summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/tnum.c9
-rw-r--r--kernel/bpf/verifier.c13
-rw-r--r--kernel/cpu.c143
-rw-r--r--kernel/events/core.c4
-rw-r--r--kernel/futex.c1
-rw-r--r--kernel/kexec.c4
-rw-r--r--kernel/kexec_core.c8
-rw-r--r--kernel/kexec_file.c4
-rw-r--r--kernel/kexec_internal.h2
-rw-r--r--kernel/locking/lockdep.c7
-rw-r--r--kernel/locking/rwsem.c4
-rw-r--r--kernel/power/Kconfig5
-rw-r--r--kernel/power/hibernate.c23
-rw-r--r--kernel/power/main.c33
-rw-r--r--kernel/power/snapshot.c48
-rw-r--r--kernel/power/suspend.c2
-rw-r--r--kernel/power/suspend_test.c6
-rw-r--r--kernel/ptrace.c15
-rw-r--r--kernel/rseq.c2
-rw-r--r--kernel/time/posix-stubs.c3
-rw-r--r--kernel/time/tick-sched.c14
-rw-r--r--kernel/trace/trace.c5
-rw-r--r--kernel/trace/trace_events_hist.c63
-rw-r--r--kernel/trace/trace_events_trigger.c20
-rw-r--r--kernel/trace/trace_kprobe.c2
-rw-r--r--kernel/trace/trace_probe.c8
-rw-r--r--kernel/trace/trace_probe.h9
-rw-r--r--kernel/trace/trace_uprobe.c121
28 files changed, 376 insertions, 202 deletions
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index ca52b9642943..d4f335a9a899 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift)
return TNUM(a.value >> shift, a.mask >> shift);
}
-struct tnum tnum_arshift(struct tnum a, u8 min_shift)
+struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness)
{
/* if a.value is negative, arithmetic shifting by minimum shift
* will have larger negative offset compared to more shifting.
* If a.value is nonnegative, arithmetic shifting by minimum shift
* will have larger positive offset compare to more shifting.
*/
- return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift);
+ if (insn_bitness == 32)
+ return TNUM((u32)(((s32)a.value) >> min_shift),
+ (u32)(((s32)a.mask) >> min_shift));
+ else
+ return TNUM((s64)a.value >> min_shift,
+ (s64)a.mask >> min_shift);
}
struct tnum tnum_add(struct tnum a, struct tnum b)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ce85e7041f0c..7d530ce8719d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5049,9 +5049,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
/* Upon reaching here, src_known is true and
* umax_val is equal to umin_val.
*/
- dst_reg->smin_value >>= umin_val;
- dst_reg->smax_value >>= umin_val;
- dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
+ if (insn_bitness == 32) {
+ dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val);
+ dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val);
+ } else {
+ dst_reg->smin_value >>= umin_val;
+ dst_reg->smax_value >>= umin_val;
+ }
+
+ dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val,
+ insn_bitness);
/* blow away the dst_reg umin_value/umax_value and rely on
* dst_reg var_off to refine the result.
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a59cc980adad..4dc279ed3b2d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1909,6 +1909,78 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
}
EXPORT_SYMBOL(__cpuhp_remove_state);
+#ifdef CONFIG_HOTPLUG_SMT
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = true;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = false;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ for_each_online_cpu(cpu) {
+ if (topology_is_primary_thread(cpu))
+ continue;
+ ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+ if (ret)
+ break;
+ /*
+ * As this needs to hold the cpu maps lock it's impossible
+ * to call device_offline() because that ends up calling
+ * cpu_down() which takes cpu maps lock. cpu maps lock
+ * needs to be held as this might race against in kernel
+ * abusers of the hotplug machinery (thermal management).
+ *
+ * So nothing would update device:offline state. That would
+ * leave the sysfs entry stale and prevent onlining after
+ * smt control has been changed to 'off' again. This is
+ * called under the sysfs hotplug lock, so it is properly
+ * serialized against the regular offline usage.
+ */
+ cpuhp_offline_cpu_device(cpu);
+ }
+ if (!ret)
+ cpu_smt_control = ctrlval;
+ cpu_maps_update_done();
+ return ret;
+}
+
+int cpuhp_smt_enable(void)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ cpu_smt_control = CPU_SMT_ENABLED;
+ for_each_present_cpu(cpu) {
+ /* Skip online CPUs and CPUs on offline nodes */
+ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+ continue;
+ ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+ if (ret)
+ break;
+ /* See comment in cpuhp_smt_disable() */
+ cpuhp_online_cpu_device(cpu);
+ }
+ cpu_maps_update_done();
+ return ret;
+}
+#endif
+
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t show_cpuhp_state(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -2063,77 +2135,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
#ifdef CONFIG_HOTPLUG_SMT
-static void cpuhp_offline_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = true;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
-}
-
-static void cpuhp_online_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = false;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_ONLINE);
-}
-
-int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- for_each_online_cpu(cpu) {
- if (topology_is_primary_thread(cpu))
- continue;
- ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
- if (ret)
- break;
- /*
- * As this needs to hold the cpu maps lock it's impossible
- * to call device_offline() because that ends up calling
- * cpu_down() which takes cpu maps lock. cpu maps lock
- * needs to be held as this might race against in kernel
- * abusers of the hotplug machinery (thermal management).
- *
- * So nothing would update device:offline state. That would
- * leave the sysfs entry stale and prevent onlining after
- * smt control has been changed to 'off' again. This is
- * called under the sysfs hotplug lock, so it is properly
- * serialized against the regular offline usage.
- */
- cpuhp_offline_cpu_device(cpu);
- }
- if (!ret)
- cpu_smt_control = ctrlval;
- cpu_maps_update_done();
- return ret;
-}
-
-int cpuhp_smt_enable(void)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- cpu_smt_control = CPU_SMT_ENABLED;
- for_each_present_cpu(cpu) {
- /* Skip online CPUs and CPUs on offline nodes */
- if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
- continue;
- ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
- if (ret)
- break;
- /* See comment in cpuhp_smt_disable() */
- cpuhp_online_cpu_device(cpu);
- }
- cpu_maps_update_done();
- return ret;
-}
-
-
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a1f8bde19b56..2173c23c25b4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11465,8 +11465,10 @@ SYSCALL_DEFINE5(perf_event_open,
}
}
- if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader))
+ if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) {
+ err = -EINVAL;
goto err_locked;
+ }
/*
* Must be under the same ctx::mutex as perf_install_in_context(),
diff --git a/kernel/futex.c b/kernel/futex.c
index 03c518e9747e..0cf84c8664f2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1178,6 +1178,7 @@ out_error:
/**
* wait_for_owner_exiting - Block until the owner has exited
+ * @ret: owner's current futex lock status
* @exiting: Pointer to the exiting task
*
* Caller must hold a refcount on @exiting.
diff --git a/kernel/kexec.c b/kernel/kexec.c
index bc933c0db9bf..f977786fe498 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -159,6 +159,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
kimage_terminate(image);
+ ret = machine_kexec_post_load(image);
+ if (ret)
+ goto out;
+
/* Install the new kernel and uninstall the old */
image = xchg(dest_image, image);
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 15d70a90b50d..c19c0dad1ebe 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -589,6 +589,12 @@ static void kimage_free_extra_pages(struct kimage *image)
kimage_free_page_list(&image->unusable_pages);
}
+
+int __weak machine_kexec_post_load(struct kimage *image)
+{
+ return 0;
+}
+
void kimage_terminate(struct kimage *image)
{
if (*image->entry != 0)
@@ -1171,7 +1177,7 @@ int kernel_kexec(void)
* CPU hotplug again; so re-enable it here.
*/
cpu_hotplug_enable();
- pr_emerg("Starting new kernel\n");
+ pr_notice("Starting new kernel\n");
machine_shutdown();
}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index a2df93948665..faa74d5f6941 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -441,6 +441,10 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
kimage_terminate(image);
+ ret = machine_kexec_post_load(image);
+ if (ret)
+ goto out;
+
/*
* Free up any temporary buffers allocated which are not needed
* after image has been loaded
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 48aaf2ac0d0d..39d30ccf8d87 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -13,6 +13,8 @@ void kimage_terminate(struct kimage *image);
int kimage_is_destination_range(struct kimage *image,
unsigned long start, unsigned long end);
+int machine_kexec_post_load(struct kimage *image);
+
extern struct mutex kexec_mutex;
#ifdef CONFIG_KEXEC_FILE
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 32282e7112d3..32406ef0d6a2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -482,7 +482,7 @@ static struct lock_trace *save_trace(void)
struct lock_trace *trace, *t2;
struct hlist_head *hash_head;
u32 hash;
- unsigned int max_entries;
+ int max_entries;
BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE);
BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES);
@@ -490,10 +490,8 @@ static struct lock_trace *save_trace(void)
trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries);
max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries -
LOCK_TRACE_SIZE_IN_LONGS;
- trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
- if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES -
- LOCK_TRACE_SIZE_IN_LONGS - 1) {
+ if (max_entries <= 0) {
if (!debug_locks_off_graph_unlock())
return NULL;
@@ -502,6 +500,7 @@ static struct lock_trace *save_trace(void)
return NULL;
}
+ trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
hash = jhash(trace->entries, trace->nr_entries *
sizeof(trace->entries[0]), 0);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 44e68761f432..0d9b6be9ecc8 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1226,8 +1226,8 @@ wait:
* In this case, we attempt to acquire the lock again
* without sleeping.
*/
- if ((wstate == WRITER_HANDOFF) &&
- (rwsem_spin_on_owner(sem, 0) == OWNER_NULL))
+ if (wstate == WRITER_HANDOFF &&
+ rwsem_spin_on_owner(sem, RWSEM_NONSPINNABLE) == OWNER_NULL)
goto trylock_again;
/* Block until there are no active lockers. */
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index d3667b4075c1..7cbfbeacd68a 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -27,7 +27,10 @@ config SUSPEND_SKIP_SYNC
Skip the kernel sys_sync() before freezing user processes.
Some systems prefer not to pay this cost on every invocation
of suspend, or they are content with invoking sync() from
- user-space before invoking suspend. Say Y if that's your case.
+ user-space before invoking suspend. There's a run-time switch
+ at '/sys/power/sync_on_suspend' to configure this behaviour.
+ This setting changes the default for the run-tim switch. Say Y
+ to change the default to disable the kernel sys_sync().
config HIBERNATE_CALLBACKS
bool
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 3c0a5a8170b0..6dbeedb7354c 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -9,7 +9,7 @@
* Copyright (C) 2012 Bojan Smojver <bojan@rexursive.com>
*/
-#define pr_fmt(fmt) "PM: " fmt
+#define pr_fmt(fmt) "PM: hibernation: " fmt
#include <linux/export.h>
#include <linux/suspend.h>
@@ -106,7 +106,7 @@ EXPORT_SYMBOL(system_entering_hibernation);
#ifdef CONFIG_PM_DEBUG
static void hibernation_debug_sleep(void)
{
- pr_info("hibernation debug: Waiting for 5 seconds.\n");
+ pr_info("debug: Waiting for 5 seconds.\n");
mdelay(5000);
}
@@ -277,7 +277,7 @@ static int create_image(int platform_mode)
error = dpm_suspend_end(PMSG_FREEZE);
if (error) {
- pr_err("Some devices failed to power down, aborting hibernation\n");
+ pr_err("Some devices failed to power down, aborting\n");
return error;
}
@@ -295,7 +295,7 @@ static int create_image(int platform_mode)
error = syscore_suspend();
if (error) {
- pr_err("Some system devices failed to power down, aborting hibernation\n");
+ pr_err("Some system devices failed to power down, aborting\n");
goto Enable_irqs;
}
@@ -310,7 +310,7 @@ static int create_image(int platform_mode)
restore_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
if (error)
- pr_err("Error %d creating hibernation image\n", error);
+ pr_err("Error %d creating image\n", error);
if (!in_suspend) {
events_check_enabled = false;
@@ -680,7 +680,7 @@ static int load_image_and_restore(void)
if (!error)
hibernation_restore(flags & SF_PLATFORM_MODE);
- pr_err("Failed to load hibernation image, recovering.\n");
+ pr_err("Failed to load image, recovering.\n");
swsusp_free();
free_basic_memory_bitmaps();
Unlock:
@@ -743,7 +743,7 @@ int hibernate(void)
else
flags |= SF_CRC32_MODE;
- pm_pr_dbg("Writing image.\n");
+ pm_pr_dbg("Writing hibernation image.\n");
error = swsusp_write(flags);
swsusp_free();
if (!error) {
@@ -755,7 +755,7 @@ int hibernate(void)
in_suspend = 0;
pm_restore_gfp_mask();
} else {
- pm_pr_dbg("Image restored successfully.\n");
+ pm_pr_dbg("Hibernation image restored successfully.\n");
}
Free_bitmaps:
@@ -894,7 +894,7 @@ static int software_resume(void)
goto Close_Finish;
}
- pm_pr_dbg("Preparing processes for restore.\n");
+ pm_pr_dbg("Preparing processes for hibernation restore.\n");
error = freeze_processes();
if (error)
goto Close_Finish;
@@ -903,7 +903,7 @@ static int software_resume(void)
Finish:
__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
pm_restore_console();
- pr_info("resume from hibernation failed (%d)\n", error);
+ pr_info("resume failed (%d)\n", error);
atomic_inc(&snapshot_device_available);
/* For success case, the suspend path will release the lock */
Unlock:
@@ -1068,7 +1068,8 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
lock_system_sleep();
swsusp_resume_device = res;
unlock_system_sleep();
- pm_pr_dbg("Configured resume from disk to %u\n", swsusp_resume_device);
+ pm_pr_dbg("Configured hibernation resume from disk to %u\n",
+ swsusp_resume_device);
noresume = 0;
software_resume();
return n;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index e26de7af520b..69b7a8aeca3b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -190,6 +190,38 @@ static ssize_t mem_sleep_store(struct kobject *kobj, struct kobj_attribute *attr
}
power_attr(mem_sleep);
+
+/*
+ * sync_on_suspend: invoke ksys_sync_helper() before suspend.
+ *
+ * show() returns whether ksys_sync_helper() is invoked before suspend.
+ * store() accepts 0 or 1. 0 disables ksys_sync_helper() and 1 enables it.
+ */
+bool sync_on_suspend_enabled = !IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC);
+
+static ssize_t sync_on_suspend_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%d\n", sync_on_suspend_enabled);
+}
+
+static ssize_t sync_on_suspend_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned long val;
+
+ if (kstrtoul(buf, 10, &val))
+ return -EINVAL;
+
+ if (val > 1)
+ return -EINVAL;
+
+ sync_on_suspend_enabled = !!val;
+ return n;
+}
+
+power_attr(sync_on_suspend);
#endif /* CONFIG_SUSPEND */
#ifdef CONFIG_PM_SLEEP_DEBUG
@@ -855,6 +887,7 @@ static struct attribute * g[] = {
&wakeup_count_attr.attr,
#ifdef CONFIG_SUSPEND
&mem_sleep_attr.attr,
+ &sync_on_suspend_attr.attr,
#endif
#ifdef CONFIG_PM_AUTOSLEEP
&autosleep_attr.attr,
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 26b9168321e7..ddade80ad276 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -8,7 +8,7 @@
* Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
*/
-#define pr_fmt(fmt) "PM: " fmt
+#define pr_fmt(fmt) "PM: hibernation: " fmt
#include <linux/version.h>
#include <linux/module.h>
@@ -1147,24 +1147,24 @@ void free_basic_memory_bitmaps(void)
void clear_free_pages(void)
{
-#ifdef CONFIG_PAGE_POISONING_ZERO
struct memory_bitmap *bm = free_pages_map;
unsigned long pfn;
if (WARN_ON(!(free_pages_map)))
return;
- memory_bm_position_reset(bm);
- pfn = memory_bm_next_pfn(bm);
- while (pfn != BM_END_OF_MAP) {
- if (pfn_valid(pfn))
- clear_highpage(pfn_to_page(pfn));
-
+ if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) {
+ memory_bm_position_reset(bm);
pfn = memory_bm_next_pfn(bm);
+ while (pfn != BM_END_OF_MAP) {
+ if (pfn_valid(pfn))
+ clear_highpage(pfn_to_page(pfn));
+
+ pfn = memory_bm_next_pfn(bm);
+ }
+ memory_bm_position_reset(bm);
+ pr_info("free pages cleared after restore\n");
}
- memory_bm_position_reset(bm);
- pr_info("free pages cleared after restore\n");
-#endif /* PAGE_POISONING_ZERO */
}
/**
@@ -1566,9 +1566,7 @@ static unsigned long preallocate_image_highmem(unsigned long nr_pages)
*/
static unsigned long __fraction(u64 x, u64 multiplier, u64 base)
{
- x *= multiplier;
- do_div(x, base);
- return (unsigned long)x;
+ return div64_u64(x * multiplier, base);
}
static unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
@@ -1705,16 +1703,20 @@ int hibernate_preallocate_memory(void)
ktime_t start, stop;
int error;
- pr_info("Preallocating image memory... ");
+ pr_info("Preallocating image memory\n");
start = ktime_get();
error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY);
- if (error)
+ if (error) {
+ pr_err("Cannot allocate original bitmap\n");
goto err_out;
+ }
error = memory_bm_create(&copy_bm, GFP_IMAGE, PG_ANY);
- if (error)
+ if (error) {
+ pr_err("Cannot allocate copy bitmap\n");
goto err_out;
+ }
alloc_normal = 0;
alloc_highmem = 0;
@@ -1804,8 +1806,11 @@ int hibernate_preallocate_memory(void)
alloc -= pages;
pages += pages_highmem;
pages_highmem = preallocate_image_highmem(alloc);
- if (pages_highmem < alloc)
+ if (pages_highmem < alloc) {
+ pr_err("Image allocation is %lu pages short\n",
+ alloc - pages_highmem);
goto err_out;
+ }
pages += pages_highmem;
/*
* size is the desired number of saveable pages to leave in
@@ -1836,13 +1841,12 @@ int hibernate_preallocate_memory(void)
out:
stop = ktime_get();
- pr_cont("done (allocated %lu pages)\n", pages);
+ pr_info("Allocated %lu pages for snapshot\n", pages);
swsusp_show_speed(start, stop, pages, "Allocated");
return 0;
err_out:
- pr_cont("\n");
swsusp_free();
return -ENOMEM;
}
@@ -1976,7 +1980,7 @@ asmlinkage __visible int swsusp_save(void)
{
unsigned int nr_pages, nr_highmem;
- pr_info("Creating hibernation image:\n");
+ pr_info("Creating image:\n");
drain_local_pages(NULL);
nr_pages = count_data_pages();
@@ -2010,7 +2014,7 @@ asmlinkage __visible int swsusp_save(void)
nr_copy_pages = nr_pages;
nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE);
- pr_info("Hibernation image created (%d pages copied)\n", nr_pages);
+ pr_info("Image created (%d pages copied)\n", nr_pages);
return 0;
}
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f3b7239f1892..2c47280fbfc7 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -564,7 +564,7 @@ static int enter_state(suspend_state_t state)
if (state == PM_SUSPEND_TO_IDLE)
s2idle_begin();
- if (!IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC)) {
+ if (sync_on_suspend_enabled) {
trace_suspend_resume(TPS("sync_filesystems"), 0, true);
ksys_sync_helper();
trace_suspend_resume(TPS("sync_filesystems"), 0, false);
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 60564b58de07..e1ed58adb69e 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -70,7 +70,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
static char info_test[] __initdata =
KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
- unsigned long now;
+ time64_t now;
struct rtc_wkalrm alm;
int status;
@@ -81,10 +81,10 @@ repeat:
printk(err_readtime, dev_name(&rtc->dev), status);
return;
}
- rtc_tm_to_time(&alm.time, &now);
+ now = rtc_tm_to_time64(&alm.time);
memset(&alm, 0, sizeof alm);
- rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
+ rtc_time64_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
alm.enabled = true;
status = rtc_set_alarm(rtc, &alm);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index cb9ddcc08119..43d6179508d6 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -264,12 +264,17 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
return ret;
}
-static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
+static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns,
+ unsigned int mode)
{
+ int ret;
+
if (mode & PTRACE_MODE_NOAUDIT)
- return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
+ ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT);
else
- return has_ns_capability(current, ns, CAP_SYS_PTRACE);
+ ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE);
+
+ return ret == 0;
}
/* Returns 0 on success, -errno on denial. */
@@ -321,7 +326,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
gid_eq(caller_gid, tcred->sgid) &&
gid_eq(caller_gid, tcred->gid))
goto ok;
- if (ptrace_has_cap(tcred->user_ns, mode))
+ if (ptrace_has_cap(cred, tcred->user_ns, mode))
goto ok;
rcu_read_unlock();
return -EPERM;
@@ -340,7 +345,7 @@ ok:
mm = task->mm;
if (mm &&
((get_dumpable(mm) != SUID_DUMP_USER) &&
- !ptrace_has_cap(mm->user_ns, mode)))
+ !ptrace_has_cap(cred, mm->user_ns, mode)))
return -EPERM;
return security_ptrace_access_check(task, mode);
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 27c48eb7de40..a4f86a9d6937 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -310,6 +310,8 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
int ret;
if (flags & RSEQ_FLAG_UNREGISTER) {
+ if (flags & ~RSEQ_FLAG_UNREGISTER)
+ return -EINVAL;
/* Unregister rseq for current thread. */
if (current->rseq != rseq || !current->rseq)
return -EINVAL;
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 67df65f887ac..20c65a7d4e3a 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -151,6 +151,9 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
#ifdef CONFIG_COMPAT
COMPAT_SYS_NI(timer_create);
+#endif
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
COMPAT_SYS_NI(getitimer);
COMPAT_SYS_NI(setitimer);
#endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 8b192e67aabc..a792d21cac64 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now)
/*
* Do a quick check without holding jiffies_lock:
+ * The READ_ONCE() pairs with two updates done later in this function.
*/
- delta = ktime_sub(now, last_jiffies_update);
+ delta = ktime_sub(now, READ_ONCE(last_jiffies_update));
if (delta < tick_period)
return;
@@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now)
if (delta >= tick_period) {
delta = ktime_sub(delta, tick_period);
- last_jiffies_update = ktime_add(last_jiffies_update,
- tick_period);
+ /* Pairs with the lockless read in this function. */
+ WRITE_ONCE(last_jiffies_update,
+ ktime_add(last_jiffies_update, tick_period));
/* Slow path for long timeouts */
if (unlikely(delta >= tick_period)) {
@@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now)
ticks = ktime_divns(delta, incr);
- last_jiffies_update = ktime_add_ns(last_jiffies_update,
- incr * ticks);
+ /* Pairs with the lockless read in this function. */
+ WRITE_ONCE(last_jiffies_update,
+ ktime_add_ns(last_jiffies_update,
+ incr * ticks));
}
do_timer(++ticks);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ddb7e7f5fe8d..5b6ee4aadc26 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9420,6 +9420,11 @@ __init static int tracing_set_default_clock(void)
{
/* sched_clock_stable() is determined in late_initcall */
if (!trace_boot_clock && !sched_clock_stable()) {
+ if (security_locked_down(LOCKDOWN_TRACEFS)) {
+ pr_warn("Can not set tracing clock due to lockdown\n");
+ return -EPERM;
+ }
+
printk(KERN_WARNING
"Unstable clock detected, switching default tracing clock to \"global\"\n"
"If you want to keep using the local clock, then add:\n"
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index f62de5f43e79..6ac35b9e195d 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -116,6 +116,7 @@ struct hist_field {
struct ftrace_event_field *field;
unsigned long flags;
hist_field_fn_t fn;
+ unsigned int ref;
unsigned int size;
unsigned int offset;
unsigned int is_signed;
@@ -1766,11 +1767,13 @@ static struct hist_field *find_var(struct hist_trigger_data *hist_data,
struct event_trigger_data *test;
struct hist_field *hist_field;
+ lockdep_assert_held(&event_mutex);
+
hist_field = find_var_field(hist_data, var_name);
if (hist_field)
return hist_field;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
test_data = test->private_data;
hist_field = find_var_field(test_data, var_name);
@@ -1820,7 +1823,9 @@ static struct hist_field *find_file_var(struct trace_event_file *file,
struct event_trigger_data *test;
struct hist_field *hist_field;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
test_data = test->private_data;
hist_field = find_var_field(test_data, var_name);
@@ -2423,8 +2428,16 @@ static int contains_operator(char *str)
return field_op;
}
+static void get_hist_field(struct hist_field *hist_field)
+{
+ hist_field->ref++;
+}
+
static void __destroy_hist_field(struct hist_field *hist_field)
{
+ if (--hist_field->ref > 1)
+ return;
+
kfree(hist_field->var.name);
kfree(hist_field->name);
kfree(hist_field->type);
@@ -2466,6 +2479,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
if (!hist_field)
return NULL;
+ hist_field->ref = 1;
+
hist_field->hist_data = hist_data;
if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS)
@@ -2661,6 +2676,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
{
unsigned long flags = HIST_FIELD_FL_VAR_REF;
struct hist_field *ref_field;
+ int i;
+
+ /* Check if the variable already exists */
+ for (i = 0; i < hist_data->n_var_refs; i++) {
+ ref_field = hist_data->var_refs[i];
+ if (ref_field->var.idx == var_field->var.idx &&
+ ref_field->var.hist_data == var_field->hist_data) {
+ get_hist_field(ref_field);
+ return ref_field;
+ }
+ }
ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
if (ref_field) {
@@ -3115,7 +3141,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data,
{
struct event_trigger_data *test;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (test->private_data == hist_data)
return test->filter_str;
@@ -3166,9 +3194,11 @@ find_compatible_hist(struct hist_trigger_data *target_hist_data,
struct event_trigger_data *test;
unsigned int n_keys;
+ lockdep_assert_held(&event_mutex);
+
n_keys = target_hist_data->n_fields - target_hist_data->n_vals;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
hist_data = test->private_data;
@@ -5528,7 +5558,7 @@ static int hist_show(struct seq_file *m, void *v)
goto out_unlock;
}
- list_for_each_entry_rcu(data, &event_file->triggers, list) {
+ list_for_each_entry(data, &event_file->triggers, list) {
if (data->cmd_ops->trigger_type == ETT_EVENT_HIST)
hist_trigger_show(m, data, n++);
}
@@ -5921,7 +5951,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
if (hist_data->attrs->name && !named_data)
goto new;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (!hist_trigger_match(data, test, named_data, false))
continue;
@@ -6005,10 +6037,12 @@ static bool have_hist_trigger_match(struct event_trigger_data *data,
struct event_trigger_data *test, *named_data = NULL;
bool match = false;
+ lockdep_assert_held(&event_mutex);
+
if (hist_data->attrs->name)
named_data = find_named_trigger(hist_data->attrs->name);
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (hist_trigger_match(data, test, named_data, false)) {
match = true;
@@ -6026,10 +6060,12 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data,
struct hist_trigger_data *hist_data = data->private_data;
struct event_trigger_data *test, *named_data = NULL;
+ lockdep_assert_held(&event_mutex);
+
if (hist_data->attrs->name)
named_data = find_named_trigger(hist_data->attrs->name);
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (!hist_trigger_match(data, test, named_data, false))
continue;
@@ -6051,10 +6087,12 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops,
struct event_trigger_data *test, *named_data = NULL;
bool unregistered = false;
+ lockdep_assert_held(&event_mutex);
+
if (hist_data->attrs->name)
named_data = find_named_trigger(hist_data->attrs->name);
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (!hist_trigger_match(data, test, named_data, false))
continue;
@@ -6080,7 +6118,9 @@ static bool hist_file_check_refs(struct trace_event_file *file)
struct hist_trigger_data *hist_data;
struct event_trigger_data *test;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
hist_data = test->private_data;
if (check_var_refs(hist_data))
@@ -6323,7 +6363,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec,
struct enable_trigger_data *enable_data = data->private_data;
struct event_trigger_data *test;
- list_for_each_entry_rcu(test, &enable_data->file->triggers, list) {
+ list_for_each_entry_rcu(test, &enable_data->file->triggers, list,
+ lockdep_is_held(&event_mutex)) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (enable_data->enable)
test->paused = false;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 2cd53ca21b51..40106fff06a4 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -501,7 +501,9 @@ void update_cond_flag(struct trace_event_file *file)
struct event_trigger_data *data;
bool set_cond = false;
- list_for_each_entry_rcu(data, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(data, &file->triggers, list) {
if (data->filter || event_command_post_trigger(data->cmd_ops) ||
event_command_needs_rec(data->cmd_ops)) {
set_cond = true;
@@ -536,7 +538,9 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops,
struct event_trigger_data *test;
int ret = 0;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) {
ret = -EEXIST;
goto out;
@@ -581,7 +585,9 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
struct event_trigger_data *data;
bool unregistered = false;
- list_for_each_entry_rcu(data, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(data, &file->triggers, list) {
if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
unregistered = true;
list_del_rcu(&data->list);
@@ -1497,7 +1503,9 @@ int event_enable_register_trigger(char *glob,
struct event_trigger_data *test;
int ret = 0;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
test_enable_data = test->private_data;
if (test_enable_data &&
(test->cmd_ops->trigger_type ==
@@ -1537,7 +1545,9 @@ void event_enable_unregister_trigger(char *glob,
struct event_trigger_data *data;
bool unregistered = false;
- list_for_each_entry_rcu(data, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(data, &file->triggers, list) {
enable_data = data->private_data;
if (enable_data &&
(data->cmd_ops->trigger_type ==
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7f890262c8a3..3f54dc2f6e1c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -290,7 +290,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
INIT_HLIST_NODE(&tk->rp.kp.hlist);
INIT_LIST_HEAD(&tk->rp.kp.list);
- ret = trace_probe_init(&tk->tp, event, group);
+ ret = trace_probe_init(&tk->tp, event, group, false);
if (ret < 0)
goto error;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 905b10af5d5c..9ae87be422f2 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -984,15 +984,19 @@ void trace_probe_cleanup(struct trace_probe *tp)
}
int trace_probe_init(struct trace_probe *tp, const char *event,
- const char *group)
+ const char *group, bool alloc_filter)
{
struct trace_event_call *call;
+ size_t size = sizeof(struct trace_probe_event);
int ret = 0;
if (!event || !group)
return -EINVAL;
- tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL);
+ if (alloc_filter)
+ size += sizeof(struct trace_uprobe_filter);
+
+ tp->event = kzalloc(size, GFP_KERNEL);
if (!tp->event)
return -ENOMEM;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 4ee703728aec..a0ff9e200ef6 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -223,6 +223,12 @@ struct probe_arg {
const struct fetch_type *type; /* Type of this argument */
};
+struct trace_uprobe_filter {
+ rwlock_t rwlock;
+ int nr_systemwide;
+ struct list_head perf_events;
+};
+
/* Event call and class holder */
struct trace_probe_event {
unsigned int flags; /* For TP_FLAG_* */
@@ -230,6 +236,7 @@ struct trace_probe_event {
struct trace_event_call call;
struct list_head files;
struct list_head probes;
+ struct trace_uprobe_filter filter[0];
};
struct trace_probe {
@@ -322,7 +329,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp)
}
int trace_probe_init(struct trace_probe *tp, const char *event,
- const char *group);
+ const char *group, bool alloc_filter);
void trace_probe_cleanup(struct trace_probe *tp);
int trace_probe_append(struct trace_probe *tp, struct trace_probe *to);
void trace_probe_unlink(struct trace_probe *tp);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 352073d36585..2619bc5ed520 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -34,12 +34,6 @@ struct uprobe_trace_entry_head {
#define DATAOF_TRACE_ENTRY(entry, is_return) \
((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return))
-struct trace_uprobe_filter {
- rwlock_t rwlock;
- int nr_systemwide;
- struct list_head perf_events;
-};
-
static int trace_uprobe_create(int argc, const char **argv);
static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev);
static int trace_uprobe_release(struct dyn_event *ev);
@@ -60,7 +54,6 @@ static struct dyn_event_operations trace_uprobe_ops = {
*/
struct trace_uprobe {
struct dyn_event devent;
- struct trace_uprobe_filter filter;
struct uprobe_consumer consumer;
struct path path;
struct inode *inode;
@@ -351,7 +344,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
if (!tu)
return ERR_PTR(-ENOMEM);
- ret = trace_probe_init(&tu->tp, event, group);
+ ret = trace_probe_init(&tu->tp, event, group, true);
if (ret < 0)
goto error;
@@ -359,7 +352,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
tu->consumer.handler = uprobe_dispatcher;
if (is_ret)
tu->consumer.ret_handler = uretprobe_dispatcher;
- init_trace_uprobe_filter(&tu->filter);
+ init_trace_uprobe_filter(tu->tp.event->filter);
return tu;
error:
@@ -1067,13 +1060,14 @@ static void __probe_event_disable(struct trace_probe *tp)
struct trace_probe *pos;
struct trace_uprobe *tu;
+ tu = container_of(tp, struct trace_uprobe, tp);
+ WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
+
list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
tu = container_of(pos, struct trace_uprobe, tp);
if (!tu->inode)
continue;
- WARN_ON(!uprobe_filter_is_empty(&tu->filter));
-
uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
tu->inode = NULL;
}
@@ -1108,7 +1102,7 @@ static int probe_event_enable(struct trace_event_call *call,
}
tu = container_of(tp, struct trace_uprobe, tp);
- WARN_ON(!uprobe_filter_is_empty(&tu->filter));
+ WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
if (enabled)
return 0;
@@ -1205,39 +1199,39 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
}
static inline bool
-uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
+trace_uprobe_filter_event(struct trace_uprobe_filter *filter,
+ struct perf_event *event)
{
- return __uprobe_perf_filter(&tu->filter, event->hw.target->mm);
+ return __uprobe_perf_filter(filter, event->hw.target->mm);
}
-static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
+static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter,
+ struct perf_event *event)
{
bool done;
- write_lock(&tu->filter.rwlock);
+ write_lock(&filter->rwlock);
if (event->hw.target) {
list_del(&event->hw.tp_list);
- done = tu->filter.nr_systemwide ||
+ done = filter->nr_systemwide ||
(event->hw.target->flags & PF_EXITING) ||
- uprobe_filter_event(tu, event);
+ trace_uprobe_filter_event(filter, event);
} else {
- tu->filter.nr_systemwide--;
- done = tu->filter.nr_systemwide;
+ filter->nr_systemwide--;
+ done = filter->nr_systemwide;
}
- write_unlock(&tu->filter.rwlock);
+ write_unlock(&filter->rwlock);
- if (!done)
- return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
-
- return 0;
+ return done;
}
-static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
+/* This returns true if the filter always covers target mm */
+static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter,
+ struct perf_event *event)
{
bool done;
- int err;
- write_lock(&tu->filter.rwlock);
+ write_lock(&filter->rwlock);
if (event->hw.target) {
/*
* event->parent != NULL means copy_process(), we can avoid
@@ -1247,28 +1241,21 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
* attr.enable_on_exec means that exec/mmap will install the
* breakpoints we need.
*/
- done = tu->filter.nr_systemwide ||
+ done = filter->nr_systemwide ||
event->parent || event->attr.enable_on_exec ||
- uprobe_filter_event(tu, event);
- list_add(&event->hw.tp_list, &tu->filter.perf_events);
+ trace_uprobe_filter_event(filter, event);
+ list_add(&event->hw.tp_list, &filter->perf_events);
} else {
- done = tu->filter.nr_systemwide;
- tu->filter.nr_systemwide++;
+ done = filter->nr_systemwide;
+ filter->nr_systemwide++;
}
- write_unlock(&tu->filter.rwlock);
+ write_unlock(&filter->rwlock);
- err = 0;
- if (!done) {
- err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
- if (err)
- uprobe_perf_close(tu, event);
- }
- return err;
+ return done;
}
-static int uprobe_perf_multi_call(struct trace_event_call *call,
- struct perf_event *event,
- int (*op)(struct trace_uprobe *tu, struct perf_event *event))
+static int uprobe_perf_close(struct trace_event_call *call,
+ struct perf_event *event)
{
struct trace_probe *pos, *tp;
struct trace_uprobe *tu;
@@ -1278,25 +1265,59 @@ static int uprobe_perf_multi_call(struct trace_event_call *call,
if (WARN_ON_ONCE(!tp))
return -ENODEV;
+ tu = container_of(tp, struct trace_uprobe, tp);
+ if (trace_uprobe_filter_remove(tu->tp.event->filter, event))
+ return 0;
+
list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
tu = container_of(pos, struct trace_uprobe, tp);
- ret = op(tu, event);
+ ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
if (ret)
break;
}
return ret;
}
+
+static int uprobe_perf_open(struct trace_event_call *call,
+ struct perf_event *event)
+{
+ struct trace_probe *pos, *tp;
+ struct trace_uprobe *tu;
+ int err = 0;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+
+ tu = container_of(tp, struct trace_uprobe, tp);
+ if (trace_uprobe_filter_add(tu->tp.event->filter, event))
+ return 0;
+
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+ if (err) {
+ uprobe_perf_close(call, event);
+ break;
+ }
+ }
+
+ return err;
+}
+
static bool uprobe_perf_filter(struct uprobe_consumer *uc,
enum uprobe_filter_ctx ctx, struct mm_struct *mm)
{
+ struct trace_uprobe_filter *filter;
struct trace_uprobe *tu;
int ret;
tu = container_of(uc, struct trace_uprobe, consumer);
- read_lock(&tu->filter.rwlock);
- ret = __uprobe_perf_filter(&tu->filter, mm);
- read_unlock(&tu->filter.rwlock);
+ filter = tu->tp.event->filter;
+
+ read_lock(&filter->rwlock);
+ ret = __uprobe_perf_filter(filter, mm);
+ read_unlock(&filter->rwlock);
return ret;
}
@@ -1419,10 +1440,10 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type,
return 0;
case TRACE_REG_PERF_OPEN:
- return uprobe_perf_multi_call(event, data, uprobe_perf_open);
+ return uprobe_perf_open(event, data);
case TRACE_REG_PERF_CLOSE:
- return uprobe_perf_multi_call(event, data, uprobe_perf_close);
+ return uprobe_perf_close(event, data);
#endif
default:
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-22 09:22:16 +0000