summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2016-08-18 07:17:32 +0200
committerDavid S. Miller <davem@davemloft.net>2016-08-18 07:17:32 +0200
commit60747ef4d173c2747bf7f0377fb22846cb422195 (patch)
treeea0faf33b952495c47909be1400c475a3f3821b0 /kernel
parentMerge branch 'strparser' (diff)
parentMerge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net (diff)
downloadlinux-60747ef4d173c2747bf7f0377fb22846cb422195.tar.xz
linux-60747ef4d173c2747bf7f0377fb22846cb422195.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Minor overlapping changes for both merge conflicts. Resolution work done by Stephen Rothwell was used as a reference. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/verifier.c4
-rw-r--r--kernel/events/core.c79
-rw-r--r--kernel/futex.c23
-rw-r--r--kernel/irq/msi.c11
-rw-r--r--kernel/jump_label.c61
-rw-r--r--kernel/livepatch/core.c2
-rw-r--r--kernel/locking/qspinlock_paravirt.h2
-rw-r--r--kernel/locking/qspinlock_stat.h1
-rw-r--r--kernel/module.c121
-rw-r--r--kernel/power/hibernate.c4
-rw-r--r--kernel/printk/internal.h16
-rw-r--r--kernel/printk/nmi.c13
-rw-r--r--kernel/printk/printk.c27
-rw-r--r--kernel/ptrace.c4
-rw-r--r--kernel/sched/core.c19
-rw-r--r--kernel/sched/cpudeadline.c2
-rw-r--r--kernel/sched/cputime.c10
-rw-r--r--kernel/sched/deadline.c5
-rw-r--r--kernel/sched/fair.c2
-rw-r--r--kernel/seccomp.c6
-rw-r--r--kernel/time/timer.c5
-rw-r--r--kernel/trace/blktrace.c6
22 files changed, 311 insertions, 112 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0cc46f1df358..abb61f3f6900 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1078,7 +1078,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
goto error;
break;
case BPF_MAP_TYPE_CGROUP_ARRAY:
- if (func_id != BPF_FUNC_skb_in_cgroup &&
+ if (func_id != BPF_FUNC_skb_under_cgroup &&
func_id != BPF_FUNC_current_task_under_cgroup)
goto error;
break;
@@ -1102,7 +1102,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
goto error;
break;
case BPF_FUNC_current_task_under_cgroup:
- case BPF_FUNC_skb_in_cgroup:
+ case BPF_FUNC_skb_under_cgroup:
if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
goto error;
break;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 356a6c7cb52a..1903b8f3a705 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -448,7 +448,7 @@ static u64 __report_allowed;
static void perf_duration_warn(struct irq_work *w)
{
- printk_ratelimited(KERN_WARNING
+ printk_ratelimited(KERN_INFO
"perf: interrupt took too long (%lld > %lld), lowering "
"kernel.perf_event_max_sample_rate to %d\n",
__report_avg, __report_allowed,
@@ -843,6 +843,32 @@ perf_cgroup_mark_enabled(struct perf_event *event,
}
}
}
+
+/*
+ * Update cpuctx->cgrp so that it is set when first cgroup event is added and
+ * cleared when last cgroup event is removed.
+ */
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+ struct perf_event_context *ctx, bool add)
+{
+ struct perf_cpu_context *cpuctx;
+
+ if (!is_cgroup_event(event))
+ return;
+
+ if (add && ctx->nr_cgroups++)
+ return;
+ else if (!add && --ctx->nr_cgroups)
+ return;
+ /*
+ * Because cgroup events are always per-cpu events,
+ * this will always be called from the right CPU.
+ */
+ cpuctx = __get_cpu_context(ctx);
+ cpuctx->cgrp = add ? event->cgrp : NULL;
+}
+
#else /* !CONFIG_CGROUP_PERF */
static inline bool
@@ -920,6 +946,13 @@ perf_cgroup_mark_enabled(struct perf_event *event,
struct perf_event_context *ctx)
{
}
+
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+ struct perf_event_context *ctx, bool add)
+{
+}
+
#endif
/*
@@ -1392,6 +1425,7 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
+
lockdep_assert_held(&ctx->lock);
WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
@@ -1412,8 +1446,7 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
list_add_tail(&event->group_entry, list);
}
- if (is_cgroup_event(event))
- ctx->nr_cgroups++;
+ list_update_cgroup_event(event, ctx, true);
list_add_rcu(&event->event_entry, &ctx->event_list);
ctx->nr_events++;
@@ -1581,8 +1614,6 @@ static void perf_group_attach(struct perf_event *event)
static void
list_del_event(struct perf_event *event, struct perf_event_context *ctx)
{
- struct perf_cpu_context *cpuctx;
-
WARN_ON_ONCE(event->ctx != ctx);
lockdep_assert_held(&ctx->lock);
@@ -1594,20 +1625,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
event->attach_state &= ~PERF_ATTACH_CONTEXT;
- if (is_cgroup_event(event)) {
- ctx->nr_cgroups--;
- /*
- * Because cgroup events are always per-cpu events, this will
- * always be called from the right CPU.
- */
- cpuctx = __get_cpu_context(ctx);
- /*
- * If there are no more cgroup events then clear cgrp to avoid
- * stale pointer in update_cgrp_time_from_cpuctx().
- */
- if (!ctx->nr_cgroups)
- cpuctx->cgrp = NULL;
- }
+ list_update_cgroup_event(event, ctx, false);
ctx->nr_events--;
if (event->attr.inherit_stat)
@@ -1716,8 +1734,8 @@ static inline int pmu_filter_match(struct perf_event *event)
static inline int
event_filter_match(struct perf_event *event)
{
- return (event->cpu == -1 || event->cpu == smp_processor_id())
- && perf_cgroup_match(event) && pmu_filter_match(event);
+ return (event->cpu == -1 || event->cpu == smp_processor_id()) &&
+ perf_cgroup_match(event) && pmu_filter_match(event);
}
static void
@@ -1737,8 +1755,8 @@ event_sched_out(struct perf_event *event,
* maintained, otherwise bogus information is return
* via read() for time_enabled, time_running:
*/
- if (event->state == PERF_EVENT_STATE_INACTIVE
- && !event_filter_match(event)) {
+ if (event->state == PERF_EVENT_STATE_INACTIVE &&
+ !event_filter_match(event)) {
delta = tstamp - event->tstamp_stopped;
event->tstamp_running += delta;
event->tstamp_stopped = tstamp;
@@ -2236,10 +2254,15 @@ perf_install_in_context(struct perf_event_context *ctx,
lockdep_assert_held(&ctx->mutex);
- event->ctx = ctx;
if (event->cpu != -1)
event->cpu = cpu;
+ /*
+ * Ensures that if we can observe event->ctx, both the event and ctx
+ * will be 'complete'. See perf_iterate_sb_cpu().
+ */
+ smp_store_release(&event->ctx, ctx);
+
if (!task) {
cpu_function_call(cpu, __perf_install_in_context, event);
return;
@@ -5969,6 +5992,14 @@ static void perf_iterate_sb_cpu(perf_iterate_f output, void *data)
struct perf_event *event;
list_for_each_entry_rcu(event, &pel->list, sb_list) {
+ /*
+ * Skip events that are not fully formed yet; ensure that
+ * if we observe event->ctx, both event and ctx will be
+ * complete enough. See perf_install_in_context().
+ */
+ if (!smp_load_acquire(&event->ctx))
+ continue;
+
if (event->state < PERF_EVENT_STATE_INACTIVE)
continue;
if (!event_filter_match(event))
diff --git a/kernel/futex.c b/kernel/futex.c
index 33664f70e2d2..46cb3a301bc1 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -179,7 +179,15 @@ int __read_mostly futex_cmpxchg_enabled;
* Futex flags used to encode options to functions and preserve them across
* restarts.
*/
-#define FLAGS_SHARED 0x01
+#ifdef CONFIG_MMU
+# define FLAGS_SHARED 0x01
+#else
+/*
+ * NOMMU does not have per process address space. Let the compiler optimize
+ * code away.
+ */
+# define FLAGS_SHARED 0x00
+#endif
#define FLAGS_CLOCKRT 0x02
#define FLAGS_HAS_TIMEOUT 0x04
@@ -405,6 +413,16 @@ static void get_futex_key_refs(union futex_key *key)
if (!key->both.ptr)
return;
+ /*
+ * On MMU less systems futexes are always "private" as there is no per
+ * process address space. We need the smp wmb nevertheless - yes,
+ * arch/blackfin has MMU less SMP ...
+ */
+ if (!IS_ENABLED(CONFIG_MMU)) {
+ smp_mb(); /* explicit smp_mb(); (B) */
+ return;
+ }
+
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
ihold(key->shared.inode); /* implies smp_mb(); (B) */
@@ -436,6 +454,9 @@ static void drop_futex_key_refs(union futex_key *key)
return;
}
+ if (!IS_ENABLED(CONFIG_MMU))
+ return;
+
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
iput(key->shared.inode);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 54999350162c..19e9dfbe97fa 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -359,6 +359,17 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
else
dev_dbg(dev, "irq [%d-%d] for MSI\n",
virq, virq + desc->nvec_used - 1);
+ /*
+ * This flag is set by the PCI layer as we need to activate
+ * the MSI entries before the PCI layer enables MSI in the
+ * card. Otherwise the card latches a random msi message.
+ */
+ if (info->flags & MSI_FLAG_ACTIVATE_EARLY) {
+ struct irq_data *irq_data;
+
+ irq_data = irq_domain_get_irq_data(domain, desc->irq);
+ irq_domain_activate_irq(irq_data);
+ }
}
return 0;
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 0dbea887d625..93ad6c1fb9b6 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -14,6 +14,7 @@
#include <linux/err.h>
#include <linux/static_key.h>
#include <linux/jump_label_ratelimit.h>
+#include <linux/bug.h>
#ifdef HAVE_JUMP_LABEL
@@ -56,6 +57,49 @@ jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
static void jump_label_update(struct static_key *key);
+/*
+ * There are similar definitions for the !HAVE_JUMP_LABEL case in jump_label.h.
+ * The use of 'atomic_read()' requires atomic.h and its problematic for some
+ * kernel headers such as kernel.h and others. Since static_key_count() is not
+ * used in the branch statements as it is for the !HAVE_JUMP_LABEL case its ok
+ * to have it be a function here. Similarly, for 'static_key_enable()' and
+ * 'static_key_disable()', which require bug.h. This should allow jump_label.h
+ * to be included from most/all places for HAVE_JUMP_LABEL.
+ */
+int static_key_count(struct static_key *key)
+{
+ /*
+ * -1 means the first static_key_slow_inc() is in progress.
+ * static_key_enabled() must return true, so return 1 here.
+ */
+ int n = atomic_read(&key->enabled);
+
+ return n >= 0 ? n : 1;
+}
+EXPORT_SYMBOL_GPL(static_key_count);
+
+void static_key_enable(struct static_key *key)
+{
+ int count = static_key_count(key);
+
+ WARN_ON_ONCE(count < 0 || count > 1);
+
+ if (!count)
+ static_key_slow_inc(key);
+}
+EXPORT_SYMBOL_GPL(static_key_enable);
+
+void static_key_disable(struct static_key *key)
+{
+ int count = static_key_count(key);
+
+ WARN_ON_ONCE(count < 0 || count > 1);
+
+ if (count)
+ static_key_slow_dec(key);
+}
+EXPORT_SYMBOL_GPL(static_key_disable);
+
void static_key_slow_inc(struct static_key *key)
{
int v, v1;
@@ -235,6 +279,18 @@ void __init jump_label_init(void)
struct static_key *key = NULL;
struct jump_entry *iter;
+ /*
+ * Since we are initializing the static_key.enabled field with
+ * with the 'raw' int values (to avoid pulling in atomic.h) in
+ * jump_label.h, let's make sure that is safe. There are only two
+ * cases to check since we initialize to 0 or 1.
+ */
+ BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0);
+ BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1);
+
+ if (static_key_initialized)
+ return;
+
jump_label_lock();
jump_label_sort_entries(iter_start, iter_stop);
@@ -284,11 +340,14 @@ static int __jump_label_mod_text_reserved(void *start, void *end)
{
struct module *mod;
+ preempt_disable();
mod = __module_text_address((unsigned long)start);
+ WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+ preempt_enable();
+
if (!mod)
return 0;
- WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
return __jump_label_text_reserved(mod->jump_entries,
mod->jump_entries + mod->num_jump_entries,
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 5c2bc1052691..8bbe50704621 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -309,7 +309,7 @@ static int klp_write_object_relocations(struct module *pmod,
break;
}
- module_enable_ro(pmod);
+ module_enable_ro(pmod, true);
return ret;
}
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 37649e69056c..8a99abf58080 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -450,7 +450,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
goto gotlock;
}
}
- WRITE_ONCE(pn->state, vcpu_halted);
+ WRITE_ONCE(pn->state, vcpu_hashed);
qstat_inc(qstat_pv_wait_head, true);
qstat_inc(qstat_pv_wait_again, waitcnt);
pv_wait(&l->locked, _Q_SLOW_VAL);
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 22e025309845..b9d031516254 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -153,7 +153,6 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf,
*/
if ((counter == qstat_pv_latency_kick) ||
(counter == qstat_pv_latency_wake)) {
- stat = 0;
if (kicks)
stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
}
diff --git a/kernel/module.c b/kernel/module.c
index a0f48b8b00da..529efae9f481 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -265,7 +265,7 @@ static void module_assert_mutex_or_preempt(void)
if (unlikely(!debug_locks))
return;
- WARN_ON(!rcu_read_lock_sched_held() &&
+ WARN_ON_ONCE(!rcu_read_lock_sched_held() &&
!lockdep_is_held(&module_mutex));
#endif
}
@@ -337,7 +337,7 @@ static inline void add_taint_module(struct module *mod, unsigned flag,
* A thread that wants to hold a reference to a module only while it
* is running can call this to safely exit. nfsd and lockd use this.
*/
-void __module_put_and_exit(struct module *mod, long code)
+void __noreturn __module_put_and_exit(struct module *mod, long code)
{
module_put(mod);
do_exit(code);
@@ -1694,8 +1694,7 @@ static int module_add_modinfo_attrs(struct module *mod)
temp_attr = mod->modinfo_attrs;
for (i = 0; (attr = modinfo_attrs[i]) && !error; i++) {
- if (!attr->test ||
- (attr->test && attr->test(mod))) {
+ if (!attr->test || attr->test(mod)) {
memcpy(temp_attr, attr, sizeof(*temp_attr));
sysfs_attr_init(&temp_attr->attr);
error = sysfs_create_file(&mod->mkobj.kobj,
@@ -1859,10 +1858,11 @@ static void mod_sysfs_teardown(struct module *mod)
* from modification and any data from execution.
*
* General layout of module is:
- * [text] [read-only-data] [writable data]
- * text_size -----^ ^ ^
- * ro_size ------------------------| |
- * size -------------------------------------------|
+ * [text] [read-only-data] [ro-after-init] [writable data]
+ * text_size -----^ ^ ^ ^
+ * ro_size ------------------------| | |
+ * ro_after_init_size -----------------------------| |
+ * size -----------------------------------------------------------|
*
* These values are always page-aligned (as is base)
*/
@@ -1885,14 +1885,24 @@ static void frob_rodata(const struct module_layout *layout,
(layout->ro_size - layout->text_size) >> PAGE_SHIFT);
}
+static void frob_ro_after_init(const struct module_layout *layout,
+ int (*set_memory)(unsigned long start, int num_pages))
+{
+ BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1));
+ BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1));
+ BUG_ON((unsigned long)layout->ro_after_init_size & (PAGE_SIZE-1));
+ set_memory((unsigned long)layout->base + layout->ro_size,
+ (layout->ro_after_init_size - layout->ro_size) >> PAGE_SHIFT);
+}
+
static void frob_writable_data(const struct module_layout *layout,
int (*set_memory)(unsigned long start, int num_pages))
{
BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1));
- BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1));
+ BUG_ON((unsigned long)layout->ro_after_init_size & (PAGE_SIZE-1));
BUG_ON((unsigned long)layout->size & (PAGE_SIZE-1));
- set_memory((unsigned long)layout->base + layout->ro_size,
- (layout->size - layout->ro_size) >> PAGE_SHIFT);
+ set_memory((unsigned long)layout->base + layout->ro_after_init_size,
+ (layout->size - layout->ro_after_init_size) >> PAGE_SHIFT);
}
/* livepatching wants to disable read-only so it can frob module. */
@@ -1900,21 +1910,26 @@ void module_disable_ro(const struct module *mod)
{
frob_text(&mod->core_layout, set_memory_rw);
frob_rodata(&mod->core_layout, set_memory_rw);
+ frob_ro_after_init(&mod->core_layout, set_memory_rw);
frob_text(&mod->init_layout, set_memory_rw);
frob_rodata(&mod->init_layout, set_memory_rw);
}
-void module_enable_ro(const struct module *mod)
+void module_enable_ro(const struct module *mod, bool after_init)
{
frob_text(&mod->core_layout, set_memory_ro);
frob_rodata(&mod->core_layout, set_memory_ro);
frob_text(&mod->init_layout, set_memory_ro);
frob_rodata(&mod->init_layout, set_memory_ro);
+
+ if (after_init)
+ frob_ro_after_init(&mod->core_layout, set_memory_ro);
}
static void module_enable_nx(const struct module *mod)
{
frob_rodata(&mod->core_layout, set_memory_nx);
+ frob_ro_after_init(&mod->core_layout, set_memory_nx);
frob_writable_data(&mod->core_layout, set_memory_nx);
frob_rodata(&mod->init_layout, set_memory_nx);
frob_writable_data(&mod->init_layout, set_memory_nx);
@@ -1923,6 +1938,7 @@ static void module_enable_nx(const struct module *mod)
static void module_disable_nx(const struct module *mod)
{
frob_rodata(&mod->core_layout, set_memory_x);
+ frob_ro_after_init(&mod->core_layout, set_memory_x);
frob_writable_data(&mod->core_layout, set_memory_x);
frob_rodata(&mod->init_layout, set_memory_x);
frob_writable_data(&mod->init_layout, set_memory_x);
@@ -1965,6 +1981,8 @@ static void disable_ro_nx(const struct module_layout *layout)
frob_text(layout, set_memory_rw);
frob_rodata(layout, set_memory_rw);
frob_rodata(layout, set_memory_x);
+ frob_ro_after_init(layout, set_memory_rw);
+ frob_ro_after_init(layout, set_memory_x);
frob_writable_data(layout, set_memory_x);
}
@@ -2307,6 +2325,7 @@ static void layout_sections(struct module *mod, struct load_info *info)
* finder in the two loops below */
{ SHF_EXECINSTR | SHF_ALLOC, ARCH_SHF_SMALL },
{ SHF_ALLOC, SHF_WRITE | ARCH_SHF_SMALL },
+ { SHF_RO_AFTER_INIT | SHF_ALLOC, ARCH_SHF_SMALL },
{ SHF_WRITE | SHF_ALLOC, ARCH_SHF_SMALL },
{ ARCH_SHF_SMALL | SHF_ALLOC, 0 }
};
@@ -2338,7 +2357,11 @@ static void layout_sections(struct module *mod, struct load_info *info)
mod->core_layout.size = debug_align(mod->core_layout.size);
mod->core_layout.ro_size = mod->core_layout.size;
break;
- case 3: /* whole core */
+ case 2: /* RO after init */
+ mod->core_layout.size = debug_align(mod->core_layout.size);
+ mod->core_layout.ro_after_init_size = mod->core_layout.size;
+ break;
+ case 4: /* whole core */
mod->core_layout.size = debug_align(mod->core_layout.size);
break;
}
@@ -2368,7 +2391,14 @@ static void layout_sections(struct module *mod, struct load_info *info)
mod->init_layout.size = debug_align(mod->init_layout.size);
mod->init_layout.ro_size = mod->init_layout.size;
break;
- case 3: /* whole init */
+ case 2:
+ /*
+ * RO after init doesn't apply to init_layout (only
+ * core_layout), so it just takes the value of ro_size.
+ */
+ mod->init_layout.ro_after_init_size = mod->init_layout.ro_size;
+ break;
+ case 4: /* whole init */
mod->init_layout.size = debug_align(mod->init_layout.size);
break;
}
@@ -2688,13 +2718,18 @@ static inline void kmemleak_load_module(const struct module *mod,
#endif
#ifdef CONFIG_MODULE_SIG
-static int module_sig_check(struct load_info *info)
+static int module_sig_check(struct load_info *info, int flags)
{
int err = -ENOKEY;
const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1;
const void *mod = info->hdr;
- if (info->len > markerlen &&
+ /*
+ * Require flags == 0, as a module with version information
+ * removed is no longer the module that was signed
+ */
+ if (flags == 0 &&
+ info->len > markerlen &&
memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
/* We truncate the module to discard the signature */
info->len -= markerlen;
@@ -2713,7 +2748,7 @@ static int module_sig_check(struct load_info *info)
return err;
}
#else /* !CONFIG_MODULE_SIG */
-static int module_sig_check(struct load_info *info)
+static int module_sig_check(struct load_info *info, int flags)
{
return 0;
}
@@ -2921,8 +2956,12 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
return -ENOEXEC;
}
- if (!get_modinfo(info, "intree"))
+ if (!get_modinfo(info, "intree")) {
+ if (!test_taint(TAINT_OOT_MODULE))
+ pr_warn("%s: loading out-of-tree module taints kernel.\n",
+ mod->name);
add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK);
+ }
if (get_modinfo(info, "staging")) {
add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK);
@@ -3091,6 +3130,8 @@ static int move_module(struct module *mod, struct load_info *info)
static int check_module_license_and_versions(struct module *mod)
{
+ int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE);
+
/*
* ndiswrapper is under GPL by itself, but loads proprietary modules.
* Don't use add_taint_module(), as it would prevent ndiswrapper from
@@ -3109,6 +3150,9 @@ static int check_module_license_and_versions(struct module *mod)
add_taint_module(mod, TAINT_PROPRIETARY_MODULE,
LOCKDEP_NOW_UNRELIABLE);
+ if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE))
+ pr_warn("%s: module license taints kernel.\n", mod->name);
+
#ifdef CONFIG_MODVERSIONS
if ((mod->num_syms && !mod->crcs)
|| (mod->num_gpl_syms && !mod->gpl_crcs)
@@ -3156,16 +3200,41 @@ int __weak module_frob_arch_sections(Elf_Ehdr *hdr,
return 0;
}
+/* module_blacklist is a comma-separated list of module names */
+static char *module_blacklist;
+static bool blacklisted(char *module_name)
+{
+ const char *p;
+ size_t len;
+
+ if (!module_blacklist)
+ return false;
+
+ for (p = module_blacklist; *p; p += len) {
+ len = strcspn(p, ",");
+ if (strlen(module_name) == len && !memcmp(module_name, p, len))
+ return true;
+ if (p[len] == ',')
+ len++;
+ }
+ return false;
+}
+core_param(module_blacklist, module_blacklist, charp, 0400);
+
static struct module *layout_and_allocate(struct load_info *info, int flags)
{
/* Module within temporary copy. */
struct module *mod;
+ unsigned int ndx;
int err;
mod = setup_load_info(info, flags);
if (IS_ERR(mod))
return mod;
+ if (blacklisted(mod->name))
+ return ERR_PTR(-EPERM);
+
err = check_modinfo(mod, info, flags);
if (err)
return ERR_PTR(err);
@@ -3179,6 +3248,15 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
/* We will do a special allocation for per-cpu sections later. */
info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC;
+ /*
+ * Mark ro_after_init section with SHF_RO_AFTER_INIT so that
+ * layout_sections() can put it in the right place.
+ * Note: ro_after_init sections also have SHF_{WRITE,ALLOC} set.
+ */
+ ndx = find_sec(info, ".data..ro_after_init");
+ if (ndx)
+ info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT;
+
/* Determine total sizes, and put offsets in sh_entsize. For now
this is done generically; there doesn't appear to be any
special cases for the architectures. */
@@ -3345,12 +3423,14 @@ static noinline int do_init_module(struct module *mod)
/* Switch to core kallsyms now init is done: kallsyms may be walking! */
rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms);
#endif
+ module_enable_ro(mod, true);
mod_tree_remove_init(mod);
disable_ro_nx(&mod->init_layout);
module_arch_freeing_init(mod);
mod->init_layout.base = NULL;
mod->init_layout.size = 0;
mod->init_layout.ro_size = 0;
+ mod->init_layout.ro_after_init_size = 0;
mod->init_layout.text_size = 0;
/*
* We want to free module_init, but be aware that kallsyms may be
@@ -3442,8 +3522,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
/* This relies on module_mutex for list integrity. */
module_bug_finalize(info->hdr, info->sechdrs, mod);
- /* Set RO and NX regions */
- module_enable_ro(mod);
+ module_enable_ro(mod, false);
module_enable_nx(mod);
/* Mark state as coming so strong_try_module_get() ignores us,
@@ -3499,7 +3578,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
long err;
char *after_dashes;
- err = module_sig_check(info);
+ err = module_sig_check(info, flags);
if (err)
goto free_copy;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index a881c6a7ba74..33c79b6105c5 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -300,12 +300,12 @@ static int create_image(int platform_mode)
save_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true);
error = swsusp_arch_suspend();
+ /* Restore control flow magically appears here */
+ restore_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
if (error)
printk(KERN_ERR "PM: Error %d creating hibernation image\n",
error);
- /* Restore control flow magically appears here */
- restore_processor_state();
if (!in_suspend)
events_check_enabled = false;
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 5d4505f30083..7fd2838fa417 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -16,11 +16,9 @@
*/
#include <linux/percpu.h>
-typedef __printf(2, 0) int (*printk_func_t)(int level, const char *fmt,
- va_list args);
+typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
-__printf(2, 0)
-int vprintk_default(int level, const char *fmt, va_list args);
+int __printf(1, 0) vprintk_default(const char *fmt, va_list args);
#ifdef CONFIG_PRINTK_NMI
@@ -33,10 +31,9 @@ extern raw_spinlock_t logbuf_lock;
* via per-CPU variable.
*/
DECLARE_PER_CPU(printk_func_t, printk_func);
-__printf(2, 0)
-static inline int vprintk_func(int level, const char *fmt, va_list args)
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
{
- return this_cpu_read(printk_func)(level, fmt, args);
+ return this_cpu_read(printk_func)(fmt, args);
}
extern atomic_t nmi_message_lost;
@@ -47,10 +44,9 @@ static inline int get_nmi_message_lost(void)
#else /* CONFIG_PRINTK_NMI */
-__printf(2, 0)
-static inline int vprintk_func(int level, const char *fmt, va_list args)
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
{
- return vprintk_default(level, fmt, args);
+ return vprintk_default(fmt, args);
}
static inline int get_nmi_message_lost(void)
diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
index bc3eeb1ae6da..b69eb8a2876f 100644
--- a/kernel/printk/nmi.c
+++ b/kernel/printk/nmi.c
@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
* one writer running. But the buffer might get flushed from another
* CPU, so we need to be careful.
*/
-static int vprintk_nmi(int level, const char *fmt, va_list args)
+static int vprintk_nmi(const char *fmt, va_list args)
{
struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
int add = 0;
@@ -79,16 +79,7 @@ again:
if (!len)
smp_rmb();
- if (level != LOGLEVEL_DEFAULT) {
- add = snprintf(s->buffer + len, sizeof(s->buffer) - len,
- KERN_SOH "%c", '0' + level);
- add += vsnprintf(s->buffer + len + add,
- sizeof(s->buffer) - len - add,
- fmt, args);
- } else {
- add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len,
- fmt, args);
- }
+ add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
/*
* Do it once again if the buffer has been flushed in the meantime.
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a5ef95ca18c9..eea6dbc2d8cf 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1930,28 +1930,7 @@ asmlinkage int printk_emit(int facility, int level,
}
EXPORT_SYMBOL(printk_emit);
-#ifdef CONFIG_PRINTK
-#define define_pr_level(func, loglevel) \
-asmlinkage __visible void func(const char *fmt, ...) \
-{ \
- va_list args; \
- \
- va_start(args, fmt); \
- vprintk_default(loglevel, fmt, args); \
- va_end(args); \
-} \
-EXPORT_SYMBOL(func)
-
-define_pr_level(__pr_emerg, LOGLEVEL_EMERG);
-define_pr_level(__pr_alert, LOGLEVEL_ALERT);
-define_pr_level(__pr_crit, LOGLEVEL_CRIT);
-define_pr_level(__pr_err, LOGLEVEL_ERR);
-define_pr_level(__pr_warn, LOGLEVEL_WARNING);
-define_pr_level(__pr_notice, LOGLEVEL_NOTICE);
-define_pr_level(__pr_info, LOGLEVEL_INFO);
-#endif
-
-int vprintk_default(int level, const char *fmt, va_list args)
+int vprintk_default(const char *fmt, va_list args)
{
int r;
@@ -1961,7 +1940,7 @@ int vprintk_default(int level, const char *fmt, va_list args)
return r;
}
#endif
- r = vprintk_emit(0, level, NULL, 0, fmt, args);
+ r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
return r;
}
@@ -1994,7 +1973,7 @@ asmlinkage __visible int printk(const char *fmt, ...)
int r;
va_start(args, fmt);
- r = vprintk_func(LOGLEVEL_DEFAULT, fmt, args);
+ r = vprintk_func(fmt, args);
va_end(args);
return r;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index d49bfa1e53e6..1d3b7665d0be 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -585,8 +585,8 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data)
return -EINVAL;
if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
- if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) ||
- !config_enabled(CONFIG_SECCOMP))
+ if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
+ !IS_ENABLED(CONFIG_SECCOMP))
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5c883fe8e440..2a906f20fba7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -74,6 +74,7 @@
#include <linux/context_tracking.h>
#include <linux/compiler.h>
#include <linux/frame.h>
+#include <linux/prefetch.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
@@ -2972,6 +2973,23 @@ EXPORT_PER_CPU_SYMBOL(kstat);
EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
/*
+ * The function fair_sched_class.update_curr accesses the struct curr
+ * and its field curr->exec_start; when called from task_sched_runtime(),
+ * we observe a high rate of cache misses in practice.
+ * Prefetching this data results in improved performance.
+ */
+static inline void prefetch_curr_exec_start(struct task_struct *p)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ struct sched_entity *curr = (&p->se)->cfs_rq->curr;
+#else
+ struct sched_entity *curr = (&task_rq(p)->cfs)->curr;
+#endif
+ prefetch(curr);
+ prefetch(&curr->exec_start);
+}
+
+/*
* Return accounted runtime for the task.
* In case the task is currently running, return the runtime plus current's
* pending runtime that have not been accounted yet.
@@ -3005,6 +3023,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
* thread, breaking clock_gettime().
*/
if (task_current(rq, p) && task_on_rq_queued(p)) {
+ prefetch_curr_exec_start(p);
update_rq_clock(rq);
p->sched_class->update_curr(rq);
}
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5be58820465c..d4184498c9f5 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -168,7 +168,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
if (old_idx == IDX_INVALID) {
cp->size++;
- cp->elements[cp->size - 1].dl = 0;
+ cp->elements[cp->size - 1].dl = dl;
cp->elements[cp->size - 1].cpu = cpu;
cp->elements[cpu].idx = cp->size - 1;
cpudl_change_key(cp, cp->size - 1, dl);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 1934f658c036..9858266fb0b3 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -508,13 +508,21 @@ void account_process_tick(struct task_struct *p, int user_tick)
*/
void account_idle_ticks(unsigned long ticks)
{
+ cputime_t cputime, steal;
if (sched_clock_irqtime) {
irqtime_account_idle_ticks(ticks);
return;
}
- account_idle_time(jiffies_to_cputime(ticks));
+ cputime = jiffies_to_cputime(ticks);
+ steal = steal_account_process_time(cputime);
+
+ if (steal >= cputime)
+ return;
+
+ cputime -= steal;
+ account_idle_time(cputime);
}
/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fcb7f0217ff4..1ce8867283dc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -658,8 +658,11 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
*
* XXX figure out if select_task_rq_dl() deals with offline cpus.
*/
- if (unlikely(!rq->online))
+ if (unlikely(!rq->online)) {
+ lockdep_unpin_lock(&rq->lock, rf.cookie);
rq = dl_task_offline_migration(rq, p);
+ rf.cookie = lockdep_pin_lock(&rq->lock);
+ }
/*
* Queueing this task back might have overloaded rq, check if we need
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4088eedea763..039de34f1521 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4269,7 +4269,7 @@ static void sync_throttle(struct task_group *tg, int cpu)
pcfs_rq = tg->parent->cfs_rq[cpu];
cfs_rq->throttle_count = pcfs_rq->throttle_count;
- pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+ cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
}
/* conditionally throttle active cfs_rq's from put_prev_entity() */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 54d15eb2b701..ef6c6c3f9d8a 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -347,7 +347,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
{
struct seccomp_filter *sfilter;
int ret;
- const bool save_orig = config_enabled(CONFIG_CHECKPOINT_RESTORE);
+ const bool save_orig = IS_ENABLED(CONFIG_CHECKPOINT_RESTORE);
if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
return ERR_PTR(-EINVAL);
@@ -542,7 +542,7 @@ void secure_computing_strict(int this_syscall)
{
int mode = current->seccomp.mode;
- if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
+ if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) &&
unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
return;
@@ -655,7 +655,7 @@ int __secure_computing(const struct seccomp_data *sd)
int mode = current->seccomp.mode;
int this_syscall;
- if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
+ if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) &&
unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
return 0;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 555670a5143c..32bf6f75a8fe 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1496,6 +1496,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
u64 expires = KTIME_MAX;
unsigned long nextevt;
+ bool is_max_delta;
/*
* Pretend that there is no timer pending if the cpu is offline.
@@ -1506,6 +1507,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
spin_lock(&base->lock);
nextevt = __next_timer_interrupt(base);
+ is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
base->next_expiry = nextevt;
/*
* We have a fresh next event. Check whether we can forward the base:
@@ -1519,7 +1521,8 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
expires = basem;
base->is_idle = false;
} else {
- expires = basem + (nextevt - basej) * TICK_NSEC;
+ if (!is_max_delta)
+ expires = basem + (nextevt - basej) * TICK_NSEC;
/*
* If we expect to sleep more than a tick, mark the base idle:
*/
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index fb345cd11883..7598e6ca817a 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -776,7 +776,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
return;
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
- bio_op(bio), bio->bi_rw, what, error, 0, NULL);
+ bio_op(bio), bio->bi_opf, what, error, 0, NULL);
}
static void blk_add_trace_bio_bounce(void *ignore,
@@ -881,7 +881,7 @@ static void blk_add_trace_split(void *ignore,
__be64 rpdu = cpu_to_be64(pdu);
__blk_add_trace(bt, bio->bi_iter.bi_sector,
- bio->bi_iter.bi_size, bio_op(bio), bio->bi_rw,
+ bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
BLK_TA_SPLIT, bio->bi_error, sizeof(rpdu),
&rpdu);
}
@@ -915,7 +915,7 @@ static void blk_add_trace_bio_remap(void *ignore,
r.sector_from = cpu_to_be64(from);
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
- bio_op(bio), bio->bi_rw, BLK_TA_REMAP, bio->bi_error,
+ bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_error,
sizeof(r), &r);
}