xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
포크 0
코드 이슈 풀 리퀘스트 Actions Packages Projects 릴리즈 위키 활동

Merge remote-tracking branch into HEAD

소스 검색 
* keystone/mirror-android12-5.10-2022-06: (1166 commits)
  BACKPORT: exfat: improve write performance when dirsync enabled
  FROMGIT: usb: gadget: uvc: calculate the number of request depending on framesize
  ANDROID: GKI: Add tracing_is_on interface into symbol list
  UPSTREAM: usb: gadget: f_mass_storage: Make CD-ROM emulation work with Mac OS-X
  BACKPORT: io_uring: fix race between timeout flush and removal
  BACKPORT: net/sched: cls_u32: fix netns refcount changes in u32_change()
  UPSTREAM: io_uring: always use original task when preparing req identity
  FROMLIST: remoteproc: Fix dma_mem leak after rproc_shutdown
  FROMLIST: dma-mapping: Add dma_release_coherent_memory to DMA API
  ANDROID: Update QCOM symbol list for __reset_control_get
  ANDROID: vendor_hooks: Add hooks for mutex
  BACKPORT: can: ems_usb: ems_usb_start_xmit(): fix double dev_kfree_skb() in error path
  ANDROID: fix up abi issue with struct snd_pcm_runtime, again
  Revert "coredump: Snapshot the vmas in do_coredump"
  Revert "coredump: Remove the WARN_ON in dump_vma_snapshot"
  Revert "coredump: Use the vma snapshot in fill_files_note"
  Revert "pstore: Don't use semaphores in always-atomic-context code"
  Revert "PCI: Reduce warnings on possible RW1C corruption"
  ANDROID: GKI: fix crc issue with commit ce1927b8cf ("block: don't merge across cgroup boundaries if blkcg is enabled")
  ANDROID: remove CONFIG_HW_RANDOM_CAVIUM from arm64 gki_defconfig
  ...

Signed-off-by: deyaoren@google.com <deyaoren@google.com>
Change-Id: I33849fc486eb1f5fe38aa07aa9aa3436b0e0519b
Bug: 236589610
This commit is contained in:
deyaoren@google.com
2022-06-21 21:17:06 +00:00
committed by Deyao Ren
부모 69a36e2dee 4fc5e12e2d
커밋 a71f2e154d
1064개의 변경된 파일과 10465개의 추가작업 그리고 5744개의 파일을 삭제
Download Patch File Download Diff File Expand all files Collapse all files

3
kernel/async.c
파일 보기

@@ -205,9 +205,6 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data,
atomic_inc(&entry_count);
spin_unlock_irqrestore(&async_lock, flags);
/* mark that this task has queued an async job, used by module init */
current->flags |= PF_USED_ASYNC;
/* schedule for execution */
queue_work_node(node, system_unbound_wq, &entry->work);

4
kernel/audit.h
파일 보기

@@ -191,6 +191,10 @@ struct audit_context {
struct {
char *name;
} module;
struct {
struct audit_ntp_data ntp_data;
struct timespec64 tk_injoffset;
} time;
};
int fds[2];
struct audit_proctitle proctitle;

87
kernel/auditsc.c
파일 보기

@@ -1214,6 +1214,53 @@ static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
from_kuid(&init_user_ns, name->fcap.rootid));
}
static void audit_log_time(struct audit_context *context, struct audit_buffer **ab)
{
const struct audit_ntp_data *ntp = &context->time.ntp_data;
const struct timespec64 *tk = &context->time.tk_injoffset;
static const char * const ntp_name[] = {
"offset",
"freq",
"status",
"tai",
"tick",
"adjust",
};
int type;
if (context->type == AUDIT_TIME_ADJNTPVAL) {
for (type = 0; type < AUDIT_NTP_NVALS; type++) {
if (ntp->vals[type].newval != ntp->vals[type].oldval) {
if (!*ab) {
*ab = audit_log_start(context,
GFP_KERNEL,
AUDIT_TIME_ADJNTPVAL);
if (!*ab)
return;
}
audit_log_format(*ab, "op=%s old=%lli new=%lli",
ntp_name[type],
ntp->vals[type].oldval,
ntp->vals[type].newval);
audit_log_end(*ab);
*ab = NULL;
}
}
}
if (tk->tv_sec != 0 || tk->tv_nsec != 0) {
if (!*ab) {
*ab = audit_log_start(context, GFP_KERNEL,
AUDIT_TIME_INJOFFSET);
if (!*ab)
return;
}
audit_log_format(*ab, "sec=%lli nsec=%li",
(long long)tk->tv_sec, tk->tv_nsec);
audit_log_end(*ab);
*ab = NULL;
}
}
static void show_special(struct audit_context *context, int *call_panic)
{
struct audit_buffer *ab;
@@ -1319,6 +1366,11 @@ static void show_special(struct audit_context *context, int *call_panic)
audit_log_format(ab, "(null)");
break;
case AUDIT_TIME_ADJNTPVAL:
case AUDIT_TIME_INJOFFSET:
/* this call deviates from the rest, eating the buffer */
audit_log_time(context, &ab);
break;
}
audit_log_end(ab);
}
@@ -2560,31 +2612,26 @@ void __audit_fanotify(unsigned int response)
void __audit_tk_injoffset(struct timespec64 offset)
{
audit_log(audit_context(), GFP_KERNEL, AUDIT_TIME_INJOFFSET,
"sec=%lli nsec=%li",
(long long)offset.tv_sec, offset.tv_nsec);
}
struct audit_context *context = audit_context();
static void audit_log_ntp_val(const struct audit_ntp_data *ad,
const char *op, enum audit_ntp_type type)
{
const struct audit_ntp_val *val = &ad->vals[type];
if (val->newval == val->oldval)
return;
audit_log(audit_context(), GFP_KERNEL, AUDIT_TIME_ADJNTPVAL,
"op=%s old=%lli new=%lli", op, val->oldval, val->newval);
/* only set type if not already set by NTP */
if (!context->type)
context->type = AUDIT_TIME_INJOFFSET;
memcpy(&context->time.tk_injoffset, &offset, sizeof(offset));
}
void __audit_ntp_log(const struct audit_ntp_data *ad)
{
audit_log_ntp_val(ad, "offset", AUDIT_NTP_OFFSET);
audit_log_ntp_val(ad, "freq", AUDIT_NTP_FREQ);
audit_log_ntp_val(ad, "status", AUDIT_NTP_STATUS);
audit_log_ntp_val(ad, "tai", AUDIT_NTP_TAI);
audit_log_ntp_val(ad, "tick", AUDIT_NTP_TICK);
audit_log_ntp_val(ad, "adjust", AUDIT_NTP_ADJUST);
struct audit_context *context = audit_context();
int type;
for (type = 0; type < AUDIT_NTP_NVALS; type++)
if (ad->vals[type].newval != ad->vals[type].oldval) {
/* unconditionally set type, overwriting TK */
context->type = AUDIT_TIME_ADJNTPVAL;
memcpy(&context->time.ntp_data, ad, sizeof(*ad));
break;
}
}
void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries,

56
kernel/bpf/stackmap.c
파일 보기

@@ -358,7 +358,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
}
static struct perf_callchain_entry *
get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
get_callchain_entry_for_task(struct task_struct *task, u32 max_depth)
{
#ifdef CONFIG_STACKTRACE
struct perf_callchain_entry *entry;
@@ -369,9 +369,8 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
if (!entry)
return NULL;
entry->nr = init_nr +
stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr),
sysctl_perf_event_max_stack - init_nr, 0);
entry->nr = stack_trace_save_tsk(task, (unsigned long *)entry->ip,
max_depth, 0);
/* stack_trace_save_tsk() works on unsigned long array, while
* perf_callchain_entry uses u64 array. For 32-bit systems, it is
@@ -383,7 +382,7 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
int i;
/* copy data from the end to avoid using extra buffer */
for (i = entry->nr - 1; i >= (int)init_nr; i--)
for (i = entry->nr - 1; i >= 0; i--)
to[i] = (u64)(from[i]);
}
@@ -400,27 +399,19 @@ static long __bpf_get_stackid(struct bpf_map *map,
{
struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
u32 max_depth = map->value_size / stack_map_data_size(map);
/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
u32 init_nr = sysctl_perf_event_max_stack - max_depth;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
u32 hash, id, trace_nr, trace_len;
bool user = flags & BPF_F_USER_STACK;
u64 *ips;
bool hash_matches;
/* get_perf_callchain() guarantees that trace->nr >= init_nr
* and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
*/
trace_nr = trace->nr - init_nr;
if (trace_nr <= skip)
if (trace->nr <= skip)
/* skipping more than usable stack trace */
return -EFAULT;
trace_nr -= skip;
trace_nr = trace->nr - skip;
trace_len = trace_nr * sizeof(u64);
ips = trace->ip + skip + init_nr;
ips = trace->ip + skip;
hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
id = hash & (smap->n_buckets - 1);
bucket = READ_ONCE(smap->buckets[id]);
@@ -477,8 +468,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
u64, flags)
{
u32 max_depth = map->value_size / stack_map_data_size(map);
/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
u32 init_nr = sysctl_perf_event_max_stack - max_depth;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
bool user = flags & BPF_F_USER_STACK;
struct perf_callchain_entry *trace;
bool kernel = !user;
@@ -487,8 +477,12 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
return -EINVAL;
trace = get_perf_callchain(regs, init_nr, kernel, user,
sysctl_perf_event_max_stack, false, false);
max_depth += skip;
if (max_depth > sysctl_perf_event_max_stack)
max_depth = sysctl_perf_event_max_stack;
trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
false, false);
if (unlikely(!trace))
/* couldn't fetch the stack trace */
@@ -579,7 +573,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
struct perf_callchain_entry *trace_in,
void *buf, u32 size, u64 flags)
{
u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
u32 trace_nr, copy_len, elem_size, num_elem, max_depth;
bool user_build_id = flags & BPF_F_USER_BUILD_ID;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
bool user = flags & BPF_F_USER_STACK;
@@ -604,30 +598,28 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
goto err_fault;
num_elem = size / elem_size;
if (sysctl_perf_event_max_stack < num_elem)
init_nr = 0;
else
init_nr = sysctl_perf_event_max_stack - num_elem;
max_depth = num_elem + skip;
if (sysctl_perf_event_max_stack < max_depth)
max_depth = sysctl_perf_event_max_stack;
if (trace_in)
trace = trace_in;
else if (kernel && task)
trace = get_callchain_entry_for_task(task, init_nr);
trace = get_callchain_entry_for_task(task, max_depth);
else
trace = get_perf_callchain(regs, init_nr, kernel, user,
sysctl_perf_event_max_stack,
trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
false, false);
if (unlikely(!trace))
goto err_fault;
trace_nr = trace->nr - init_nr;
if (trace_nr < skip)
if (trace->nr < skip)
goto err_fault;
trace_nr -= skip;
trace_nr = trace->nr - skip;
trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
copy_len = trace_nr * elem_size;
ips = trace->ip + skip + init_nr;
ips = trace->ip + skip;
if (user && user_build_id)
stack_map_get_build_id_offset(buf, ips, trace_nr, user);
else

3
kernel/bpf/syscall.c
파일 보기

@@ -1310,6 +1310,7 @@ int generic_map_delete_batch(struct bpf_map *map,
maybe_wait_bpf_programs(map);
if (err)
break;
cond_resched();
}
if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
err = -EFAULT;
@@ -1367,6 +1368,7 @@ int generic_map_update_batch(struct bpf_map *map,
if (err)
break;
cond_resched();
}
if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
@@ -1464,6 +1466,7 @@ int generic_map_lookup_batch(struct bpf_map *map,
swap(prev_key, key);
retry = MAP_LOOKUP_RETRIES;
cp++;
cond_resched();
}
if (err == -EFAULT)

19
kernel/cgroup/cgroup-internal.h
파일 보기

@@ -65,6 +65,25 @@ static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc)
return container_of(kfc, struct cgroup_fs_context, kfc);
}
struct cgroup_pidlist;
struct cgroup_file_ctx {
struct cgroup_namespace *ns;
struct {
void *trigger;
} psi;
struct {
bool started;
struct css_task_iter iter;
} procs;
struct {
struct cgroup_pidlist *pidlist;
} procs1;
};
/*
* A cgroup can be associated with multiple css_sets as different tasks may
* belong to different cgroups on different hierarchies. In the other

32
kernel/cgroup/cgroup-v1.c
파일 보기

@@ -394,6 +394,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
* next pid to display, if any
*/
struct kernfs_open_file *of = s->private;
struct cgroup_file_ctx *ctx = of->priv;
struct cgroup *cgrp = seq_css(s)->cgroup;
struct cgroup_pidlist *l;
enum cgroup_filetype type = seq_cft(s)->private;
@@ -403,25 +404,24 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
mutex_lock(&cgrp->pidlist_mutex);
/*
* !NULL @of->priv indicates that this isn't the first start()
* after open. If the matching pidlist is around, we can use that.
* Look for it. Note that @of->priv can't be used directly. It
* could already have been destroyed.
* !NULL @ctx->procs1.pidlist indicates that this isn't the first
* start() after open. If the matching pidlist is around, we can use
* that. Look for it. Note that @ctx->procs1.pidlist can't be used
* directly. It could already have been destroyed.
*/
if (of->priv)
of->priv = cgroup_pidlist_find(cgrp, type);
if (ctx->procs1.pidlist)
ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type);
/*
* Either this is the first start() after open or the matching
* pidlist has been destroyed inbetween. Create a new one.
*/
if (!of->priv) {
ret = pidlist_array_load(cgrp, type,
(struct cgroup_pidlist **)&of->priv);
if (!ctx->procs1.pidlist) {
ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist);
if (ret)
return ERR_PTR(ret);
}
l = of->priv;
l = ctx->procs1.pidlist;
if (pid) {
int end = l->length;
@@ -449,7 +449,8 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
struct kernfs_open_file *of = s->private;
struct cgroup_pidlist *l = of->priv;
struct cgroup_file_ctx *ctx = of->priv;
struct cgroup_pidlist *l = ctx->procs1.pidlist;
if (l)
mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
@@ -460,7 +461,8 @@ static void cgroup_pidlist_stop(struct seq_file *s, void *v)
static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
struct kernfs_open_file *of = s->private;
struct cgroup_pidlist *l = of->priv;
struct cgroup_file_ctx *ctx = of->priv;
struct cgroup_pidlist *l = ctx->procs1.pidlist;
pid_t *p = v;
pid_t *end = l->list + l->length;
/*
@@ -545,6 +547,7 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct cgroup *cgrp;
struct cgroup_file_ctx *ctx;
BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
@@ -552,8 +555,9 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
* Release agent gets called with all capabilities,
* require capabilities to set release agent.
*/
if ((of->file->f_cred->user_ns != &init_user_ns) ||
!capable(CAP_SYS_ADMIN))
ctx = of->priv;
if ((ctx->ns->user_ns != &init_user_ns) ||
!file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN))
return -EPERM;
cgrp = cgroup_kn_lock_live(of->kn, false);

84
kernel/cgroup/cgroup.c
파일 보기

@@ -3617,6 +3617,7 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
static ssize_t cgroup_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;
struct cgroup *cgrp;
struct psi_group *psi;
@@ -3629,7 +3630,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
cgroup_kn_unlock(of->kn);
/* Allow only one trigger per file descriptor */
if (of->priv) {
if (ctx->psi.trigger) {
cgroup_put(cgrp);
return -EBUSY;
}
@@ -3641,7 +3642,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
return PTR_ERR(new);
}
smp_store_release(&of->priv, new);
smp_store_release(&ctx->psi.trigger, new);
cgroup_put(cgrp);
return nbytes;
@@ -3671,12 +3672,15 @@ static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
poll_table *pt)
{
return psi_trigger_poll(&of->priv, of->file, pt);
struct cgroup_file_ctx *ctx = of->priv;
return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
}
static void cgroup_pressure_release(struct kernfs_open_file *of)
{
psi_trigger_destroy(of->priv);
struct cgroup_file_ctx *ctx = of->priv;
psi_trigger_destroy(ctx->psi.trigger);
}
bool cgroup_psi_enabled(void)
@@ -3729,24 +3733,43 @@ static ssize_t cgroup_freeze_write(struct kernfs_open_file *of,
static int cgroup_file_open(struct kernfs_open_file *of)
{
struct cftype *cft = of->kn->priv;
struct cgroup_file_ctx *ctx;
int ret;
if (cft->open)
return cft->open(of);
return 0;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->ns = current->nsproxy->cgroup_ns;
get_cgroup_ns(ctx->ns);
of->priv = ctx;
if (!cft->open)
return 0;
ret = cft->open(of);
if (ret) {
put_cgroup_ns(ctx->ns);
kfree(ctx);
}
return ret;
}
static void cgroup_file_release(struct kernfs_open_file *of)
{
struct cftype *cft = of->kn->priv;
struct cgroup_file_ctx *ctx = of->priv;
if (cft->release)
cft->release(of);
put_cgroup_ns(ctx->ns);
kfree(ctx);
}
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
struct cgroup_file_ctx *ctx = of->priv;
struct cgroup *cgrp = of->kn->parent->priv;
struct cftype *cft = of->kn->priv;
struct cgroup_subsys_state *css;
@@ -3763,7 +3786,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
*/
if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
!(cft->flags & CFTYPE_NS_DELEGATABLE) &&
ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp)
ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp)
return -EPERM;
if (cft->write)
@@ -4671,21 +4694,21 @@ void css_task_iter_end(struct css_task_iter *it)
static void cgroup_procs_release(struct kernfs_open_file *of)
{
if (of->priv) {
css_task_iter_end(of->priv);
kfree(of->priv);
}
struct cgroup_file_ctx *ctx = of->priv;
if (ctx->procs.started)
css_task_iter_end(&ctx->procs.iter);
}
static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos)
{
struct kernfs_open_file *of = s->private;
struct css_task_iter *it = of->priv;
struct cgroup_file_ctx *ctx = of->priv;
if (pos)
(*pos)++;
return css_task_iter_next(it);
return css_task_iter_next(&ctx->procs.iter);
}
static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
@@ -4693,21 +4716,18 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
{
struct kernfs_open_file *of = s->private;
struct cgroup *cgrp = seq_css(s)->cgroup;
struct css_task_iter *it = of->priv;
struct cgroup_file_ctx *ctx = of->priv;
struct css_task_iter *it = &ctx->procs.iter;
/*
* When a seq_file is seeked, it's always traversed sequentially
* from position 0, so we can simply keep iterating on !0 *pos.
*/
if (!it) {
if (!ctx->procs.started) {
if (WARN_ON_ONCE((*pos)))
return ERR_PTR(-EINVAL);
it = kzalloc(sizeof(*it), GFP_KERNEL);
if (!it)
return ERR_PTR(-ENOMEM);
of->priv = it;
css_task_iter_start(&cgrp->self, iter_flags, it);
ctx->procs.started = true;
} else if (!(*pos)) {
css_task_iter_end(it);
css_task_iter_start(&cgrp->self, iter_flags, it);
@@ -4758,9 +4778,9 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb)
static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
struct cgroup *dst_cgrp,
struct super_block *sb)
struct super_block *sb,
struct cgroup_namespace *ns)
{
struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
struct cgroup *com_cgrp = src_cgrp;
int ret;
@@ -4789,11 +4809,12 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
static int cgroup_attach_permissions(struct cgroup *src_cgrp,
struct cgroup *dst_cgrp,
struct super_block *sb, bool threadgroup)
struct super_block *sb, bool threadgroup,
struct cgroup_namespace *ns)
{
int ret = 0;
ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb);
ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns);
if (ret)
return ret;
@@ -4810,6 +4831,7 @@ static int cgroup_attach_permissions(struct cgroup *src_cgrp,
static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct cgroup_file_ctx *ctx = of->priv;
struct cgroup *src_cgrp, *dst_cgrp;
struct task_struct *task;
ssize_t ret;
@@ -4830,7 +4852,8 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
spin_unlock_irq(&css_set_lock);
ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
of->file->f_path.dentry->d_sb, true);
of->file->f_path.dentry->d_sb, true,
ctx->ns);
if (ret)
goto out_finish;
@@ -4852,6 +4875,7 @@ static void *cgroup_threads_start(struct seq_file *s, loff_t *pos)
static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct cgroup_file_ctx *ctx = of->priv;
struct cgroup *src_cgrp, *dst_cgrp;
struct task_struct *task;
ssize_t ret;
@@ -4875,7 +4899,8 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
/* thread migrations follow the cgroup.procs delegation rule */
ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
of->file->f_path.dentry->d_sb, false);
of->file->f_path.dentry->d_sb, false,
ctx->ns);
if (ret)
goto out_finish;
@@ -6058,7 +6083,8 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
goto err;
ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb,
!(kargs->flags & CLONE_THREAD));
!(kargs->flags & CLONE_THREAD),
current->nsproxy->cgroup_ns);
if (ret)
goto err;

2
kernel/cgroup/cpuset.c
파일 보기

@@ -2238,6 +2238,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
cgroup_taskset_first(tset, &css);
cs = css_cs(css);
cpus_read_lock();
mutex_lock(&cpuset_mutex);
guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@@ -2291,6 +2292,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
wake_up(&cpuset_attach_wq);
mutex_unlock(&cpuset_mutex);
cpus_read_unlock();
}
/* The various types of files and directories in a cpuset file system */

2
kernel/debug/kdb/kdb_support.c
파일 보기

@@ -350,7 +350,7 @@ int kdb_getarea_size(void *res, unsigned long addr, size_t size)
*/
int kdb_putarea_size(unsigned long addr, void *res, size_t size)
{
int ret = copy_from_kernel_nofault((char *)addr, (char *)res, size);
int ret = copy_to_kernel_nofault((char *)addr, (char *)res, size);
if (ret) {
if (!KDB_STATE(SUPPRESS)) {
kdb_printf("kdb_putarea: Bad address 0x%lx\n", addr);

10
kernel/dma/coherent.c
파일 보기

@@ -84,7 +84,7 @@ out:
return ret;
}
static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
static void _dma_release_coherent_memory(struct dma_coherent_mem *mem)
{
if (!mem)
return;
@@ -136,10 +136,16 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
ret = dma_assign_coherent_memory(dev, mem);
if (ret)
dma_release_coherent_memory(mem);
_dma_release_coherent_memory(mem);
return ret;
}
void dma_release_coherent_memory(struct device *dev)
{
if (dev)
_dma_release_coherent_memory(dev->dma_mem);
}
static void *__dma_alloc_from_coherent(struct device *dev,
struct dma_coherent_mem *mem,
ssize_t size, dma_addr_t *dma_handle)

4
kernel/dma/debug.c
파일 보기

@@ -928,7 +928,7 @@ static __init int dma_debug_cmdline(char *str)
global_disable = true;
}
return 0;
return 1;
}
static __init int dma_debug_entries_cmdline(char *str)
@@ -937,7 +937,7 @@ static __init int dma_debug_entries_cmdline(char *str)
return -EINVAL;
if (!get_option(&str, &nr_prealloc_entries))
nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
return 0;
return 1;
}
__setup("dma_debug=", dma_debug_cmdline);

3
kernel/dma/swiotlb.c
파일 보기

@@ -598,7 +598,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
tlb_addr = slot_addr(io_tlb_start, index) + offset;
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
(!(attrs & DMA_ATTR_OVERWRITE) || dir == DMA_TO_DEVICE ||
dir == DMA_BIDIRECTIONAL))
swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
return tlb_addr;
}

3
kernel/events/core.c
파일 보기

@@ -10220,8 +10220,11 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
}
/* ready to consume more filters */
kfree(filename);
filename = NULL;
state = IF_STATE_ACTION;
filter = NULL;
kernel = 0;
}
}

7
kernel/fork.c
파일 보기

@@ -2315,10 +2315,6 @@ static __latent_entropy struct task_struct *copy_process(
goto bad_fork_cancel_cgroup;
}
/* past the last point of failure */
if (pidfile)
fd_install(pidfd, pidfile);
init_task_pid_links(p);
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -2367,6 +2363,9 @@ static __latent_entropy struct task_struct *copy_process(
syscall_tracepoint_update(p);
write_unlock_irq(&tasklist_lock);
if (pidfile)
fd_install(pidfd, pidfile);
proc_fork_connector(p);
sched_post_fork(p);
cgroup_post_fork(p, args);

4
kernel/livepatch/core.c
파일 보기

@@ -191,7 +191,7 @@ static int klp_find_object_symbol(const char *objname, const char *name,
return -EINVAL;
}
static int klp_resolve_symbols(Elf64_Shdr *sechdrs, const char *strtab,
static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab,
unsigned int symndx, Elf_Shdr *relasec,
const char *sec_objname)
{
@@ -219,7 +219,7 @@ static int klp_resolve_symbols(Elf64_Shdr *sechdrs, const char *strtab,
relas = (Elf_Rela *) relasec->sh_addr;
/* For each rela in this klp relocation section */
for (i = 0; i < relasec->sh_size / sizeof(Elf_Rela); i++) {
sym = (Elf64_Sym *)sechdrs[symndx].sh_addr + ELF_R_SYM(relas[i].r_info);
sym = (Elf_Sym *)sechdrs[symndx].sh_addr + ELF_R_SYM(relas[i].r_info);
if (sym->st_shndx != SHN_LIVEPATCH) {
pr_err("symbol %s is not marked as a livepatch symbol\n",
strtab + sym->st_name);

18
kernel/locking/lockdep.c
파일 보기

@@ -182,11 +182,9 @@ static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES);
static struct hlist_head lock_keys_hash[KEYHASH_SIZE];
unsigned long nr_lock_classes;
unsigned long nr_zapped_classes;
#ifndef CONFIG_DEBUG_LOCKDEP
static
#endif
unsigned long max_lock_class_idx;
struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
static DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
static inline struct lock_class *hlock_class(struct held_lock *hlock)
{
@@ -337,7 +335,7 @@ static inline void lock_release_holdtime(struct held_lock *hlock)
* elements. These elements are linked together by the lock_entry member in
* struct lock_class.
*/
LIST_HEAD(all_lock_classes);
static LIST_HEAD(all_lock_classes);
static LIST_HEAD(free_lock_classes);
/**
@@ -1239,6 +1237,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
struct lockdep_subclass_key *key;
struct hlist_head *hash_head;
struct lock_class *class;
int idx;
DEBUG_LOCKS_WARN_ON(!irqs_disabled());
@@ -1304,6 +1303,9 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
* of classes.
*/
list_move_tail(&class->lock_entry, &all_lock_classes);
idx = class - lock_classes;
if (idx > max_lock_class_idx)
max_lock_class_idx = idx;
if (verbose(class)) {
graph_unlock();
@@ -3387,7 +3389,7 @@ struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i)
u16 chain_hlock = chain_hlocks[chain->base + i];
unsigned int class_idx = chain_hlock_class_idx(chain_hlock);
return lock_classes + class_idx - 1;
return lock_classes + class_idx;
}
/*
@@ -3455,7 +3457,7 @@ static void print_chain_keys_chain(struct lock_chain *chain)
hlock_id = chain_hlocks[chain->base + i];
chain_key = print_chain_key_iteration(hlock_id, chain_key);
print_lock_name(lock_classes + chain_hlock_class_idx(hlock_id) - 1);
print_lock_name(lock_classes + chain_hlock_class_idx(hlock_id));
printk("\n");
}
}
@@ -5919,6 +5921,8 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
WRITE_ONCE(class->name, NULL);
nr_lock_classes--;
__clear_bit(class - lock_classes, lock_classes_in_use);
if (class - lock_classes == max_lock_class_idx)
max_lock_class_idx--;
} else {
WARN_ONCE(true, "%s() failed for class %s\n", __func__,
class->name);

6
kernel/locking/lockdep_internals.h
파일 보기

@@ -121,7 +121,6 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
extern struct list_head all_lock_classes;
extern struct lock_chain lock_chains[];
#define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1)
@@ -151,6 +150,10 @@ extern unsigned int nr_large_chain_blocks;
extern unsigned int max_lockdep_depth;
extern unsigned int max_bfs_queue_depth;
extern unsigned long max_lock_class_idx;
extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
extern unsigned long lock_classes_in_use[];
#ifdef CONFIG_PROVE_LOCKING
extern unsigned long lockdep_count_forward_deps(struct lock_class *);
@@ -205,7 +208,6 @@ struct lockdep_stats {
};
DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
#define __debug_atomic_inc(ptr) \
this_cpu_inc(lockdep_stats.ptr);

51
kernel/locking/lockdep_proc.c
파일 보기

@@ -24,14 +24,33 @@
#include "lockdep_internals.h"
/*
* Since iteration of lock_classes is done without holding the lockdep lock,
* it is not safe to iterate all_lock_classes list directly as the iteration
* may branch off to free_lock_classes or the zapped list. Iteration is done
* directly on the lock_classes array by checking the lock_classes_in_use
* bitmap and max_lock_class_idx.
*/
#define iterate_lock_classes(idx, class) \
for (idx = 0, class = lock_classes; idx <= max_lock_class_idx; \
idx++, class++)
static void *l_next(struct seq_file *m, void *v, loff_t *pos)
{
return seq_list_next(v, &all_lock_classes, pos);
struct lock_class *class = v;
++class;
*pos = class - lock_classes;
return (*pos > max_lock_class_idx) ? NULL : class;
}
static void *l_start(struct seq_file *m, loff_t *pos)
{
return seq_list_start_head(&all_lock_classes, *pos);
unsigned long idx = *pos;
if (idx > max_lock_class_idx)
return NULL;
return lock_classes + idx;
}
static void l_stop(struct seq_file *m, void *v)
@@ -57,14 +76,16 @@ static void print_name(struct seq_file *m, struct lock_class *class)
static int l_show(struct seq_file *m, void *v)
{
struct lock_class *class = list_entry(v, struct lock_class, lock_entry);
struct lock_class *class = v;
struct lock_list *entry;
char usage[LOCK_USAGE_CHARS];
int idx = class - lock_classes;
if (v == &all_lock_classes) {
if (v == lock_classes)
seq_printf(m, "all lock classes:\n");
if (!test_bit(idx, lock_classes_in_use))
return 0;
}
seq_printf(m, "%p", class->key);
#ifdef CONFIG_DEBUG_LOCKDEP
@@ -218,8 +239,11 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
#ifdef CONFIG_PROVE_LOCKING
struct lock_class *class;
unsigned long idx;
list_for_each_entry(class, &all_lock_classes, lock_entry) {
iterate_lock_classes(idx, class) {
if (!test_bit(idx, lock_classes_in_use))
continue;
if (class->usage_mask == 0)
nr_unused++;
@@ -252,6 +276,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
sum_forward_deps += lockdep_count_forward_deps(class);
}
#ifdef CONFIG_DEBUG_LOCKDEP
DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused);
#endif
@@ -343,6 +368,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
seq_printf(m, " max bfs queue depth: %11u\n",
max_bfs_queue_depth);
#endif
seq_printf(m, " max lock class index: %11lu\n",
max_lock_class_idx);
lockdep_stats_debug_show(m);
seq_printf(m, " debug_locks: %11u\n",
debug_locks);
@@ -620,12 +647,16 @@ static int lock_stat_open(struct inode *inode, struct file *file)
if (!res) {
struct lock_stat_data *iter = data->stats;
struct seq_file *m = file->private_data;
unsigned long idx;
list_for_each_entry(class, &all_lock_classes, lock_entry) {
iterate_lock_classes(idx, class) {
if (!test_bit(idx, lock_classes_in_use))
continue;
iter->class = class;
iter->stats = lock_stats(class);
iter++;
}
data->iter_end = iter;
sort(data->stats, data->iter_end - data->stats,
@@ -643,6 +674,7 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
struct lock_class *class;
unsigned long idx;
char c;
if (count) {
@@ -652,8 +684,11 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf,
if (c != '0')
return count;
list_for_each_entry(class, &all_lock_classes, lock_entry)
iterate_lock_classes(idx, class) {
if (!test_bit(idx, lock_classes_in_use))
continue;
clear_lock_stats(class);
}
}
return count;
}

1
kernel/locking/mutex.c
파일 보기

@@ -1049,6 +1049,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
goto err;
}
trace_android_vh_mutex_start_check_new_owner(lock);
spin_unlock(&lock->wait_lock);
schedule_preempt_disabled();

25
kernel/module.c
파일 보기

@@ -3739,12 +3739,6 @@ static noinline int do_init_module(struct module *mod)
}
freeinit->module_init = mod->init_layout.base;
/*
* We want to find out whether @mod uses async during init. Clear
* PF_USED_ASYNC. async_schedule*() will set it.
*/
current->flags &= ~PF_USED_ASYNC;
do_mod_ctors(mod);
/* Start the module */
if (mod->init != NULL)
@@ -3770,22 +3764,13 @@ static noinline int do_init_module(struct module *mod)
/*
* We need to finish all async code before the module init sequence
* is done. This has potential to deadlock. For example, a newly
* detected block device can trigger request_module() of the
* default iosched from async probing task. Once userland helper
* reaches here, async_synchronize_full() will wait on the async
* task waiting on request_module() and deadlock.
* is done. This has potential to deadlock if synchronous module
* loading is requested from async (which is not allowed!).
*
* This deadlock is avoided by perfomring async_synchronize_full()
* iff module init queued any async jobs. This isn't a full
* solution as it will deadlock the same if module loading from
* async jobs nests more than once; however, due to the various
* constraints, this hack seems to be the best option for now.
* Please refer to the following thread for details.
*
* http://thread.gmane.org/gmane.linux.kernel/1420814
* See commit 0fdff3ec6d87 ("async, kmod: warn on synchronous
* request_module() from async workers") for more details.
*/
if (!mod->async_probe_requested && (current->flags & PF_USED_ASYNC))
if (!mod->async_probe_requested)
async_synchronize_full();
ftrace_free_mem(mod, mod->init_layout.base, mod->init_layout.base +

2
kernel/power/hibernate.c
파일 보기

@@ -1323,7 +1323,7 @@ static int __init resumedelay_setup(char *str)
int rc = kstrtouint(str, 0, &resume_delay);
if (rc)
return rc;
pr_warn("resumedelay: bad option string '%s'\n", str);
return 1;
}

8
kernel/power/suspend_test.c
파일 보기

@@ -157,22 +157,22 @@ static int __init setup_test_suspend(char *value)
value++;
suspend_type = strsep(&value, ",");
if (!suspend_type)
return 0;
return 1;
repeat = strsep(&value, ",");
if (repeat) {
if (kstrtou32(repeat, 0, &test_repeat_count_max))
return 0;
return 1;
}
for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
if (!strcmp(pm_labels[i], suspend_type)) {
test_state_label = pm_labels[i];
return 0;
return 1;
}
printk(warn_bad_state, suspend_type);
return 0;
return 1;
}
__setup("test_suspend", setup_test_suspend);

6
kernel/printk/printk.c
파일 보기

@@ -149,8 +149,10 @@ static int __control_devkmsg(char *str)
static int __init control_devkmsg(char *str)
{
if (__control_devkmsg(str) < 0)
if (__control_devkmsg(str) < 0) {
pr_warn("printk.devkmsg: bad option string '%s'\n", str);
return 1;
}
/*
* Set sysctl string accordingly:
@@ -169,7 +171,7 @@ static int __init control_devkmsg(char *str)
*/
devkmsg_log |= DEVKMSG_LOG_MASK_LOCK;
return 0;
return 1;
}
__setup("printk.devkmsg=", control_devkmsg);

47
kernel/ptrace.c
파일 보기

@@ -370,6 +370,26 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
return !err;
}
static int check_ptrace_options(unsigned long data)
{
if (data & ~(unsigned long)PTRACE_O_MASK)
return -EINVAL;
if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
!IS_ENABLED(CONFIG_SECCOMP))
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (seccomp_mode(&current->seccomp) != SECCOMP_MODE_DISABLED ||
current->ptrace & PT_SUSPEND_SECCOMP)
return -EPERM;
}
return 0;
}
static int ptrace_attach(struct task_struct *task, long request,
unsigned long addr,
unsigned long flags)
@@ -381,8 +401,16 @@ static int ptrace_attach(struct task_struct *task, long request,
if (seize) {
if (addr != 0)
goto out;
/*
* This duplicates the check in check_ptrace_options() because
* ptrace_attach() and ptrace_setoptions() have historically
* used different error codes for unknown ptrace options.
*/
if (flags & ~(unsigned long)PTRACE_O_MASK)
goto out;
retval = check_ptrace_options(flags);
if (retval)
return retval;
flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT);
} else {
flags = PT_PTRACED;
@@ -655,22 +683,11 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
static int ptrace_setoptions(struct task_struct *child, unsigned long data)
{
unsigned flags;
int ret;
if (data & ~(unsigned long)PTRACE_O_MASK)
return -EINVAL;
if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
!IS_ENABLED(CONFIG_SECCOMP))
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (seccomp_mode(&current->seccomp) != SECCOMP_MODE_DISABLED ||
current->ptrace & PT_SUSPEND_SECCOMP)
return -EPERM;
}
ret = check_ptrace_options(data);
if (ret)
return ret;
/* Avoid intermediate state when all opts are cleared */
flags = child->ptrace;

10
kernel/rcu/tree_plugin.h
파일 보기

@@ -541,6 +541,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
/* Unboost if we were boosted. */
if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
rt_mutex_futex_unlock(&rnp->boost_mtx);
} else {
local_irq_restore(flags);
}
@@ -628,7 +629,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
set_tsk_need_resched(current);
set_preempt_need_resched();
if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
!rdp->defer_qs_iw_pending && exp) {
!rdp->defer_qs_iw_pending && exp && cpu_online(rdp->cpu)) {
// Get scheduler to re-evaluate and call hooks.
// If !IRQ_WORK, FQS scan will eventually IPI.
init_irq_work(&rdp->defer_qs_iw,
@@ -1646,7 +1647,11 @@ static void wake_nocb_gp(struct rcu_data *rdp, bool force,
rcu_nocb_unlock_irqrestore(rdp, flags);
return;
}
del_timer(&rdp->nocb_timer);
if (READ_ONCE(rdp->nocb_defer_wakeup) > RCU_NOCB_WAKE_NOT) {
WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
del_timer(&rdp->nocb_timer);
}
rcu_nocb_unlock_irqrestore(rdp, flags);
raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
if (force || READ_ONCE(rdp_gp->nocb_gp_sleep)) {
@@ -2164,7 +2169,6 @@ static void do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
return;
}
ndw = READ_ONCE(rdp->nocb_defer_wakeup);
WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake"));
}

13
kernel/rseq.c
파일 보기

@@ -120,8 +120,13 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
u32 sig;
int ret;
if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
#ifdef CONFIG_64BIT
if (get_user(ptr, &t->rseq->rseq_cs))
return -EFAULT;
#else
if (copy_from_user(&ptr, &t->rseq->rseq_cs, sizeof(ptr)))
return -EFAULT;
#endif
if (!ptr) {
memset(rseq_cs, 0, sizeof(*rseq_cs));
return 0;
@@ -204,9 +209,13 @@ static int clear_rseq_cs(struct task_struct *t)
*
* Set rseq_cs to NULL.
*/
if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
#ifdef CONFIG_64BIT
return put_user(0UL, &t->rseq->rseq_cs);
#else
if (clear_user(&t->rseq->rseq_cs, sizeof(t->rseq->rseq_cs)))
return -EFAULT;
return 0;
#endif
}
/*

1
kernel/sched/core.c
파일 보기

@@ -39,6 +39,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);

10
kernel/sched/debug.c
파일 보기

@@ -910,25 +910,15 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
static void sched_show_numa(struct task_struct *p, struct seq_file *m)
{
#ifdef CONFIG_NUMA_BALANCING
struct mempolicy *pol;
if (p->mm)
P(mm->numa_scan_seq);
task_lock(p);
pol = p->mempolicy;
if (pol && !(pol->flags & MPOL_F_MORON))
pol = NULL;
mpol_get(pol);
task_unlock(p);
P(numa_pages_migrated);
P(numa_preferred_nid);
P(total_numa_faults);
SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
task_node(p), task_numa_group_id(p));
show_numa_stats(p, m);
mpol_put(pol);
#endif
}

101
kernel/sched/topology.c
파일 보기

@@ -1542,66 +1542,58 @@ static void init_numa_topology_type(void)
}
}
#define NR_DISTANCE_VALUES (1 << DISTANCE_BITS)
void sched_init_numa(void)
{
int next_distance, curr_distance = node_distance(0, 0);
struct sched_domain_topology_level *tl;
int level = 0;
int i, j, k;
sched_domains_numa_distance = kzalloc(sizeof(int) * (nr_node_ids + 1), GFP_KERNEL);
if (!sched_domains_numa_distance)
return;
/* Includes NUMA identity node at level 0. */
sched_domains_numa_distance[level++] = curr_distance;
sched_domains_numa_levels = level;
unsigned long *distance_map;
int nr_levels = 0;
int i, j;
/*
* O(nr_nodes^2) deduplicating selection sort -- in order to find the
* unique distances in the node_distance() table.
*
* Assumes node_distance(0,j) includes all distances in
* node_distance(i,j) in order to avoid cubic time.
*/
next_distance = curr_distance;
distance_map = bitmap_alloc(NR_DISTANCE_VALUES, GFP_KERNEL);
if (!distance_map)
return;
bitmap_zero(distance_map, NR_DISTANCE_VALUES);
for (i = 0; i < nr_node_ids; i++) {
for (j = 0; j < nr_node_ids; j++) {
for (k = 0; k < nr_node_ids; k++) {
int distance = node_distance(i, k);
int distance = node_distance(i, j);
if (distance > curr_distance &&
(distance < next_distance ||
next_distance == curr_distance))
next_distance = distance;
/*
* While not a strong assumption it would be nice to know
* about cases where if node A is connected to B, B is not
* equally connected to A.
*/
if (sched_debug() && node_distance(k, i) != distance)
sched_numa_warn("Node-distance not symmetric");
if (sched_debug() && i && !find_numa_distance(distance))
sched_numa_warn("Node-0 not representative");
if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) {
sched_numa_warn("Invalid distance value range");
return;
}
if (next_distance != curr_distance) {
sched_domains_numa_distance[level++] = next_distance;
sched_domains_numa_levels = level;
curr_distance = next_distance;
} else break;
}
/*
* In case of sched_debug() we verify the above assumption.
*/
if (!sched_debug())
break;
bitmap_set(distance_map, distance, 1);
}
}
/*
* We can now figure out how many unique distance values there are and
* allocate memory accordingly.
*/
nr_levels = bitmap_weight(distance_map, NR_DISTANCE_VALUES);
sched_domains_numa_distance = kcalloc(nr_levels, sizeof(int), GFP_KERNEL);
if (!sched_domains_numa_distance) {
bitmap_free(distance_map);
return;
}
for (i = 0, j = 0; i < nr_levels; i++, j++) {
j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j);
sched_domains_numa_distance[i] = j;
}
bitmap_free(distance_map);
/*
* 'level' contains the number of unique distances
* 'nr_levels' contains the number of unique distances
*
* The sched_domains_numa_distance[] array includes the actual distance
* numbers.
@@ -1610,15 +1602,15 @@ void sched_init_numa(void)
/*
* Here, we should temporarily reset sched_domains_numa_levels to 0.
* If it fails to allocate memory for array sched_domains_numa_masks[][],
* the array will contain less then 'level' members. This could be
* the array will contain less then 'nr_levels' members. This could be
* dangerous when we use it to iterate array sched_domains_numa_masks[][]
* in other functions.
*
* We reset it to 'level' at the end of this function.
* We reset it to 'nr_levels' at the end of this function.
*/
sched_domains_numa_levels = 0;
sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
sched_domains_numa_masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL);
if (!sched_domains_numa_masks)
return;
@@ -1626,7 +1618,7 @@ void sched_init_numa(void)
* Now for each level, construct a mask per node which contains all
* CPUs of nodes that are that many hops away from us.
*/
for (i = 0; i < level; i++) {
for (i = 0; i < nr_levels; i++) {
sched_domains_numa_masks[i] =
kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
if (!sched_domains_numa_masks[i])
@@ -1634,12 +1626,17 @@ void sched_init_numa(void)
for (j = 0; j < nr_node_ids; j++) {
struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
int k;
if (!mask)
return;
sched_domains_numa_masks[i][j] = mask;
for_each_node(k) {
if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
sched_numa_warn("Node-distance not symmetric");
if (node_distance(j, k) > sched_domains_numa_distance[i])
continue;
@@ -1651,7 +1648,7 @@ void sched_init_numa(void)
/* Compute default topology size */
for (i = 0; sched_domain_topology[i].mask; i++);
tl = kzalloc((i + level + 1) *
tl = kzalloc((i + nr_levels + 1) *
sizeof(struct sched_domain_topology_level), GFP_KERNEL);
if (!tl)
return;
@@ -1674,7 +1671,7 @@ void sched_init_numa(void)
/*
* .. and append 'j' levels of NUMA goodness.
*/
for (j = 1; j < level; i++, j++) {
for (j = 1; j < nr_levels; i++, j++) {
tl[i] = (struct sched_domain_topology_level){
.mask = sd_numa_mask,
.sd_flags = cpu_numa_flags,
@@ -1686,8 +1683,8 @@ void sched_init_numa(void)
sched_domain_topology = tl;
sched_domains_numa_levels = level;
sched_max_numa_distance = sched_domains_numa_distance[level - 1];
sched_domains_numa_levels = nr_levels;
sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1];
init_numa_topology_type();
}

5
kernel/stackleak.c
파일 보기

@@ -48,7 +48,7 @@ int stack_erasing_sysctl(struct ctl_table *table, int write,
#define skip_erasing() false
#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */
asmlinkage void notrace stackleak_erase(void)
asmlinkage void noinstr stackleak_erase(void)
{
/* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */
unsigned long kstack_ptr = current->lowest_stack;
@@ -102,9 +102,8 @@ asmlinkage void notrace stackleak_erase(void)
/* Reset the 'lowest_stack' value for the next syscall */
current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64;
}
NOKPROBE_SYMBOL(stackleak_erase);
void __used __no_caller_saved_registers notrace stackleak_track_stack(void)
void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
{
unsigned long sp = current_stack_pointer;

18
kernel/trace/trace.c
파일 보기

@@ -234,7 +234,7 @@ static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
static int __init set_trace_boot_options(char *str)
{
strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
return 0;
return 1;
}
__setup("trace_options=", set_trace_boot_options);
@@ -245,12 +245,16 @@ static int __init set_trace_boot_clock(char *str)
{
strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
trace_boot_clock = trace_boot_clock_buf;
return 0;
return 1;
}
__setup("trace_clock=", set_trace_boot_clock);
static int __init set_tracepoint_printk(char *str)
{
/* Ignore the "tp_printk_stop_on_boot" param */
if (*str == '_')
return 0;
if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0))
tracepoint_printk = 1;
return 1;
@@ -1487,10 +1491,12 @@ static int __init set_buf_size(char *str)
if (!str)
return 0;
buf_size = memparse(str, &str);
/* nr_entries can not be zero */
if (buf_size == 0)
return 0;
trace_buf_size = buf_size;
/*
* nr_entries can not be zero and the startup
* tests require some buffer space. Therefore
* ensure we have at least 4096 bytes of buffer.
*/
trace_buf_size = max(4096UL, buf_size);
return 1;
}
__setup("trace_buf_size=", set_buf_size);

107
kernel/trace/trace_events_filter.c
파일 보기

@@ -5,6 +5,7 @@
* Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
*/
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/mutex.h>
@@ -654,6 +655,52 @@ DEFINE_EQUALITY_PRED(32);
DEFINE_EQUALITY_PRED(16);
DEFINE_EQUALITY_PRED(8);
/* user space strings temp buffer */
#define USTRING_BUF_SIZE 1024
struct ustring_buffer {
char buffer[USTRING_BUF_SIZE];
};
static __percpu struct ustring_buffer *ustring_per_cpu;
static __always_inline char *test_string(char *str)
{
struct ustring_buffer *ubuf;
char *kstr;
if (!ustring_per_cpu)
return NULL;
ubuf = this_cpu_ptr(ustring_per_cpu);
kstr = ubuf->buffer;
/* For safety, do not trust the string pointer */
if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE))
return NULL;
return kstr;
}
static __always_inline char *test_ustring(char *str)
{
struct ustring_buffer *ubuf;
char __user *ustr;
char *kstr;
if (!ustring_per_cpu)
return NULL;
ubuf = this_cpu_ptr(ustring_per_cpu);
kstr = ubuf->buffer;
/* user space address? */
ustr = (char __user *)str;
if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE))
return NULL;
return kstr;
}
/* Filter predicate for fixed sized arrays of characters */
static int filter_pred_string(struct filter_pred *pred, void *event)
{
@@ -667,19 +714,43 @@ static int filter_pred_string(struct filter_pred *pred, void *event)
return match;
}
/* Filter predicate for char * pointers */
static int filter_pred_pchar(struct filter_pred *pred, void *event)
static __always_inline int filter_pchar(struct filter_pred *pred, char *str)
{
char **addr = (char **)(event + pred->offset);
int cmp, match;
int len = strlen(*addr) + 1; /* including tailing '\0' */
int len;
cmp = pred->regex.match(*addr, &pred->regex, len);
len = strlen(str) + 1; /* including tailing '\0' */
cmp = pred->regex.match(str, &pred->regex, len);
match = cmp ^ pred->not;
return match;
}
/* Filter predicate for char * pointers */
static int filter_pred_pchar(struct filter_pred *pred, void *event)
{
char **addr = (char **)(event + pred->offset);
char *str;
str = test_string(*addr);
if (!str)
return 0;
return filter_pchar(pred, str);
}
/* Filter predicate for char * pointers in user space*/
static int filter_pred_pchar_user(struct filter_pred *pred, void *event)
{
char **addr = (char **)(event + pred->offset);
char *str;
str = test_ustring(*addr);
if (!str)
return 0;
return filter_pchar(pred, str);
}
/*
* Filter predicate for dynamic sized arrays of characters.
@@ -1158,6 +1229,7 @@ static int parse_pred(const char *str, void *data,
struct filter_pred *pred = NULL;
char num_buf[24]; /* Big enough to hold an address */
char *field_name;
bool ustring = false;
char q;
u64 val;
int len;
@@ -1192,6 +1264,12 @@ static int parse_pred(const char *str, void *data,
return -EINVAL;
}
/* See if the field is a user space string */
if ((len = str_has_prefix(str + i, ".ustring"))) {
ustring = true;
i += len;
}
while (isspace(str[i]))
i++;
@@ -1320,8 +1398,20 @@ static int parse_pred(const char *str, void *data,
} else if (field->filter_type == FILTER_DYN_STRING)
pred->fn = filter_pred_strloc;
else
pred->fn = filter_pred_pchar;
else {
if (!ustring_per_cpu) {
/* Once allocated, keep it around for good */
ustring_per_cpu = alloc_percpu(struct ustring_buffer);
if (!ustring_per_cpu)
goto err_mem;
}
if (ustring)
pred->fn = filter_pred_pchar_user;
else
pred->fn = filter_pred_pchar;
}
/* go past the last quote */
i++;
@@ -1387,6 +1477,9 @@ static int parse_pred(const char *str, void *data,
err_free:
kfree(pred);
return -EINVAL;
err_mem:
kfree(pred);
return -ENOMEM;
}
enum {

6
kernel/trace/trace_events_hist.c
파일 보기

@@ -1985,9 +1985,9 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
/*
* For backward compatibility, if field_name
* was "cpu", then we treat this the same as
* common_cpu.
* common_cpu. This also works for "CPU".
*/
if (strcmp(field_name, "cpu") == 0) {
if (field && field->filter_type == FILTER_CPU) {
*flags |= HIST_FIELD_FL_CPU;
} else {
hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
@@ -4365,7 +4365,7 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
if (hist_field->flags & HIST_FIELD_FL_STACKTRACE)
cmp_fn = tracing_map_cmp_none;
else if (!field)
else if (!field || hist_field->flags & HIST_FIELD_FL_CPU)
cmp_fn = tracing_map_cmp_num(hist_field->size,
hist_field->is_signed);
else if (is_string_field(field))

52
kernel/trace/trace_events_trigger.c
파일 보기

@@ -940,6 +940,16 @@ static void
traceon_trigger(struct event_trigger_data *data, void *rec,
struct ring_buffer_event *event)
{
struct trace_event_file *file = data->private_data;
if (file) {
if (tracer_tracing_is_on(file->tr))
return;
tracer_tracing_on(file->tr);
return;
}
if (tracing_is_on())
return;
@@ -950,8 +960,15 @@ static void
traceon_count_trigger(struct event_trigger_data *data, void *rec,
struct ring_buffer_event *event)
{
if (tracing_is_on())
return;
struct trace_event_file *file = data->private_data;
if (file) {
if (tracer_tracing_is_on(file->tr))
return;
} else {
if (tracing_is_on())
return;
}
if (!data->count)
return;
@@ -959,13 +976,26 @@ traceon_count_trigger(struct event_trigger_data *data, void *rec,
if (data->count != -1)
(data->count)--;
tracing_on();
if (file)
tracer_tracing_on(file->tr);
else
tracing_on();
}
static void
traceoff_trigger(struct event_trigger_data *data, void *rec,
struct ring_buffer_event *event)
{
struct trace_event_file *file = data->private_data;
if (file) {
if (!tracer_tracing_is_on(file->tr))
return;
tracer_tracing_off(file->tr);
return;
}
if (!tracing_is_on())
return;
@@ -976,8 +1006,15 @@ static void
traceoff_count_trigger(struct event_trigger_data *data, void *rec,
struct ring_buffer_event *event)
{
if (!tracing_is_on())
return;
struct trace_event_file *file = data->private_data;
if (file) {
if (!tracer_tracing_is_on(file->tr))
return;
} else {
if (!tracing_is_on())
return;
}
if (!data->count)
return;
@@ -985,7 +1022,10 @@ traceoff_count_trigger(struct event_trigger_data *data, void *rec,
if (data->count != -1)
(data->count)--;
tracing_off();
if (file)
tracer_tracing_off(file->tr);
else
tracing_off();
}
static int

2
kernel/trace/trace_kprobe.c
파일 보기

@@ -31,7 +31,7 @@ static int __init set_kprobe_boot_events(char *str)
strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE);
disable_tracing_selftest("running kprobe events");
return 0;
return 1;
}
__setup("kprobe_event=", set_kprobe_boot_events);

19
kernel/watch_queue.c
파일 보기

@@ -54,6 +54,7 @@ static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
bit += page->index;
set_bit(bit, wqueue->notes_bitmap);
generic_pipe_buf_release(pipe, buf);
}
// No try_steal function => no stealing
@@ -112,7 +113,7 @@ static bool post_one_notification(struct watch_queue *wqueue,
buf->offset = offset;
buf->len = len;
buf->flags = PIPE_BUF_FLAG_WHOLE;
pipe->head = head + 1;
smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */
if (!test_and_clear_bit(note, wqueue->notes_bitmap)) {
spin_unlock_irq(&pipe->rd_wait.lock);
@@ -243,7 +244,8 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
goto error;
}
ret = pipe_resize_ring(pipe, nr_notes);
nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE;
ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes));
if (ret < 0)
goto error;
@@ -268,11 +270,11 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
wqueue->notes = pages;
wqueue->notes_bitmap = bitmap;
wqueue->nr_pages = nr_pages;
wqueue->nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE;
wqueue->nr_notes = nr_notes;
return 0;
error_p:
for (i = 0; i < nr_pages; i++)
while (--i >= 0)
__free_page(pages[i]);
kfree(pages);
error:
@@ -320,7 +322,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe,
tf[i].info_mask & WATCH_INFO_LENGTH)
goto err_filter;
/* Ignore any unknown types */
if (tf[i].type >= sizeof(wfilter->type_filter) * 8)
if (tf[i].type >= WATCH_TYPE__NR)
continue;
nr_filter++;
}
@@ -336,7 +338,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe,
q = wfilter->filters;
for (i = 0; i < filter.nr_filters; i++) {
if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG)
if (tf[i].type >= WATCH_TYPE__NR)
continue;
q->type = tf[i].type;
@@ -371,6 +373,8 @@ static void __put_watch_queue(struct kref *kref)
for (i = 0; i < wqueue->nr_pages; i++)
__free_page(wqueue->notes[i]);
kfree(wqueue->notes);
bitmap_free(wqueue->notes_bitmap);
wfilter = rcu_access_pointer(wqueue->filter);
if (wfilter)
@@ -395,6 +399,7 @@ static void free_watch(struct rcu_head *rcu)
put_watch_queue(rcu_access_pointer(watch->queue));
atomic_dec(&watch->cred->user->nr_watches);
put_cred(watch->cred);
kfree(watch);
}
static void __put_watch(struct kref *kref)
@@ -566,7 +571,7 @@ void watch_queue_clear(struct watch_queue *wqueue)
rcu_read_lock();
spin_lock_bh(&wqueue->lock);
/* Prevent new additions and prevent notifications from happening */
/* Prevent new notifications from being stored. */
wqueue->defunct = true;
while (!hlist_empty(&wqueue->watches)) {