct task_struct *task,
* we raced with task_work_run(), *pprev == NULL/exited.
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
- while ((work = READ_ONCE(*pprev))) {
- if (!match(work, data))
+ work = READ_ONCE(*pprev);
+ while (work) {
+ if (!match(work, data)) {
pprev = &work->next;
- else if (cmpxchg(pprev, work, work->next) == work)
+ work = READ_ONCE(*pprev);
+ } else if (try_cmpxchg(pprev, &work, work->next))
break;
}
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -151,16 +153,16 @@ void task_work_run(void)
* work->func() can do task_work_add(), do not set
* work_exited unless the list is empty.
*/
+ work = READ_ONCE(task->task_works);
do {
head = NULL;
- work = READ_ONCE(task->task_works);
if (!work) {
if (task->flags & PF_EXITING)
head = &work_exited;
else
break;
}
- } while (cmpxchg(&task->task_works, work, head) != work);
+ } while (!try_cmpxchg(&task->task_works, &work, head));
if (!work)
break;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index cee5da1e54c4..8058bec87ace 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -310,7 +310,7 @@ static void clocksource_verify_choose_cpus(void)
* CPUs that are currently online.
*/
for (i = 1; i < n; i++) {
- cpu = prandom_u32() % nr_cpu_ids;
+ cpu = prandom_u32_max(nr_cpu_ids);
cpu = cpumask_next(cpu - 1, cpu_online_mask);
if (cpu >= nr_cpu_ids)
cpu = cpumask_first(cpu_online_mask);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 23af5eca11b1..3ae661ab6260 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2037,11 +2037,11 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
struct restart_block *restart;
do {
- set_current_state(TASK_INTERRUPTIBLE);
+ set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
hrtimer_sleeper_start_expires(t, mode);
if (likely(t->task))
- freezable_schedule();
+ schedule();
hrtimer_cancel(&t->timer);
mode = HRTIMER_MODE_ABS;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 688552df95ca..49fb9ec8366d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1706,6 +1706,9 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE))
return -EINVAL;
+ if (unlikely(!(ctx->data->sample_flags & PERF_SAMPLE_BRANCH_STACK)))
+ return -ENOENT;
+
if (unlikely(!br_stack))
return -ENOENT;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 447d2e2a8549..fbf2543111c0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1644,6 +1644,18 @@ ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_ex
static struct ftrace_ops *
ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
+static bool skip_record(struct dyn_ftrace *rec)
+{
+ /*
+ * At boot up, weak functions are set to disable. Function tracing
+ * can be enabled before they are, and they still need to be disabled now.
+ * If the record is disabled, still continue if it is marked as already
+ * enabled (this is needed to keep the accounting working).
+ */
+ return rec->flags & FTRACE_FL_DISABLED &&
+ !(rec->flags & FTRACE_FL_ENABLED);
+}
+
static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
int filter_hash,
bool inc)
@@ -1693,7 +1705,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
int in_hash = 0;
int match = 0;
- if (rec->flags & FTRACE_FL_DISABLED)
+ if (skip_record(rec))
continue;
if (all) {
@@ -2016,7 +2028,6 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
static void print_ip_ins(const char *fmt, const unsigned char *p)
{
char ins[MCOUNT_INSN_SIZE];
- int i;
if (copy_from_kernel_nofault(ins, p, MCOUNT_INSN_SIZE)) {
printk(KERN_CONT "%s[FAULT] %px\n", fmt, p);
@@ -2024,9 +2035,7 @@ static void print_ip_ins(const char *fmt, const unsigned char *p)
}
printk(KERN_CONT "%s", fmt);
-
- for (i = 0; i < MCOUNT_INSN_SIZE; i++)
- printk(KERN_CONT "%s%02x", i ? ":" : "", ins[i]);
+ pr_cont("%*phC", MCOUNT_INSN_SIZE, ins);
}
enum ftrace_bug_type ftrace_bug_type;
@@ -2126,7 +2135,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
ftrace_bug_type = FTRACE_BUG_UNKNOWN;
- if (rec->flags & FTRACE_FL_DISABLED)
+ if (skip_record(rec))
return FTRACE_UPDATE_IGNORE;
/*
@@ -2241,7 +2250,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
if (update) {
/* If there's no more users, clear all flags */
if (!ftrace_rec_count(rec))
- rec->flags = 0;
+ rec->flags &= FTRACE_FL_DISABLED;
else
/*
* Just disable the record, but keep the ops TRAMP
@@ -2634,7 +2643,7 @@ void __weak ftrace_replace_code(int mod_flags)
do_for_each_ftrace_rec(pg, rec) {
- if (rec->flags & FTRACE_FL_DISABLED)
+ if (skip_record(rec))
continue;
failed = __ftrace_replace_code(rec, enable);
@@ -5427,6 +5436,8 @@ static struct ftrace_ops stub_ops = {
* it is safe to modify the ftrace record, where it should be
* currently calling @old_addr directly, to call @new_addr.
*
+ * This is called with direct_mutex locked.
+ *
* Safety checks should be made to make sure that the code at
* @rec->ip is currently calling @old_addr. And this must
* also update entry->direct to @new_addr.
@@ -5439,6 +5450,8 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
unsigned long ip = rec->ip;
int ret;
+ lockdep_assert_held(&direct_mutex);
+
/*
* The ftrace_lock was used to determine if the record
* had more than one registered user to it. If it did,
@@ -5461,7 +5474,7 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
if (ret)
goto out_lock;
- ret = register_ftrace_function(&stub_ops);
+ ret = register_ftrace_function_nolock(&stub_ops);
if (ret) {
ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
goto out_lock;
@@ -6081,8 +6094,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
if (filter_hash) {
orig_hash = &iter->ops->func_hash->filter_hash;
- if (iter->tr && !list_empty(&iter->tr->mod_trace))
- iter->hash->flags |= FTRACE_HASH_FL_MOD;
+ if (iter->tr) {
+ if (list_empty(&iter->tr->mod_trace))
+ iter->hash->flags &= ~FTRACE_HASH_FL_MOD;
+ else
+ iter->hash->flags |= FTRACE_HASH_FL_MOD;
+ }
} else
orig_hash = &iter->ops->func_hash->notrace_hash;
diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c
index 18b0f1cbb947..80e04a1e1977 100644
--- a/kernel/trace/kprobe_event_gen_test.c
+++ b/kernel/trace/kprobe_event_gen_test.c
@@ -35,6 +35,45 @@
static struct trace_event_file *gen_kprobe_test;
static struct trace_event_file *gen_kretprobe_test;
+#define KPROBE_GEN_TEST_FUNC "do_sys_open"
+
+/* X86 */
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_32)
+#define KPROBE_GEN_TEST_ARG0 "dfd=%ax"
+#define KPROBE_GEN_TEST_ARG1 "filename=%dx"
+#define KPROBE_GEN_TEST_ARG2 "flags=%cx"
+#define KPROBE_GEN_TEST_ARG3 "mode=+4($stack)"
+
+/* ARM64 */
+#elif defined(CONFIG_ARM64)
+#define KPROBE_GEN_TEST_ARG0 "dfd=%x0"
+#define KPROBE_GEN_TEST_ARG1 "filename=%x1"
+#define KPROBE_GEN_TEST_ARG2 "flags=%x2"
+#define KPROBE_GEN_TEST_ARG3 "mode=%x3"
+
+/* ARM */
+#elif defined(CONFIG_ARM)
+#define KPROBE_GEN_TEST_ARG0 "dfd=%r0"
+#define KPROBE_GEN_TEST_ARG1 "filename=%r1"
+#define KPROBE_GEN_TEST_ARG2 "flags=%r2"
+#define KPROBE_GEN_TEST_ARG3 "mode=%r3"
+
+/* RISCV */
+#elif defined(CONFIG_RISCV)
+#define KPROBE_GEN_TEST_ARG0 "dfd=%a0"
+#define KPROBE_GEN_TEST_ARG1 "filename=%a1"
+#define KPROBE_GEN_TEST_ARG2 "flags=%a2"
+#define KPROBE_GEN_TEST_ARG3 "mode=%a3"
+
+/* others */
+#else
+#define KPROBE_GEN_TEST_ARG0 NULL
+#define KPROBE_GEN_TEST_ARG1 NULL
+#define KPROBE_GEN_TEST_ARG2 NULL
+#define KPROBE_GEN_TEST_ARG3 NULL
+#endif
+
+
/*
* Test to make sure we can create a kprobe event, then add more
* fields.
@@ -58,14 +97,14 @@ static int __init test_gen_kprobe_cmd(void)
* fields.
*/
ret = kprobe_event_gen_cmd_start(&cmd, "gen_kprobe_test",
- "do_sys_open",
- "dfd=%ax", "filename=%dx");
+ KPROBE_GEN_TEST_FUNC,
+ KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1);
if (ret)
goto free;
/* Use kprobe_event_add_fields to add the rest of the fields */
- ret = kprobe_event_add_fields(&cmd, "flags=%cx", "mode=+4($stack)");
+ ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3);
if (ret)
goto free;
@@ -128,7 +167,7 @@ static int __init test_gen_kretprobe_cmd(void)
* Define the kretprobe event.
*/
ret = kretprobe_event_gen_cmd_start(&cmd, "gen_kretprobe_test",
- "do_sys_open",
+ KPROBE_GEN_TEST_FUNC,
"$retval");
if (ret)
goto free;
@@ -206,7 +245,7 @@ static void __exit kprobe_event_gen_test_exit(void)
WARN_ON(kprobe_event_delete("gen_kprobe_test"));
/* Disable the event or you can't remove it */
- WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr,
+ WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
"kprobes",
"gen_kretprobe_test", false));
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d59b6a328b7f..199759c73519 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -413,6 +413,7 @@ struct rb_irq_work {
struct irq_work work;
wait_queue_head_t waiters;
wait_queue_head_t full_waiters;
+ long wait_index;
bool waiters_pending;
bool full_waiters_pending;
bool wakeup_full;
@@ -884,7 +885,7 @@ size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu)
}
/**
- * ring_buffer_nr_pages_dirty - get the number of used pages in the ring buffer
+ * ring_buffer_nr_dirty_pages - get the number of used pages in the ring buffer
* @buffer: The ring_buffer to get the number of pages from
* @cpu: The cpu of the ring_buffer to get the number of pages from
*
@@ -917,13 +918,45 @@ static void rb_wake_up_waiters(struct irq_work *work)
struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
wake_up_all(&rbwork->waiters);
- if (rbwork->wakeup_full) {
+ if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
rbwork->wakeup_full = false;
+ rbwork->full_waiters_pending = false;
wake_up_all(&rbwork->full_waiters);
}
}
/**
+ * ring_buffer_wake_waiters - wake up any waiters on this ring buffer
+ * @buffer: The ring buffer to wake waiters on
+ *
+ * In the case of a file that represents a ring buffer is closing,
+ * it is prudent to wake up any waiters that are on this.
+ */
+void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct rb_irq_work *rbwork;
+
+ if (cpu == RING_BUFFER_ALL_CPUS) {
+
+ /* Wake up individual ones too. One level recursion */
+ for_each_buffer_cpu(buffer, cpu)
+ ring_buffer_wake_waiters(buffer, cpu);
+
+ rbwork = &buffer->irq_work;
+ } else {
+ cpu_buffer = buffer->buffers[cpu];
+ rbwork = &cpu_buffer->irq_work;
+ }
+
+ rbwork->wait_index++;
+ /* make sure the waiters see the new index */
+ smp_wmb();
+
+ rb_wake_up_waiters(&rbwork->work);
+}
+
+/**
* ring_buffer_wait - wait for input to the ring buffer
* @buffer: buffer to wait on
* @cpu: the cpu buffer to wait on
@@ -938,6 +971,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
struct ring_buffer_per_cpu *cpu_buffer;
DEFINE_WAIT(wait);
struct rb_irq_work *work;
+ long wait_index;
int ret = 0;
/*
@@ -956,6 +990,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
work = &cpu_buffer->irq_work;
}
+ wait_index = READ_ONCE(work->wait_index);
while (true) {
if (full)
@@ -1011,7 +1046,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
nr_pages = cpu_buffer->nr_pages;
dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
if (!cpu_buffer->shortest_full ||
- cpu_buffer->shortest_full < full)
+ cpu_buffer->shortest_full > full)
cpu_buffer->shortest_full = full;
raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
if (!pagebusy &&
@@ -1020,6 +1055,11 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
}
schedule();
+
+ /* Make sure to see the new wait index */
+ smp_rmb();
+ if (wait_index != work->wait_index)
+ break;
}
if (full)
@@ -2608,6 +2648,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
/* Mark the rest of the page with padding */
rb_event_set_padding(event);
+ /* Make sure the padding is visible before the write update */
+ smp_wmb();
+
/* Set the write back to the previous setting */
local_sub(length, &tail_page->write);
return;
@@ -2619,6 +2662,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
/* time delta must be non zero */
event->time_delta = 1;
+ /* Make sure the padding is visible before the tail_page->write update */
+ smp_wmb();
+
/* Set write to end of buffer */
length = (tail + length) - BUF_PAGE_SIZE;
local_sub(length, &tail_page->write);
@@ -4587,6 +4633,33 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
arch_spin_unlock(&cpu_buffer->lock);
local_irq_restore(flags);
+ /*
+ * The writer has preempt disable, wait for it. But not forever
+ * Although, 1 second is pretty much "forever"
+ */
+#define USECS_WAIT 1000000
+ for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
+ /* If the write is past the end of page, a writer is still updating it */
+ if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+ break;
+
+ udelay(1);
+
+ /* Get the latest version of the reader write value */
+ smp_rmb();
+ }
+
+ /* The writer is not moving forward? Something is wrong */
+ if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT))
+ reader = NULL;
+
+ /*
+ * Make sure we see any padding after the write update
+ * (see rb_reset_tail())
+ */
+ smp_rmb();
+
+
return reader;
}
@@ -5232,7 +5305,7 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
/**
- * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
+ * ring_buffer_reset_online_cpus - reset a ring buffer per CPU buffer
* @buffer: The ring buffer to reset a per cpu buffer of
* @cpu: The CPU buffer to be reset
*/
@@ -5302,7 +5375,7 @@ void ring_buffer_reset(struct trace_buffer *buffer)
EXPORT_SYMBOL_GPL(ring_buffer_reset);
/**
- * rind_buffer_empty - is the ring buffer empty?
+ * ring_buffer_empty - is the ring buffer empty?
* @buffer: The ring buffer to test
*/
bool ring_buffer_empty(struct trace_buffer *buffer)
@@ -5616,7 +5689,15 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
unsigned int pos = 0;
unsigned int size;
- if (full)
+ /*
+ * If a full page is expected, this can still be returned
+ * if there's been a previous partial read and the
+ * rest of the page can be read and the commit page is off
+ * the reader page.
+ */
+ if (full &&
+ (!read || (len < (commit - read)) ||
+ cpu_buffer->reader_page == cpu_buffer->commit_page))
goto out_unlock;
if (len > (commit - read))
diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c
index 83cace53b9fa..b2b49a27e886 100644
--- a/kernel/trace/rv/monitors/wip/wip.c
+++ b/kernel/trace/rv/monitors/wip/wip.c
@@ -16,7 +16,7 @@
#include "wip.h"
-struct rv_monitor rv_wip;
+static struct rv_monitor rv_wip;
DECLARE_DA_MON_PER_CPU(wip, unsigned char);
static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip)
@@ -60,7 +60,7 @@ static void disable_wip(void)
da_monitor_destroy_wip();
}
-struct rv_monitor rv_wip = {
+static struct rv_monitor rv_wip = {
.name = "wip",
.description = "wakeup in preemptive per-cpu testing monitor.",
.enable = enable_wip,
@@ -69,13 +69,13 @@ struct rv_monitor rv_wip = {
.enabled = 0,
};
-static int register_wip(void)
+static int __init register_wip(void)
{
rv_register_monitor(&rv_wip);
return 0;
}
-static void unregister_wip(void)
+static void __exit unregister_wip(void)
{
rv_unregister_monitor(&rv_wip);
}
diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c
index 599225d9cf38..0e43dd2db685 100644
--- a/kernel/trace/rv/monitors/wwnr/wwnr.c
+++ b/kernel/trace/rv/monitors/wwnr/wwnr.c
@@ -15,7 +15,7 @@
#include "wwnr.h"
-struct rv_monitor rv_wwnr;
+static struct rv_monitor rv_wwnr;
DECLARE_DA_MON_PER_TASK(wwnr, unsigned char);
static void handle_switch(void *data, bool preempt, struct task_struct *p,
@@ -59,7 +59,7 @@ static void disable_wwnr(void)
da_monitor_destroy_wwnr();
}
-struct rv_monitor rv_wwnr = {
+static struct rv_monitor rv_wwnr = {
.name = "wwnr",
.description = "wakeup while not running per-task testing model.",
.enable = enable_wwnr,
@@ -68,13 +68,13 @@ struct rv_monitor rv_wwnr = {
.enabled = 0,
};
-static int register_wwnr(void)
+static int __init register_wwnr(void)
{
rv_register_monitor(&rv_wwnr);
return 0;
}
-static void unregister_wwnr(void)
+static void __exit unregister_wwnr(void)
{
rv_unregister_monitor(&rv_wwnr);
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d3005279165d..47a44b055a1d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1193,12 +1193,14 @@ void *tracing_cond_snapshot_data(struct trace_array *tr)
{
void *cond_data = NULL;
+ local_irq_disable();
arch_spin_lock(&tr->max_lock);
if (tr->cond_snapshot)
cond_data = tr->cond_snapshot->cond_data;
arch_spin_unlock(&tr->max_lock);
+ local_irq_enable();
return cond_data;
}
@@ -1334,9 +1336,11 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data,
goto fail_unlock;
}
+ local_irq_disable();
arch_spin_lock(&tr->max_lock);
tr->cond_snapshot = cond_snapshot;
arch_spin_unlock(&tr->max_lock);
+ local_irq_enable();
mutex_unlock(&trace_types_lock);
@@ -1363,6 +1367,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
{
int ret = 0;
+ local_irq_disable();
arch_spin_lock(&tr->max_lock);
if (!tr->cond_snapshot)
@@ -1373,6 +1378,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
}
arch_spin_unlock(&tr->max_lock);
+ local_irq_enable();
return ret;
}
@@ -2200,6 +2206,11 @@ static size_t tgid_map_max;
#define SAVED_CMDLINES_DEFAULT 128
#define NO_CMDLINE_MAP UINT_MAX
+/*
+ * Preemption must be disabled before acquiring trace_cmdline_lock.
+ * The various trace_arrays' max_lock must be acquired in a context
+ * where interrupt is disabled.
+ */
static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
struct saved_cmdlines_buffer {
unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -2412,7 +2423,11 @@ static int trace_save_cmdline(struct task_struct *tsk)
* the lock, but we also don't want to spin
* nor do we want to disable interrupts,
* so if we miss here, then better luck next time.
+ *
+ * This is called within the scheduler and wake up, so interrupts
+ * had better been disabled and run queue lock been held.
*/
+ lockdep_assert_preemption_disabled();
if (!arch_spin_trylock(&trace_cmdline_lock))
return 0;
@@ -5890,9 +5905,11 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
char buf[64];
int r;
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@@ -5917,10 +5934,12 @@ static int tracing_resize_saved_cmdlines(unsigned int val)
return -ENOMEM;
}
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
savedcmd_temp = savedcmd;
savedcmd = s;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
free_saved_cmdlines_buffer(savedcmd_temp);
return 0;
@@ -6373,10 +6392,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
#ifdef CONFIG_TRACER_SNAPSHOT
if (t->use_max_tr) {
+ local_irq_disable();
arch_spin_lock(&tr->max_lock);
if (tr->cond_snapshot)
ret = -EBUSY;
arch_spin_unlock(&tr->max_lock);
+ local_irq_enable();
if (ret)
goto out;
}
@@ -6407,12 +6428,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
if (tr->current_trace->reset)
tr->current_trace->reset(tr);
+#ifdef CONFIG_TRACER_MAX_TRACE
+ had_max_tr = tr->current_trace->use_max_tr;
+
/* Current trace needs to be nop_trace before synchronize_rcu */
tr->current_trace = &nop_trace;
-#ifdef CONFIG_TRACER_MAX_TRACE
- had_max_tr = tr->allocated_snapshot;
-
if (had_max_tr && !t->use_max_tr) {
/*
* We need to make sure that the update_max_tr sees that
@@ -6425,11 +6446,13 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
free_snapshot(tr);
}
- if (t->use_max_tr && !had_max_tr) {
+ if (t->use_max_tr && !tr->allocated_snapshot) {
ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
goto out;
}
+#else
+ tr->current_trace = &nop_trace;
#endif
if (t->init) {
@@ -7436,10 +7459,12 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
goto out;
}
+ local_irq_disable();
arch_spin_lock(&tr->max_lock);
if (tr->cond_snapshot)
ret = -EBUSY;
arch_spin_unlock(&tr->max_lock);
+ local_irq_enable();
if (ret)
goto out;
@@ -8137,6 +8162,12 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
__trace_array_put(iter->tr);
+ iter->wait_index++;
+ /* Make sure the waiters see the new wait_index */
+ smp_wmb();
+
+ ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
if (info->spare)
ring_buffer_free_read_page(iter->array_buffer->buffer,
info->spare_cpu, info->spare);
@@ -8290,6 +8321,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
/* did we read anything? */
if (!spd.nr_pages) {
+ long wait_index;
+
if (ret)
goto out;
@@ -8297,10 +8330,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
goto out;
+ wait_index = READ_ONCE(iter->wait_index);
+
ret = wait_on_pipe(iter, iter->tr->buffer_percent);
if (ret)
goto out;
+ /* No need to wait after waking up when tracing is off */
+ if (!tracer_tracing_is_on(iter->tr))
+ goto out;
+
+ /* Make sure we see the new wait_index */
+ smp_rmb();
+ if (wait_index != iter->wait_index)
+ goto out;
+
goto again;
}
@@ -8311,12 +8355,34 @@ out:
return ret;
}
+/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */
+static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct ftrace_buffer_info *info = file->private_data;
+ struct trace_iterator *iter = &info->iter;
+
+ if (cmd)
+ return -ENOIOCTLCMD;
+
+ mutex_lock(&trace_types_lock);
+
+ iter->wait_index++;
+ /* Make sure the waiters see the new wait_index */
+ smp_wmb();
+
+ ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
+ mutex_unlock(&trace_types_lock);
+ return 0;
+}
+
static const struct file_operations tracing_buffers_fops = {
.open = tracing_buffers_open,
.read = tracing_buffers_read,
.poll = tracing_buffers_poll,
.release = tracing_buffers_release,
.splice_read = tracing_buffers_splice_read,
+ .unlocked_ioctl = tracing_buffers_ioctl,
.llseek = no_llseek,
};
@@ -9005,6 +9071,8 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
tracer_tracing_off(tr);
if (tr->current_trace->stop)
tr->current_trace->stop(tr);
+ /* Wake up any waiters */
+ ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS);
}
mutex_unlock(&trace_types_lock);
}
@@ -10091,7 +10159,7 @@ __init static int tracer_alloc_buffers(void)
* buffer. The memory will be removed once the "instance" is removed.
*/
ret = cpuhp_setup_state_multi(CPUHP_TRACE_RB_PREPARE,
- "trace/RB:preapre", trace_rb_cpu_prepare,
+ "trace/RB:prepare", trace_rb_cpu_prepare,
NULL);
if (ret < 0)
goto out_free_cpumask;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 900e75d96c84..54ee5711c729 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1435,8 +1435,6 @@ event_trigger_unlock_commit(struct trace_event_file *file,
struct filter_pred;
struct regex;
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
-
typedef int (*regex_match_func)(char *str, struct regex *r, int len);
enum regex_type {
@@ -1455,17 +1453,6 @@ struct regex {
regex_match_func match;
};
-struct filter_pred {
- filter_pred_fn_t fn;
- u64 val;
- struct regex regex;
- unsigned short *ops;
- struct ftrace_event_field *field;
- int offset;
- int not;
- int op;
-};
-
static inline bool is_string_field(struct ftrace_event_field *field)
{
return field->filter_type == FILTER_DYN_STRING ||
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 801c2a7f7605..54d5fa35c90a 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -51,7 +51,7 @@ static void trace_do_benchmark(void)
local_irq_disable();
start = trace_clock_local();
- trace_benchmark_event(bm_str);
+ trace_benchmark_event(bm_str, bm_last);
stop = trace_clock_local();
local_irq_enable();
diff --git a/kernel/trace/trace_benchmark.h b/kernel/trace/trace_benchmark.h
index 79e6fbe5b365..c3e91060dc94 100644
--- a/kernel/trace/trace_benchmark.h
+++ b/kernel/trace/trace_benchmark.h
@@ -14,19 +14,21 @@ extern void trace_benchmark_unreg(void);
TRACE_EVENT_FN(benchmark_event,
- TP_PROTO(const char *str),
+ TP_PROTO(const char *str, u64 delta),
- TP_ARGS(str),
+ TP_ARGS(str, delta),
TP_STRUCT__entry(
__array( char, str, BENCHMARK_EVENT_STRLEN )
+ __field( u64, delta)
),
TP_fast_assign(
memcpy(__entry->str, str, BENCHMARK_EVENT_STRLEN);
+ __entry->delta = delta;
),
- TP_printk("%s", __entry->str),
+ TP_printk("%s delta=%llu", __entry->str, __entry->delta),
trace_benchmark_reg, trace_benchmark_unreg
);
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 1783e3478912..5dd0617e5df6 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -16,6 +16,7 @@
#include "trace_dynevent.h"
#include "trace_probe.h"
#include "trace_probe_tmpl.h"
+#include "trace_probe_kernel.h"
#define EPROBE_EVENT_SYSTEM "eprobes"
@@ -26,6 +27,9 @@ struct trace_eprobe {
/* tracepoint event */
const char *event_name;
+ /* filter string for the tracepoint */
+ char *filter_str;
+
struct trace_event_call *event;
struct dyn_event devent;
@@ -453,29 +457,14 @@ NOKPROBE_SYMBOL(process_fetch_insn)
static nokprobe_inline int
fetch_store_strlen_user(unsigned long addr)
{
- const void __user *uaddr = (__force const void __user *)addr;
-
- return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+ return kern_fetch_store_strlen_user(addr);
}
/* Return the length of string -- including null terminal byte */
static nokprobe_inline int
fetch_store_strlen(unsigned long addr)
{
- int ret, len = 0;
- u8 c;
-
-#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
- if (addr < TASK_SIZE)
- return fetch_store_strlen_user(addr);
-#endif
-
- do {
- ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
- len++;
- } while (c && ret == 0 && len < MAX_STRING_SIZE);
-
- return (ret < 0) ? ret : len;
+ return kern_fetch_store_strlen(addr);
}
/*
@@ -485,21 +474,7 @@ fetch_store_strlen(unsigned long addr)
static nokprobe_inline int
fetch_store_string_user(unsigned long addr, void *dest, void *base)
{
- const void __user *uaddr = (__force const void __user *)addr;
- int maxlen = get_loc_len(*(u32 *)dest);
- void *__dest;
- long ret;
-
- if (unlikely(!maxlen))
- return -ENOMEM;
-
- __dest = get_loc_data(dest, base);
-
- ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
- if (ret >= 0)
- *(u32 *)dest = make_data_loc(ret, __dest - base);
-
- return ret;
+ return kern_fetch_store_string_user(addr, dest, base);
}
/*
@@ -509,29 +484,7 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
static nokprobe_inline int
fetch_store_string(unsigned long addr, void *dest, void *base)
{
- int maxlen = get_loc_len(*(u32 *)dest);
- void *__dest;
- long ret;
-
-#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
- if ((unsigned long)addr < TASK_SIZE)
- return fetch_store_string_user(addr, dest, base);
-#endif
-
- if (unlikely(!maxlen))
- return -ENOMEM;
-
- __dest = get_loc_data(dest, base);
-
- /*
- * Try to get string again, since the string can be changed while
- * probing.
- */
- ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
- if (ret >= 0)
- *(u32 *)dest = make_data_loc(ret, __dest - base);
-
- return ret;
+ return kern_fetch_store_string(addr, dest, base);
}
static nokprobe_inline int
@@ -664,14 +617,15 @@ static struct event_trigger_data *
new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file)
{
struct event_trigger_data *trigger;
+ struct event_filter *filter = NULL;
struct eprobe_data *edata;
+ int ret;
edata = kzalloc(sizeof(*edata), GFP_KERNEL);
trigger = kzalloc(sizeof(*trigger), GFP_KERNEL);
if (!trigger || !edata) {
- kfree(edata);
- kfree(trigger);
- return ERR_PTR(-ENOMEM);
+ ret = -ENOMEM;
+ goto error;
}
trigger->flags = EVENT_TRIGGER_FL_PROBE;
@@ -686,13 +640,25 @@ new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file)
trigger->cmd_ops = &event_trigger_cmd;
INIT_LIST_HEAD(&trigger->list);
- RCU_INIT_POINTER(trigger->filter, NULL);
+
+ if (ep->filter_str) {
+ ret = create_event_filter(file->tr, file->event_call,
+ ep->filter_str, false, &filter);
+ if (ret)
+ goto error;
+ }
+ RCU_INIT_POINTER(trigger->filter, filter);
edata->file = file;
edata->ep = ep;
trigger->private_data = edata;
return trigger;
+error:
+ free_event_filter(filter);
+ kfree(edata);
+ kfree(trigger);
+ return ERR_PTR(ret);
}
static int enable_eprobe(struct trace_eprobe *ep,
@@ -726,6 +692,7 @@ static int disable_eprobe(struct trace_eprobe *ep,
{
struct event_trigger_data *trigger = NULL, *iter;
struct trace_event_file *file;
+ struct event_filter *filter;
struct eprobe_data *edata;
file = find_event_file(tr, ep->event_system, ep->event_name);
@@ -752,6 +719,10 @@ static int disable_eprobe(struct trace_eprobe *ep,
/* Make sure nothing is using the edata or trigger */
tracepoint_synchronize_unregister();
+ filter = rcu_access_pointer(trigger->filter);
+
+ if (filter)
+ free_event_filter(filter);
kfree(edata);
kfree(trigger);
@@ -927,12 +898,62 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[
return ret;
}
+static int trace_eprobe_parse_filter(struct trace_eprobe *ep, int argc, const char *argv[])
+{
+ struct event_filter *dummy;
+ int i, ret, len = 0;
+ char *p;
+
+ if (argc == 0) {
+ trace_probe_log_err(0, NO_EP_FILTER);
+ return -EINVAL;
+ }
+
+ /* Recover the filter string */
+ for (i = 0; i < argc; i++)
+ len += strlen(argv[i]) + 1;
+
+ ep->filter_str = kzalloc(len, GFP_KERNEL);
+ if (!ep->filter_str)
+ return -ENOMEM;
+
+ p = ep->filter_str;
+ for (i = 0; i < argc; i++) {
+ ret = snprintf(p, len, "%s ", argv[i]);
+ if (ret < 0)
+ goto error;
+ if (ret > len) {
+ ret = -E2BIG;
+ goto error;
+ }
+ p += ret;
+ len -= ret;
+ }
+ p[-1] = '\0';
+
+ /*
+ * Ensure the filter string can be parsed correctly. Note, this
+ * filter string is for the original event, not for the eprobe.
+ */
+ ret = create_event_filter(top_trace_array(), ep->event, ep->filter_str,
+ true, &dummy);
+ free_event_filter(dummy);
+ if (ret)
+ goto error;
+
+ return 0;
+error:
+ kfree(ep->filter_str);
+ ep->filter_str = NULL;
+ return ret;
+}
+
static int __trace_eprobe_create(int argc, const char *argv[])
{
/*
* Argument syntax:
- * e[:[GRP/][ENAME]] SYSTEM.EVENT [FETCHARGS]
- * Fetch args:
+ * e[:[GRP/][ENAME]] SYSTEM.EVENT [FETCHARGS] [if FILTER]
+ * Fetch args (no space):
* <name>=$<field>[:TYPE]
*/
const char *event = NULL, *group = EPROBE_EVENT_SYSTEM;
@@ -942,8 +963,8 @@ static int __trace_eprobe_create(int argc, const char *argv[])
char buf1[MAX_EVENT_NAME_LEN];
char buf2[MAX_EVENT_NAME_LEN];
char gbuf[MAX_EVENT_NAME_LEN];
- int ret = 0;
- int i;
+ int ret = 0, filter_idx = 0;
+ int i, filter_cnt;
if (argc < 2 || argv[0][0] != 'e')
return -ECANCELED;
@@ -968,11 +989,19 @@ static int __trace_eprobe_create(int argc, const char *argv[])
}
if (!event) {
- strscpy(buf1, argv[1], MAX_EVENT_NAME_LEN);
- sanitize_event_name(buf1);
+ strscpy(buf1, sys_event, MAX_EVENT_NAME_LEN);
event = buf1;
}
+ for (i = 2; i < argc; i++) {
+ if (!strcmp(argv[i], "if")) {
+ filter_idx = i + 1;
+ filter_cnt = argc - filter_idx;
+ argc = i;
+ break;
+ }
+ }
+
mutex_lock(&event_mutex);
event_call = find_and_get_event(sys_name, sys_event);
ep = alloc_event_probe(group, event, event_call, argc - 2);
@@ -988,6 +1017,14 @@ static int __trace_eprobe_create(int argc, const char *argv[])
goto error;
}
+ if (filter_idx) {
+ trace_probe_log_set_index(filter_idx);
+ ret = trace_eprobe_parse_filter(ep, filter_cnt, argv + filter_idx);
+ if (ret)
+ goto parse_error;
+ } else
+ ep->filter_str = NULL;
+
argc -= 2; argv += 2;
/* parse arguments */
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 4b1057ab9d96..96acc2b71ac7 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -43,6 +43,42 @@ enum filter_op_ids { OPS };
static const char * ops[] = { OPS };
+enum filter_pred_fn {
+ FILTER_PRED_FN_NOP,
+ FILTER_PRED_FN_64,
+ FILTER_PRED_FN_S64,
+ FILTER_PRED_FN_U64,
+ FILTER_PRED_FN_32,
+ FILTER_PRED_FN_S32,
+ FILTER_PRED_FN_U32,
+ FILTER_PRED_FN_16,
+ FILTER_PRED_FN_S16,
+ FILTER_PRED_FN_U16,
+ FILTER_PRED_FN_8,
+ FILTER_PRED_FN_S8,
+ FILTER_PRED_FN_U8,
+ FILTER_PRED_FN_COMM,
+ FILTER_PRED_FN_STRING,
+ FILTER_PRED_FN_STRLOC,
+ FILTER_PRED_FN_STRRELLOC,
+ FILTER_PRED_FN_PCHAR_USER,
+ FILTER_PRED_FN_PCHAR,
+ FILTER_PRED_FN_CPU,
+ FILTER_PRED_FN_,
+ FILTER_PRED_TEST_VISITED,
+};
+
+struct filter_pred {
+ enum filter_pred_fn fn_num;
+ u64 val;
+ struct regex regex;
+ unsigned short *ops;
+ struct ftrace_event_field *field;
+ int offset;
+ int not;
+ int op;
+};
+
/*
* pred functions are OP_LE, OP_LT, OP_GE, OP_GT, and OP_BAND
* pred_funcs_##type below must match the order of them above.
@@ -590,44 +626,48 @@ out_free:
return ERR_PTR(ret);
}
+enum pred_cmp_types {
+ PRED_CMP_TYPE_NOP,
+ PRED_CMP_TYPE_LT,
+ PRED_CMP_TYPE_LE,
+ PRED_CMP_TYPE_GT,
+ PRED_CMP_TYPE_GE,
+ PRED_CMP_TYPE_BAND,
+};
+
#define DEFINE_COMPARISON_PRED(type) \
-static int filter_pred_LT_##type(struct filter_pred *pred, void *event) \
-{ \
- type *addr = (type *)(event + pred->offset); \
- type val = (type)pred->val; \
- return *addr < val; \
-} \
-static int filter_pred_LE_##type(struct filter_pred *pred, void *event) \
-{ \
- type *addr = (type *)(event + pred->offset); \
- type val = (type)pred->val; \
- return *addr <= val; \
-} \
-static int filter_pred_GT_##type(struct filter_pred *pred, void *event) \
+static int filter_pred_##type(struct filter_pred *pred, void *event) \
{ \
- type *addr = (type *)(event + pred->offset); \
- type val = (type)pred->val; \
- return *addr > val; \
-} \
-static int filter_pred_GE_##type(struct filter_pred *pred, void *event) \
-{ \
- type *addr = (type *)(event + pred->offset); \
- type val = (type)pred->val; \
- return *addr >= val; \
-} \
-static int filter_pred_BAND_##type(struct filter_pred *pred, void *event) \
-{ \
- type *addr = (type *)(event + pred->offset); \
- type val = (type)pred->val; \
- return !!(*addr & val); \
-} \
-static const filter_pred_fn_t pred_funcs_##type[] = { \
- filter_pred_LE_##type, \
- filter_pred_LT_##type, \
- filter_pred_GE_##type, \
- filter_pred_GT_##type, \
- filter_pred_BAND_##type, \
-};
+ switch (pred->op) { \
+ case OP_LT: { \
+ type *addr = (type *)(event + pred->offset); \
+ type val = (type)pred->val; \
+ return *addr < val; \
+ } \
+ case OP_LE: { \
+ type *addr = (type *)(event + pred->offset); \
+ type val = (type)pred->val; \
+ return *addr <= val; \
+ } \
+ case OP_GT: { \
+ type *addr = (type *)(event + pred->offset); \
+ type val = (type)pred->val; \
+ return *addr > val; \
+ } \
+ case OP_GE: { \
+ type *addr = (type *)(event + pred->offset); \
+ type val = (type)pred->val; \
+ return *addr >= val; \
+ } \
+ case OP_BAND: { \
+ type *addr = (type *)(event + pred->offset); \
+ type val = (type)pred->val; \
+ return !!(*addr & val); \
+ } \
+ default: \
+ return 0; \
+ } \
+}
#define DEFINE_EQUALITY_PRED(size) \
static int filter_pred_##size(struct filter_pred *pred, void *event) \
@@ -836,11 +876,6 @@ static int filter_pred_comm(struct filter_pred *pred, void *event)
return cmp ^ pred->not;
}
-static int filter_pred_none(struct filter_pred *pred, void *event)
-{
- return 0;
-}
-
/*
* regex_match_foo - Basic regex callbacks
*
@@ -986,6 +1021,19 @@ static void filter_build_regex(struct filter_pred *pred)
}
}
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+static int test_pred_visited_fn(struct filter_pred *pred, void *event);
+#else
+static int test_pred_visited_fn(struct filter_pred *pred, void *event)
+{
+ return 0;
+}
+#endif
+
+
+static int filter_pred_fn_call(struct filter_pred *pred, void *event);
+
/* return 1 if event matches, 0 otherwise (discard) */
int filter_match_preds(struct event_filter *filter, void *rec)
{
@@ -1003,7 +1051,7 @@ int filter_match_preds(struct event_filter *filter, void *rec)
for (i = 0; prog[i].pred; i++) {
struct filter_pred *pred = prog[i].pred;
- int match = pred->fn(pred, rec);
+ int match = filter_pred_fn_call(pred, rec);
if (match == prog[i].when_to_branch)
i = prog[i].target;
}
@@ -1189,10 +1237,10 @@ int filter_assign_type(const char *type)
return FILTER_OTHER;
}
-static filter_pred_fn_t select_comparison_fn(enum filter_op_ids op,
- int field_size, int field_is_signed)
+static enum filter_pred_fn select_comparison_fn(enum filter_op_ids op,
+ int field_size, int field_is_signed)
{
- filter_pred_fn_t fn = NULL;
+ enum filter_pred_fn fn = FILTER_PRED_FN_NOP;
int pred_func_index = -1;
switch (op) {
@@ -1201,50 +1249,99 @@ static filter_pred_fn_t select_comparison_fn(enum filter_op_ids op,
break;
default:
if (WARN_ON_ONCE(op < PRED_FUNC_START))
- return NULL;
+ return fn;
pred_func_index = op - PRED_FUNC_START;
if (WARN_ON_ONCE(pred_func_index > PRED_FUNC_MAX))
- return NULL;
+ return fn;
}
switch (field_size) {
case 8:
if (pred_func_index < 0)
- fn = filter_pred_64;
+ fn = FILTER_PRED_FN_64;
else if (field_is_signed)
- fn = pred_funcs_s64[pred_func_index];
+ fn = FILTER_PRED_FN_S64;
else
- fn = pred_funcs_u64[pred_func_index];
+ fn = FILTER_PRED_FN_U64;
break;
case 4:
if (pred_func_index < 0)
- fn = filter_pred_32;
+ fn = FILTER_PRED_FN_32;
else if (field_is_signed)
- fn = pred_funcs_s32[pred_func_index];
+ fn = FILTER_PRED_FN_S32;
else
- fn = pred_funcs_u32[pred_func_index];
+ fn = FILTER_PRED_FN_U32;
break;
case 2:
if (pred_func_index < 0)
- fn = filter_pred_16;
+ fn = FILTER_PRED_FN_16;
else if (field_is_signed)
- fn = pred_funcs_s16[pred_func_index];
+ fn = FILTER_PRED_FN_S16;
else
- fn = pred_funcs_u16[pred_func_index];
+ fn = FILTER_PRED_FN_U16;
break;
case 1:
if (pred_func_index < 0)
- fn = filter_pred_8;
+ fn = FILTER_PRED_FN_8;
else if (field_is_signed)
- fn = pred_funcs_s8[pred_func_index];
+ fn = FILTER_PRED_FN_S8;
else
- fn = pred_funcs_u8[pred_func_index];
+ fn = FILTER_PRED_FN_U8;
break;
}
return fn;
}
+
+static int filter_pred_fn_call(struct filter_pred *pred, void *event)
+{
+ switch (pred->fn_num) {
+ case FILTER_PRED_FN_64:
+ return filter_pred_64(pred, event);
+ case FILTER_PRED_FN_S64:
+ return filter_pred_s64(pred, event);
+ case FILTER_PRED_FN_U64:
+ return filter_pred_u64(pred, event);
+ case FILTER_PRED_FN_32:
+ return filter_pred_32(pred, event);
+ case FILTER_PRED_FN_S32:
+ return filter_pred_s32(pred, event);
+ case FILTER_PRED_FN_U32:
+ return filter_pred_u32(pred, event);
+ case FILTER_PRED_FN_16:
+ return filter_pred_16(pred, event);
+ case FILTER_PRED_FN_S16:
+ return filter_pred_s16(pred, event);
+ case FILTER_PRED_FN_U16:
+ return filter_pred_u16(pred, event);
+ case FILTER_PRED_FN_8:
+ return filter_pred_8(pred, event);
+ case FILTER_PRED_FN_S8:
+ return filter_pred_s8(pred, event);
+ case FILTER_PRED_FN_U8:
+ return filter_pred_u8(pred, event);
+ case FILTER_PRED_FN_COMM:
+ return filter_pred_comm(pred, event);
+ case FILTER_PRED_FN_STRING:
+ return filter_pred_string(pred, event);
+ case FILTER_PRED_FN_STRLOC:
+ return filter_pred_strloc(pred, event);
+ case FILTER_PRED_FN_STRRELLOC:
+ return filter_pred_strrelloc(pred, event);
+ case FILTER_PRED_FN_PCHAR_USER:
+ return filter_pred_pchar_user(pred, event);
+ case FILTER_PRED_FN_PCHAR:
+ return filter_pred_pchar(pred, event);
+ case FILTER_PRED_FN_CPU:
+ return filter_pred_cpu(pred, event);
+ case FILTER_PRED_TEST_VISITED:
+ return test_pred_visited_fn(pred, event);
+ default:
+ return 0;
+ }
+}
+
/* Called when a predicate is encountered by predicate_parse() */
static int parse_pred(const char *str, void *data,
int pos, struct filter_parse_error *pe,
@@ -1338,7 +1435,7 @@ static int parse_pred(const char *str, void *data,
parse_error(pe, FILT_ERR_IP_FIELD_ONLY, pos + i);
goto err_free;
}
- pred->fn = filter_pred_none;
+ pred->fn_num = FILTER_PRED_FN_NOP;
/*
* Quotes are not required, but if they exist then we need
@@ -1416,16 +1513,16 @@ static int parse_pred(const char *str, void *data,
filter_build_regex(pred);
if (field->filter_type == FILTER_COMM) {
- pred->fn = filter_pred_comm;
+ pred->fn_num = FILTER_PRED_FN_COMM;
} else if (field->filter_type == FILTER_STATIC_STRING) {
- pred->fn = filter_pred_string;
+ pred->fn_num = FILTER_PRED_FN_STRING;
pred->regex.field_len = field->size;
} else if (field->filter_type == FILTER_DYN_STRING) {
- pred->fn = filter_pred_strloc;
+ pred->fn_num = FILTER_PRED_FN_STRLOC;
} else if (field->filter_type == FILTER_RDYN_STRING)
- pred->fn = filter_pred_strrelloc;
+ pred->fn_num = FILTER_PRED_FN_STRRELLOC;
else {
if (!ustring_per_cpu) {
@@ -1436,9 +1533,9 @@ static int parse_pred(const char *str, void *data,
}
if (ustring)
- pred->fn = filter_pred_pchar_user;
+ pred->fn_num = FILTER_PRED_FN_PCHAR_USER;
else
- pred->fn = filter_pred_pchar;
+ pred->fn_num = FILTER_PRED_FN_PCHAR;
}
/* go past the last quote */
i++;
@@ -1486,10 +1583,10 @@ static int parse_pred(const char *str, void *data,
pred->val = val;
if (field->filter_type == FILTER_CPU)
- pred->fn = filter_pred_cpu;
+ pred->fn_num = FILTER_PRED_FN_CPU;
else {
- pred->fn = select_comparison_fn(pred->op, field->size,
- field->is_signed);
+ pred->fn_num = select_comparison_fn(pred->op, field->size,
+ field->is_signed);
if (pred->op == OP_NE)
pred->not = 1;
}
@@ -2296,7 +2393,7 @@ static void update_pred_fn(struct event_filter *filter, char *fields)
struct filter_pred *pred = prog[i].pred;
struct ftrace_event_field *field = pred->field;
- WARN_ON_ONCE(!pred->fn);
+ WARN_ON_ONCE(pred->fn_num == FILTER_PRED_FN_NOP);
if (!field) {
WARN_ONCE(1, "all leafs should have field defined %d", i);
@@ -2306,7 +2403,7 @@ static void update_pred_fn(struct event_filter *filter, char *fields)
if (!strchr(fields, *field->name))
continue;
- pred->fn = test_pred_visited_fn;
+ pred->fn_num = FILTER_PRED_TEST_VISITED;
}
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index fdf784620c28..48465f7e97b4 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -104,6 +104,38 @@ enum field_op_id {
FIELD_OP_MULT,
};
+enum hist_field_fn {
+ HIST_FIELD_FN_NOP,
+ HIST_FIELD_FN_VAR_REF,
+ HIST_FIELD_FN_COUNTER,
+ HIST_FIELD_FN_CONST,
+ HIST_FIELD_FN_LOG2,
+ HIST_FIELD_FN_BUCKET,
+ HIST_FIELD_FN_TIMESTAMP,
+ HIST_FIELD_FN_CPU,
+ HIST_FIELD_FN_STRING,
+ HIST_FIELD_FN_DYNSTRING,
+ HIST_FIELD_FN_RELDYNSTRING,
+ HIST_FIELD_FN_PSTRING,
+ HIST_FIELD_FN_S64,
+ HIST_FIELD_FN_U64,
+ HIST_FIELD_FN_S32,
+ HIST_FIELD_FN_U32,
+ HIST_FIELD_FN_S16,
+ HIST_FIELD_FN_U16,
+ HIST_FIELD_FN_S8,
+ HIST_FIELD_FN_U8,
+ HIST_FIELD_FN_UMINUS,
+ HIST_FIELD_FN_MINUS,
+ HIST_FIELD_FN_PLUS,
+ HIST_FIELD_FN_DIV,
+ HIST_FIELD_FN_MULT,
+ HIST_FIELD_FN_DIV_POWER2,
+ HIST_FIELD_FN_DIV_NOT_POWER2,
+ HIST_FIELD_FN_DIV_MULT_SHIFT,
+ HIST_FIELD_FN_EXECNAME,
+};
+
/*
* A hist_var (histogram variable) contains variable information for
* hist_fields having the HIST_FIELD_FL_VAR or HIST_FIELD_FL_VAR_REF
@@ -123,15 +155,15 @@ struct hist_var {
struct hist_field {
struct ftrace_event_field *field;
unsigned long flags;
- hist_field_fn_t fn;
- unsigned int ref;
- unsigned int size;
- unsigned int offset;
- unsigned int is_signed;
unsigned long buckets;
const char *type;
struct hist_field *operands[HIST_FIELD_OPERANDS_MAX];
struct hist_trigger_data *hist_data;
+ enum hist_field_fn fn_num;
+ unsigned int ref;
+ unsigned int size;
+ unsigned int offset;
+ unsigned int is_signed;
/*
* Variable fields contain variable-specific info in var.
@@ -166,14 +198,11 @@ struct hist_field {
u64 div_multiplier;
};
-static u64 hist_field_none(struct hist_field *field,
- struct tracing_map_elt *elt,
- struct trace_buffer *buffer,
- struct ring_buffer_event *rbe,
- void *event)
-{
- return 0;
-}
+static u64 hist_fn_call(struct hist_field *hist_field,
+ struct tracing_map_elt *elt,
+ struct trace_buffer *buffer,
+ struct ring_buffer_event *rbe,
+ void *event);
static u64 hist_field_const(struct hist_field *field,
struct tracing_map_elt *elt,
@@ -250,7 +279,7 @@ static u64 hist_field_log2(struct hist_field *hist_field,
{
struct hist_field *operand = hist_field->operands[0];
- u64 val = operand->fn(operand, elt, buffer, rbe, event);
+ u64 val = hist_fn_call(operand, elt, buffer, rbe, event);
return (u64) ilog2(roundup_pow_of_two(val));
}
@@ -264,7 +293,7 @@ static u64 hist_field_bucket(struct hist_field *hist_field,
struct hist_field *operand = hist_field->operands[0];
unsigned long buckets = hist_field->buckets;
- u64 val = operand->fn(operand, elt, buffer, rbe, event);
+ u64 val = hist_fn_call(operand, elt, buffer, rbe, event);
if (WARN_ON_ONCE(!buckets))
return val;
@@ -285,8 +314,8 @@ static u64 hist_field_plus(struct hist_field *hist_field,
struct hist_field *operand1 = hist_field->operands[0];
struct hist_field *operand2 = hist_field->operands[1];
- u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
- u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+ u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
+ u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event);
return val1 + val2;
}
@@ -300,8 +329,8 @@ static u64 hist_field_minus(struct hist_field *hist_field,
struct hist_field *operand1 = hist_field->operands[0];
struct hist_field *operand2 = hist_field->operands[1];
- u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
- u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+ u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
+ u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event);
return val1 - val2;
}
@@ -315,8 +344,8 @@ static u64 hist_field_div(struct hist_field *hist_field,
struct hist_field *operand1 = hist_field->operands[0];
struct hist_field *operand2 = hist_field->operands[1];
- u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
- u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+ u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
+ u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event);
/* Return -1 for the undefined case */
if (!val2)
@@ -338,7 +367,7 @@ static u64 div_by_power_of_two(struct hist_field *hist_field,
struct hist_field *operand1 = hist_field->operands[0];
struct hist_field *operand2 = hist_field->operands[1];
- u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+ u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
return val1 >> __ffs64(operand2->constant);
}
@@ -352,7 +381,7 @@ static u64 div_by_not_power_of_two(struct hist_field *hist_field,
struct hist_field *operand1 = hist_field->operands[0];
struct hist_field *operand2 = hist_field->operands[1];
- u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+ u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
return div64_u64(val1, operand2->constant);
}
@@ -366,7 +395,7 @@ static u64 div_by_mult_and_shift(struct hist_field *hist_field,
struct hist_field *operand1 = hist_field->operands[0];
struct hist_field *operand2 = hist_field->operands[1];
- u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+ u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
/*
* If the divisor is a constant, do a multiplication and shift instead.
@@ -400,8 +429,8 @@ static u64 hist_field_mult(struct hist_field *hist_field,
struct hist_field *operand1 = hist_field->operands[0];
struct hist_field *operand2 = hist_field->operands[1];
- u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
- u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+ u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
+ u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event);
return val1 * val2;
}
@@ -414,7 +443,7 @@ static u64 hist_field_unary_minus(struct hist_field *hist_field,
{
struct hist_field *operand = hist_field->operands[0];
- s64 sval = (s64)operand->fn(operand, elt, buffer, rbe, event);
+ s64 sval = (s64)hist_fn_call(operand, elt, buffer, rbe, event);
u64 val = (u64)-sval;
return val;
@@ -657,19 +686,19 @@ struct snapshot_context {
* Returns the specific division function to use if the divisor
* is constant. This avoids extra branches when the trigger is hit.
*/
-static hist_field_fn_t hist_field_get_div_fn(struct hist_field *divisor)
+static enum hist_field_fn hist_field_get_div_fn(struct hist_field *divisor)
{
u64 div = divisor->constant;
if (!(div & (div - 1)))
- return div_by_power_of_two;
+ return HIST_FIELD_FN_DIV_POWER2;
/* If the divisor is too large, do a regular division */
if (div > (1 << HIST_DIV_SHIFT))
- return div_by_not_power_of_two;
+ return HIST_FIELD_FN_DIV_NOT_POWER2;
divisor->div_multiplier = div64_u64((u64)(1 << HIST_DIV_SHIFT), div);
- return div_by_mult_and_shift;
+ return HIST_FIELD_FN_DIV_MULT_SHIFT;
}
static void track_data_free(struct track_data *track_data)
@@ -1334,38 +1363,32 @@ static const char *hist_field_name(struct hist_field *field,
return field_name;
}
-static hist_field_fn_t select_value_fn(int field_size, int field_is_signed)
+static enum hist_field_fn select_value_fn(int field_size, int field_is_signed)
{
- hist_field_fn_t fn = NULL;
-
switch (field_size) {
case 8:
if (field_is_signed)
- fn = hist_field_s64;
+ return HIST_FIELD_FN_S64;
else
- fn = hist_field_u64;
- break;
+ return HIST_FIELD_FN_U64;
case 4:
if (field_is_signed)
- fn = hist_field_s32;
+ return HIST_FIELD_FN_S32;
else
- fn = hist_field_u32;
- break;
+ return HIST_FIELD_FN_U32;
case 2:
if (field_is_signed)
- fn = hist_field_s16;
+ return HIST_FIELD_FN_S16;
else
- fn = hist_field_u16;
- break;
+ return HIST_FIELD_FN_U16;
case 1:
if (field_is_signed)
- fn = hist_field_s8;
+ return HIST_FIELD_FN_S8;
else
- fn = hist_field_u8;
- break;
+ return HIST_FIELD_FN_U8;
}
- return fn;
+ return HIST_FIELD_FN_NOP;
}
static int parse_map_size(char *str)
@@ -1922,19 +1945,19 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
goto out; /* caller will populate */
if (flags & HIST_FIELD_FL_VAR_REF) {
- hist_field->fn = hist_field_var_ref;
+ hist_field->fn_num = HIST_FIELD_FN_VAR_REF;
goto out;
}
if (flags & HIST_FIELD_FL_HITCOUNT) {
- hist_field->fn = hist_field_counter;
+ hist_field->fn_num = HIST_FIELD_FN_COUNTER;
hist_field->size = sizeof(u64);
hist_field->type = "u64";
goto out;
}
if (flags & HIST_FIELD_FL_CONST) {
- hist_field->fn = hist_field_const;
+ hist_field->fn_num = HIST_FIELD_FN_CONST;
hist_field->size = sizeof(u64);
hist_field->type = kstrdup("u64", GFP_KERNEL);
if (!hist_field->type)
@@ -1943,14 +1966,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
}
if (flags & HIST_FIELD_FL_STACKTRACE) {
- hist_field->fn = hist_field_none;
+ hist_field->fn_num = HIST_FIELD_FN_NOP;
goto out;
}
if (flags & (HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET)) {
unsigned long fl = flags & ~(HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET);
- hist_field->fn = flags & HIST_FIELD_FL_LOG2 ? hist_field_log2 :
- hist_field_bucket;
+ hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 :
+ HIST_FIELD_FN_BUCKET;
hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
hist_field->size = hist_field->operands[0]->size;
hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL);
@@ -1960,14 +1983,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
}
if (flags & HIST_FIELD_FL_TIMESTAMP) {
- hist_field->fn = hist_field_timestamp;
+ hist_field->fn_num = HIST_FIELD_FN_TIMESTAMP;
hist_field->size = sizeof(u64);
hist_field->type = "u64";
goto out;
}
if (flags & HIST_FIELD_FL_CPU) {
- hist_field->fn = hist_field_cpu;
+ hist_field->fn_num = HIST_FIELD_FN_CPU;
hist_field->size = sizeof(int);
hist_field->type = "unsigned int";
goto out;
@@ -1987,14 +2010,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
goto free;
if (field->filter_type == FILTER_STATIC_STRING) {
- hist_field->fn = hist_field_string;
+ hist_field->fn_num = HIST_FIELD_FN_STRING;
hist_field->size = field->size;
} else if (field->filter_type == FILTER_DYN_STRING) {
- hist_field->fn = hist_field_dynstring;
+ hist_field->fn_num = HIST_FIELD_FN_DYNSTRING;
} else if (field->filter_type == FILTER_RDYN_STRING)
- hist_field->fn = hist_field_reldynstring;
+ hist_field->fn_num = HIST_FIELD_FN_RELDYNSTRING;
else
- hist_field->fn = hist_field_pstring;
+ hist_field->fn_num = HIST_FIELD_FN_PSTRING;
} else {
hist_field->size = field->size;
hist_field->is_signed = field->is_signed;
@@ -2002,9 +2025,9 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
if (!hist_field->type)
goto free;
- hist_field->fn = select_value_fn(field->size,
- field->is_signed);
- if (!hist_field->fn) {
+ hist_field->fn_num = select_value_fn(field->size,
+ field->is_signed);
+ if (hist_field->fn_num == HIST_FIELD_FN_NOP) {
destroy_hist_field(hist_field, 0);
return NULL;
}
@@ -2340,7 +2363,7 @@ static struct hist_field *create_alias(struct hist_trigger_data *hist_data,
if (!alias)
return NULL;
- alias->fn = var_ref->fn;
+ alias->fn_num = var_ref->fn_num;
alias->operands[0] = var_ref;
if (init_var_ref(alias, var_ref, var_ref->system, var_ref->event_name)) {
@@ -2523,7 +2546,7 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
expr->flags |= operand1->flags &
(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
- expr->fn = hist_field_unary_minus;
+ expr->fn_num = HIST_FIELD_FN_UMINUS;
expr->operands[0] = operand1;
expr->size = operand1->size;
expr->is_signed = operand1->is_signed;
@@ -2595,7 +2618,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
unsigned long operand_flags, operand2_flags;
int field_op, ret = -EINVAL;
char *sep, *operand1_str;
- hist_field_fn_t op_fn;
+ enum hist_field_fn op_fn;
bool combine_consts;
if (*n_subexprs > 3) {
@@ -2654,16 +2677,16 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
switch (field_op) {
case FIELD_OP_MINUS:
- op_fn = hist_field_minus;
+ op_fn = HIST_FIELD_FN_MINUS;
break;
case FIELD_OP_PLUS:
- op_fn = hist_field_plus;
+ op_fn = HIST_FIELD_FN_PLUS;
break;
case FIELD_OP_DIV:
- op_fn = hist_field_div;
+ op_fn = HIST_FIELD_FN_DIV;
break;
case FIELD_OP_MULT:
- op_fn = hist_field_mult;
+ op_fn = HIST_FIELD_FN_MULT;
break;
default:
ret = -EINVAL;
@@ -2719,13 +2742,16 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
op_fn = hist_field_get_div_fn(operand2);
}
+ expr->fn_num = op_fn;
+
if (combine_consts) {
if (var1)
expr->operands[0] = var1;
if (var2)
expr->operands[1] = var2;
- expr->constant = op_fn(expr, NULL, NULL, NULL, NULL);
+ expr->constant = hist_fn_call(expr, NULL, NULL, NULL, NULL);
+ expr->fn_num = HIST_FIELD_FN_CONST;
expr->operands[0] = NULL;
expr->operands[1] = NULL;
@@ -2739,8 +2765,6 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
expr->name = expr_str(expr, 0);
} else {
- expr->fn = op_fn;
-
/* The operand sizes should be the same, so just pick one */
expr->size = operand1->size;
expr->is_signed = operand1->is_signed;
@@ -3065,7 +3089,7 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,
struct hist_field *var = field_var->var;
struct hist_field *val = field_var->val;
- var_val = val->fn(val, elt, buffer, rbe, rec);
+ var_val = hist_fn_call(val, elt, buffer, rbe, rec);
var_idx = var->var.idx;
if (val->flags & HIST_FIELD_FL_STRING) {
@@ -4186,6 +4210,74 @@ static u64 hist_field_execname(struct hist_field *hist_field,
return (u64)(unsigned long)(elt_data->comm);
}
+static u64 hist_fn_call(struct hist_field *hist_field,
+ struct tracing_map_elt *elt,
+ struct trace_buffer *buffer,
+ struct ring_buffer_event *rbe,
+ void *event)
+{
+ switch (hist_field->fn_num) {
+ case HIST_FIELD_FN_VAR_REF:
+ return hist_field_var_ref(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_COUNTER:
+ return hist_field_counter(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_CONST:
+ return hist_field_const(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_LOG2:
+ return hist_field_log2(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_BUCKET:
+ return hist_field_bucket(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_TIMESTAMP:
+ return hist_field_timestamp(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_CPU:
+ return hist_field_cpu(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_STRING:
+ return hist_field_string(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_DYNSTRING:
+ return hist_field_dynstring(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_RELDYNSTRING:
+ return hist_field_reldynstring(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_PSTRING:
+ return hist_field_pstring(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_S64:
+ return hist_field_s64(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_U64:
+ return hist_field_u64(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_S32:
+ return hist_field_s32(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_U32:
+ return hist_field_u32(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_S16:
+ return hist_field_s16(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_U16:
+ return hist_field_u16(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_S8:
+ return hist_field_s8(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_U8:
+ return hist_field_u8(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_UMINUS:
+ return hist_field_unary_minus(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_MINUS:
+ return hist_field_minus(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_PLUS:
+ return hist_field_plus(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_DIV:
+ return hist_field_div(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_MULT:
+ return hist_field_mult(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_DIV_POWER2:
+ return div_by_power_of_two(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_DIV_NOT_POWER2:
+ return div_by_not_power_of_two(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_DIV_MULT_SHIFT:
+ return div_by_mult_and_shift(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_EXECNAME:
+ return hist_field_execname(hist_field, elt, buffer, rbe, event);
+ default:
+ return 0;
+ }
+}
+
/* Convert a var that points to common_pid.execname to a string */
static void update_var_execname(struct hist_field *hist_field)
{
@@ -4197,7 +4289,7 @@ static void update_var_execname(struct hist_field *hist_field)
kfree_const(hist_field->type);
hist_field->type = "char[]";
- hist_field->fn = hist_field_execname;
+ hist_field->fn_num = HIST_FIELD_FN_EXECNAME;
}
static int create_var_field(struct hist_trigger_data *hist_data,
@@ -4956,7 +5048,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
for_each_hist_val_field(i, hist_data) {
hist_field = hist_data->fields[i];
- hist_val = hist_field->fn(hist_field, elt, buffer, rbe, rec);
+ hist_val = hist_fn_call(hist_field, elt, buffer, rbe, rec);
if (hist_field->flags & HIST_FIELD_FL_VAR) {
var_idx = hist_field->var.idx;
@@ -4987,7 +5079,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
for_each_hist_key_field(i, hist_data) {
hist_field = hist_data->fields[i];
if (hist_field->flags & HIST_FIELD_FL_VAR) {
- hist_val = hist_field->fn(hist_field, elt, buffer, rbe, rec);
+ hist_val = hist_fn_call(hist_field, elt, buffer, rbe, rec);
var_idx = hist_field->var.idx;
tracing_map_set_var(elt, var_idx, hist_val);
}
@@ -5062,7 +5154,7 @@ static void event_hist_trigger(struct event_trigger_data *data,
HIST_STACKTRACE_SKIP);
key = entries;
} else {
- field_contents = key_field->fn(key_field, elt, buffer, rbe, rec);
+ field_contents = hist_fn_call(key_field, elt, buffer, rbe, rec);
if (key_field->flags & HIST_FIELD_FL_STRING) {
key = (void *)(unsigned long)field_contents;
use_compound_key = true;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 5e8c07aef071..e310052dc83c 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -17,6 +17,8 @@
/* for gfp flag names */
#include <linux/trace_events.h>
#include <trace/events/mmflags.h>
+#include "trace_probe.h"
+#include "trace_probe_kernel.h"
#include "trace_synth.h"
@@ -409,6 +411,7 @@ static unsigned int trace_string(struct synth_trace_event *entry,
{
unsigned int len = 0;
char *str_field;
+ int ret;
if (is_dynamic) {
u32 data_offset;
@@ -417,19 +420,27 @@ static unsigned int trace_string(struct synth_trace_event *entry,
data_offset += event->n_u64 * sizeof(u64);
data_offset += data_size;
- str_field = (char *)entry + data_offset;
-
- len = strlen(str_val) + 1;
- strscpy(str_field, str_val, len);
+ len = kern_fetch_store_strlen((unsigned long)str_val);
data_offset |= len << 16;
*(u32 *)&entry->fields[*n_u64] = data_offset;
+ ret = kern_fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
+
(*n_u64)++;
} else {
str_field = (char *)&entry->fields[*n_u64];
- strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ if ((unsigned long)str_val < TASK_SIZE)
+ ret = strncpy_from_user_nofault(str_field, str_val, STR_VAR_LEN_MAX);
+ else
+#endif
+ ret = strncpy_from_kernel_nofault(str_field, str_val, STR_VAR_LEN_MAX);
+
+ if (ret < 0)
+ strcpy(str_field, FAULT_STRING);
+
(*n_u64) += STR_VAR_LEN_MAX / sizeof(u64);
}
@@ -462,7 +473,7 @@ static notrace void trace_event_raw_event_synth(void *__data,
val_idx = var_ref_idx[field_pos];
str_val = (char *)(long)var_ref_vals[val_idx];
- len = strlen(str_val) + 1;
+ len = kern_fetch_store_strlen((unsigned long)str_val);
fields_size += len;
}
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index a6621c52ce45..ae78c2d53c8a 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -14,6 +14,7 @@
#include <linux/uio.h>
#include <linux/ioctl.h>
#include <linux/jhash.h>
+#include <linux/refcount.h>
#include <linux/trace_events.h>
#include <linux/tracefs.h>
#include <linux/types.h>
@@ -39,28 +40,69 @@
*/
#define MAX_PAGE_ORDER 0
#define MAX_PAGES (1 << MAX_PAGE_ORDER)
-#define MAX_EVENTS (MAX_PAGES * PAGE_SIZE)
+#define MAX_BYTES (MAX_PAGES * PAGE_SIZE)
+#define MAX_EVENTS (MAX_BYTES * 8)
/* Limit how long of an event name plus args within the subsystem. */
#define MAX_EVENT_DESC 512
#define EVENT_NAME(user_event) ((user_event)->tracepoint.name)
#define MAX_FIELD_ARRAY_SIZE 1024
-#define MAX_FIELD_ARG_NAME 256
-static char *register_page_data;
+/*
+ * The MAP_STATUS_* macros are used for taking a index and determining the
+ * appropriate byte and the bit in the byte to set/reset for an event.
+ *
+ * The lower 3 bits of the index decide which bit to set.
+ * The remaining upper bits of the index decide which byte to use for the bit.
+ *
+ * This is used when an event has a probe attached/removed to reflect live
+ * status of the event wanting tracing or not to user-programs via shared
+ * memory maps.
+ */
+#define MAP_STATUS_BYTE(index) ((index) >> 3)
+#define MAP_STATUS_MASK(index) BIT((index) & 7)
+
+/*
+ * Internal bits (kernel side only) to keep track of connected probes:
+ * These are used when status is requested in text form about an event. These
+ * bits are compared against an internal byte on the event to determine which
+ * probes to print out to the user.
+ *
+ * These do not reflect the mapped bytes between the user and kernel space.
+ */
+#define EVENT_STATUS_FTRACE BIT(0)
+#define EVENT_STATUS_PERF BIT(1)
+#define EVENT_STATUS_OTHER BIT(7)
+
+/*
+ * Stores the pages, tables, and locks for a group of events.
+ * Each logical grouping of events has its own group, with a
+ * matching page for status checks within user programs. This
+ * allows for isolation of events to user programs by various
+ * means.
+ */
+struct user_event_group {
+ struct page *pages;
+ char *register_page_data;
+ char *system_name;
+ struct hlist_node node;
+ struct mutex reg_mutex;
+ DECLARE_HASHTABLE(register_table, 8);
+ DECLARE_BITMAP(page_bitmap, MAX_EVENTS);
+};
-static DEFINE_MUTEX(reg_mutex);
-static DEFINE_HASHTABLE(register_table, 4);
-static DECLARE_BITMAP(page_bitmap, MAX_EVENTS);
+/* Group for init_user_ns mapping, top-most group */
+static struct user_event_group *init_group;
/*
* Stores per-event properties, as users register events
* within a file a user_event might be created if it does not
* already exist. These are globally used and their lifetime
* is tied to the refcnt member. These cannot go away until the
- * refcnt reaches zero.
+ * refcnt reaches one.
*/
struct user_event {
+ struct user_event_group *group;
struct tracepoint tracepoint;
struct trace_event_call call;
struct trace_event_class class;
@@ -68,10 +110,11 @@ struct user_event {
struct hlist_node node;
struct list_head fields;
struct list_head validators;
- atomic_t refcnt;
+ refcount_t refcnt;
int index;
int flags;
int min_size;
+ char status;
};
/*
@@ -86,6 +129,11 @@ struct user_event_refs {
struct user_event *events[];
};
+struct user_event_file_info {
+ struct user_event_group *group;
+ struct user_event_refs *refs;
+};
+
#define VALIDATOR_ENSURE_NULL (1 << 0)
#define VALIDATOR_REL (1 << 1)
@@ -98,7 +146,8 @@ struct user_event_validator {
typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
void *tpdata, bool *faulted);
-static int user_event_parse(char *name, char *args, char *flags,
+static int user_event_parse(struct user_event_group *group, char *name,
+ char *args, char *flags,
struct user_event **newuser);
static u32 user_event_key(char *name)
@@ -106,6 +155,144 @@ static u32 user_event_key(char *name)
return jhash(name, strlen(name), 0);
}
+static void set_page_reservations(char *pages, bool set)
+{
+ int page;
+
+ for (page = 0; page < MAX_PAGES; ++page) {
+ void *addr = pages + (PAGE_SIZE * page);
+
+ if (set)
+ SetPageReserved(virt_to_page(addr));
+ else
+ ClearPageReserved(virt_to_page(addr));
+ }
+}
+
+static void user_event_group_destroy(struct user_event_group *group)
+{
+ if (group->register_page_data)
+ set_page_reservations(group->register_page_data, false);
+
+ if (group->pages)
+ __free_pages(group->pages, MAX_PAGE_ORDER);
+
+ kfree(group->system_name);
+ kfree(group);
+}
+
+static char *user_event_group_system_name(struct user_namespace *user_ns)
+{
+ char *system_name;
+ int len = sizeof(USER_EVENTS_SYSTEM) + 1;
+
+ if (user_ns != &init_user_ns) {
+ /*
+ * Unexpected at this point:
+ * We only currently support init_user_ns.
+ * When we enable more, this will trigger a failure so log.
+ */
+ pr_warn("user_events: Namespace other than init_user_ns!\n");
+ return NULL;
+ }
+
+ system_name = kmalloc(len, GFP_KERNEL);
+
+ if (!system_name)
+ return NULL;
+
+ snprintf(system_name, len, "%s", USER_EVENTS_SYSTEM);
+
+ return system_name;
+}
+
+static inline struct user_event_group
+*user_event_group_from_user_ns(struct user_namespace *user_ns)
+{
+ if (user_ns == &init_user_ns)
+ return init_group;
+
+ return NULL;
+}
+
+static struct user_event_group *current_user_event_group(void)
+{
+ struct user_namespace *user_ns = current_user_ns();
+ struct user_event_group *group = NULL;
+
+ while (user_ns) {
+ group = user_event_group_from_user_ns(user_ns);
+
+ if (group)
+ break;
+
+ user_ns = user_ns->parent;
+ }
+
+ return group;
+}
+
+static struct user_event_group
+*user_event_group_create(struct user_namespace *user_ns)
+{
+ struct user_event_group *group;
+
+ group = kzalloc(sizeof(*group), GFP_KERNEL);
+
+ if (!group)
+ return NULL;
+
+ group->system_name = user_event_group_system_name(user_ns);
+
+ if (!group->system_name)
+ goto error;
+
+ group->pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER);
+
+ if (!group->pages)
+ goto error;
+
+ group->register_page_data = page_address(group->pages);
+
+ set_page_reservations(group->register_page_data, true);
+
+ /* Zero all bits beside 0 (which is reserved for failures) */
+ bitmap_zero(group->page_bitmap, MAX_EVENTS);
+ set_bit(0, group->page_bitmap);
+
+ mutex_init(&group->reg_mutex);
+ hash_init(group->register_table);
+
+ return group;
+error:
+ if (group)
+ user_event_group_destroy(group);
+
+ return NULL;
+};
+
+static __always_inline
+void user_event_register_set(struct user_event *user)
+{
+ int i = user->index;
+
+ user->group->register_page_data[MAP_STATUS_BYTE(i)] |= MAP_STATUS_MASK(i);
+}
+
+static __always_inline
+void user_event_register_clear(struct user_event *user)
+{
+ int i = user->index;
+
+ user->group->register_page_data[MAP_STATUS_BYTE(i)] &= ~MAP_STATUS_MASK(i);
+}
+
+static __always_inline __must_check
+bool user_event_last_ref(struct user_event *user)
+{
+ return refcount_read(&user->refcnt) == 1;
+}
+
static __always_inline __must_check
size_t copy_nofault(void *addr, size_t bytes, struct iov_iter *i)
{
@@ -141,7 +328,8 @@ static struct list_head *user_event_get_fields(struct trace_event_call *call)
*
* Upon success user_event has its ref count increased by 1.
*/
-static int user_event_parse_cmd(char *raw_command, struct user_event **newuser)
+static int user_event_parse_cmd(struct user_event_group *group,
+ char *raw_command, struct user_event **newuser)
{
char *name = raw_command;
char *args = strpbrk(name, " ");
@@ -155,7 +343,7 @@ static int user_event_parse_cmd(char *raw_command, struct user_event **newuser)
if (flags)
*flags++ = '\0';
- return user_event_parse(name, args, flags, newuser);
+ return user_event_parse(group, name, args, flags, newuser);
}
static int user_field_array_size(const char *type)
@@ -277,7 +465,7 @@ static int user_event_add_field(struct user_event *user, const char *type,
goto add_field;
add_validator:
- if (strstr(type, "char") != 0)
+ if (strstr(type, "char") != NULL)
validator_flags |= VALIDATOR_ENSURE_NULL;
validator = kmalloc(sizeof(*validator), GFP_KERNEL);
@@ -458,7 +646,7 @@ static const char *user_field_format(const char *type)
return "%d";
if (strcmp(type, "unsigned char") == 0)
return "%u";
- if (strstr(type, "char[") != 0)
+ if (strstr(type, "char[") != NULL)
return "%s";
/* Unknown, likely struct, allowed treat as 64-bit */
@@ -479,10 +667,52 @@ static bool user_field_is_dyn_string(const char *type, const char **str_func)
return false;
check:
- return strstr(type, "char") != 0;
+ return strstr(type, "char") != NULL;
}
#define LEN_OR_ZERO (len ? len - pos : 0)
+static int user_dyn_field_set_string(int argc, const char **argv, int *iout,
+ char *buf, int len, bool *colon)
+{
+ int pos = 0, i = *iout;
+
+ *colon = false;
+
+ for (; i < argc; ++i) {
+ if (i != *iout)
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", argv[i]);
+
+ if (strchr(argv[i], ';')) {
+ ++i;
+ *colon = true;
+ break;
+ }
+ }
+
+ /* Actual set, advance i */
+ if (len != 0)
+ *iout = i;
+
+ return pos + 1;
+}
+
+static int user_field_set_string(struct ftrace_event_field *field,
+ char *buf, int len, bool colon)
+{
+ int pos = 0;
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->type);
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->name);
+
+ if (colon)
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ";");
+
+ return pos + 1;
+}
+
static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
{
struct ftrace_event_field *field, *next;
@@ -600,8 +830,8 @@ static int destroy_user_event(struct user_event *user)
dyn_event_remove(&user->devent);
- register_page_data[user->index] = 0;
- clear_bit(user->index, page_bitmap);
+ user_event_register_clear(user);
+ clear_bit(user->index, user->group->page_bitmap);
hash_del(&user->node);
user_event_destroy_validators(user);
@@ -612,16 +842,17 @@ static int destroy_user_event(struct user_event *user)
return ret;
}
-static struct user_event *find_user_event(char *name, u32 *outkey)
+static struct user_event *find_user_event(struct user_event_group *group,
+ char *name, u32 *outkey)
{
struct user_event *user;
u32 key = user_event_key(name);
*outkey = key;
- hash_for_each_possible(register_table, user, node, key)
+ hash_for_each_possible(group->register_table, user, node, key)
if (!strcmp(EVENT_NAME(user), name)) {
- atomic_inc(&user->refcnt);
+ refcount_inc(&user->refcnt);
return user;
}
@@ -779,7 +1010,12 @@ static void update_reg_page_for(struct user_event *user)
rcu_read_unlock_sched();
}
- register_page_data[user->index] = status;
+ if (status)
+ user_event_register_set(user);
+ else
+ user_event_register_clear(user);
+
+ user->status = status;
}
/*
@@ -835,17 +1071,18 @@ static int user_event_reg(struct trace_event_call *call,
return ret;
inc:
- atomic_inc(&user->refcnt);
+ refcount_inc(&user->refcnt);
update_reg_page_for(user);
return 0;
dec:
update_reg_page_for(user);
- atomic_dec(&user->refcnt);
+ refcount_dec(&user->refcnt);
return 0;
}
static int user_event_create(const char *raw_command)
{
+ struct user_event_group *group;
struct user_event *user;
char *name;
int ret;
@@ -861,14 +1098,19 @@ static int user_event_create(const char *raw_command)
if (!name)
return -ENOMEM;
- mutex_lock(&reg_mutex);
+ group = current_user_event_group();
- ret = user_event_parse_cmd(name, &user);
+ if (!group)
+ return -ENOENT;
+
+ mutex_lock(&group->reg_mutex);
+
+ ret = user_event_parse_cmd(group, name, &user);
if (!ret)
- atomic_dec(&user->refcnt);
+ refcount_dec(&user->refcnt);
- mutex_unlock(&reg_mutex);
+ mutex_unlock(&group->reg_mutex);
if (ret)
kfree(name);
@@ -910,14 +1152,14 @@ static bool user_event_is_busy(struct dyn_event *ev)
{
struct user_event *user = container_of(ev, struct user_event, devent);
- return atomic_read(&user->refcnt) != 0;
+ return !user_event_last_ref(user);
}
static int user_event_free(struct dyn_event *ev)
{
struct user_event *user = container_of(ev, struct user_event, devent);
- if (atomic_read(&user->refcnt) != 0)
+ if (!user_event_last_ref(user))
return -EBUSY;
return destroy_user_event(user);
@@ -926,49 +1168,35 @@ static int user_event_free(struct dyn_event *ev)
static bool user_field_match(struct ftrace_event_field *field, int argc,
const char **argv, int *iout)
{
- char *field_name, *arg_name;
- int len, pos, i = *iout;
+ char *field_name = NULL, *dyn_field_name = NULL;
bool colon = false, match = false;
+ int dyn_len, len;
- if (i >= argc)
+ if (*iout >= argc)
return false;
- len = MAX_FIELD_ARG_NAME;
- field_name = kmalloc(len, GFP_KERNEL);
- arg_name = kmalloc(len, GFP_KERNEL);
-
- if (!arg_name || !field_name)
- goto out;
-
- pos = 0;
-
- for (; i < argc; ++i) {
- if (i != *iout)
- pos += snprintf(arg_name + pos, len - pos, " ");
+ dyn_len = user_dyn_field_set_string(argc, argv, iout, dyn_field_name,
+ 0, &colon);
- pos += snprintf(arg_name + pos, len - pos, argv[i]);
+ len = user_field_set_string(field, field_name, 0, colon);
- if (strchr(argv[i], ';')) {
- ++i;
- colon = true;
- break;
- }
- }
+ if (dyn_len != len)
+ return false;
- pos = 0;
+ dyn_field_name = kmalloc(dyn_len, GFP_KERNEL);
+ field_name = kmalloc(len, GFP_KERNEL);
- pos += snprintf(field_name + pos, len - pos, field->type);
- pos += snprintf(field_name + pos, len - pos, " ");
- pos += snprintf(field_name + pos, len - pos, field->name);
+ if (!dyn_field_name || !field_name)
+ goto out;
- if (colon)
- pos += snprintf(field_name + pos, len - pos, ";");
+ user_dyn_field_set_string(argc, argv, iout, dyn_field_name,
+ dyn_len, &colon);
- *iout = i;
+ user_field_set_string(field, field_name, len, colon);
- match = strcmp(arg_name, field_name) == 0;
+ match = strcmp(dyn_field_name, field_name) == 0;
out:
- kfree(arg_name);
+ kfree(dyn_field_name);
kfree(field_name);
return match;
@@ -1036,7 +1264,8 @@ static int user_event_trace_register(struct user_event *user)
* The name buffer lifetime is owned by this method for success cases only.
* Upon success the returned user_event has its ref count increased by 1.
*/
-static int user_event_parse(char *name, char *args, char *flags,
+static int user_event_parse(struct user_event_group *group, char *name,
+ char *args, char *flags,
struct user_event **newuser)
{
int ret;
@@ -1046,7 +1275,7 @@ static int user_event_parse(char *name, char *args, char *flags,
/* Prevent dyn_event from racing */
mutex_lock(&event_mutex);
- user = find_user_event(name, &key);
+ user = find_user_event(group, name, &key);
mutex_unlock(&event_mutex);
if (user) {
@@ -1059,7 +1288,7 @@ static int user_event_parse(char *name, char *args, char *flags,
return 0;
}
- index = find_first_zero_bit(page_bitmap, MAX_EVENTS);
+ index = find_first_zero_bit(group->page_bitmap, MAX_EVENTS);
if (index == MAX_EVENTS)
return -EMFILE;
@@ -1073,6 +1302,7 @@ static int user_event_parse(char *name, char *args, char *flags,
INIT_LIST_HEAD(&user->fields);
INIT_LIST_HEAD(&user->validators);
+ user->group = group;
user->tracepoint.name = name;
ret = user_event_parse_fields(user, args);
@@ -1091,8 +1321,8 @@ static int user_event_parse(char *name, char *args, char *flags,
user->call.flags = TRACE_EVENT_FL_TRACEPOINT;
user->call.tp = &user->tracepoint;
user->call.event.funcs = &user_event_funcs;
+ user->class.system = group->system_name;
- user->class.system = USER_EVENTS_SYSTEM;
user->class.fields_array = user_event_fields_array;
user->class.get_fields = user_event_get_fields;
user->class.reg = user_event_reg;
@@ -1110,13 +1340,13 @@ static int user_event_parse(char *name, char *args, char *flags,
user->index = index;
- /* Ensure we track ref */
- atomic_inc(&user->refcnt);
+ /* Ensure we track self ref and caller ref (2) */
+ refcount_set(&user->refcnt, 2);
dyn_event_init(&user->devent, &user_event_dops);
dyn_event_add(&user->devent, &user->call);
- set_bit(user->index, page_bitmap);
- hash_add(register_table, &user->node, key);
+ set_bit(user->index, group->page_bitmap);
+ hash_add(group->register_table, &user->node, key);
mutex_unlock(&event_mutex);
@@ -1134,32 +1364,20 @@ put_user:
/*
* Deletes a previously created event if it is no longer being used.
*/
-static int delete_user_event(char *name)
+static int delete_user_event(struct user_event_group *group, char *name)
{
u32 key;
- int ret;
- struct user_event *user = find_user_event(name, &key);
+ struct user_event *user = find_user_event(group, name, &key);
if (!user)
return -ENOENT;
- /* Ensure we are the last ref */
- if (atomic_read(&user->refcnt) != 1) {
- ret = -EBUSY;
- goto put_ref;
- }
-
- ret = destroy_user_event(user);
-
- if (ret)
- goto put_ref;
+ refcount_dec(&user->refcnt);
- return ret;
-put_ref:
- /* No longer have this ref */
- atomic_dec(&user->refcnt);
+ if (!user_event_last_ref(user))
+ return -EBUSY;
- return ret;
+ return destroy_user_event(user);
}
/*
@@ -1167,6 +1385,7 @@ put_ref:
*/
static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
{
+ struct user_event_file_info *info = file->private_data;
struct user_event_refs *refs;
struct user_event *user = NULL;
struct tracepoint *tp;
@@ -1178,7 +1397,7 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
rcu_read_lock_sched();
- refs = rcu_dereference_sched(file->private_data);
+ refs = rcu_dereference_sched(info->refs);
/*
* The refs->events array is protected by RCU, and new items may be
@@ -1236,6 +1455,28 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
return ret;
}
+static int user_events_open(struct inode *node, struct file *file)
+{
+ struct user_event_group *group;
+ struct user_event_file_info *info;
+
+ group = current_user_event_group();
+
+ if (!group)
+ return -ENOENT;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+
+ if (!info)
+ return -ENOMEM;
+
+ info->group = group;
+
+ file->private_data = info;
+
+ return 0;
+}
+
static ssize_t user_events_write(struct file *file, const char __user *ubuf,
size_t count, loff_t *ppos)
{
@@ -1245,7 +1486,8 @@ static ssize_t user_events_write(struct file *file, const char __user *ubuf,
if (unlikely(*ppos != 0))
return -EFAULT;
- if (unlikely(import_single_range(READ, (char *)ubuf, count, &iov, &i)))
+ if (unlikely(import_single_range(WRITE, (char __user *)ubuf,
+ count, &iov, &i)))
return -EFAULT;
return user_events_write_core(file, &i);
@@ -1256,13 +1498,15 @@ static ssize_t user_events_write_iter(struct kiocb *kp, struct iov_iter *i)
return user_events_write_core(kp->ki_filp, i);
}
-static int user_events_ref_add(struct file *file, struct user_event *user)
+static int user_events_ref_add(struct user_event_file_info *info,
+ struct user_event *user)
{
+ struct user_event_group *group = info->group;
struct user_event_refs *refs, *new_refs;
int i, size, count = 0;
- refs = rcu_dereference_protected(file->private_data,
- lockdep_is_held(&reg_mutex));
+ refs = rcu_dereference_protected(info->refs,
+ lockdep_is_held(&group->reg_mutex));
if (refs) {
count = refs->count;
@@ -1286,9 +1530,9 @@ static int user_events_ref_add(struct file *file, struct user_event *user)
new_refs->events[i] = user;
- atomic_inc(&user->refcnt);
+ refcount_inc(&user->refcnt);
- rcu_assign_pointer(file->private_data, new_refs);
+ rcu_assign_pointer(info->refs, new_refs);
if (refs)
kfree_rcu(refs, rcu);
@@ -1309,13 +1553,24 @@ static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg)
if (size > PAGE_SIZE)
return -E2BIG;
- return copy_struct_from_user(kreg, sizeof(*kreg), ureg, size);
+ if (size < offsetofend(struct user_reg, write_index))
+ return -EINVAL;
+
+ ret = copy_struct_from_user(kreg, sizeof(*kreg), ureg, size);
+
+ if (ret)
+ return ret;
+
+ kreg->size = size;
+
+ return 0;
}
/*
* Registers a user_event on behalf of a user process.
*/
-static long user_events_ioctl_reg(struct file *file, unsigned long uarg)
+static long user_events_ioctl_reg(struct user_event_file_info *info,
+ unsigned long uarg)
{
struct user_reg __user *ureg = (struct user_reg __user *)uarg;
struct user_reg reg;
@@ -1336,24 +1591,24 @@ static long user_events_ioctl_reg(struct file *file, unsigned long uarg)
return ret;
}
- ret = user_event_parse_cmd(name, &user);
+ ret = user_event_parse_cmd(info->group, name, &user);
if (ret) {
kfree(name);
return ret;
}
- ret = user_events_ref_add(file, user);
+ ret = user_events_ref_add(info, user);
/* No longer need parse ref, ref_add either worked or not */
- atomic_dec(&user->refcnt);
+ refcount_dec(&user->refcnt);
/* Positive number is index and valid */
if (ret < 0)
return ret;
put_user((u32)ret, &ureg->write_index);
- put_user(user->index, &ureg->status_index);
+ put_user(user->index, &ureg->status_bit);
return 0;
}
@@ -1361,7 +1616,8 @@ static long user_events_ioctl_reg(struct file *file, unsigned long uarg)
/*
* Deletes a user_event on behalf of a user process.
*/
-static long user_events_ioctl_del(struct file *file, unsigned long uarg)
+static long user_events_ioctl_del(struct user_event_file_info *info,
+ unsigned long uarg)
{
void __user *ubuf = (void __user *)uarg;
char *name;
@@ -1374,7 +1630,7 @@ static long user_events_ioctl_del(struct file *file, unsigned long uarg)
/* event_mutex prevents dyn_event from racing */
mutex_lock(&event_mutex);
- ret = delete_user_event(name);
+ ret = delete_user_event(info->group, name);
mutex_unlock(&event_mutex);
kfree(name);
@@ -1388,19 +1644,21 @@ static long user_events_ioctl_del(struct file *file, unsigned long uarg)
static long user_events_ioctl(struct file *file, unsigned int cmd,
unsigned long uarg)
{
+ struct user_event_file_info *info = file->private_data;
+ struct user_event_group *group = info->group;
long ret = -ENOTTY;
switch (cmd) {
case DIAG_IOCSREG:
- mutex_lock(&reg_mutex);
- ret = user_events_ioctl_reg(file, uarg);
- mutex_unlock(&reg_mutex);
+ mutex_lock(&group->reg_mutex);
+ ret = user_events_ioctl_reg(info, uarg);
+ mutex_unlock(&group->reg_mutex);
break;
case DIAG_IOCSDEL:
- mutex_lock(&reg_mutex);
- ret = user_events_ioctl_del(file, uarg);
- mutex_unlock(&reg_mutex);
+ mutex_lock(&group->reg_mutex);
+ ret = user_events_ioctl_del(info, uarg);
+ mutex_unlock(&group->reg_mutex);
break;
}
@@ -1412,17 +1670,24 @@ static long user_events_ioctl(struct file *file, unsigned int cmd,
*/
static int user_events_release(struct inode *node, struct file *file)
{
+ struct user_event_file_info *info = file->private_data;
+ struct user_event_group *group;
struct user_event_refs *refs;
struct user_event *user;
int i;
+ if (!info)
+ return -EINVAL;
+
+ group = info->group;
+
/*
* Ensure refs cannot change under any situation by taking the
* register mutex during the final freeing of the references.
*/
- mutex_lock(&reg_mutex);
+ mutex_lock(&group->reg_mutex);
- refs = file->private_data;
+ refs = info->refs;
if (!refs)
goto out;
@@ -1436,37 +1701,56 @@ static int user_events_release(struct inode *node, struct file *file)
user = refs->events[i];
if (user)
- atomic_dec(&user->refcnt);
+ refcount_dec(&user->refcnt);
}
out:
file->private_data = NULL;
- mutex_unlock(&reg_mutex);
+ mutex_unlock(&group->reg_mutex);
kfree(refs);
+ kfree(info);
return 0;
}
static const struct file_operations user_data_fops = {
+ .open = user_events_open,
.write = user_events_write,
.write_iter = user_events_write_iter,
.unlocked_ioctl = user_events_ioctl,
.release = user_events_release,
};
+static struct user_event_group *user_status_group(struct file *file)
+{
+ struct seq_file *m = file->private_data;
+
+ if (!m)
+ return NULL;
+
+ return m->private;
+}
+
/*
* Maps the shared page into the user process for checking if event is enabled.
*/
static int user_status_mmap(struct file *file, struct vm_area_struct *vma)
{
+ char *pages;
+ struct user_event_group *group = user_status_group(file);
unsigned long size = vma->vm_end - vma->vm_start;
- if (size != MAX_EVENTS)
+ if (size != MAX_BYTES)
+ return -EINVAL;
+
+ if (!group)
return -EINVAL;
+ pages = group->register_page_data;
+
return remap_pfn_range(vma, vma->vm_start,
- virt_to_phys(register_page_data) >> PAGE_SHIFT,
+ virt_to_phys(pages) >> PAGE_SHIFT,
size, vm_get_page_prot(VM_READ));
}
@@ -1490,14 +1774,18 @@ static void user_seq_stop(struct seq_file *m, void *p)
static int user_seq_show(struct seq_file *m, void *p)
{
+ struct user_event_group *group = m->private;
struct user_event *user;
char status;
int i, active = 0, busy = 0, flags;
- mutex_lock(&reg_mutex);
+ if (!group)
+ return -EINVAL;
+
+ mutex_lock(&group->reg_mutex);
- hash_for_each(register_table, i, user, node) {
- status = register_page_data[user->index];
+ hash_for_each(group->register_table, i, user, node) {
+ status = user->status;
flags = user->flags;
seq_printf(m, "%d:%s", user->index, EVENT_NAME(user));
@@ -1520,7 +1808,7 @@ static int user_seq_show(struct seq_file *m, void *p)
active++;
}
- mutex_unlock(&reg_mutex);
+ mutex_unlock(&group->reg_mutex);
seq_puts(m, "\n");
seq_printf(m, "Active: %d\n", active);
@@ -1539,7 +1827,24 @@ static const struct seq_operations user_seq_ops = {
static int user_status_open(struct inode *node, struct file *file)
{
- return seq_open(file, &user_seq_ops);
+ struct user_event_group *group;
+ int ret;
+
+ group = current_user_event_group();
+
+ if (!group)
+ return -ENOENT;
+
+ ret = seq_open(file, &user_seq_ops);
+
+ if (!ret) {
+ /* Chain group to seq_file */
+ struct seq_file *m = file->private_data;
+
+ m->private = group;
+ }
+
+ return ret;
}
static const struct file_operations user_status_fops = {
@@ -1580,42 +1885,21 @@ err:
return -ENODEV;
}
-static void set_page_reservations(bool set)
-{
- int page;
-
- for (page = 0; page < MAX_PAGES; ++page) {
- void *addr = register_page_data + (PAGE_SIZE * page);
-
- if (set)
- SetPageReserved(virt_to_page(addr));
- else
- ClearPageReserved(virt_to_page(addr));
- }
-}
-
static int __init trace_events_user_init(void)
{
- struct page *pages;
int ret;
- /* Zero all bits beside 0 (which is reserved for failures) */
- bitmap_zero(page_bitmap, MAX_EVENTS);
- set_bit(0, page_bitmap);
+ init_group = user_event_group_create(&init_user_ns);
- pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER);
- if (!pages)
+ if (!init_group)
return -ENOMEM;
- register_page_data = page_address(pages);
-
- set_page_reservations(true);
ret = create_user_tracefs();
if (ret) {
pr_warn("user_events could not register with tracefs\n");
- set_page_reservations(false);
- __free_pages(pages, MAX_PAGE_ORDER);
+ user_event_group_destroy(init_group);
+ init_group = NULL;
return ret;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 23f7f0ec4f4c..5a75b039e586 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -20,6 +20,7 @@
#include "trace_kprobe_selftest.h"
#include "trace_probe.h"
#include "trace_probe_tmpl.h"
+#include "trace_probe_kernel.h"
#define KPROBE_EVENT_SYSTEM "kprobes"
#define KRETPROBE_MAXACTIVE_MAX 4096
@@ -1223,29 +1224,14 @@ static const struct file_operations kprobe_profile_ops = {
static nokprobe_inline int
fetch_store_strlen_user(unsigned long addr)
{
- const void __user *uaddr = (__force const void __user *)addr;
-
- return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+ return kern_fetch_store_strlen_user(addr);
}
/* Return the length of string -- including null terminal byte */
static nokprobe_inline int
fetch_store_strlen(unsigned long addr)
{
- int ret, len = 0;
- u8 c;
-
-#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
- if (addr < TASK_SIZE)
- return fetch_store_strlen_user(addr);
-#endif
-
- do {
- ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
- len++;
- } while (c && ret == 0 && len < MAX_STRING_SIZE);
-
- return (ret < 0) ? ret : len;
+ return kern_fetch_store_strlen(addr);
}
/*
@@ -1255,21 +1241,7 @@ fetch_store_strlen(unsigned long addr)
static nokprobe_inline int
fetch_store_string_user(unsigned long addr, void *dest, void *base)
{
- const void __user *uaddr = (__force const void __user *)addr;
- int maxlen = get_loc_len(*(u32 *)dest);
- void *__dest;
- long ret;
-
- if (unlikely(!maxlen))
- return -ENOMEM;
-
- __dest = get_loc_data(dest, base);
-
- ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
- if (ret >= 0)
- *(u32 *)dest = make_data_loc(ret, __dest - base);
-
- return ret;
+ return kern_fetch_store_string_user(addr, dest, base);
}
/*
@@ -1279,29 +1251,7 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
static nokprobe_inline int
fetch_store_string(unsigned long addr, void *dest, void *base)
{
- int maxlen = get_loc_len(*(u32 *)dest);
- void *__dest;
- long ret;
-
-#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
- if ((unsigned long)addr < TASK_SIZE)
- return fetch_store_string_user(addr, dest, base);
-#endif
-
- if (unlikely(!maxlen))
- return -ENOMEM;
-
- __dest = get_loc_data(dest, base);
-
- /*
- * Try to get string again, since the string can be changed while
- * probing.
- */
- ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
- if (ret >= 0)
- *(u32 *)dest = make_data_loc(ret, __dest - base);
-
- return ret;
+ return kern_fetch_store_string(addr, dest, base);
}
static nokprobe_inline int
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 313439920a8c..78d536d3ff3d 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1786,8 +1786,9 @@ static int start_per_cpu_kthreads(void)
for_each_cpu(cpu, current_mask) {
retval = start_kthread(cpu);
if (retval) {
+ cpus_read_unlock();
stop_per_cpu_kthreads();
- break;
+ return retval;
}
}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 3b3869ae8cfd..de38f1c03776 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -445,7 +445,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(SAME_PROBE, "There is already the exact same probe event"),\
C(NO_EVENT_INFO, "This requires both group and event name to attach"),\
C(BAD_ATTACH_EVENT, "Attached event does not exist"),\
- C(BAD_ATTACH_ARG, "Attached event does not have this field"),
+ C(BAD_ATTACH_ARG, "Attached event does not have this field"),\
+ C(NO_EP_FILTER, "No filter rule after 'if'"),
#undef C
#define C(a, b) TP_ERR_##a
diff --git a/kernel/trace/trace_probe_kernel.h b/kernel/trace/trace_probe_kernel.h
new file mode 100644
index 000000000000..77dbd9ff9782
--- /dev/null
+++ b/kernel/trace/trace_probe_kernel.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TRACE_PROBE_KERNEL_H_
+#define __TRACE_PROBE_KERNEL_H_
+
+#define FAULT_STRING "(fault)"
+
+/*
+ * This depends on trace_probe.h, but can not include it due to
+ * the way trace_probe_tmpl.h is used by trace_kprobe.c and trace_eprobe.c.
+ * Which means that any other user must include trace_probe.h before including
+ * this file.
+ */
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+kern_fetch_store_strlen_user(unsigned long addr)
+{
+ const void __user *uaddr = (__force const void __user *)addr;
+ int ret;
+
+ ret = strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+ /*
+ * strnlen_user_nofault returns zero on fault, insert the
+ * FAULT_STRING when that occurs.
+ */
+ if (ret <= 0)
+ return strlen(FAULT_STRING) + 1;
+ return ret;
+}
+
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+kern_fetch_store_strlen(unsigned long addr)
+{
+ int ret, len = 0;
+ u8 c;
+
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ if (addr < TASK_SIZE)
+ return kern_fetch_store_strlen_user(addr);
+#endif
+
+ do {
+ ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
+ len++;
+ } while (c && ret == 0 && len < MAX_STRING_SIZE);
+
+ /* For faults, return enough to hold the FAULT_STRING */
+ return (ret < 0) ? strlen(FAULT_STRING) + 1 : len;
+}
+
+static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base, int len)
+{
+ if (ret >= 0) {
+ *(u32 *)dest = make_data_loc(ret, __dest - base);
+ } else {
+ strscpy(__dest, FAULT_STRING, len);
+ ret = strlen(__dest) + 1;
+ }
+}
+
+/*
+ * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
+ * with max length and relative data location.
+ */
+static nokprobe_inline int
+kern_fetch_store_string_user(unsigned long addr, void *dest, void *base)
+{
+ const void __user *uaddr = (__force const void __user *)addr;
+ int maxlen = get_loc_len(*(u32 *)dest);
+ void *__dest;
+ long ret;
+
+ if (unlikely(!maxlen))
+ return -ENOMEM;
+
+ __dest = get_loc_data(dest, base);
+
+ ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
+ set_data_loc(ret, dest, __dest, base, maxlen);
+
+ return ret;
+}
+
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
+ * length and relative data location.
+ */
+static nokprobe_inline int
+kern_fetch_store_string(unsigned long addr, void *dest, void *base)
+{
+ int maxlen = get_loc_len(*(u32 *)dest);
+ void *__dest;
+ long ret;
+
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ if ((unsigned long)addr < TASK_SIZE)
+ return kern_fetch_store_string_user(addr, dest, base);
+#endif
+
+ if (unlikely(!maxlen))
+ return -ENOMEM;
+
+ __dest = get_loc_data(dest, base);
+
+ /*
+ * Try to get string again, since the string can be changed while
+ * probing.
+ */
+ ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
+ set_data_loc(ret, dest, __dest, base, maxlen);
+
+ return ret;
+}
+
+#endif /* __TRACE_PROBE_KERNEL_H_ */
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9901708ce6b8..c774e560f2f9 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -961,7 +961,7 @@ create_sort_entry(void *key, struct tracing_map_elt *elt)
static void detect_dups(struct tracing_map_sort_entry **sort_entries,
int n_entries, unsigned int key_size)
{
- unsigned int dups = 0, total_dups = 0;
+ unsigned int total_dups = 0;
int i;
void *key;
@@ -974,11 +974,10 @@ static void detect_dups(struct tracing_map_sort_entry **sort_entries,
key = sort_entries[0]->key;
for (i = 1; i < n_entries; i++) {
if (!memcmp(sort_entries[i]->key, key, key_size)) {
- dups++; total_dups++;
+ total_dups++;
continue;
}
key = sort_entries[i]->key;
- dups = 0;
}
WARN_ONCE(total_dups > 0,
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index ef42c1a11920..f23144af5743 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -640,7 +640,6 @@ static void tp_module_going_check_quiescent(struct tracepoint *tp, void *priv)
static int tracepoint_module_coming(struct module *mod)
{
struct tp_module *tp_mod;
- int ret = 0;
if (!mod->num_tracepoints)
return 0;
@@ -652,19 +651,18 @@ static int tracepoint_module_coming(struct module *mod)
*/
if (trace_module_has_bad_taint(mod))
return 0;
- mutex_lock(&tracepoint_module_list_mutex);
+
tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
- if (!tp_mod) {
- ret = -ENOMEM;
- goto end;
- }
+ if (!tp_mod)
+ return -ENOMEM;
tp_mod->mod = mod;
+
+ mutex_lock(&tracepoint_module_list_mutex);
list_add_tail(&tp_mod->list, &tracepoint_module_list);
blocking_notifier_call_chain(&tracepoint_notify_list,
MODULE_STATE_COMING, tp_mod);
-end:
mutex_unlock(&tracepoint_module_list_mutex);
- return ret;
+ return 0;
}
static void tracepoint_module_going(struct module *mod)
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 06ea04d44685..ee8e57fd6f90 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -87,10 +87,6 @@ static struct ctl_table user_table[] = {
UCOUNT_ENTRY("max_fanotify_groups"),
UCOUNT_ENTRY("max_fanotify_marks"),
#endif
- { },
- { },
- { },
- { },
{ }
};
#endif /* CONFIG_SYSCTL */
@@ -263,29 +259,29 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
put_ucounts(ucounts);
}
-long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
+long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v)
{
struct ucounts *iter;
long max = LONG_MAX;
long ret = 0;
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
- long new = atomic_long_add_return(v, &iter->ucount[type]);
+ long new = atomic_long_add_return(v, &iter->rlimit[type]);
if (new < 0 || new > max)
ret = LONG_MAX;
else if (iter == ucounts)
ret = new;
- max = READ_ONCE(iter->ns->ucount_max[type]);
+ max = get_userns_rlimit_max(iter->ns, type);
}
return ret;
}
-bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
+bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v)
{
struct ucounts *iter;
long new = -1; /* Silence compiler warning */
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
- long dec = atomic_long_sub_return(v, &iter->ucount[type]);
+ long dec = atomic_long_sub_return(v, &iter->rlimit[type]);
WARN_ON_ONCE(dec < 0);
if (iter == ucounts)
new = dec;
@@ -294,11 +290,11 @@ bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
}
static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
- struct ucounts *last, enum ucount_type type)
+ struct ucounts *last, enum rlimit_type type)
{
struct ucounts *iter, *next;
for (iter = ucounts; iter != last; iter = next) {
- long dec = atomic_long_sub_return(1, &iter->ucount[type]);
+ long dec = atomic_long_sub_return(1, &iter->rlimit[type]);
WARN_ON_ONCE(dec < 0);
next = iter->ns->ucounts;
if (dec == 0)
@@ -306,12 +302,12 @@ static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
}
}
-void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type)
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type)
{
do_dec_rlimit_put_ucounts(ucounts, NULL, type);
}
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
{
/* Caller must hold a reference to ucounts */
struct ucounts *iter;
@@ -319,12 +315,12 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
long dec, ret = 0;
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
- long new = atomic_long_add_return(1, &iter->ucount[type]);
+ long new = atomic_long_add_return(1, &iter->rlimit[type]);
if (new < 0 || new > max)
goto unwind;
if (iter == ucounts)
ret = new;
- max = READ_ONCE(iter->ns->ucount_max[type]);
+ max = get_userns_rlimit_max(iter->ns, type);
/*
* Grab an extra ucount reference for the caller when
* the rlimit count was previously 0.
@@ -336,24 +332,24 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
}
return ret;
dec_unwind:
- dec = atomic_long_sub_return(1, &iter->ucount[type]);
+ dec = atomic_long_sub_return(1, &iter->rlimit[type]);
WARN_ON_ONCE(dec < 0);
unwind:
do_dec_rlimit_put_ucounts(ucounts, iter, type);
return 0;
}
-bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long rlimit)
+bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long rlimit)
{
struct ucounts *iter;
long max = rlimit;
if (rlimit > LONG_MAX)
max = LONG_MAX;
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
- long val = get_ucounts_value(iter, type);
+ long val = get_rlimit_value(iter, type);
if (val < 0 || val > max)
return true;
- max = READ_ONCE(iter->ns->ucount_max[type]);
+ max = get_userns_rlimit_max(iter->ns, type);
}
return false;
}
diff --git a/kernel/umh.c b/kernel/umh.c
index b989736e8707..850631518665 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -28,6 +28,7 @@
#include <linux/async.h>
#include <linux/uaccess.h>
#include <linux/initrd.h>
+#include <linux/freezer.h>
#include <trace/events/module.h>
@@ -403,6 +404,7 @@ EXPORT_SYMBOL(call_usermodehelper_setup);
*/
int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
{
+ unsigned int state = TASK_UNINTERRUPTIBLE;
DECLARE_COMPLETION_ONSTACK(done);
int retval = 0;
@@ -436,18 +438,22 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
if (wait == UMH_NO_WAIT) /* task has freed sub_info */
goto unlock;
- if (wait & UMH_KILLABLE) {
- retval = wait_for_completion_killable(&done);
- if (!retval)
- goto wait_done;
+ if (wait & UMH_KILLABLE)
+ state |= TASK_KILLABLE;
+
+ if (wait & UMH_FREEZABLE)
+ state |= TASK_FREEZABLE;
+ retval = wait_for_completion_state(&done, state);
+ if (!retval)
+ goto wait_done;
+
+ if (wait & UMH_KILLABLE) {
/* umh_complete() will see NULL and free sub_info */
if (xchg(&sub_info->complete, NULL))
goto unlock;
- /* fallthrough, umh_complete() was already called */
}
- wait_for_completion(&done);
wait_done:
retval = sub_info->retval;
out:
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 3f464bbda0e9..54211dbd516c 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -136,13 +136,13 @@ int create_user_ns(struct cred *new)
ns->owner = owner;
ns->group = group;
INIT_WORK(&ns->work, free_user_ns);
- for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) {
+ for (i = 0; i < UCOUNT_COUNTS; i++) {
ns->ucount_max[i] = INT_MAX;
}
- set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit());
- set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE));
- set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING));
- set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK));
+ set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit());
+ set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE));
+ set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING));
+ set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK));
ns->ucounts = ucounts;
/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 4ca61d49885b..064072c16e3d 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -8,6 +8,7 @@
#include <linux/export.h>
#include <linux/uts.h>
#include <linux/utsname.h>
+#include <linux/random.h>
#include <linux/sysctl.h>
#include <linux/wait.h>
#include <linux/rwsem.h>
@@ -57,6 +58,7 @@ static int proc_do_uts_string(struct ctl_table *table, int write,
* theoretically be incorrect if there are two parallel writes
* at non-zero offsets to the same sysctl.
*/
+ add_device_randomness(tmp_data, sizeof(tmp_data));
down_write(&uts_sem);
memcpy(get_uts(table), tmp_data, sizeof(tmp_data));
up_write(&uts_sem);
@@ -74,6 +76,13 @@ static DEFINE_CTL_TABLE_POLL(domainname_poll);
static struct ctl_table uts_kern_table[] = {
{
+ .procname = "arch",
+ .data = init_uts_ns.name.machine,
+ .maxlen = sizeof(init_uts_ns.name.machine),
+ .mode = 0444,
+ .proc_handler = proc_do_uts_string,
+ },
+ {
.procname = "ostype",
.data = init_uts_ns.name.sysname,
.maxlen = sizeof(init_uts_ns.name.sysname),