aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.kexec148
-rw-r--r--kernel/acct.c8
-rw-r--r--kernel/audit.c5
-rw-r--r--kernel/audit.h2
-rw-r--r--kernel/audit_tree.c6
-rw-r--r--kernel/audit_watch.c9
-rw-r--r--kernel/auditfilter.c19
-rw-r--r--kernel/auditsc.c20
-rw-r--r--kernel/bpf/Kconfig1
-rw-r--r--kernel/bpf/Makefile3
-rw-r--r--kernel/bpf/arraymap.c58
-rw-r--r--kernel/bpf/bpf_iter.c8
-rw-r--r--kernel/bpf/bpf_local_storage.c49
-rw-r--r--kernel/bpf/bpf_lru_list.h1
-rw-r--r--kernel/bpf/bpf_struct_ops.c47
-rw-r--r--kernel/bpf/btf.c64
-rw-r--r--kernel/bpf/cgroup.c66
-rw-r--r--kernel/bpf/cgroup_iter.c65
-rw-r--r--kernel/bpf/core.c249
-rw-r--r--kernel/bpf/cpumap.c126
-rw-r--r--kernel/bpf/cpumask.c26
-rw-r--r--kernel/bpf/devmap.c12
-rw-r--r--kernel/bpf/disasm.c58
-rw-r--r--kernel/bpf/hashtab.c29
-rw-r--r--kernel/bpf/helpers.c203
-rw-r--r--kernel/bpf/inode.c7
-rw-r--r--kernel/bpf/map_iter.c40
-rw-r--r--kernel/bpf/memalloc.c526
-rw-r--r--kernel/bpf/mprog.c452
-rw-r--r--kernel/bpf/offload.c31
-rw-r--r--kernel/bpf/preload/iterators/Makefile2
-rw-r--r--kernel/bpf/preload/iterators/iterators.bpf.c9
-rw-r--r--kernel/bpf/preload/iterators/iterators.lskel-little-endian.h526
-rw-r--r--kernel/bpf/queue_stack_maps.c21
-rw-r--r--kernel/bpf/ringbuf.c29
-rw-r--r--kernel/bpf/stackmap.c2
-rw-r--r--kernel/bpf/syscall.c444
-rw-r--r--kernel/bpf/task_iter.c286
-rw-r--r--kernel/bpf/tcx.c346
-rw-r--r--kernel/bpf/trampoline.c9
-rw-r--r--kernel/bpf/verifier.c2319
-rw-r--r--kernel/capability.c2
-rw-r--r--kernel/cgroup/cgroup-v1.c7
-rw-r--r--kernel/cgroup/cgroup.c192
-rw-r--r--kernel/cgroup/cpuset.c1532
-rw-r--r--kernel/cgroup/legacy_freezer.c8
-rw-r--r--kernel/cgroup/misc.c55
-rw-r--r--kernel/cgroup/namespace.c6
-rw-r--r--kernel/cgroup/rstat.c21
-rw-r--r--kernel/configs/debug.config2
-rw-r--r--kernel/configs/hardening.config98
-rw-r--r--kernel/configs/kvm_guest.config1
-rw-r--r--kernel/configs/nopm.config2
-rw-r--r--kernel/configs/rust.config1
-rw-r--r--kernel/configs/tiny-base.config2
-rw-r--r--kernel/configs/x86_debug.config1
-rw-r--r--kernel/configs/xen.config2
-rw-r--r--kernel/cpu.c213
-rw-r--r--kernel/crash_core.c602
-rw-r--r--kernel/cred.c274
-rw-r--r--kernel/debug/debug_core.c5
-rw-r--r--kernel/debug/kdb/kdb_io.c2
-rw-r--r--kernel/debug/kdb/kdb_main.c7
-rw-r--r--kernel/dma/Kconfig37
-rw-r--r--kernel/dma/contiguous.c103
-rw-r--r--kernel/dma/debug.c22
-rw-r--r--kernel/dma/direct.c79
-rw-r--r--kernel/dma/direct.h1
-rw-r--r--kernel/dma/mapping.c28
-rw-r--r--kernel/dma/pool.c4
-rw-r--r--kernel/dma/swiotlb.c740
-rw-r--r--kernel/entry/common.c3
-rw-r--r--kernel/events/core.c320
-rw-r--r--kernel/events/hw_breakpoint.c28
-rw-r--r--kernel/events/ring_buffer.c11
-rw-r--r--kernel/events/uprobes.c6
-rw-r--r--kernel/exit.c139
-rw-r--r--kernel/exit.h30
-rw-r--r--kernel/fork.c77
-rw-r--r--kernel/freezer.c41
-rw-r--r--kernel/futex/core.c98
-rw-r--r--kernel/futex/futex.h106
-rw-r--r--kernel/futex/pi.c91
-rw-r--r--kernel/futex/requeue.c25
-rw-r--r--kernel/futex/syscalls.c235
-rw-r--r--kernel/futex/waitwake.c129
-rw-r--r--kernel/gcov/Makefile2
-rw-r--r--kernel/gcov/fs.c2
-rw-r--r--kernel/groups.c2
-rw-r--r--kernel/iomem.c13
-rw-r--r--kernel/irq/chip.c11
-rw-r--r--kernel/irq/debugfs.c1
-rw-r--r--kernel/irq/generic-chip.c31
-rw-r--r--kernel/irq/internals.h4
-rw-r--r--kernel/irq/manage.c41
-rw-r--r--kernel/irq/matrix.c6
-rw-r--r--kernel/irq/msi.c12
-rw-r--r--kernel/kallsyms.c27
-rw-r--r--kernel/kallsyms_selftest.c45
-rw-r--r--kernel/kcmp.c4
-rw-r--r--kernel/kcsan/kcsan_test.c9
-rw-r--r--kernel/kcsan/selftest.c9
-rw-r--r--kernel/kexec.c7
-rw-r--r--kernel/kexec_core.c60
-rw-r--r--kernel/kexec_file.c195
-rw-r--r--kernel/kprobes.c95
-rw-r--r--kernel/ksysfs.c15
-rw-r--r--kernel/kthread.c22
-rw-r--r--kernel/livepatch/core.c2
-rw-r--r--kernel/locking/lock_events.c10
-rw-r--r--kernel/locking/lockdep.c39
-rw-r--r--kernel/locking/lockdep_proc.c2
-rw-r--r--kernel/locking/locktorture.c224
-rw-r--r--kernel/locking/mutex.c3
-rw-r--r--kernel/locking/qspinlock_paravirt.h20
-rw-r--r--kernel/locking/rtmutex.c37
-rw-r--r--kernel/locking/rwbase_rt.c8
-rw-r--r--kernel/locking/rwsem.c8
-rw-r--r--kernel/locking/spinlock_rt.c6
-rw-r--r--kernel/locking/test-ww_mutex.c48
-rw-r--r--kernel/locking/ww_rt_mutex.c2
-rw-r--r--kernel/module/Kconfig25
-rw-r--r--kernel/module/decompress.c8
-rw-r--r--kernel/module/main.c16
-rw-r--r--kernel/module/stats.c2
-rw-r--r--kernel/module/sysfs.c2
-rw-r--r--kernel/nsproxy.c4
-rw-r--r--kernel/padata.c8
-rw-r--r--kernel/panic.c25
-rw-r--r--kernel/params.c2
-rw-r--r--kernel/pid.c5
-rw-r--r--kernel/pid_namespace.c12
-rw-r--r--kernel/pid_sysctl.h28
-rw-r--r--kernel/power/hibernate.c18
-rw-r--r--kernel/power/power.h4
-rw-r--r--kernel/power/poweroff.c2
-rw-r--r--kernel/power/qos.c9
-rw-r--r--kernel/power/snapshot.c203
-rw-r--r--kernel/power/swap.c47
-rw-r--r--kernel/printk/Makefile2
-rw-r--r--kernel/printk/internal.h33
-rw-r--r--kernel/printk/nbcon.c1029
-rw-r--r--kernel/printk/printk.c379
-rw-r--r--kernel/printk/printk_ringbuffer.c2
-rw-r--r--kernel/printk/printk_safe.c9
-rw-r--r--kernel/ptrace.c2
-rw-r--r--kernel/rcu/rcu.h29
-rw-r--r--kernel/rcu/rcu_segcblist.c4
-rw-r--r--kernel/rcu/rcuscale.c83
-rw-r--r--kernel/rcu/rcutorture.c44
-rw-r--r--kernel/rcu/refscale.c43
-rw-r--r--kernel/rcu/srcutiny.c1
-rw-r--r--kernel/rcu/srcutree.c74
-rw-r--r--kernel/rcu/tasks.h177
-rw-r--r--kernel/rcu/tiny.c1
-rw-r--r--kernel/rcu/tree.c322
-rw-r--r--kernel/rcu/tree.h4
-rw-r--r--kernel/rcu/tree_exp.h6
-rw-r--r--kernel/rcu/tree_nocb.h23
-rw-r--r--kernel/rcu/tree_stall.h137
-rw-r--r--kernel/rcu/update.c9
-rw-r--r--kernel/reboot.c4
-rw-r--r--kernel/relay.c2
-rw-r--r--kernel/resource.c55
-rw-r--r--kernel/scftorture.c12
-rw-r--r--kernel/sched/build_utility.c1
-rw-r--r--kernel/sched/completion.c26
-rw-r--r--kernel/sched/core.c1239
-rw-r--r--kernel/sched/cpudeadline.c2
-rw-r--r--kernel/sched/cpufreq_schedutil.c69
-rw-r--r--kernel/sched/cpupri.c1
-rw-r--r--kernel/sched/deadline.c73
-rw-r--r--kernel/sched/debug.c56
-rw-r--r--kernel/sched/fair.c1995
-rw-r--r--kernel/sched/features.h25
-rw-r--r--kernel/sched/idle.c5
-rw-r--r--kernel/sched/pelt.c2
-rw-r--r--kernel/sched/psi.c60
-rw-r--r--kernel/sched/rt.c100
-rw-r--r--kernel/sched/sched.h117
-rw-r--r--kernel/sched/stop_task.c4
-rw-r--r--kernel/sched/swait.c8
-rw-r--r--kernel/sched/topology.c230
-rw-r--r--kernel/sched/wait.c65
-rw-r--r--kernel/seccomp.c84
-rw-r--r--kernel/signal.c95
-rw-r--r--kernel/smp.c52
-rw-r--r--kernel/smpboot.c3
-rw-r--r--kernel/softirq.c2
-rw-r--r--kernel/stacktrace.c2
-rw-r--r--kernel/sys.c77
-rw-r--r--kernel/sys_ni.c20
-rw-r--r--kernel/sysctl.c11
-rw-r--r--kernel/task_work.c1
-rw-r--r--kernel/taskstats.c5
-rw-r--r--kernel/time/alarmtimer.c11
-rw-r--r--kernel/time/clocksource.c8
-rw-r--r--kernel/time/hrtimer.c33
-rw-r--r--kernel/time/posix-clock.c36
-rw-r--r--kernel/time/posix-stubs.c45
-rw-r--r--kernel/time/tick-sched.c224
-rw-r--r--kernel/time/time.c169
-rw-r--r--kernel/time/time_test.c2
-rw-r--r--kernel/torture.c104
-rw-r--r--kernel/trace/Makefile1
-rw-r--r--kernel/trace/bpf_trace.c447
-rw-r--r--kernel/trace/fprobe.c36
-rw-r--r--kernel/trace/ftrace.c10
-rw-r--r--kernel/trace/rethook.c113
-rw-r--r--kernel/trace/ring_buffer.c261
-rw-r--r--kernel/trace/synth_event_gen_test.c11
-rw-r--r--kernel/trace/trace.c451
-rw-r--r--kernel/trace/trace.h31
-rw-r--r--kernel/trace/trace_btf.c122
-rw-r--r--kernel/trace/trace_btf.h11
-rw-r--r--kernel/trace/trace_entries.h2
-rw-r--r--kernel/trace/trace_eprobe.c27
-rw-r--r--kernel/trace/trace_events.c383
-rw-r--r--kernel/trace/trace_events_filter.c318
-rw-r--r--kernel/trace/trace_events_hist.c23
-rw-r--r--kernel/trace/trace_events_inject.c3
-rw-r--r--kernel/trace/trace_events_synth.c8
-rw-r--r--kernel/trace/trace_events_user.c109
-rw-r--r--kernel/trace/trace_export.c9
-rw-r--r--kernel/trace/trace_fprobe.c60
-rw-r--r--kernel/trace/trace_hwlat.c2
-rw-r--r--kernel/trace/trace_kprobe.c113
-rw-r--r--kernel/trace/trace_output.c8
-rw-r--r--kernel/trace/trace_probe.c499
-rw-r--r--kernel/trace/trace_probe.h33
-rw-r--r--kernel/trace/trace_seq.c6
-rw-r--r--kernel/trace/trace_syscalls.c16
-rw-r--r--kernel/trace/trace_uprobe.c11
-rw-r--r--kernel/ucount.c5
-rw-r--r--kernel/up.c2
-rw-r--r--kernel/user.c13
-rw-r--r--kernel/user_namespace.c5
-rw-r--r--kernel/watch_queue.c2
-rw-r--r--kernel/watchdog.c18
-rw-r--r--kernel/workqueue.c1673
-rw-r--r--kernel/workqueue_internal.h2
241 files changed, 17730 insertions, 7823 deletions
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
new file mode 100644
index 000000000000..2fd510256604
--- /dev/null
+++ b/kernel/Kconfig.kexec
@@ -0,0 +1,148 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+menu "Kexec and crash features"
+
+config CRASH_CORE
+ bool
+
+config KEXEC_CORE
+ select CRASH_CORE
+ bool
+
+config KEXEC_ELF
+ bool
+
+config HAVE_IMA_KEXEC
+ bool
+
+config KEXEC
+ bool "Enable kexec system call"
+ depends on ARCH_SUPPORTS_KEXEC
+ select KEXEC_CORE
+ help
+ kexec is a system call that implements the ability to shutdown your
+ current kernel, and to start another kernel. It is like a reboot
+ but it is independent of the system firmware. And like a reboot
+ you can start any kernel with it, not just Linux.
+
+ The name comes from the similarity to the exec system call.
+
+ It is an ongoing process to be certain the hardware in a machine
+ is properly shutdown, so do not be surprised if this code does not
+ initially work for you. As of this writing the exact hardware
+ interface is strongly in flux, so no good recommendation can be
+ made.
+
+config KEXEC_FILE
+ bool "Enable kexec file based system call"
+ depends on ARCH_SUPPORTS_KEXEC_FILE
+ select KEXEC_CORE
+ help
+ This is new version of kexec system call. This system call is
+ file based and takes file descriptors as system call argument
+ for kernel and initramfs as opposed to list of segments as
+ accepted by kexec system call.
+
+config KEXEC_SIG
+ bool "Verify kernel signature during kexec_file_load() syscall"
+ depends on ARCH_SUPPORTS_KEXEC_SIG
+ depends on KEXEC_FILE
+ help
+ This option makes the kexec_file_load() syscall check for a valid
+ signature of the kernel image. The image can still be loaded without
+ a valid signature unless you also enable KEXEC_SIG_FORCE, though if
+ there's a signature that we can check, then it must be valid.
+
+ In addition to this option, you need to enable signature
+ verification for the corresponding kernel image type being
+ loaded in order for this to work.
+
+config KEXEC_SIG_FORCE
+ bool "Require a valid signature in kexec_file_load() syscall"
+ depends on ARCH_SUPPORTS_KEXEC_SIG_FORCE
+ depends on KEXEC_SIG
+ help
+ This option makes kernel signature verification mandatory for
+ the kexec_file_load() syscall.
+
+config KEXEC_IMAGE_VERIFY_SIG
+ bool "Enable Image signature verification support (ARM)"
+ default ARCH_DEFAULT_KEXEC_IMAGE_VERIFY_SIG
+ depends on ARCH_SUPPORTS_KEXEC_IMAGE_VERIFY_SIG
+ depends on KEXEC_SIG
+ depends on EFI && SIGNED_PE_FILE_VERIFICATION
+ help
+ Enable Image signature verification support.
+
+config KEXEC_BZIMAGE_VERIFY_SIG
+ bool "Enable bzImage signature verification support"
+ depends on ARCH_SUPPORTS_KEXEC_BZIMAGE_VERIFY_SIG
+ depends on KEXEC_SIG
+ depends on SIGNED_PE_FILE_VERIFICATION
+ select SYSTEM_TRUSTED_KEYRING
+ help
+ Enable bzImage signature verification support.
+
+config KEXEC_JUMP
+ bool "kexec jump"
+ depends on ARCH_SUPPORTS_KEXEC_JUMP
+ depends on KEXEC && HIBERNATION
+ help
+ Jump between original kernel and kexeced kernel and invoke
+ code in physical address mode via KEXEC
+
+config CRASH_DUMP
+ bool "kernel crash dumps"
+ depends on ARCH_SUPPORTS_CRASH_DUMP
+ select CRASH_CORE
+ select KEXEC_CORE
+ help
+ Generate crash dump after being started by kexec.
+ This should be normally only set in special crash dump kernels
+ which are loaded in the main kernel with kexec-tools into
+ a specially reserved region and then later executed after
+ a crash by kdump/kexec. The crash dump kernel must be compiled
+ to a memory address not used by the main kernel or BIOS using
+ PHYSICAL_START, or it must be built as a relocatable image
+ (CONFIG_RELOCATABLE=y).
+ For more details see Documentation/admin-guide/kdump/kdump.rst
+
+ For s390, this option also enables zfcpdump.
+ See also <file:Documentation/arch/s390/zfcpdump.rst>
+
+config CRASH_HOTPLUG
+ bool "Update the crash elfcorehdr on system configuration changes"
+ default y
+ depends on CRASH_DUMP && (HOTPLUG_CPU || MEMORY_HOTPLUG)
+ depends on ARCH_SUPPORTS_CRASH_HOTPLUG
+ help
+ Enable direct update to the crash elfcorehdr (which contains
+ the list of CPUs and memory regions to be dumped upon a crash)
+ in response to hot plug/unplug or online/offline of CPUs or
+ memory. This is a much more advanced approach than userspace
+ attempting that.
+
+ If unsure, say Y.
+
+config CRASH_MAX_MEMORY_RANGES
+ int "Specify the maximum number of memory regions for the elfcorehdr"
+ default 8192
+ depends on CRASH_HOTPLUG
+ help
+ For the kexec_file_load() syscall path, specify the maximum number of
+ memory regions that the elfcorehdr buffer/segment can accommodate.
+ These regions are obtained via walk_system_ram_res(); eg. the
+ 'System RAM' entries in /proc/iomem.
+ This value is combined with NR_CPUS_DEFAULT and multiplied by
+ sizeof(Elf64_Phdr) to determine the final elfcorehdr memory buffer/
+ segment size.
+ The value 8192, for example, covers a (sparsely populated) 1TiB system
+ consisting of 128MiB memblocks, while resulting in an elfcorehdr
+ memory buffer/segment size under 1MiB. This represents a sane choice
+ to accommodate both baremetal and virtual machine configurations.
+
+ For the kexec_load() syscall path, CRASH_MAX_MEMORY_RANGES is part of
+ the computation behind the value provided through the
+ /sys/kernel/crash_elfcorehdr_size attribute.
+
+endmenu
diff --git a/kernel/acct.c b/kernel/acct.c
index 010667ce6080..986c8214dabf 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -246,7 +246,7 @@ static int acct_on(struct filename *pathname)
filp_close(file, NULL);
return PTR_ERR(internal);
}
- err = __mnt_want_write(internal);
+ err = mnt_get_write_access(internal);
if (err) {
mntput(internal);
kfree(acct);
@@ -271,7 +271,7 @@ static int acct_on(struct filename *pathname)
old = xchg(&ns->bacct, &acct->pin);
mutex_unlock(&acct->lock);
pin_kill(old);
- __mnt_drop_write(mnt);
+ mnt_put_write_access(mnt);
mntput(mnt);
return 0;
}
@@ -445,7 +445,7 @@ static void fill_ac(acct_t *ac)
memset(ac, 0, sizeof(acct_t));
ac->ac_version = ACCT_VERSION | ACCT_BYTEORDER;
- strlcpy(ac->ac_comm, current->comm, sizeof(ac->ac_comm));
+ strscpy(ac->ac_comm, current->comm, sizeof(ac->ac_comm));
/* calculate run_time in nsec*/
run_time = ktime_get_ns();
@@ -470,7 +470,7 @@ static void fill_ac(acct_t *ac)
do_div(elapsed, AHZ);
btime = ktime_get_real_seconds() - elapsed;
ac->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX);
-#if ACCT_VERSION==2
+#if ACCT_VERSION == 2
ac->ac_ahz = AHZ;
#endif
diff --git a/kernel/audit.c b/kernel/audit.c
index 9bc0b0301198..16205dd29843 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -53,9 +53,7 @@
#include <net/sock.h>
#include <net/netlink.h>
#include <linux/skbuff.h>
-#ifdef CONFIG_SECURITY
#include <linux/security.h>
-#endif
#include <linux/freezer.h>
#include <linux/pid_namespace.h>
#include <net/netns/generic.h>
@@ -323,7 +321,8 @@ static inline int audit_rate_check(void)
unsigned long now;
int retval = 0;
- if (!audit_rate_limit) return 1;
+ if (!audit_rate_limit)
+ return 1;
spin_lock_irqsave(&lock, flags);
if (++messages < audit_rate_limit) {
diff --git a/kernel/audit.h b/kernel/audit.h
index 94738bce40b2..a60d2840559e 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -334,7 +334,7 @@ static inline int audit_signal_info_syscall(struct task_struct *t)
return 0;
}
-#define audit_filter_inodes(t, c) AUDIT_STATE_DISABLED
+#define audit_filter_inodes(t, c) do { } while (0)
#endif /* CONFIG_AUDITSYSCALL */
extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index e867c17d3f84..1b07e6f12a07 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -34,7 +34,7 @@ struct audit_chunk {
struct list_head list;
struct audit_tree *owner;
unsigned index; /* index; upper bit indicates 'will prune' */
- } owners[];
+ } owners[] __counted_by(count);
};
struct audit_tree_mark {
@@ -87,8 +87,8 @@ static struct task_struct *prune_thread;
* that makes a difference. Some.
*/
-static struct fsnotify_group *audit_tree_group;
-static struct kmem_cache *audit_tree_mark_cachep __read_mostly;
+static struct fsnotify_group *audit_tree_group __ro_after_init;
+static struct kmem_cache *audit_tree_mark_cachep __ro_after_init;
static struct audit_tree *alloc_tree(const char *s)
{
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 65075f1e4ac8..7a98cd176a12 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -527,11 +527,18 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark)
unsigned long ino;
dev_t dev;
- exe_file = get_task_exe_file(tsk);
+ /* only do exe filtering if we are recording @current events/records */
+ if (tsk != current)
+ return 0;
+
+ if (!current->mm)
+ return 0;
+ exe_file = get_mm_exe_file(current->mm);
if (!exe_file)
return 0;
ino = file_inode(exe_file)->i_ino;
dev = file_inode(exe_file)->i_sb->s_dev;
fput(exe_file);
+
return audit_mark_compare(mark, ino, dev);
}
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 42d99896e7a6..8317a37dea0b 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -221,7 +221,7 @@ static int audit_match_signal(struct audit_entry *entry)
entry->rule.mask));
}
- switch(audit_classify_arch(arch->val)) {
+ switch (audit_classify_arch(arch->val)) {
case 0: /* native */
return (audit_match_class_bits(AUDIT_CLASS_SIGNAL,
entry->rule.mask));
@@ -243,7 +243,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *
err = -EINVAL;
listnr = rule->flags & ~AUDIT_FILTER_PREPEND;
- switch(listnr) {
+ switch (listnr) {
default:
goto exit_err;
#ifdef CONFIG_AUDITSYSCALL
@@ -344,7 +344,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
switch (entry->rule.listnr) {
case AUDIT_FILTER_FS:
- switch(f->type) {
+ switch (f->type) {
case AUDIT_FSTYPE:
case AUDIT_FILTERKEY:
break;
@@ -651,7 +651,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
data->fields[i] = f->type;
data->fieldflags[i] = audit_ops[f->op];
- switch(f->type) {
+ switch (f->type) {
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
@@ -694,7 +694,8 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
data->values[i] = f->val;
}
}
- for (i = 0; i < AUDIT_BITMASK_SIZE; i++) data->mask[i] = krule->mask[i];
+ for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
+ data->mask[i] = krule->mask[i];
return data;
}
@@ -717,7 +718,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
a->fields[i].op != b->fields[i].op)
return 1;
- switch(a->fields[i].type) {
+ switch (a->fields[i].type) {
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
@@ -946,7 +947,7 @@ static inline int audit_add_rule(struct audit_entry *entry)
int dont_count = 0;
/* If any of these, don't count towards total */
- switch(entry->rule.listnr) {
+ switch (entry->rule.listnr) {
case AUDIT_FILTER_USER:
case AUDIT_FILTER_EXCLUDE:
case AUDIT_FILTER_FS:
@@ -1029,7 +1030,7 @@ int audit_del_rule(struct audit_entry *entry)
int dont_count = 0;
/* If any of these, don't count towards total */
- switch(entry->rule.listnr) {
+ switch (entry->rule.listnr) {
case AUDIT_FILTER_USER:
case AUDIT_FILTER_EXCLUDE:
case AUDIT_FILTER_FS:
@@ -1083,7 +1084,7 @@ static void audit_list_rules(int seq, struct sk_buff_head *q)
/* This is a blocking read, so use audit_filter_mutex instead of rcu
* iterator to sync with list writers. */
- for (i=0; i<AUDIT_NR_FILTERS; i++) {
+ for (i = 0; i < AUDIT_NR_FILTERS; i++) {
list_for_each_entry(r, &audit_rules_list[i], list) {
struct audit_rule_data *data;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index addeed3df15d..6f0d6fb6523f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -143,6 +143,8 @@ static const struct audit_nfcfgop_tab audit_nfcfgs[] = {
{ AUDIT_NFT_OP_OBJ_RESET, "nft_reset_obj" },
{ AUDIT_NFT_OP_FLOWTABLE_REGISTER, "nft_register_flowtable" },
{ AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, "nft_unregister_flowtable" },
+ { AUDIT_NFT_OP_SETELEM_RESET, "nft_reset_setelem" },
+ { AUDIT_NFT_OP_RULE_RESET, "nft_reset_rule" },
{ AUDIT_NFT_OP_INVALID, "nft_invalid" },
};
@@ -880,7 +882,8 @@ static void audit_filter_syscall(struct task_struct *tsk,
*/
static int audit_filter_inode_name(struct task_struct *tsk,
struct audit_names *n,
- struct audit_context *ctx) {
+ struct audit_context *ctx)
+{
int h = audit_hash_ino((u32)n->ino);
struct list_head *list = &audit_inode_hash[h];
@@ -1064,7 +1067,8 @@ int audit_alloc(struct task_struct *tsk)
return 0;
}
- if (!(context = audit_alloc_context(state))) {
+ context = audit_alloc_context(state);
+ if (!context) {
kfree(key);
audit_log_lost("out of memory in audit_alloc");
return -ENOMEM;
@@ -2124,7 +2128,7 @@ retry:
d = dentry;
rcu_read_lock();
seq = read_seqbegin(&rename_lock);
- for(;;) {
+ for (;;) {
struct inode *inode = d_backing_inode(d);
if (inode && unlikely(inode->i_fsnotify_marks)) {
@@ -2208,7 +2212,7 @@ __audit_reusename(const __user char *uptr)
if (!n->name)
continue;
if (n->name->uptr == uptr) {
- n->name->refcnt++;
+ atomic_inc(&n->name->refcnt);
return n->name;
}
}
@@ -2237,7 +2241,7 @@ void __audit_getname(struct filename *name)
n->name = name;
n->name_len = AUDIT_NAME_FULL;
name->aname = n;
- name->refcnt++;
+ atomic_inc(&name->refcnt);
}
static inline int audit_copy_fcaps(struct audit_names *name,
@@ -2369,7 +2373,7 @@ out_alloc:
return;
if (name) {
n->name = name;
- name->refcnt++;
+ atomic_inc(&name->refcnt);
}
out:
@@ -2456,6 +2460,8 @@ void __audit_inode_child(struct inode *parent,
}
}
+ cond_resched();
+
/* is there a matching child entry? */
list_for_each_entry(n, &context->names_list, list) {
/* can only match entries that have a name */
@@ -2494,7 +2500,7 @@ void __audit_inode_child(struct inode *parent,
if (found_parent) {
found_child->name = found_parent->name;
found_child->name_len = AUDIT_NAME_FULL;
- found_child->name->refcnt++;
+ atomic_inc(&found_child->name->refcnt);
}
}
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig
index 2dfe1079f772..6a906ff93006 100644
--- a/kernel/bpf/Kconfig
+++ b/kernel/bpf/Kconfig
@@ -31,6 +31,7 @@ config BPF_SYSCALL
select TASKS_TRACE_RCU
select BINARY_PRINTF
select NET_SOCK_MSG if NET
+ select NET_XGRESS if NET
select PAGE_POOL if NET
default n
help
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 1d3892168d32..f526b7573e97 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list
obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
-obj-$(CONFIG_BPF_SYSCALL) += disasm.o
+obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o
obj-$(CONFIG_BPF_JIT) += trampoline.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o
obj-$(CONFIG_BPF_JIT) += dispatcher.o
@@ -21,6 +21,7 @@ obj-$(CONFIG_BPF_SYSCALL) += devmap.o
obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
obj-$(CONFIG_BPF_SYSCALL) += offload.o
obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
+obj-$(CONFIG_BPF_SYSCALL) += tcx.o
endif
ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..c85ff9162a5c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1012,11 +1012,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map,
mutex_unlock(&aux->poke_mutex);
}
+void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+ struct bpf_prog *new, struct bpf_prog *old)
+{
+ WARN_ON_ONCE(1);
+}
+
static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
struct bpf_prog *old,
struct bpf_prog *new)
{
- u8 *old_addr, *new_addr, *old_bypass_addr;
struct prog_poke_elem *elem;
struct bpf_array_aux *aux;
@@ -1025,7 +1030,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
list_for_each_entry(elem, &aux->poke_progs, list) {
struct bpf_jit_poke_descriptor *poke;
- int i, ret;
+ int i;
for (i = 0; i < elem->aux->size_poke_tab; i++) {
poke = &elem->aux->poke_tab[i];
@@ -1044,21 +1049,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
* activated, so tail call updates can arrive from here
* while JIT is still finishing its final fixup for
* non-activated poke entries.
- * 3) On program teardown, the program's kallsym entry gets
- * removed out of RCU callback, but we can only untrack
- * from sleepable context, therefore bpf_arch_text_poke()
- * might not see that this is in BPF text section and
- * bails out with -EINVAL. As these are unreachable since
- * RCU grace period already passed, we simply skip them.
- * 4) Also programs reaching refcount of zero while patching
+ * 3) Also programs reaching refcount of zero while patching
* is in progress is okay since we're protected under
* poke_mutex and untrack the programs before the JIT
- * buffer is freed. When we're still in the middle of
- * patching and suddenly kallsyms entry of the program
- * gets evicted, we just skip the rest which is fine due
- * to point 3).
- * 5) Any other error happening below from bpf_arch_text_poke()
- * is a unexpected bug.
+ * buffer is freed.
*/
if (!READ_ONCE(poke->tailcall_target_stable))
continue;
@@ -1068,39 +1062,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
poke->tail_call.key != key)
continue;
- old_bypass_addr = old ? NULL : poke->bypass_addr;
- old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
- new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
-
- if (new) {
- ret = bpf_arch_text_poke(poke->tailcall_target,
- BPF_MOD_JUMP,
- old_addr, new_addr);
- BUG_ON(ret < 0 && ret != -EINVAL);
- if (!old) {
- ret = bpf_arch_text_poke(poke->tailcall_bypass,
- BPF_MOD_JUMP,
- poke->bypass_addr,
- NULL);
- BUG_ON(ret < 0 && ret != -EINVAL);
- }
- } else {
- ret = bpf_arch_text_poke(poke->tailcall_bypass,
- BPF_MOD_JUMP,
- old_bypass_addr,
- poke->bypass_addr);
- BUG_ON(ret < 0 && ret != -EINVAL);
- /* let other CPUs finish the execution of program
- * so that it will not possible to expose them
- * to invalid nop, stack unwind, nop state
- */
- if (!ret)
- synchronize_rcu();
- ret = bpf_arch_text_poke(poke->tailcall_target,
- BPF_MOD_JUMP,
- old_addr, NULL);
- BUG_ON(ret < 0 && ret != -EINVAL);
- }
+ bpf_arch_poke_desc_update(poke, new, old);
}
}
}
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 96856f130cbf..0fae79164187 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -782,9 +782,7 @@ struct bpf_iter_num_kern {
int end; /* final value, exclusive */
} __aligned(8);
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
{
@@ -793,8 +791,6 @@ __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num));
BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num));
- BTF_TYPE_EMIT(struct btf_iter_num);
-
/* start == end is legit, it's an empty range and we'll just get NULL
* on first (and any subsequent) bpf_iter_num_next() call
*/
@@ -845,4 +841,4 @@ __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it)
s->cur = s->end = 0;
}
-__diag_pop();
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b5149cfce7d4..146824cc9689 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -553,7 +553,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
void *value, u64 map_flags, gfp_t gfp_flags)
{
struct bpf_local_storage_data *old_sdata = NULL;
- struct bpf_local_storage_elem *selem = NULL;
+ struct bpf_local_storage_elem *alloc_selem, *selem = NULL;
struct bpf_local_storage *local_storage;
unsigned long flags;
int err;
@@ -607,11 +607,12 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
}
}
- if (gfp_flags == GFP_KERNEL) {
- selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
- if (!selem)
- return ERR_PTR(-ENOMEM);
- }
+ /* A lookup has just been done before and concluded a new selem is
+ * needed. The chance of an unnecessary alloc is unlikely.
+ */
+ alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
+ if (!alloc_selem)
+ return ERR_PTR(-ENOMEM);
raw_spin_lock_irqsave(&local_storage->lock, flags);
@@ -623,13 +624,13 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
* simple.
*/
err = -EAGAIN;
- goto unlock_err;
+ goto unlock;
}
old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
err = check_flags(old_sdata, map_flags);
if (err)
- goto unlock_err;
+ goto unlock;
if (old_sdata && (map_flags & BPF_F_LOCK)) {
copy_map_value_locked(&smap->map, old_sdata->data, value,
@@ -638,23 +639,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
goto unlock;
}
- if (gfp_flags != GFP_KERNEL) {
- /* local_storage->lock is held. Hence, we are sure
- * we can unlink and uncharge the old_sdata successfully
- * later. Hence, instead of charging the new selem now
- * and then uncharge the old selem later (which may cause
- * a potential but unnecessary charge failure), avoid taking
- * a charge at all here (the "!old_sdata" check) and the
- * old_sdata will not be uncharged later during
- * bpf_selem_unlink_storage_nolock().
- */
- selem = bpf_selem_alloc(smap, owner, value, !old_sdata, gfp_flags);
- if (!selem) {
- err = -ENOMEM;
- goto unlock_err;
- }
- }
-
+ alloc_selem = NULL;
/* First, link the new selem to the map */
bpf_selem_link_map(smap, selem);
@@ -665,20 +650,16 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
if (old_sdata) {
bpf_selem_unlink_map(SELEM(old_sdata));
bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
- false, false);
+ true, false);
}
unlock:
raw_spin_unlock_irqrestore(&local_storage->lock, flags);
- return SDATA(selem);
-
-unlock_err:
- raw_spin_unlock_irqrestore(&local_storage->lock, flags);
- if (selem) {
+ if (alloc_selem) {
mem_uncharge(smap, owner, smap->elem_size);
- bpf_selem_free(selem, smap, true);
+ bpf_selem_free(alloc_selem, smap, true);
}
- return ERR_PTR(err);
+ return err ? ERR_PTR(err) : SDATA(selem);
}
static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache)
@@ -779,7 +760,7 @@ void bpf_local_storage_destroy(struct bpf_local_storage *local_storage)
* of the loop will set the free_cgroup_storage to true.
*/
free_storage = bpf_selem_unlink_storage_nolock(
- local_storage, selem, false, true);
+ local_storage, selem, true, true);
}
raw_spin_unlock_irqrestore(&local_storage->lock, flags);
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index 8f3c8b2b4490..cbd8d3720c2b 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -75,6 +75,5 @@ void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
void bpf_lru_destroy(struct bpf_lru *lru);
struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash);
void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node);
-void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node);
#endif
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 116a0ce378ec..db6176fb64dc 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -374,9 +374,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
struct bpf_struct_ops_value *uvalue, *kvalue;
const struct btf_member *member;
const struct btf_type *t = st_ops->type;
- struct bpf_tramp_links *tlinks = NULL;
+ struct bpf_tramp_links *tlinks;
void *udata, *kdata;
- int prog_fd, err = 0;
+ int prog_fd, err;
void *image, *image_end;
u32 i;
@@ -509,9 +509,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
}
if (st_map->map.map_flags & BPF_F_LINK) {
- err = st_ops->validate(kdata);
- if (err)
- goto reset_unlock;
+ err = 0;
+ if (st_ops->validate) {
+ err = st_ops->validate(kdata);
+ if (err)
+ goto reset_unlock;
+ }
set_memory_rox((long)st_map->image, 1);
/* Let bpf_link handle registration & unregistration.
*
@@ -612,7 +615,10 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map)
if (st_map->links)
bpf_struct_ops_map_put_progs(st_map);
bpf_map_area_free(st_map->links);
- bpf_jit_free_exec(st_map->image);
+ if (st_map->image) {
+ bpf_jit_free_exec(st_map->image);
+ bpf_jit_uncharge_modmem(PAGE_SIZE);
+ }
bpf_map_area_free(st_map->uvalue);
bpf_map_area_free(st_map);
}
@@ -654,6 +660,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
struct bpf_struct_ops_map *st_map;
const struct btf_type *t, *vt;
struct bpf_map *map;
+ int ret;
st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id);
if (!st_ops)
@@ -663,9 +670,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
if (attr->value_size != vt->size)
return ERR_PTR(-EINVAL);
- if (attr->map_flags & BPF_F_LINK && (!st_ops->validate || !st_ops->update))
- return ERR_PTR(-EOPNOTSUPP);
-
t = st_ops->type;
st_map_size = sizeof(*st_map) +
@@ -681,12 +685,27 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
st_map->st_ops = st_ops;
map = &st_map->map;
+ ret = bpf_jit_charge_modmem(PAGE_SIZE);
+ if (ret) {
+ __bpf_struct_ops_map_free(map);
+ return ERR_PTR(ret);
+ }
+
+ st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
+ if (!st_map->image) {
+ /* __bpf_struct_ops_map_free() uses st_map->image as flag
+ * for "charged or not". In this case, we need to unchange
+ * here.
+ */
+ bpf_jit_uncharge_modmem(PAGE_SIZE);
+ __bpf_struct_ops_map_free(map);
+ return ERR_PTR(-ENOMEM);
+ }
st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
st_map->links =
bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
NUMA_NO_NODE);
- st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
- if (!st_map->uvalue || !st_map->links || !st_map->image) {
+ if (!st_map->uvalue || !st_map->links) {
__bpf_struct_ops_map_free(map);
return ERR_PTR(-ENOMEM);
}
@@ -815,7 +834,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
struct bpf_struct_ops_map *st_map, *old_st_map;
struct bpf_map *old_map;
struct bpf_struct_ops_link *st_link;
- int err = 0;
+ int err;
st_link = container_of(link, struct bpf_struct_ops_link, link);
st_map = container_of(new_map, struct bpf_struct_ops_map, map);
@@ -823,6 +842,9 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
if (!bpf_struct_ops_valid_to_reg(new_map))
return -EINVAL;
+ if (!st_map->st_ops->update)
+ return -EOPNOTSUPP;
+
mutex_lock(&update_mutex);
old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
@@ -904,4 +926,3 @@ err_out:
kfree(link);
return err;
}
-
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 817204d53372..15d71d2986d3 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -29,6 +29,7 @@
#include <net/netfilter/nf_bpf_link.h>
#include <net/sock.h>
+#include <net/xdp.h>
#include "../tools/lib/bpf/relo_core.h"
/* BTF (BPF Type Format) is the meta data format which describes
@@ -552,7 +553,7 @@ s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind)
return -ENOENT;
}
-static s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p)
+s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p)
{
struct btf *btf;
s32 ret;
@@ -3292,6 +3293,8 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
type = BPF_KPTR_UNREF;
else if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off)))
type = BPF_KPTR_REF;
+ else if (!strcmp("percpu_kptr", __btf_name_by_offset(btf, t->name_off)))
+ type = BPF_KPTR_PERCPU;
else
return -EINVAL;
@@ -3307,10 +3310,10 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
return BTF_FIELD_FOUND;
}
-static const char *btf_find_decl_tag_value(const struct btf *btf,
- const struct btf_type *pt,
- int comp_idx, const char *tag_key)
+const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
+ int comp_idx, const char *tag_key)
{
+ const char *value = NULL;
int i;
for (i = 1; i < btf_nr_types(btf); i++) {
@@ -3324,9 +3327,14 @@ static const char *btf_find_decl_tag_value(const struct btf *btf,
continue;
if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len))
continue;
- return __btf_name_by_offset(btf, t->name_off) + len;
+ /* Prevent duplicate entries for same type */
+ if (value)
+ return ERR_PTR(-EEXIST);
+ value = __btf_name_by_offset(btf, t->name_off) + len;
}
- return NULL;
+ if (!value)
+ return ERR_PTR(-ENOENT);
+ return value;
}
static int
@@ -3344,7 +3352,7 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt,
if (t->size != sz)
return BTF_FIELD_IGNORE;
value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:");
- if (!value_type)
+ if (IS_ERR(value_type))
return -EINVAL;
node_field_name = strstr(value_type, ":");
if (!node_field_name)
@@ -3456,6 +3464,7 @@ static int btf_find_struct_field(const struct btf *btf,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_find_kptr(btf, member_type, off, sz,
idx < info_cnt ? &info[idx] : &tmp);
if (ret < 0)
@@ -3522,6 +3531,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_find_kptr(btf, var_type, off, sz,
idx < info_cnt ? &info[idx] : &tmp);
if (ret < 0)
@@ -3782,6 +3792,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]);
if (ret < 0)
goto end;
@@ -6133,8 +6144,9 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
const char *tname, *mname, *tag_value;
u32 vlen, elem_id, mid;
- *flag = 0;
again:
+ if (btf_type_is_modifier(t))
+ t = btf_type_skip_modifiers(btf, t->type, NULL);
tname = __btf_name_by_offset(btf, t->name_off);
if (!btf_type_is_struct(t)) {
bpf_log(log, "Type '%s' is not a struct\n", tname);
@@ -6142,6 +6154,14 @@ again:
}
vlen = btf_type_vlen(t);
+ if (BTF_INFO_KIND(t->info) == BTF_KIND_UNION && vlen != 1 && !(*flag & PTR_UNTRUSTED))
+ /*
+ * walking unions yields untrusted pointers
+ * with exception of __bpf_md_ptr and other
+ * unions with a single member
+ */
+ *flag |= PTR_UNTRUSTED;
+
if (off + size > t->size) {
/* If the last element is a variable size array, we may
* need to relax the rule.
@@ -6302,15 +6322,6 @@ error:
* of this field or inside of this struct
*/
if (btf_type_is_struct(mtype)) {
- if (BTF_INFO_KIND(mtype->info) == BTF_KIND_UNION &&
- btf_type_vlen(mtype) != 1)
- /*
- * walking unions yields untrusted pointers
- * with exception of __bpf_md_ptr and other
- * unions with a single member
- */
- *flag |= PTR_UNTRUSTED;
-
/* our field must be inside that union or struct */
t = mtype;
@@ -6368,7 +6379,7 @@ error:
* that also allows using an array of int as a scratch
* space. e.g. skb->cb[].
*/
- if (off + size > mtrue_end) {
+ if (off + size > mtrue_end && !(*flag & PTR_UNTRUSTED)) {
bpf_log(log,
"access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n",
mname, mtrue_end, tname, off, size);
@@ -6476,7 +6487,7 @@ bool btf_struct_ids_match(struct bpf_verifier_log *log,
bool strict)
{
const struct btf_type *type;
- enum bpf_type_flag flag;
+ enum bpf_type_flag flag = 0;
int err;
/* Are we already done? */
@@ -6948,7 +6959,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
* (either PTR_TO_CTX or SCALAR_VALUE).
*/
int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
- struct bpf_reg_state *regs)
+ struct bpf_reg_state *regs, bool is_ex_cb)
{
struct bpf_verifier_log *log = &env->log;
struct bpf_prog *prog = env->prog;
@@ -7005,7 +7016,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
tname, nargs, MAX_BPF_FUNC_REG_ARGS);
return -EINVAL;
}
- /* check that function returns int */
+ /* check that function returns int, exception cb also requires this */
t = btf_type_by_id(btf, t->type);
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
@@ -7054,6 +7065,14 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
i, btf_type_str(t), tname);
return -EINVAL;
}
+ /* We have already ensured that the callback returns an integer, just
+ * like all global subprogs. We need to determine it only has a single
+ * scalar argument.
+ */
+ if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) {
+ bpf_log(log, "exception cb only supports single integer argument\n");
+ return -EINVAL;
+ }
return 0;
}
@@ -7831,6 +7850,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
case BPF_PROG_TYPE_SYSCALL:
return BTF_KFUNC_HOOK_SYSCALL;
case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
return BTF_KFUNC_HOOK_CGROUP_SKB;
case BPF_PROG_TYPE_SCHED_ACT:
return BTF_KFUNC_HOOK_SCHED_ACT;
@@ -8500,7 +8520,7 @@ bool btf_nested_type_is_trusted(struct bpf_verifier_log *log,
tname = btf_name_by_offset(btf, walk_type->name_off);
ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix);
- if (ret < 0)
+ if (ret >= sizeof(safe_tname))
return false;
safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info));
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 5b2741aa0d9b..491d20038cbe 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -785,7 +785,8 @@ found:
* to descendants
* @cgrp: The cgroup which descendants to traverse
* @link: A link for which to replace BPF program
- * @type: Type of attach operation
+ * @new_prog: &struct bpf_prog for the target BPF program with its refcnt
+ * incremented
*
* Must be called with cgroup_mutex held.
*/
@@ -1334,7 +1335,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
* @skb: The skb that is being sent or received
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
*
* If no socket is passed, or the socket is not of type INET or INET6,
* this function does nothing and returns 0.
@@ -1424,7 +1425,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
/**
* __cgroup_bpf_run_filter_sk() - Run a program on a sock
* @sk: sock structure to manipulate
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
*
* socket is passed is expected to be of type INET or INET6.
*
@@ -1449,18 +1450,22 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
* provided by user sockaddr
* @sk: sock struct that will use sockaddr
* @uaddr: sockaddr struct provided by user
- * @type: The type of program to be executed
+ * @uaddrlen: Pointer to the size of the sockaddr struct provided by user. It is
+ * read-only for AF_INET[6] uaddr but can be modified for AF_UNIX
+ * uaddr.
+ * @atype: The type of program to be executed
* @t_ctx: Pointer to attach type specific context
* @flags: Pointer to u32 which contains higher bits of BPF program
* return value (OR'ed together).
*
- * socket is expected to be of type INET or INET6.
+ * socket is expected to be of type INET, INET6 or UNIX.
*
* This function will return %-EPERM if an attached program is found and
* returned value != 1 during execution. In all other cases, 0 is returned.
*/
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
struct sockaddr *uaddr,
+ int *uaddrlen,
enum cgroup_bpf_attach_type atype,
void *t_ctx,
u32 *flags)
@@ -1472,21 +1477,31 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
};
struct sockaddr_storage unspec;
struct cgroup *cgrp;
+ int ret;
/* Check socket family since not all sockets represent network
* endpoint (e.g. AF_UNIX).
*/
- if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+ if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 &&
+ sk->sk_family != AF_UNIX)
return 0;
if (!ctx.uaddr) {
memset(&unspec, 0, sizeof(unspec));
ctx.uaddr = (struct sockaddr *)&unspec;
+ ctx.uaddrlen = 0;
+ } else {
+ ctx.uaddrlen = *uaddrlen;
}
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
- return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run,
- 0, flags);
+ ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run,
+ 0, flags);
+
+ if (!ret && uaddr)
+ *uaddrlen = ctx.uaddrlen;
+
+ return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
@@ -1496,7 +1511,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
* @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
* sk with connection information (IP addresses, etc.) May not contain
* cgroup info if it is a req sock.
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
*
* socket passed is expected to be of type INET or INET6.
*
@@ -1670,7 +1685,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
* @ppos: value-result argument: value is position at which read from or write
* to sysctl is happening, result is new position if program overrode it,
* initial value otherwise
- * @type: type of program to be executed
+ * @atype: type of program to be executed
*
* Program is run when sysctl is being accessed, either read or written, and
* can allow or deny such access.
@@ -1785,7 +1800,7 @@ static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx,
}
int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
- int *optname, char __user *optval,
+ int *optname, sockptr_t optval,
int *optlen, char **kernel_optval)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1808,7 +1823,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
ctx.optlen = *optlen;
- if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) {
+ if (copy_from_sockptr(ctx.optval, optval,
+ min(*optlen, max_optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1875,8 +1891,8 @@ out:
}
int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
- int optname, char __user *optval,
- int __user *optlen, int max_optlen,
+ int optname, sockptr_t optval,
+ sockptr_t optlen, int max_optlen,
int retval)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1903,8 +1919,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
* one that kernel returned as well to let
* BPF programs inspect the value.
*/
-
- if (get_user(ctx.optlen, optlen)) {
+ if (copy_from_sockptr(&ctx.optlen, optlen,
+ sizeof(ctx.optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1915,8 +1931,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
}
orig_optlen = ctx.optlen;
- if (copy_from_user(ctx.optval, optval,
- min(ctx.optlen, max_optlen)) != 0) {
+ if (copy_from_sockptr(ctx.optval, optval,
+ min(ctx.optlen, max_optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1930,7 +1946,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
if (ret < 0)
goto out;
- if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) {
+ if (!sockptr_is_null(optval) &&
+ (ctx.optlen > max_optlen || ctx.optlen < 0)) {
if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) {
pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
ctx.optlen, max_optlen);
@@ -1942,11 +1959,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
}
if (ctx.optlen != 0) {
- if (optval && copy_to_user(optval, ctx.optval, ctx.optlen)) {
+ if (!sockptr_is_null(optval) &&
+ copy_to_sockptr(optval, ctx.optval, ctx.optlen)) {
ret = -EFAULT;
goto out;
}
- if (put_user(ctx.optlen, optlen)) {
+ if (copy_to_sockptr(optlen, &ctx.optlen, sizeof(ctx.optlen))) {
ret = -EFAULT;
goto out;
}
@@ -2519,10 +2537,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
return NULL;
default:
return &bpf_get_retval_proto;
@@ -2534,10 +2555,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
return NULL;
default:
return &bpf_set_retval_proto;
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
index 810378f04fbc..f04a468cf6a7 100644
--- a/kernel/bpf/cgroup_iter.c
+++ b/kernel/bpf/cgroup_iter.c
@@ -282,7 +282,7 @@ static struct bpf_iter_reg bpf_cgroup_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__cgroup, cgroup),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &cgroup_iter_seq_info,
};
@@ -294,3 +294,66 @@ static int __init bpf_cgroup_iter_init(void)
}
late_initcall(bpf_cgroup_iter_init);
+
+struct bpf_iter_css {
+ __u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_kern {
+ struct cgroup_subsys_state *start;
+ struct cgroup_subsys_state *pos;
+ unsigned int flags;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
+ struct cgroup_subsys_state *start, unsigned int flags)
+{
+ struct bpf_iter_css_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css));
+
+ kit->start = NULL;
+ switch (flags) {
+ case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+ case BPF_CGROUP_ITER_DESCENDANTS_POST:
+ case BPF_CGROUP_ITER_ANCESTORS_UP:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ kit->start = start;
+ kit->pos = NULL;
+ kit->flags = flags;
+ return 0;
+}
+
+__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it)
+{
+ struct bpf_iter_css_kern *kit = (void *)it;
+
+ if (!kit->start)
+ return NULL;
+
+ switch (kit->flags) {
+ case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+ kit->pos = css_next_descendant_pre(kit->pos, kit->start);
+ break;
+ case BPF_CGROUP_ITER_DESCENDANTS_POST:
+ kit->pos = css_next_descendant_post(kit->pos, kit->start);
+ break;
+ case BPF_CGROUP_ITER_ANCESTORS_UP:
+ kit->pos = kit->pos ? kit->pos->parent : kit->start;
+ }
+
+ return kit->pos;
+}
+
+__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it)
+{
+}
+
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index dc85240a0134..fe254ae035fe 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -61,6 +61,7 @@
#define AX regs[BPF_REG_AX]
#define ARG1 regs[BPF_REG_ARG1]
#define CTX regs[BPF_REG_CTX]
+#define OFF insn->off
#define IMM insn->imm
struct bpf_mem_alloc bpf_global_ma;
@@ -211,7 +212,7 @@ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
const struct bpf_line_info *linfo;
void **jited_linfo;
- if (!prog->aux->jited_linfo)
+ if (!prog->aux->jited_linfo || prog->aux->func_idx > prog->aux->func_cnt)
/* Userspace did not provide linfo */
return;
@@ -370,9 +371,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
s32 end_new, s32 curr, const bool probe_pass)
{
- const s32 off_min = S16_MIN, off_max = S16_MAX;
+ s64 off_min, off_max, off;
s32 delta = end_new - end_old;
- s32 off = insn->off;
+
+ if (insn->code == (BPF_JMP32 | BPF_JA)) {
+ off = insn->imm;
+ off_min = S32_MIN;
+ off_max = S32_MAX;
+ } else {
+ off = insn->off;
+ off_min = S16_MIN;
+ off_max = S16_MAX;
+ }
if (curr < pos && curr + off + 1 >= end_old)
off += delta;
@@ -380,8 +390,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
off -= delta;
if (off < off_min || off > off_max)
return -ERANGE;
- if (!probe_pass)
- insn->off = off;
+ if (!probe_pass) {
+ if (insn->code == (BPF_JMP32 | BPF_JA))
+ insn->imm = off;
+ else
+ insn->off = off;
+ }
return 0;
}
@@ -529,7 +543,7 @@ static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
{
int i;
- for (i = 0; i < fp->aux->func_cnt; i++)
+ for (i = 0; i < fp->aux->real_func_cnt; i++)
bpf_prog_kallsyms_del(fp->aux->func[i]);
}
@@ -579,7 +593,7 @@ bpf_prog_ksym_set_name(struct bpf_prog *prog)
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
/* prog->aux->name will be ignored if full btf name is available */
- if (prog->aux->func_info_cnt) {
+ if (prog->aux->func_info_cnt && prog->aux->func_idx < prog->aux->func_info_cnt) {
type = btf_type_by_id(prog->aux->btf,
prog->aux->func_info[prog->aux->func_idx].type_id);
func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
@@ -613,7 +627,11 @@ static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
if (val < ksym->start)
return -1;
- if (val >= ksym->end)
+ /* Ensure that we detect return addresses as part of the program, when
+ * the final instruction is a call for a program part of the stack
+ * trace. Therefore, do val > ksym->end instead of val >= ksym->end.
+ */
+ if (val > ksym->end)
return 1;
return 0;
@@ -723,7 +741,7 @@ bool is_bpf_text_address(unsigned long addr)
return ret;
}
-static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
{
struct bpf_ksym *ksym = bpf_ksym_find(addr);
@@ -860,7 +878,7 @@ static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
GFP_KERNEL);
if (!pack)
return NULL;
- pack->ptr = module_alloc(BPF_PROG_PACK_SIZE);
+ pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE);
if (!pack->ptr) {
kfree(pack);
return NULL;
@@ -884,7 +902,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
mutex_lock(&pack_mutex);
if (size > BPF_PROG_PACK_SIZE) {
size = round_up(size, PAGE_SIZE);
- ptr = module_alloc(size);
+ ptr = bpf_jit_alloc_exec(size);
if (ptr) {
bpf_fill_ill_insns(ptr, size);
set_vm_flush_reset_perms(ptr);
@@ -922,7 +940,7 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
mutex_lock(&pack_mutex);
if (hdr->size > BPF_PROG_PACK_SIZE) {
- module_memfree(hdr);
+ bpf_jit_free_exec(hdr);
goto out;
}
@@ -946,7 +964,7 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0,
BPF_PROG_CHUNK_COUNT, 0) == 0) {
list_del(&pack->list);
- module_memfree(pack->ptr);
+ bpf_jit_free_exec(pack->ptr);
kfree(pack);
}
out:
@@ -1198,7 +1216,7 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
if (!extra_pass)
addr = NULL;
else if (prog->aux->func &&
- off >= 0 && off < prog->aux->func_cnt)
+ off >= 0 && off < prog->aux->real_func_cnt)
addr = (u8 *)prog->aux->func[off]->bpf_func;
else
return -EINVAL;
@@ -1271,7 +1289,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
case BPF_ALU | BPF_MOD | BPF_K:
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
- *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
+ *to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off);
break;
case BPF_ALU64 | BPF_ADD | BPF_K:
@@ -1285,7 +1303,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
case BPF_ALU64 | BPF_MOD | BPF_K:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
- *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
+ *to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off);
break;
case BPF_JMP | BPF_JEQ | BPF_K:
@@ -1523,6 +1541,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(ALU64, DIV, X), \
INSN_3(ALU64, MOD, X), \
INSN_2(ALU64, NEG), \
+ INSN_3(ALU64, END, TO_LE), \
/* Immediate based. */ \
INSN_3(ALU64, ADD, K), \
INSN_3(ALU64, SUB, K), \
@@ -1591,6 +1610,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(JMP, JSLE, K), \
INSN_3(JMP, JSET, K), \
INSN_2(JMP, JA), \
+ INSN_2(JMP32, JA), \
/* Store instructions. */ \
/* Register based. */ \
INSN_3(STX, MEM, B), \
@@ -1610,6 +1630,9 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(LDX, MEM, H), \
INSN_3(LDX, MEM, W), \
INSN_3(LDX, MEM, DW), \
+ INSN_3(LDX, MEMSX, B), \
+ INSN_3(LDX, MEMSX, H), \
+ INSN_3(LDX, MEMSX, W), \
/* Immediate based. */ \
INSN_3(LD, IMM, DW)
@@ -1635,12 +1658,6 @@ bool bpf_opcode_in_insntable(u8 code)
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
-u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
-{
- memset(dst, 0, size);
- return -EFAULT;
-}
-
/**
* ___bpf_prog_run - run eBPF program on a given context
* @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1666,6 +1683,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
[BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W,
};
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
@@ -1733,13 +1753,36 @@ select_insn:
DST = -DST;
CONT;
ALU_MOV_X:
- DST = (u32) SRC;
+ switch (OFF) {
+ case 0:
+ DST = (u32) SRC;
+ break;
+ case 8:
+ DST = (u32)(s8) SRC;
+ break;
+ case 16:
+ DST = (u32)(s16) SRC;
+ break;
+ }
CONT;
ALU_MOV_K:
DST = (u32) IMM;
CONT;
ALU64_MOV_X:
- DST = SRC;
+ switch (OFF) {
+ case 0:
+ DST = SRC;
+ break;
+ case 8:
+ DST = (s8) SRC;
+ break;
+ case 16:
+ DST = (s16) SRC;
+ break;
+ case 32:
+ DST = (s32) SRC;
+ break;
+ }
CONT;
ALU64_MOV_K:
DST = IMM;
@@ -1761,36 +1804,114 @@ select_insn:
(*(s64 *) &DST) >>= IMM;
CONT;
ALU64_MOD_X:
- div64_u64_rem(DST, SRC, &AX);
- DST = AX;
+ switch (OFF) {
+ case 0:
+ div64_u64_rem(DST, SRC, &AX);
+ DST = AX;
+ break;
+ case 1:
+ AX = div64_s64(DST, SRC);
+ DST = DST - AX * SRC;
+ break;
+ }
CONT;
ALU_MOD_X:
- AX = (u32) DST;
- DST = do_div(AX, (u32) SRC);
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ DST = do_div(AX, (u32) SRC);
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ AX = do_div(AX, abs((s32)SRC));
+ if ((s32)DST < 0)
+ DST = (u32)-AX;
+ else
+ DST = (u32)AX;
+ break;
+ }
CONT;
ALU64_MOD_K:
- div64_u64_rem(DST, IMM, &AX);
- DST = AX;
+ switch (OFF) {
+ case 0:
+ div64_u64_rem(DST, IMM, &AX);
+ DST = AX;
+ break;
+ case 1:
+ AX = div64_s64(DST, IMM);
+ DST = DST - AX * IMM;
+ break;
+ }
CONT;
ALU_MOD_K:
- AX = (u32) DST;
- DST = do_div(AX, (u32) IMM);
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ DST = do_div(AX, (u32) IMM);
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ AX = do_div(AX, abs((s32)IMM));
+ if ((s32)DST < 0)
+ DST = (u32)-AX;
+ else
+ DST = (u32)AX;
+ break;
+ }
CONT;
ALU64_DIV_X:
- DST = div64_u64(DST, SRC);
+ switch (OFF) {
+ case 0:
+ DST = div64_u64(DST, SRC);
+ break;
+ case 1:
+ DST = div64_s64(DST, SRC);
+ break;
+ }
CONT;
ALU_DIV_X:
- AX = (u32) DST;
- do_div(AX, (u32) SRC);
- DST = (u32) AX;
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ do_div(AX, (u32) SRC);
+ DST = (u32) AX;
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ do_div(AX, abs((s32)SRC));
+ if (((s32)DST < 0) == ((s32)SRC < 0))
+ DST = (u32)AX;
+ else
+ DST = (u32)-AX;
+ break;
+ }
CONT;
ALU64_DIV_K:
- DST = div64_u64(DST, IMM);
+ switch (OFF) {
+ case 0:
+ DST = div64_u64(DST, IMM);
+ break;
+ case 1:
+ DST = div64_s64(DST, IMM);
+ break;
+ }
CONT;
ALU_DIV_K:
- AX = (u32) DST;
- do_div(AX, (u32) IMM);
- DST = (u32) AX;
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ do_div(AX, (u32) IMM);
+ DST = (u32) AX;
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ do_div(AX, abs((s32)IMM));
+ if (((s32)DST < 0) == ((s32)IMM < 0))
+ DST = (u32)AX;
+ else
+ DST = (u32)-AX;
+ break;
+ }
CONT;
ALU_END_TO_BE:
switch (IMM) {
@@ -1818,6 +1939,19 @@ select_insn:
break;
}
CONT;
+ ALU64_END_TO_LE:
+ switch (IMM) {
+ case 16:
+ DST = (__force u16) __swab16(DST);
+ break;
+ case 32:
+ DST = (__force u32) __swab32(DST);
+ break;
+ case 64:
+ DST = (__force u64) __swab64(DST);
+ break;
+ }
+ CONT;
/* CALL */
JMP_CALL:
@@ -1867,6 +2001,9 @@ out:
JMP_JA:
insn += insn->off;
CONT;
+ JMP32_JA:
+ insn += insn->imm;
+ CONT;
JMP_EXIT:
return BPF_R0;
/* JMP */
@@ -1931,8 +2068,8 @@ out:
DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
CONT; \
LDX_PROBE_MEM_##SIZEOP: \
- bpf_probe_read_kernel(&DST, sizeof(SIZE), \
- (const void *)(long) (SRC + insn->off)); \
+ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \
+ (const void *)(long) (SRC + insn->off)); \
DST = *((SIZE *)&DST); \
CONT;
@@ -1942,6 +2079,21 @@ out:
LDST(DW, u64)
#undef LDST
+#define LDSX(SIZEOP, SIZE) \
+ LDX_MEMSX_##SIZEOP: \
+ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
+ CONT; \
+ LDX_PROBE_MEMSX_##SIZEOP: \
+ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \
+ (const void *)(long) (SRC + insn->off)); \
+ DST = *((SIZE *)&DST); \
+ CONT;
+
+ LDSX(B, s8)
+ LDSX(H, s16)
+ LDSX(W, s32)
+#undef LDSX
+
#define ATOMIC_ALU_OP(BOP, KOP) \
case BOP: \
if (BPF_SIZE(insn->code) == BPF_W) \
@@ -2577,7 +2729,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
#endif
if (aux->dst_trampoline)
bpf_trampoline_put(aux->dst_trampoline);
- for (i = 0; i < aux->func_cnt; i++) {
+ for (i = 0; i < aux->real_func_cnt; i++) {
/* We can just unlink the subprog poke descriptor table as
* it was originally linked to the main program and is also
* released along with it.
@@ -2585,7 +2737,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
aux->func[i]->aux->poke_tab = NULL;
bpf_jit_free(aux->func[i]);
}
- if (aux->func_cnt) {
+ if (aux->real_func_cnt) {
kfree(aux->func);
bpf_prog_unlock_free(aux->prog);
} else {
@@ -2770,6 +2922,15 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len)
return -ENOTSUPP;
}
+bool __weak bpf_jit_supports_exceptions(void)
+{
+ return false;
+}
+
+void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
+{
+}
+
#ifdef CONFIG_BPF_SYSCALL
static int __init bpf_global_ma_init(void)
{
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 286ab3db0fde..8a0bb80fe48a 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -61,8 +61,6 @@ struct bpf_cpu_map_entry {
/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
struct xdp_bulk_queue __percpu *bulkq;
- struct bpf_cpu_map *cmap;
-
/* Queue with potential multi-producers, and single-consumer kthread */
struct ptr_ring *queue;
struct task_struct *kthread;
@@ -70,11 +68,8 @@ struct bpf_cpu_map_entry {
struct bpf_cpumap_val value;
struct bpf_prog *prog;
- atomic_t refcnt; /* Control when this struct can be free'ed */
- struct rcu_head rcu;
-
- struct work_struct kthread_stop_wq;
struct completion kthread_running;
+ struct rcu_work free_work;
};
struct bpf_cpu_map {
@@ -119,11 +114,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
return &cmap->map;
}
-static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
-{
- atomic_inc(&rcpu->refcnt);
-}
-
static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
{
/* The tear-down procedure should have made sure that queue is
@@ -144,35 +134,6 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
}
}
-static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
-{
- if (atomic_dec_and_test(&rcpu->refcnt)) {
- if (rcpu->prog)
- bpf_prog_put(rcpu->prog);
- /* The queue should be empty at this point */
- __cpu_map_ring_cleanup(rcpu->queue);
- ptr_ring_cleanup(rcpu->queue, NULL);
- kfree(rcpu->queue);
- kfree(rcpu);
- }
-}
-
-/* called from workqueue, to workaround syscall using preempt_disable */
-static void cpu_map_kthread_stop(struct work_struct *work)
-{
- struct bpf_cpu_map_entry *rcpu;
-
- rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
-
- /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
- * as it waits until all in-flight call_rcu() callbacks complete.
- */
- rcu_barrier();
-
- /* kthread_stop will wake_up_process and wait for it to complete */
- kthread_stop(rcpu->kthread);
-}
-
static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
struct list_head *listp,
struct xdp_cpumap_stats *stats)
@@ -397,7 +358,6 @@ static int cpu_map_kthread_run(void *data)
}
__set_current_state(TASK_RUNNING);
- put_cpu_map_entry(rcpu);
return 0;
}
@@ -474,9 +434,6 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
if (IS_ERR(rcpu->kthread))
goto free_prog;
- get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
- get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
-
/* Make sure kthread runs on a single CPU */
kthread_bind(rcpu->kthread, cpu);
wake_up_process(rcpu->kthread);
@@ -503,40 +460,40 @@ free_rcu:
return NULL;
}
-static void __cpu_map_entry_free(struct rcu_head *rcu)
+static void __cpu_map_entry_free(struct work_struct *work)
{
struct bpf_cpu_map_entry *rcpu;
/* This cpu_map_entry have been disconnected from map and one
- * RCU grace-period have elapsed. Thus, XDP cannot queue any
+ * RCU grace-period have elapsed. Thus, XDP cannot queue any
* new packets and cannot change/set flush_needed that can
* find this entry.
*/
- rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+ rcpu = container_of(to_rcu_work(work), struct bpf_cpu_map_entry, free_work);
+ /* kthread_stop will wake_up_process and wait for it to complete.
+ * cpu_map_kthread_run() makes sure the pointer ring is empty
+ * before exiting.
+ */
+ kthread_stop(rcpu->kthread);
+
+ if (rcpu->prog)
+ bpf_prog_put(rcpu->prog);
+ /* The queue should be empty at this point */
+ __cpu_map_ring_cleanup(rcpu->queue);
+ ptr_ring_cleanup(rcpu->queue, NULL);
+ kfree(rcpu->queue);
free_percpu(rcpu->bulkq);
- /* Cannot kthread_stop() here, last put free rcpu resources */
- put_cpu_map_entry(rcpu);
+ kfree(rcpu);
}
-/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
- * ensure any driver rcu critical sections have completed, but this
- * does not guarantee a flush has happened yet. Because driver side
- * rcu_read_lock/unlock only protects the running XDP program. The
- * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
- * pending flush op doesn't fail.
- *
- * The bpf_cpu_map_entry is still used by the kthread, and there can
- * still be pending packets (in queue and percpu bulkq). A refcnt
- * makes sure to last user (kthread_stop vs. call_rcu) free memory
- * resources.
- *
- * The rcu callback __cpu_map_entry_free flush remaining packets in
- * percpu bulkq to queue. Due to caller map_delete_elem() disable
- * preemption, cannot call kthread_stop() to make sure queue is empty.
- * Instead a work_queue is started for stopping kthread,
- * cpu_map_kthread_stop, which waits for an RCU grace period before
- * stopping kthread, emptying the queue.
+/* After the xchg of the bpf_cpu_map_entry pointer, we need to make sure the old
+ * entry is no longer in use before freeing. We use queue_rcu_work() to call
+ * __cpu_map_entry_free() in a separate workqueue after waiting for an RCU grace
+ * period. This means that (a) all pending enqueue and flush operations have
+ * completed (because of the RCU callback), and (b) we are in a workqueue
+ * context where we can stop the kthread and wait for it to exit before freeing
+ * everything.
*/
static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
@@ -545,9 +502,8 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu)));
if (old_rcpu) {
- call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
- INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
- schedule_work(&old_rcpu->kthread_stop_wq);
+ INIT_RCU_WORK(&old_rcpu->free_work, __cpu_map_entry_free);
+ queue_rcu_work(system_wq, &old_rcpu->free_work);
}
}
@@ -559,7 +515,7 @@ static long cpu_map_delete_elem(struct bpf_map *map, void *key)
if (key_cpu >= map->max_entries)
return -EINVAL;
- /* notice caller map_delete_elem() use preempt_disable() */
+ /* notice caller map_delete_elem() uses rcu_read_lock() */
__cpu_map_entry_replace(cmap, key_cpu, NULL);
return 0;
}
@@ -595,7 +551,6 @@ static long cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu);
if (!rcpu)
return -ENOMEM;
- rcpu->cmap = cmap;
}
rcu_read_lock();
__cpu_map_entry_replace(cmap, key_cpu, rcpu);
@@ -611,16 +566,15 @@ static void cpu_map_free(struct bpf_map *map)
/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the bpf programs (can be more than one that used this map) were
* disconnected from events. Wait for outstanding critical sections in
- * these programs to complete. The rcu critical section only guarantees
- * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
- * It does __not__ ensure pending flush operations (if any) are
- * complete.
+ * these programs to complete. synchronize_rcu() below not only
+ * guarantees no further "XDP/bpf-side" reads against
+ * bpf_cpu_map->cpu_map, but also ensure pending flush operations
+ * (if any) are completed.
*/
-
synchronize_rcu();
- /* For cpu_map the remote CPUs can still be using the entries
- * (struct bpf_cpu_map_entry).
+ /* The only possible user of bpf_cpu_map_entry is
+ * cpu_map_kthread_run().
*/
for (i = 0; i < cmap->map.max_entries; i++) {
struct bpf_cpu_map_entry *rcpu;
@@ -629,8 +583,8 @@ static void cpu_map_free(struct bpf_map *map)
if (!rcpu)
continue;
- /* bq flush and cleanup happens after RCU grace-period */
- __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+ /* Stop kthread and cleanup entry directly */
+ __cpu_map_entry_free(&rcpu->free_work.work);
}
bpf_map_area_free(cmap->cpu_map);
bpf_map_area_free(cmap);
@@ -810,6 +764,16 @@ void __cpu_map_flush(void)
}
}
+#ifdef CONFIG_DEBUG_NET
+bool cpu_map_check_flush(void)
+{
+ if (list_empty(this_cpu_ptr(&cpu_map_flush_list)))
+ return false;
+ __cpu_map_flush();
+ return true;
+}
+#endif
+
static int __init cpu_map_init(void)
{
int cpu;
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 938a60ff4295..e01c741e54e7 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -9,7 +9,6 @@
/**
* struct bpf_cpumask - refcounted BPF cpumask wrapper structure
* @cpumask: The actual cpumask embedded in the struct.
- * @rcu: The RCU head used to free the cpumask with RCU safety.
* @usage: Object reference counter. When the refcount goes to 0, the
* memory is released back to the BPF allocator, which provides
* RCU safety.
@@ -25,7 +24,6 @@
*/
struct bpf_cpumask {
cpumask_t cpumask;
- struct rcu_head rcu;
refcount_t usage;
};
@@ -36,9 +34,7 @@ static bool cpu_valid(u32 cpu)
return cpu < nr_cpu_ids;
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global kfuncs as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
/**
* bpf_cpumask_create() - Create a mutable BPF cpumask.
@@ -82,16 +78,6 @@ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask)
return cpumask;
}
-static void cpumask_free_cb(struct rcu_head *head)
-{
- struct bpf_cpumask *cpumask;
-
- cpumask = container_of(head, struct bpf_cpumask, rcu);
- migrate_disable();
- bpf_mem_cache_free(&bpf_cpumask_ma, cpumask);
- migrate_enable();
-}
-
/**
* bpf_cpumask_release() - Release a previously acquired BPF cpumask.
* @cpumask: The cpumask being released.
@@ -102,8 +88,12 @@ static void cpumask_free_cb(struct rcu_head *head)
*/
__bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask)
{
- if (refcount_dec_and_test(&cpumask->usage))
- call_rcu(&cpumask->rcu, cpumask_free_cb);
+ if (!refcount_dec_and_test(&cpumask->usage))
+ return;
+
+ migrate_disable();
+ bpf_mem_cache_free_rcu(&bpf_cpumask_ma, cpumask);
+ migrate_enable();
}
/**
@@ -415,7 +405,7 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
return cpumask_any_and_distribute(src1, src2);
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(cpumask_kfunc_btf_ids)
BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 49cc0b5671c6..a936c704d4e7 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -65,7 +65,6 @@ struct xdp_dev_bulk_queue {
struct bpf_dtab_netdev {
struct net_device *dev; /* must be first member, due to tracepoint */
struct hlist_node index_hlist;
- struct bpf_dtab *dtab;
struct bpf_prog *xdp_prog;
struct rcu_head rcu;
unsigned int idx;
@@ -419,6 +418,16 @@ void __dev_flush(void)
}
}
+#ifdef CONFIG_DEBUG_NET
+bool dev_check_flush(void)
+{
+ if (list_empty(this_cpu_ptr(&dev_flush_list)))
+ return false;
+ __dev_flush();
+ return true;
+}
+#endif
+
/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
* by local_bh_disable() (from XDP calls inside NAPI). The
* rcu_read_lock_bh_held() below makes lockdep accept both.
@@ -874,7 +883,6 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
}
dev->idx = idx;
- dev->dtab = dtab;
if (prog) {
dev->xdp_prog = prog;
dev->val.bpf_prog.id = prog->aux->id;
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 7b4afb7d96db..49940c26a227 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -87,6 +87,17 @@ const char *const bpf_alu_string[16] = {
[BPF_END >> 4] = "endian",
};
+static const char *const bpf_alu_sign_string[16] = {
+ [BPF_DIV >> 4] = "s/=",
+ [BPF_MOD >> 4] = "s%=",
+};
+
+static const char *const bpf_movsx_string[4] = {
+ [0] = "(s8)",
+ [1] = "(s16)",
+ [3] = "(s32)",
+};
+
static const char *const bpf_atomic_alu_string[16] = {
[BPF_ADD >> 4] = "add",
[BPF_AND >> 4] = "and",
@@ -101,6 +112,12 @@ static const char *const bpf_ldst_string[] = {
[BPF_DW >> 3] = "u64",
};
+static const char *const bpf_ldsx_string[] = {
+ [BPF_W >> 3] = "s32",
+ [BPF_H >> 3] = "s16",
+ [BPF_B >> 3] = "s8",
+};
+
static const char *const bpf_jmp_string[16] = {
[BPF_JA >> 4] = "jmp",
[BPF_JEQ >> 4] = "==",
@@ -128,6 +145,27 @@ static void print_bpf_end_insn(bpf_insn_print_t verbose,
insn->imm, insn->dst_reg);
}
+static void print_bpf_bswap_insn(bpf_insn_print_t verbose,
+ void *private_data,
+ const struct bpf_insn *insn)
+{
+ verbose(private_data, "(%02x) r%d = bswap%d r%d\n",
+ insn->code, insn->dst_reg,
+ insn->imm, insn->dst_reg);
+}
+
+static bool is_sdiv_smod(const struct bpf_insn *insn)
+{
+ return (BPF_OP(insn->code) == BPF_DIV || BPF_OP(insn->code) == BPF_MOD) &&
+ insn->off == 1;
+}
+
+static bool is_movsx(const struct bpf_insn *insn)
+{
+ return BPF_OP(insn->code) == BPF_MOV &&
+ (insn->off == 8 || insn->off == 16 || insn->off == 32);
+}
+
void print_bpf_insn(const struct bpf_insn_cbs *cbs,
const struct bpf_insn *insn,
bool allow_ptr_leaks)
@@ -138,7 +176,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
if (class == BPF_ALU || class == BPF_ALU64) {
if (BPF_OP(insn->code) == BPF_END) {
if (class == BPF_ALU64)
- verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code);
+ print_bpf_bswap_insn(verbose, cbs->private_data, insn);
else
print_bpf_end_insn(verbose, cbs->private_data, insn);
} else if (BPF_OP(insn->code) == BPF_NEG) {
@@ -147,17 +185,20 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
insn->dst_reg, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg);
} else if (BPF_SRC(insn->code) == BPF_X) {
- verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n",
+ verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n",
insn->code, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg,
- bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4]
+ : bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_movsx(insn) ? bpf_movsx_string[(insn->off >> 3) - 1] : "",
class == BPF_ALU ? 'w' : 'r',
insn->src_reg);
} else {
verbose(cbs->private_data, "(%02x) %c%d %s %d\n",
insn->code, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg,
- bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4]
+ : bpf_alu_string[BPF_OP(insn->code) >> 4],
insn->imm);
}
} else if (class == BPF_STX) {
@@ -218,13 +259,15 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
}
} else if (class == BPF_LDX) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
+ if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) {
verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);
return;
}
verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n",
insn->code, insn->dst_reg,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ BPF_MODE(insn->code) == BPF_MEM ?
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3] :
+ bpf_ldsx_string[BPF_SIZE(insn->code) >> 3],
insn->src_reg, insn->off);
} else if (class == BPF_LD) {
if (BPF_MODE(insn->code) == BPF_ABS) {
@@ -279,6 +322,9 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
} else if (insn->code == (BPF_JMP | BPF_JA)) {
verbose(cbs->private_data, "(%02x) goto pc%+d\n",
insn->code, insn->off);
+ } else if (insn->code == (BPF_JMP32 | BPF_JA)) {
+ verbose(cbs->private_data, "(%02x) gotol pc%+d\n",
+ insn->code, insn->imm);
} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
verbose(cbs->private_data, "(%02x) exit\n", insn->code);
} else if (BPF_SRC(insn->code) == BPF_X) {
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 56d3da7d0bc6..fd8d4b0addfc 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -155,13 +155,15 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab,
hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
preempt_disable();
+ local_irq_save(flags);
if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
__this_cpu_dec(*(htab->map_locked[hash]));
+ local_irq_restore(flags);
preempt_enable();
return -EBUSY;
}
- raw_spin_lock_irqsave(&b->raw_lock, flags);
+ raw_spin_lock(&b->raw_lock);
*pflags = flags;
return 0;
@@ -172,8 +174,9 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab,
unsigned long flags)
{
hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
- raw_spin_unlock_irqrestore(&b->raw_lock, flags);
+ raw_spin_unlock(&b->raw_lock);
__this_cpu_dec(*(htab->map_locked[hash]));
+ local_irq_restore(flags);
preempt_enable();
}
@@ -302,6 +305,7 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
struct htab_elem *l;
if (node) {
+ bpf_map_inc_elem_count(&htab->map);
l = container_of(node, struct htab_elem, lru_node);
memcpy(l->key, key, htab->map.key_size);
return l;
@@ -510,12 +514,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
htab->n_buckets > U32_MAX / sizeof(struct bucket))
goto free_htab;
+ err = bpf_map_init_elem_count(&htab->map);
+ if (err)
+ goto free_htab;
+
err = -ENOMEM;
htab->buckets = bpf_map_area_alloc(htab->n_buckets *
sizeof(struct bucket),
htab->map.numa_node);
if (!htab->buckets)
- goto free_htab;
+ goto free_elem_count;
for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) {
htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map,
@@ -593,6 +601,8 @@ free_map_locked:
bpf_map_area_free(htab->buckets);
bpf_mem_alloc_destroy(&htab->pcpu_ma);
bpf_mem_alloc_destroy(&htab->ma);
+free_elem_count:
+ bpf_map_free_elem_count(&htab->map);
free_htab:
lockdep_unregister_key(&htab->lockdep_key);
bpf_map_area_free(htab);
@@ -804,6 +814,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
if (l == tgt_l) {
hlist_nulls_del_rcu(&l->hash_node);
check_and_free_fields(htab, l);
+ bpf_map_dec_elem_count(&htab->map);
break;
}
@@ -900,6 +911,8 @@ static bool is_map_full(struct bpf_htab *htab)
static void inc_elem_count(struct bpf_htab *htab)
{
+ bpf_map_inc_elem_count(&htab->map);
+
if (htab->use_percpu_counter)
percpu_counter_add_batch(&htab->pcount, 1, PERCPU_COUNTER_BATCH);
else
@@ -908,6 +921,8 @@ static void inc_elem_count(struct bpf_htab *htab)
static void dec_elem_count(struct bpf_htab *htab)
{
+ bpf_map_dec_elem_count(&htab->map);
+
if (htab->use_percpu_counter)
percpu_counter_add_batch(&htab->pcount, -1, PERCPU_COUNTER_BATCH);
else
@@ -920,6 +935,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
htab_put_fd_value(htab, l);
if (htab_is_prealloc(htab)) {
+ bpf_map_dec_elem_count(&htab->map);
check_and_free_fields(htab, l);
__pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
@@ -1000,6 +1016,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
if (!l)
return ERR_PTR(-E2BIG);
l_new = container_of(l, struct htab_elem, fnode);
+ bpf_map_inc_elem_count(&htab->map);
}
} else {
if (is_map_full(htab))
@@ -1168,6 +1185,7 @@ err:
static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem)
{
check_and_free_fields(htab, elem);
+ bpf_map_dec_elem_count(&htab->map);
bpf_lru_push_free(&htab->lru, &elem->lru_node);
}
@@ -1357,8 +1375,10 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
err:
htab_unlock_bucket(htab, b, hash, flags);
err_lock_bucket:
- if (l_new)
+ if (l_new) {
+ bpf_map_dec_elem_count(&htab->map);
bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+ }
return ret;
}
@@ -1523,6 +1543,7 @@ static void htab_map_free(struct bpf_map *map)
prealloc_destroy(htab);
}
+ bpf_map_free_elem_count(map);
free_percpu(htab->extra_elems);
bpf_map_area_free(htab->buckets);
bpf_mem_alloc_destroy(&htab->pcpu_ma);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9e80efa59a5d..56b0c1f678ee 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -22,6 +22,7 @@
#include <linux/security.h>
#include <linux/btf_ids.h>
#include <linux/bpf_mem_alloc.h>
+#include <linux/kasan.h>
#include "../../lib/kstrtox.h"
@@ -286,6 +287,7 @@ static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0");
BUILD_BUG_ON(sizeof(*l) != sizeof(__u32));
BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32));
+ preempt_disable();
arch_spin_lock(l);
}
@@ -294,6 +296,7 @@ static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
arch_spinlock_t *l = (void *)lock;
arch_spin_unlock(l);
+ preempt_enable();
}
#else
@@ -1174,13 +1177,6 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
ret = -EBUSY;
goto out;
}
- if (!atomic64_read(&map->usercnt)) {
- /* maps with timers must be either held by user space
- * or pinned in bpffs.
- */
- ret = -EPERM;
- goto out;
- }
/* allocate hrtimer via map_kmalloc to use memcg accounting */
t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node);
if (!t) {
@@ -1193,7 +1189,21 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
rcu_assign_pointer(t->callback_fn, NULL);
hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
t->timer.function = bpf_timer_cb;
- timer->timer = t;
+ WRITE_ONCE(timer->timer, t);
+ /* Guarantee the order between timer->timer and map->usercnt. So
+ * when there are concurrent uref release and bpf timer init, either
+ * bpf_timer_cancel_and_free() called by uref release reads a no-NULL
+ * timer or atomic64_read() below returns a zero usercnt.
+ */
+ smp_mb();
+ if (!atomic64_read(&map->usercnt)) {
+ /* maps with timers must be either held by user space
+ * or pinned in bpffs.
+ */
+ WRITE_ONCE(timer->timer, NULL);
+ kfree(t);
+ ret = -EPERM;
+ }
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
return ret;
@@ -1269,7 +1279,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
if (in_nmi())
return -EOPNOTSUPP;
- if (flags > BPF_F_TIMER_ABS)
+ if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN))
return -EINVAL;
__bpf_spin_lock_irqsave(&timer->lock);
t = timer->timer;
@@ -1283,6 +1293,9 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
else
mode = HRTIMER_MODE_REL_SOFT;
+ if (flags & BPF_F_TIMER_CPU_PIN)
+ mode |= HRTIMER_MODE_PINNED;
+
hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode);
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
@@ -1368,7 +1381,7 @@ void bpf_timer_cancel_and_free(void *val)
/* The subsequent bpf_timer_start/cancel() helpers won't be able to use
* this timer, since it won't be initialized.
*/
- timer->timer = NULL;
+ WRITE_ONCE(timer->timer, NULL);
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
if (!t)
@@ -1805,8 +1818,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
}
}
-void __bpf_obj_drop_impl(void *p, const struct btf_record *rec);
-
void bpf_list_head_free(const struct btf_field *field, void *list_head,
struct bpf_spin_lock *spin_lock)
{
@@ -1838,7 +1849,7 @@ unlock:
* bpf_list_head which needs to be freed.
*/
migrate_disable();
- __bpf_obj_drop_impl(obj, field->graph_root.value_rec);
+ __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false);
migrate_enable();
}
}
@@ -1877,14 +1888,12 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
migrate_disable();
- __bpf_obj_drop_impl(obj, field->graph_root.value_rec);
+ __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false);
migrate_enable();
}
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
{
@@ -1900,9 +1909,19 @@ __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
return p;
}
+__bpf_kfunc void *bpf_percpu_obj_new_impl(u64 local_type_id__k, void *meta__ign)
+{
+ u64 size = local_type_id__k;
+
+ /* The verifier has ensured that meta__ign must be NULL */
+ return bpf_mem_alloc(&bpf_global_percpu_ma, size);
+}
+
/* Must be called under migrate_disable(), as required by bpf_mem_free */
-void __bpf_obj_drop_impl(void *p, const struct btf_record *rec)
+void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu)
{
+ struct bpf_mem_alloc *ma;
+
if (rec && rec->refcount_off >= 0 &&
!refcount_dec_and_test((refcount_t *)(p + rec->refcount_off))) {
/* Object is refcounted and refcount_dec didn't result in 0
@@ -1913,7 +1932,15 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec)
if (rec)
bpf_obj_free_fields(rec, p);
- bpf_mem_free(&bpf_global_ma, p);
+
+ if (percpu)
+ ma = &bpf_global_percpu_ma;
+ else
+ ma = &bpf_global_ma;
+ if (rec && rec->refcount_off >= 0)
+ bpf_mem_free_rcu(ma, p);
+ else
+ bpf_mem_free(ma, p);
}
__bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
@@ -1921,7 +1948,13 @@ __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
struct btf_struct_meta *meta = meta__ign;
void *p = p__alloc;
- __bpf_obj_drop_impl(p, meta ? meta->record : NULL);
+ __bpf_obj_drop_impl(p, meta ? meta->record : NULL, false);
+}
+
+__bpf_kfunc void bpf_percpu_obj_drop_impl(void *p__alloc, void *meta__ign)
+{
+ /* The verifier has ensured that meta__ign must be NULL */
+ bpf_mem_free_rcu(&bpf_global_percpu_ma, p__alloc);
}
__bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta__ign)
@@ -1942,23 +1975,29 @@ __bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta
return (void *)p__refcounted_kptr;
}
-static int __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head,
+static int __bpf_list_add(struct bpf_list_node_kern *node,
+ struct bpf_list_head *head,
bool tail, struct btf_record *rec, u64 off)
{
- struct list_head *n = (void *)node, *h = (void *)head;
+ struct list_head *n = &node->list_head, *h = (void *)head;
/* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
* called on its fields, so init here
*/
if (unlikely(!h->next))
INIT_LIST_HEAD(h);
- if (!list_empty(n)) {
+
+ /* node->owner != NULL implies !list_empty(n), no need to separately
+ * check the latter
+ */
+ if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) {
/* Only called from BPF prog, no need to migrate_disable */
- __bpf_obj_drop_impl((void *)n - off, rec);
+ __bpf_obj_drop_impl((void *)n - off, rec, false);
return -EINVAL;
}
tail ? list_add_tail(n, h) : list_add(n, h);
+ WRITE_ONCE(node->owner, head);
return 0;
}
@@ -1967,25 +2006,26 @@ __bpf_kfunc int bpf_list_push_front_impl(struct bpf_list_head *head,
struct bpf_list_node *node,
void *meta__ign, u64 off)
{
+ struct bpf_list_node_kern *n = (void *)node;
struct btf_struct_meta *meta = meta__ign;
- return __bpf_list_add(node, head, false,
- meta ? meta->record : NULL, off);
+ return __bpf_list_add(n, head, false, meta ? meta->record : NULL, off);
}
__bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head,
struct bpf_list_node *node,
void *meta__ign, u64 off)
{
+ struct bpf_list_node_kern *n = (void *)node;
struct btf_struct_meta *meta = meta__ign;
- return __bpf_list_add(node, head, true,
- meta ? meta->record : NULL, off);
+ return __bpf_list_add(n, head, true, meta ? meta->record : NULL, off);
}
static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail)
{
struct list_head *n, *h = (void *)head;
+ struct bpf_list_node_kern *node;
/* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
* called on its fields, so init here
@@ -1994,8 +2034,14 @@ static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tai
INIT_LIST_HEAD(h);
if (list_empty(h))
return NULL;
+
n = tail ? h->prev : h->next;
+ node = container_of(n, struct bpf_list_node_kern, list_head);
+ if (WARN_ON_ONCE(READ_ONCE(node->owner) != head))
+ return NULL;
+
list_del_init(n);
+ WRITE_ONCE(node->owner, NULL);
return (struct bpf_list_node *)n;
}
@@ -2012,31 +2058,40 @@ __bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head)
__bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
struct bpf_rb_node *node)
{
+ struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node;
struct rb_root_cached *r = (struct rb_root_cached *)root;
- struct rb_node *n = (struct rb_node *)node;
+ struct rb_node *n = &node_internal->rb_node;
- if (RB_EMPTY_NODE(n))
+ /* node_internal->owner != root implies either RB_EMPTY_NODE(n) or
+ * n is owned by some other tree. No need to check RB_EMPTY_NODE(n)
+ */
+ if (READ_ONCE(node_internal->owner) != root)
return NULL;
rb_erase_cached(n, r);
RB_CLEAR_NODE(n);
+ WRITE_ONCE(node_internal->owner, NULL);
return (struct bpf_rb_node *)n;
}
/* Need to copy rbtree_add_cached's logic here because our 'less' is a BPF
* program
*/
-static int __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
+static int __bpf_rbtree_add(struct bpf_rb_root *root,
+ struct bpf_rb_node_kern *node,
void *less, struct btf_record *rec, u64 off)
{
struct rb_node **link = &((struct rb_root_cached *)root)->rb_root.rb_node;
- struct rb_node *parent = NULL, *n = (struct rb_node *)node;
+ struct rb_node *parent = NULL, *n = &node->rb_node;
bpf_callback_t cb = (bpf_callback_t)less;
bool leftmost = true;
- if (!RB_EMPTY_NODE(n)) {
+ /* node->owner != NULL implies !RB_EMPTY_NODE(n), no need to separately
+ * check the latter
+ */
+ if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) {
/* Only called from BPF prog, no need to migrate_disable */
- __bpf_obj_drop_impl((void *)n - off, rec);
+ __bpf_obj_drop_impl((void *)n - off, rec, false);
return -EINVAL;
}
@@ -2052,6 +2107,7 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
rb_link_node(n, parent, link);
rb_insert_color_cached(n, (struct rb_root_cached *)root, leftmost);
+ WRITE_ONCE(node->owner, root);
return 0;
}
@@ -2060,8 +2116,9 @@ __bpf_kfunc int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node
void *meta__ign, u64 off)
{
struct btf_struct_meta *meta = meta__ign;
+ struct bpf_rb_node_kern *n = (void *)node;
- return __bpf_rbtree_add(root, node, (void *)less, meta ? meta->record : NULL, off);
+ return __bpf_rbtree_add(root, n, (void *)less, meta ? meta->record : NULL, off);
}
__bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root)
@@ -2167,7 +2224,12 @@ __bpf_kfunc struct cgroup *bpf_cgroup_from_id(u64 cgid)
__bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task,
struct cgroup *ancestor)
{
- return task_under_cgroup_hierarchy(task, ancestor);
+ long ret;
+
+ rcu_read_lock();
+ ret = task_under_cgroup_hierarchy(task, ancestor);
+ rcu_read_unlock();
+ return ret;
}
#endif /* CONFIG_CGROUPS */
@@ -2239,11 +2301,14 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
case BPF_DYNPTR_TYPE_RINGBUF:
return ptr->data + ptr->offset + offset;
case BPF_DYNPTR_TYPE_SKB:
- return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt);
+ if (buffer__opt)
+ return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt);
+ else
+ return skb_pointer_if_linear(ptr->data, ptr->offset + offset, len);
case BPF_DYNPTR_TYPE_XDP:
{
void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len);
- if (xdp_ptr)
+ if (!IS_ERR_OR_NULL(xdp_ptr))
return xdp_ptr;
if (!buffer__opt)
@@ -2402,14 +2467,59 @@ __bpf_kfunc void bpf_rcu_read_unlock(void)
rcu_read_unlock();
}
-__diag_pop();
+struct bpf_throw_ctx {
+ struct bpf_prog_aux *aux;
+ u64 sp;
+ u64 bp;
+ int cnt;
+};
+
+static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp)
+{
+ struct bpf_throw_ctx *ctx = cookie;
+ struct bpf_prog *prog;
+
+ if (!is_bpf_text_address(ip))
+ return !ctx->cnt;
+ prog = bpf_prog_ksym_find(ip);
+ ctx->cnt++;
+ if (bpf_is_subprog(prog))
+ return true;
+ ctx->aux = prog->aux;
+ ctx->sp = sp;
+ ctx->bp = bp;
+ return false;
+}
+
+__bpf_kfunc void bpf_throw(u64 cookie)
+{
+ struct bpf_throw_ctx ctx = {};
+
+ arch_bpf_stack_walk(bpf_stack_walker, &ctx);
+ WARN_ON_ONCE(!ctx.aux);
+ if (ctx.aux)
+ WARN_ON_ONCE(!ctx.aux->exception_boundary);
+ WARN_ON_ONCE(!ctx.bp);
+ WARN_ON_ONCE(!ctx.cnt);
+ /* Prevent KASAN false positives for CONFIG_KASAN_STACK by unpoisoning
+ * deeper stack depths than ctx.sp as we do not return from bpf_throw,
+ * which skips compiler generated instrumentation to do the same.
+ */
+ kasan_unpoison_task_stack_below((void *)(long)ctx.sp);
+ ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp);
+ WARN(1, "A call to BPF exception callback should never return\n");
+}
+
+__bpf_kfunc_end_defs();
BTF_SET8_START(generic_btf_ids)
#ifdef CONFIG_KEXEC_CORE
BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
#endif
BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_percpu_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_obj_drop_impl, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_percpu_obj_drop_impl, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_refcount_acquire_impl, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_list_push_front_impl)
BTF_ID_FLAGS(func, bpf_list_push_back_impl)
@@ -2429,6 +2539,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU)
#endif
BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_throw)
BTF_SET8_END(generic_btf_ids)
static const struct btf_kfunc_id_set generic_kfunc_set = {
@@ -2455,6 +2566,20 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW)
BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+#ifdef CONFIG_CGROUPS
+BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
+#endif
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
BTF_ID_FLAGS(func, bpf_dynptr_adjust)
BTF_ID_FLAGS(func, bpf_dynptr_is_null)
BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 4174f76133df..1aafb2ff2e95 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -118,9 +118,7 @@ static struct inode *bpf_get_inode(struct super_block *sb,
return ERR_PTR(-ENOSPC);
inode->i_ino = get_next_ino();
- inode->i_atime = current_time(inode);
- inode->i_mtime = inode->i_atime;
- inode->i_ctime = inode->i_atime;
+ simple_inode_init_ts(inode);
inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
@@ -148,8 +146,7 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
d_instantiate(dentry, inode);
dget(dentry);
- dir->i_mtime = current_time(dir);
- dir->i_ctime = dir->i_mtime;
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
}
static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir,
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index b0fa190b0979..6abd7c5df4b3 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -78,8 +78,7 @@ static const struct seq_operations bpf_map_seq_ops = {
.show = bpf_map_seq_show,
};
-BTF_ID_LIST(btf_bpf_map_id)
-BTF_ID(struct, bpf_map)
+BTF_ID_LIST_GLOBAL_SINGLE(btf_bpf_map_id, struct, bpf_map)
static const struct bpf_iter_seq_info bpf_map_seq_info = {
.seq_ops = &bpf_map_seq_ops,
@@ -93,7 +92,7 @@ static struct bpf_iter_reg bpf_map_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__bpf_map, map),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &bpf_map_seq_info,
};
@@ -193,3 +192,38 @@ static int __init bpf_map_iter_init(void)
}
late_initcall(bpf_map_iter_init);
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
+{
+ s64 *pcount;
+ s64 ret = 0;
+ int cpu;
+
+ if (!map || !map->elem_count)
+ return 0;
+
+ for_each_possible_cpu(cpu) {
+ pcount = per_cpu_ptr(map->elem_count, cpu);
+ ret += READ_ONCE(*pcount);
+ }
+ return ret;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(bpf_map_iter_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS)
+BTF_SET8_END(bpf_map_iter_kfunc_ids)
+
+static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = {
+ .owner = THIS_MODULE,
+ .set = &bpf_map_iter_kfunc_ids,
+};
+
+static int init_subsystem(void)
+{
+ return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_map_iter_kfunc_set);
+}
+late_initcall(init_subsystem);
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 0668bcd7c926..6a51cfe4c2d6 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -98,11 +98,23 @@ struct bpf_mem_cache {
int free_cnt;
int low_watermark, high_watermark, batch;
int percpu_size;
+ bool draining;
+ struct bpf_mem_cache *tgt;
- struct rcu_head rcu;
+ /* list of objects to be freed after RCU GP */
struct llist_head free_by_rcu;
+ struct llist_node *free_by_rcu_tail;
struct llist_head waiting_for_gp;
+ struct llist_node *waiting_for_gp_tail;
+ struct rcu_head rcu;
atomic_t call_rcu_in_progress;
+ struct llist_head free_llist_extra_rcu;
+
+ /* list of objects to be freed after RCU tasks trace GP */
+ struct llist_head free_by_rcu_ttrace;
+ struct llist_head waiting_for_gp_ttrace;
+ struct rcu_head rcu_ttrace;
+ atomic_t call_rcu_ttrace_in_progress;
};
struct bpf_mem_caches {
@@ -153,59 +165,87 @@ static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
#endif
}
+static void inc_active(struct bpf_mem_cache *c, unsigned long *flags)
+{
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ /* In RT irq_work runs in per-cpu kthread, so disable
+ * interrupts to avoid preemption and interrupts and
+ * reduce the chance of bpf prog executing on this cpu
+ * when active counter is busy.
+ */
+ local_irq_save(*flags);
+ /* alloc_bulk runs from irq_work which will not preempt a bpf
+ * program that does unit_alloc/unit_free since IRQs are
+ * disabled there. There is no race to increment 'active'
+ * counter. It protects free_llist from corruption in case NMI
+ * bpf prog preempted this loop.
+ */
+ WARN_ON_ONCE(local_inc_return(&c->active) != 1);
+}
+
+static void dec_active(struct bpf_mem_cache *c, unsigned long *flags)
+{
+ local_dec(&c->active);
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_irq_restore(*flags);
+}
+
+static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
+{
+ unsigned long flags;
+
+ inc_active(c, &flags);
+ __llist_add(obj, &c->free_llist);
+ c->free_cnt++;
+ dec_active(c, &flags);
+}
+
/* Mostly runs from irq_work except __init phase. */
-static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
+static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic)
{
struct mem_cgroup *memcg = NULL, *old_memcg;
- unsigned long flags;
+ gfp_t gfp;
void *obj;
int i;
- memcg = get_memcg(c);
- old_memcg = set_active_memcg(memcg);
+ gfp = __GFP_NOWARN | __GFP_ACCOUNT;
+ gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL;
+
for (i = 0; i < cnt; i++) {
/*
- * free_by_rcu is only manipulated by irq work refill_work().
- * IRQ works on the same CPU are called sequentially, so it is
- * safe to use __llist_del_first() here. If alloc_bulk() is
- * invoked by the initial prefill, there will be no running
- * refill_work(), so __llist_del_first() is fine as well.
- *
- * In most cases, objects on free_by_rcu are from the same CPU.
- * If some objects come from other CPUs, it doesn't incur any
- * harm because NUMA_NO_NODE means the preference for current
- * numa node and it is not a guarantee.
+ * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is
+ * done only by one CPU == current CPU. Other CPUs might
+ * llist_add() and llist_del_all() in parallel.
*/
- obj = __llist_del_first(&c->free_by_rcu);
- if (!obj) {
- /* Allocate, but don't deplete atomic reserves that typical
- * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
- * will allocate from the current numa node which is what we
- * want here.
- */
- obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT);
- if (!obj)
- break;
- }
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- /* In RT irq_work runs in per-cpu kthread, so disable
- * interrupts to avoid preemption and interrupts and
- * reduce the chance of bpf prog executing on this cpu
- * when active counter is busy.
- */
- local_irq_save(flags);
- /* alloc_bulk runs from irq_work which will not preempt a bpf
- * program that does unit_alloc/unit_free since IRQs are
- * disabled there. There is no race to increment 'active'
- * counter. It protects free_llist from corruption in case NMI
- * bpf prog preempted this loop.
+ obj = llist_del_first(&c->free_by_rcu_ttrace);
+ if (!obj)
+ break;
+ add_obj_to_free_list(c, obj);
+ }
+ if (i >= cnt)
+ return;
+
+ for (; i < cnt; i++) {
+ obj = llist_del_first(&c->waiting_for_gp_ttrace);
+ if (!obj)
+ break;
+ add_obj_to_free_list(c, obj);
+ }
+ if (i >= cnt)
+ return;
+
+ memcg = get_memcg(c);
+ old_memcg = set_active_memcg(memcg);
+ for (; i < cnt; i++) {
+ /* Allocate, but don't deplete atomic reserves that typical
+ * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
+ * will allocate from the current numa node which is what we
+ * want here.
*/
- WARN_ON_ONCE(local_inc_return(&c->active) != 1);
- __llist_add(obj, &c->free_llist);
- c->free_cnt++;
- local_dec(&c->active);
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- local_irq_restore(flags);
+ obj = __alloc(c, node, gfp);
+ if (!obj)
+ break;
+ add_obj_to_free_list(c, obj);
}
set_active_memcg(old_memcg);
mem_cgroup_put(memcg);
@@ -222,20 +262,24 @@ static void free_one(void *obj, bool percpu)
kfree(obj);
}
-static void free_all(struct llist_node *llnode, bool percpu)
+static int free_all(struct llist_node *llnode, bool percpu)
{
struct llist_node *pos, *t;
+ int cnt = 0;
- llist_for_each_safe(pos, t, llnode)
+ llist_for_each_safe(pos, t, llnode) {
free_one(pos, percpu);
+ cnt++;
+ }
+ return cnt;
}
static void __free_rcu(struct rcu_head *head)
{
- struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+ struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace);
- free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
- atomic_set(&c->call_rcu_in_progress, 0);
+ free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
+ atomic_set(&c->call_rcu_ttrace_in_progress, 0);
}
static void __free_rcu_tasks_trace(struct rcu_head *head)
@@ -254,60 +298,132 @@ static void enque_to_free(struct bpf_mem_cache *c, void *obj)
struct llist_node *llnode = obj;
/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
- * Nothing races to add to free_by_rcu list.
+ * Nothing races to add to free_by_rcu_ttrace list.
*/
- __llist_add(llnode, &c->free_by_rcu);
+ llist_add(llnode, &c->free_by_rcu_ttrace);
}
-static void do_call_rcu(struct bpf_mem_cache *c)
+static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
{
struct llist_node *llnode, *t;
- if (atomic_xchg(&c->call_rcu_in_progress, 1))
+ if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) {
+ if (unlikely(READ_ONCE(c->draining))) {
+ llnode = llist_del_all(&c->free_by_rcu_ttrace);
+ free_all(llnode, !!c->percpu_size);
+ }
return;
+ }
+
+ WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
+ llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace))
+ llist_add(llnode, &c->waiting_for_gp_ttrace);
+
+ if (unlikely(READ_ONCE(c->draining))) {
+ __free_rcu(&c->rcu_ttrace);
+ return;
+ }
- WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
- llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
- /* There is no concurrent __llist_add(waiting_for_gp) access.
- * It doesn't race with llist_del_all either.
- * But there could be two concurrent llist_del_all(waiting_for_gp):
- * from __free_rcu() and from drain_mem_cache().
- */
- __llist_add(llnode, &c->waiting_for_gp);
/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
* If RCU Tasks Trace grace period implies RCU grace period, free
* these elements directly, else use call_rcu() to wait for normal
* progs to finish and finally do free_one() on each element.
*/
- call_rcu_tasks_trace(&c->rcu, __free_rcu_tasks_trace);
+ call_rcu_tasks_trace(&c->rcu_ttrace, __free_rcu_tasks_trace);
}
static void free_bulk(struct bpf_mem_cache *c)
{
+ struct bpf_mem_cache *tgt = c->tgt;
struct llist_node *llnode, *t;
unsigned long flags;
int cnt;
+ WARN_ON_ONCE(tgt->unit_size != c->unit_size);
+ WARN_ON_ONCE(tgt->percpu_size != c->percpu_size);
+
do {
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- local_irq_save(flags);
- WARN_ON_ONCE(local_inc_return(&c->active) != 1);
+ inc_active(c, &flags);
llnode = __llist_del_first(&c->free_llist);
if (llnode)
cnt = --c->free_cnt;
else
cnt = 0;
- local_dec(&c->active);
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- local_irq_restore(flags);
+ dec_active(c, &flags);
if (llnode)
- enque_to_free(c, llnode);
+ enque_to_free(tgt, llnode);
} while (cnt > (c->high_watermark + c->low_watermark) / 2);
/* and drain free_llist_extra */
llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
- enque_to_free(c, llnode);
- do_call_rcu(c);
+ enque_to_free(tgt, llnode);
+ do_call_rcu_ttrace(tgt);
+}
+
+static void __free_by_rcu(struct rcu_head *head)
+{
+ struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+ struct bpf_mem_cache *tgt = c->tgt;
+ struct llist_node *llnode;
+
+ WARN_ON_ONCE(tgt->unit_size != c->unit_size);
+ WARN_ON_ONCE(tgt->percpu_size != c->percpu_size);
+
+ llnode = llist_del_all(&c->waiting_for_gp);
+ if (!llnode)
+ goto out;
+
+ llist_add_batch(llnode, c->waiting_for_gp_tail, &tgt->free_by_rcu_ttrace);
+
+ /* Objects went through regular RCU GP. Send them to RCU tasks trace */
+ do_call_rcu_ttrace(tgt);
+out:
+ atomic_set(&c->call_rcu_in_progress, 0);
+}
+
+static void check_free_by_rcu(struct bpf_mem_cache *c)
+{
+ struct llist_node *llnode, *t;
+ unsigned long flags;
+
+ /* drain free_llist_extra_rcu */
+ if (unlikely(!llist_empty(&c->free_llist_extra_rcu))) {
+ inc_active(c, &flags);
+ llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu))
+ if (__llist_add(llnode, &c->free_by_rcu))
+ c->free_by_rcu_tail = llnode;
+ dec_active(c, &flags);
+ }
+
+ if (llist_empty(&c->free_by_rcu))
+ return;
+
+ if (atomic_xchg(&c->call_rcu_in_progress, 1)) {
+ /*
+ * Instead of kmalloc-ing new rcu_head and triggering 10k
+ * call_rcu() to hit rcutree.qhimark and force RCU to notice
+ * the overload just ask RCU to hurry up. There could be many
+ * objects in free_by_rcu list.
+ * This hint reduces memory consumption for an artificial
+ * benchmark from 2 Gbyte to 150 Mbyte.
+ */
+ rcu_request_urgent_qs_task(current);
+ return;
+ }
+
+ WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
+
+ inc_active(c, &flags);
+ WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu));
+ c->waiting_for_gp_tail = c->free_by_rcu_tail;
+ dec_active(c, &flags);
+
+ if (unlikely(READ_ONCE(c->draining))) {
+ free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
+ atomic_set(&c->call_rcu_in_progress, 0);
+ } else {
+ call_rcu_hurry(&c->rcu, __free_by_rcu);
+ }
}
static void bpf_mem_refill(struct irq_work *work)
@@ -321,9 +437,11 @@ static void bpf_mem_refill(struct irq_work *work)
/* irq_work runs on this cpu and kmalloc will allocate
* from the current numa node which is what we want here.
*/
- alloc_bulk(c, c->batch, NUMA_NO_NODE);
+ alloc_bulk(c, c->batch, NUMA_NO_NODE, true);
else if (cnt > c->high_watermark)
free_bulk(c);
+
+ check_free_by_rcu(c);
}
static void notrace irq_work_raise(struct bpf_mem_cache *c)
@@ -345,8 +463,7 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
* Typical case will be between 11K and 116K closer to 11K.
* bpf progs can and should share bpf_mem_cache when possible.
*/
-
-static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+static void init_refill_work(struct bpf_mem_cache *c)
{
init_irq_work(&c->refill_work, bpf_mem_refill);
if (c->unit_size <= 256) {
@@ -362,12 +479,36 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
c->high_watermark = max(96 * 256 / c->unit_size, 3);
}
c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);
+}
+static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+{
/* To avoid consuming memory assume that 1st run of bpf
* prog won't be doing more than 4 map_update_elem from
* irq disabled region
*/
- alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu));
+ alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
+}
+
+static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
+{
+ struct llist_node *first;
+ unsigned int obj_size;
+
+ first = c->free_llist.first;
+ if (!first)
+ return 0;
+
+ if (c->percpu_size)
+ obj_size = pcpu_alloc_size(((void **)first)[1]);
+ else
+ obj_size = ksize(first);
+ if (obj_size != c->unit_size) {
+ WARN_ONCE(1, "bpf_mem_cache[%u]: percpu %d, unexpected object size %u, expect %u\n",
+ idx, c->percpu_size, obj_size, c->unit_size);
+ return -EINVAL;
+ }
+ return 0;
}
/* When size != 0 bpf_mem_cache for each cpu.
@@ -380,20 +521,22 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
{
static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+ int cpu, i, err, unit_size, percpu_size = 0;
struct bpf_mem_caches *cc, __percpu *pcc;
struct bpf_mem_cache *c, __percpu *pc;
struct obj_cgroup *objcg = NULL;
- int cpu, i, unit_size, percpu_size = 0;
+
+ /* room for llist_node and per-cpu pointer */
+ if (percpu)
+ percpu_size = LLIST_NODE_SZ + sizeof(void *);
+ ma->percpu = percpu;
if (size) {
pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL);
if (!pc)
return -ENOMEM;
- if (percpu)
- /* room for llist_node and per-cpu pointer */
- percpu_size = LLIST_NODE_SZ + sizeof(void *);
- else
+ if (!percpu)
size += LLIST_NODE_SZ; /* room for llist_node */
unit_size = size;
@@ -406,19 +549,18 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
c->unit_size = unit_size;
c->objcg = objcg;
c->percpu_size = percpu_size;
+ c->tgt = c;
+ init_refill_work(c);
prefill_mem_cache(c, cpu);
}
ma->cache = pc;
return 0;
}
- /* size == 0 && percpu is an invalid combination */
- if (WARN_ON_ONCE(percpu))
- return -EINVAL;
-
pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
if (!pcc)
return -ENOMEM;
+ err = 0;
#ifdef CONFIG_MEMCG_KMEM
objcg = get_obj_cgroup_from_current();
#endif
@@ -428,11 +570,32 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
c = &cc->cache[i];
c->unit_size = sizes[i];
c->objcg = objcg;
+ c->percpu_size = percpu_size;
+ c->tgt = c;
+
+ init_refill_work(c);
+ /* Another bpf_mem_cache will be used when allocating
+ * c->unit_size in bpf_mem_alloc(), so doesn't prefill
+ * for the bpf_mem_cache because these free objects will
+ * never be used.
+ */
+ if (i != bpf_mem_cache_idx(c->unit_size))
+ continue;
prefill_mem_cache(c, cpu);
+ err = check_obj_size(c, i);
+ if (err)
+ goto out;
}
}
+
+out:
ma->caches = pcc;
- return 0;
+ /* refill_work is either zeroed or initialized, so it is safe to
+ * call irq_work_sync().
+ */
+ if (err)
+ bpf_mem_alloc_destroy(ma);
+ return err;
}
static void drain_mem_cache(struct bpf_mem_cache *c)
@@ -441,19 +604,57 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
/* No progs are using this bpf_mem_cache, but htab_map_free() called
* bpf_mem_cache_free() for all remaining elements and they can be in
- * free_by_rcu or in waiting_for_gp lists, so drain those lists now.
+ * free_by_rcu_ttrace or in waiting_for_gp_ttrace lists, so drain those lists now.
*
- * Except for waiting_for_gp list, there are no concurrent operations
+ * Except for waiting_for_gp_ttrace list, there are no concurrent operations
* on these lists, so it is safe to use __llist_del_all().
*/
- free_all(__llist_del_all(&c->free_by_rcu), percpu);
- free_all(llist_del_all(&c->waiting_for_gp), percpu);
+ free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu);
+ free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
free_all(__llist_del_all(&c->free_llist), percpu);
free_all(__llist_del_all(&c->free_llist_extra), percpu);
+ free_all(__llist_del_all(&c->free_by_rcu), percpu);
+ free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu);
+ free_all(llist_del_all(&c->waiting_for_gp), percpu);
+}
+
+static void check_mem_cache(struct bpf_mem_cache *c)
+{
+ WARN_ON_ONCE(!llist_empty(&c->free_by_rcu_ttrace));
+ WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
+ WARN_ON_ONCE(!llist_empty(&c->free_llist));
+ WARN_ON_ONCE(!llist_empty(&c->free_llist_extra));
+ WARN_ON_ONCE(!llist_empty(&c->free_by_rcu));
+ WARN_ON_ONCE(!llist_empty(&c->free_llist_extra_rcu));
+ WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
+}
+
+static void check_leaked_objs(struct bpf_mem_alloc *ma)
+{
+ struct bpf_mem_caches *cc;
+ struct bpf_mem_cache *c;
+ int cpu, i;
+
+ if (ma->cache) {
+ for_each_possible_cpu(cpu) {
+ c = per_cpu_ptr(ma->cache, cpu);
+ check_mem_cache(c);
+ }
+ }
+ if (ma->caches) {
+ for_each_possible_cpu(cpu) {
+ cc = per_cpu_ptr(ma->caches, cpu);
+ for (i = 0; i < NUM_CACHES; i++) {
+ c = &cc->cache[i];
+ check_mem_cache(c);
+ }
+ }
+ }
}
static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
{
+ check_leaked_objs(ma);
free_percpu(ma->cache);
free_percpu(ma->caches);
ma->cache = NULL;
@@ -462,8 +663,8 @@ static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
static void free_mem_alloc(struct bpf_mem_alloc *ma)
{
- /* waiting_for_gp lists was drained, but __free_rcu might
- * still execute. Wait for it now before we freeing percpu caches.
+ /* waiting_for_gp[_ttrace] lists were drained, but RCU callbacks
+ * might still execute. Wait for them.
*
* rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(),
* but rcu_barrier_tasks_trace() and rcu_barrier() below are only used
@@ -472,7 +673,8 @@ static void free_mem_alloc(struct bpf_mem_alloc *ma)
* rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by
* using rcu_trace_implies_rcu_gp() as well.
*/
- rcu_barrier_tasks_trace();
+ rcu_barrier(); /* wait for __free_by_rcu */
+ rcu_barrier_tasks_trace(); /* wait for __free_rcu */
if (!rcu_trace_implies_rcu_gp())
rcu_barrier();
free_mem_alloc_no_barrier(ma);
@@ -498,7 +700,7 @@ static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
return;
}
- copy = kmalloc(sizeof(*ma), GFP_KERNEL);
+ copy = kmemdup(ma, sizeof(*ma), GFP_KERNEL);
if (!copy) {
/* Slow path with inline barrier-s */
free_mem_alloc(ma);
@@ -506,10 +708,7 @@ static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
}
/* Defer barriers into worker to let the rest of map memory to be freed */
- copy->cache = ma->cache;
- ma->cache = NULL;
- copy->caches = ma->caches;
- ma->caches = NULL;
+ memset(ma, 0, sizeof(*ma));
INIT_WORK(&copy->work, free_mem_alloc_deferred);
queue_work(system_unbound_wq, &copy->work);
}
@@ -524,17 +723,10 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
rcu_in_progress = 0;
for_each_possible_cpu(cpu) {
c = per_cpu_ptr(ma->cache, cpu);
- /*
- * refill_work may be unfinished for PREEMPT_RT kernel
- * in which irq work is invoked in a per-CPU RT thread.
- * It is also possible for kernel with
- * arch_irq_work_has_interrupt() being false and irq
- * work is invoked in timer interrupt. So waiting for
- * the completion of irq work to ease the handling of
- * concurrency.
- */
+ WRITE_ONCE(c->draining, true);
irq_work_sync(&c->refill_work);
drain_mem_cache(c);
+ rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
}
/* objcg is the same across cpus */
@@ -548,8 +740,10 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
cc = per_cpu_ptr(ma->caches, cpu);
for (i = 0; i < NUM_CACHES; i++) {
c = &cc->cache[i];
+ WRITE_ONCE(c->draining, true);
irq_work_sync(&c->refill_work);
drain_mem_cache(c);
+ rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
}
}
@@ -581,16 +775,23 @@ static void notrace *unit_alloc(struct bpf_mem_cache *c)
local_irq_save(flags);
if (local_inc_return(&c->active) == 1) {
llnode = __llist_del_first(&c->free_llist);
- if (llnode)
+ if (llnode) {
cnt = --c->free_cnt;
+ *(struct bpf_mem_cache **)llnode = c;
+ }
}
local_dec(&c->active);
- local_irq_restore(flags);
WARN_ON(cnt < 0);
if (cnt < c->low_watermark)
irq_work_raise(c);
+ /* Enable IRQ after the enqueue of irq work completes, so irq work
+ * will run after IRQ is enabled and free_llist may be refilled by
+ * irq work before other task preempts current task.
+ */
+ local_irq_restore(flags);
+
return llnode;
}
@@ -606,6 +807,12 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
BUILD_BUG_ON(LLIST_NODE_SZ > 8);
+ /*
+ * Remember bpf_mem_cache that allocated this object.
+ * The hint is not accurate.
+ */
+ c->tgt = *(struct bpf_mem_cache **)llnode;
+
local_irq_save(flags);
if (local_inc_return(&c->active) == 1) {
__llist_add(llnode, &c->free_llist);
@@ -620,11 +827,37 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
llist_add(llnode, &c->free_llist_extra);
}
local_dec(&c->active);
- local_irq_restore(flags);
if (cnt > c->high_watermark)
/* free few objects from current cpu into global kmalloc pool */
irq_work_raise(c);
+ /* Enable IRQ after irq_work_raise() completes, otherwise when current
+ * task is preempted by task which does unit_alloc(), unit_alloc() may
+ * return NULL unexpectedly because irq work is already pending but can
+ * not been triggered and free_llist can not be refilled timely.
+ */
+ local_irq_restore(flags);
+}
+
+static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr)
+{
+ struct llist_node *llnode = ptr - LLIST_NODE_SZ;
+ unsigned long flags;
+
+ c->tgt = *(struct bpf_mem_cache **)llnode;
+
+ local_irq_save(flags);
+ if (local_inc_return(&c->active) == 1) {
+ if (__llist_add(llnode, &c->free_by_rcu))
+ c->free_by_rcu_tail = llnode;
+ } else {
+ llist_add(llnode, &c->free_llist_extra_rcu);
+ }
+ local_dec(&c->active);
+
+ if (!atomic_read(&c->call_rcu_in_progress))
+ irq_work_raise(c);
+ local_irq_restore(flags);
}
/* Called from BPF program or from sys_bpf syscall.
@@ -646,6 +879,17 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
return !ret ? NULL : ret + LLIST_NODE_SZ;
}
+static notrace int bpf_mem_free_idx(void *ptr, bool percpu)
+{
+ size_t size;
+
+ if (percpu)
+ size = pcpu_alloc_size(*((void **)ptr));
+ else
+ size = ksize(ptr - LLIST_NODE_SZ);
+ return bpf_mem_cache_idx(size);
+}
+
void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
{
int idx;
@@ -653,13 +897,27 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
if (!ptr)
return;
- idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ));
+ idx = bpf_mem_free_idx(ptr, ma->percpu);
if (idx < 0)
return;
unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
}
+void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
+{
+ int idx;
+
+ if (!ptr)
+ return;
+
+ idx = bpf_mem_free_idx(ptr, ma->percpu);
+ if (idx < 0)
+ return;
+
+ unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr);
+}
+
void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma)
{
void *ret;
@@ -676,6 +934,14 @@ void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr)
unit_free(this_cpu_ptr(ma->cache), ptr);
}
+void notrace bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
+{
+ if (!ptr)
+ return;
+
+ unit_free_rcu(this_cpu_ptr(ma->cache), ptr);
+}
+
/* Directly does a kfree() without putting 'ptr' back to the free_llist
* for reuse and without waiting for a rcu_tasks_trace gp.
* The caller must first go through the rcu_tasks_trace gp for 'ptr'
@@ -712,9 +978,49 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
memcg = get_memcg(c);
old_memcg = set_active_memcg(memcg);
ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT);
+ if (ret)
+ *(struct bpf_mem_cache **)ret = c;
set_active_memcg(old_memcg);
mem_cgroup_put(memcg);
}
return !ret ? NULL : ret + LLIST_NODE_SZ;
}
+
+/* The alignment of dynamic per-cpu area is 8, so c->unit_size and the
+ * actual size of dynamic per-cpu area will always be matched and there is
+ * no need to adjust size_index for per-cpu allocation. However for the
+ * simplicity of the implementation, use an unified size_index for both
+ * kmalloc and per-cpu allocation.
+ */
+static __init int bpf_mem_cache_adjust_size(void)
+{
+ unsigned int size;
+
+ /* Adjusting the indexes in size_index() according to the object_size
+ * of underlying slab cache, so bpf_mem_alloc() will select a
+ * bpf_mem_cache with unit_size equal to the object_size of
+ * the underlying slab cache.
+ *
+ * The maximal value of KMALLOC_MIN_SIZE and __kmalloc_minalign() is
+ * 256-bytes, so only do adjustment for [8-bytes, 192-bytes].
+ */
+ for (size = 192; size >= 8; size -= 8) {
+ unsigned int kmalloc_size, index;
+
+ kmalloc_size = kmalloc_size_roundup(size);
+ if (kmalloc_size == size)
+ continue;
+
+ if (kmalloc_size <= 192)
+ index = size_index[(kmalloc_size - 1) / 8];
+ else
+ index = fls(kmalloc_size - 1) - 1;
+ /* Only overwrite if necessary */
+ if (size_index[(size - 1) / 8] != index)
+ size_index[(size - 1) / 8] = index;
+ }
+
+ return 0;
+}
+subsys_initcall(bpf_mem_cache_adjust_size);
diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c
new file mode 100644
index 000000000000..1394168062e8
--- /dev/null
+++ b/kernel/bpf/mprog.c
@@ -0,0 +1,452 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <linux/bpf.h>
+#include <linux/bpf_mprog.h>
+
+static int bpf_mprog_link(struct bpf_tuple *tuple,
+ u32 id_or_fd, u32 flags,
+ enum bpf_prog_type type)
+{
+ struct bpf_link *link = ERR_PTR(-EINVAL);
+ bool id = flags & BPF_F_ID;
+
+ if (id)
+ link = bpf_link_by_id(id_or_fd);
+ else if (id_or_fd)
+ link = bpf_link_get_from_fd(id_or_fd);
+ if (IS_ERR(link))
+ return PTR_ERR(link);
+ if (type && link->prog->type != type) {
+ bpf_link_put(link);
+ return -EINVAL;
+ }
+
+ tuple->link = link;
+ tuple->prog = link->prog;
+ return 0;
+}
+
+static int bpf_mprog_prog(struct bpf_tuple *tuple,
+ u32 id_or_fd, u32 flags,
+ enum bpf_prog_type type)
+{
+ struct bpf_prog *prog = ERR_PTR(-EINVAL);
+ bool id = flags & BPF_F_ID;
+
+ if (id)
+ prog = bpf_prog_by_id(id_or_fd);
+ else if (id_or_fd)
+ prog = bpf_prog_get(id_or_fd);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+ if (type && prog->type != type) {
+ bpf_prog_put(prog);
+ return -EINVAL;
+ }
+
+ tuple->link = NULL;
+ tuple->prog = prog;
+ return 0;
+}
+
+static int bpf_mprog_tuple_relative(struct bpf_tuple *tuple,
+ u32 id_or_fd, u32 flags,
+ enum bpf_prog_type type)
+{
+ bool link = flags & BPF_F_LINK;
+ bool id = flags & BPF_F_ID;
+
+ memset(tuple, 0, sizeof(*tuple));
+ if (link)
+ return bpf_mprog_link(tuple, id_or_fd, flags, type);
+ /* If no relevant flag is set and no id_or_fd was passed, then
+ * tuple link/prog is just NULLed. This is the case when before/
+ * after selects first/last position without passing fd.
+ */
+ if (!id && !id_or_fd)
+ return 0;
+ return bpf_mprog_prog(tuple, id_or_fd, flags, type);
+}
+
+static void bpf_mprog_tuple_put(struct bpf_tuple *tuple)
+{
+ if (tuple->link)
+ bpf_link_put(tuple->link);
+ else if (tuple->prog)
+ bpf_prog_put(tuple->prog);
+}
+
+/* The bpf_mprog_{replace,delete}() operate on exact idx position with the
+ * one exception that for deletion we support delete from front/back. In
+ * case of front idx is -1, in case of back idx is bpf_mprog_total(entry).
+ * Adjustment to first and last entry is trivial. The bpf_mprog_insert()
+ * we have to deal with the following cases:
+ *
+ * idx + before:
+ *
+ * Insert P4 before P3: idx for old array is 1, idx for new array is 2,
+ * hence we adjust target idx for the new array, so that memmove copies
+ * P1 and P2 to the new entry, and we insert P4 into idx 2. Inserting
+ * before P1 would have old idx -1 and new idx 0.
+ *
+ * +--+--+--+ +--+--+--+--+ +--+--+--+--+
+ * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3|
+ * +--+--+--+ +--+--+--+--+ +--+--+--+--+
+ *
+ * idx + after:
+ *
+ * Insert P4 after P2: idx for old array is 2, idx for new array is 2.
+ * Again, memmove copies P1 and P2 to the new entry, and we insert P4
+ * into idx 2. Inserting after P3 would have both old/new idx at 4 aka
+ * bpf_mprog_total(entry).
+ *
+ * +--+--+--+ +--+--+--+--+ +--+--+--+--+
+ * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3|
+ * +--+--+--+ +--+--+--+--+ +--+--+--+--+
+ */
+static int bpf_mprog_replace(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_tuple *ntuple, int idx)
+{
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ struct bpf_prog *oprog;
+
+ bpf_mprog_read(entry, idx, &fp, &cp);
+ oprog = READ_ONCE(fp->prog);
+ bpf_mprog_write(fp, cp, ntuple);
+ if (!ntuple->link) {
+ WARN_ON_ONCE(cp->link);
+ bpf_prog_put(oprog);
+ }
+ *entry_new = entry;
+ return 0;
+}
+
+static int bpf_mprog_insert(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_tuple *ntuple, int idx, u32 flags)
+{
+ int total = bpf_mprog_total(entry);
+ struct bpf_mprog_entry *peer;
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+
+ peer = bpf_mprog_peer(entry);
+ bpf_mprog_entry_copy(peer, entry);
+ if (idx == total)
+ goto insert;
+ else if (flags & BPF_F_BEFORE)
+ idx += 1;
+ bpf_mprog_entry_grow(peer, idx);
+insert:
+ bpf_mprog_read(peer, idx, &fp, &cp);
+ bpf_mprog_write(fp, cp, ntuple);
+ bpf_mprog_inc(peer);
+ *entry_new = peer;
+ return 0;
+}
+
+static int bpf_mprog_delete(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_tuple *dtuple, int idx)
+{
+ int total = bpf_mprog_total(entry);
+ struct bpf_mprog_entry *peer;
+
+ peer = bpf_mprog_peer(entry);
+ bpf_mprog_entry_copy(peer, entry);
+ if (idx == -1)
+ idx = 0;
+ else if (idx == total)
+ idx = total - 1;
+ bpf_mprog_entry_shrink(peer, idx);
+ bpf_mprog_dec(peer);
+ bpf_mprog_mark_for_release(peer, dtuple);
+ *entry_new = peer;
+ return 0;
+}
+
+/* In bpf_mprog_pos_*() we evaluate the target position for the BPF
+ * program/link that needs to be replaced, inserted or deleted for
+ * each "rule" independently. If all rules agree on that position
+ * or existing element, then enact replacement, addition or deletion.
+ * If this is not the case, then the request cannot be satisfied and
+ * we bail out with an error.
+ */
+static int bpf_mprog_pos_exact(struct bpf_mprog_entry *entry,
+ struct bpf_tuple *tuple)
+{
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ int i;
+
+ for (i = 0; i < bpf_mprog_total(entry); i++) {
+ bpf_mprog_read(entry, i, &fp, &cp);
+ if (tuple->prog == READ_ONCE(fp->prog))
+ return tuple->link == cp->link ? i : -EBUSY;
+ }
+ return -ENOENT;
+}
+
+static int bpf_mprog_pos_before(struct bpf_mprog_entry *entry,
+ struct bpf_tuple *tuple)
+{
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ int i;
+
+ for (i = 0; i < bpf_mprog_total(entry); i++) {
+ bpf_mprog_read(entry, i, &fp, &cp);
+ if (tuple->prog == READ_ONCE(fp->prog) &&
+ (!tuple->link || tuple->link == cp->link))
+ return i - 1;
+ }
+ return tuple->prog ? -ENOENT : -1;
+}
+
+static int bpf_mprog_pos_after(struct bpf_mprog_entry *entry,
+ struct bpf_tuple *tuple)
+{
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ int i;
+
+ for (i = 0; i < bpf_mprog_total(entry); i++) {
+ bpf_mprog_read(entry, i, &fp, &cp);
+ if (tuple->prog == READ_ONCE(fp->prog) &&
+ (!tuple->link || tuple->link == cp->link))
+ return i + 1;
+ }
+ return tuple->prog ? -ENOENT : bpf_mprog_total(entry);
+}
+
+int bpf_mprog_attach(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_prog *prog_new, struct bpf_link *link,
+ struct bpf_prog *prog_old,
+ u32 flags, u32 id_or_fd, u64 revision)
+{
+ struct bpf_tuple rtuple, ntuple = {
+ .prog = prog_new,
+ .link = link,
+ }, otuple = {
+ .prog = prog_old,
+ .link = link,
+ };
+ int ret, idx = -ERANGE, tidx;
+
+ if (revision && revision != bpf_mprog_revision(entry))
+ return -ESTALE;
+ if (bpf_mprog_exists(entry, prog_new))
+ return -EEXIST;
+ ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd,
+ flags & ~BPF_F_REPLACE,
+ prog_new->type);
+ if (ret)
+ return ret;
+ if (flags & BPF_F_REPLACE) {
+ tidx = bpf_mprog_pos_exact(entry, &otuple);
+ if (tidx < 0) {
+ ret = tidx;
+ goto out;
+ }
+ idx = tidx;
+ } else if (bpf_mprog_total(entry) == bpf_mprog_max()) {
+ ret = -ERANGE;
+ goto out;
+ }
+ if (flags & BPF_F_BEFORE) {
+ tidx = bpf_mprog_pos_before(entry, &rtuple);
+ if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+ ret = tidx < -1 ? tidx : -ERANGE;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (flags & BPF_F_AFTER) {
+ tidx = bpf_mprog_pos_after(entry, &rtuple);
+ if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+ ret = tidx < 0 ? tidx : -ERANGE;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (idx < -1) {
+ if (rtuple.prog || flags) {
+ ret = -EINVAL;
+ goto out;
+ }
+ idx = bpf_mprog_total(entry);
+ flags = BPF_F_AFTER;
+ }
+ if (idx >= bpf_mprog_max()) {
+ ret = -ERANGE;
+ goto out;
+ }
+ if (flags & BPF_F_REPLACE)
+ ret = bpf_mprog_replace(entry, entry_new, &ntuple, idx);
+ else
+ ret = bpf_mprog_insert(entry, entry_new, &ntuple, idx, flags);
+out:
+ bpf_mprog_tuple_put(&rtuple);
+ return ret;
+}
+
+static int bpf_mprog_fetch(struct bpf_mprog_entry *entry,
+ struct bpf_tuple *tuple, int idx)
+{
+ int total = bpf_mprog_total(entry);
+ struct bpf_mprog_cp *cp;
+ struct bpf_mprog_fp *fp;
+ struct bpf_prog *prog;
+ struct bpf_link *link;
+
+ if (idx == -1)
+ idx = 0;
+ else if (idx == total)
+ idx = total - 1;
+ bpf_mprog_read(entry, idx, &fp, &cp);
+ prog = READ_ONCE(fp->prog);
+ link = cp->link;
+ /* The deletion request can either be without filled tuple in which
+ * case it gets populated here based on idx, or with filled tuple
+ * where the only thing we end up doing is the WARN_ON_ONCE() assert.
+ * If we hit a BPF link at the given index, it must not be removed
+ * from opts path.
+ */
+ if (link && !tuple->link)
+ return -EBUSY;
+ WARN_ON_ONCE(tuple->prog && tuple->prog != prog);
+ WARN_ON_ONCE(tuple->link && tuple->link != link);
+ tuple->prog = prog;
+ tuple->link = link;
+ return 0;
+}
+
+int bpf_mprog_detach(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_prog *prog, struct bpf_link *link,
+ u32 flags, u32 id_or_fd, u64 revision)
+{
+ struct bpf_tuple rtuple, dtuple = {
+ .prog = prog,
+ .link = link,
+ };
+ int ret, idx = -ERANGE, tidx;
+
+ if (flags & BPF_F_REPLACE)
+ return -EINVAL;
+ if (revision && revision != bpf_mprog_revision(entry))
+ return -ESTALE;
+ if (!bpf_mprog_total(entry))
+ return -ENOENT;
+ ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags,
+ prog ? prog->type :
+ BPF_PROG_TYPE_UNSPEC);
+ if (ret)
+ return ret;
+ if (dtuple.prog) {
+ tidx = bpf_mprog_pos_exact(entry, &dtuple);
+ if (tidx < 0) {
+ ret = tidx;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (flags & BPF_F_BEFORE) {
+ tidx = bpf_mprog_pos_before(entry, &rtuple);
+ if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+ ret = tidx < -1 ? tidx : -ERANGE;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (flags & BPF_F_AFTER) {
+ tidx = bpf_mprog_pos_after(entry, &rtuple);
+ if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+ ret = tidx < 0 ? tidx : -ERANGE;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (idx < -1) {
+ if (rtuple.prog || flags) {
+ ret = -EINVAL;
+ goto out;
+ }
+ idx = bpf_mprog_total(entry);
+ flags = BPF_F_AFTER;
+ }
+ if (idx >= bpf_mprog_max()) {
+ ret = -ERANGE;
+ goto out;
+ }
+ ret = bpf_mprog_fetch(entry, &dtuple, idx);
+ if (ret)
+ goto out;
+ ret = bpf_mprog_delete(entry, entry_new, &dtuple, idx);
+out:
+ bpf_mprog_tuple_put(&rtuple);
+ return ret;
+}
+
+int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr,
+ struct bpf_mprog_entry *entry)
+{
+ u32 __user *uprog_flags, *ulink_flags;
+ u32 __user *uprog_id, *ulink_id;
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ struct bpf_prog *prog;
+ const u32 flags = 0;
+ u32 id, count = 0;
+ u64 revision = 1;
+ int i, ret = 0;
+
+ if (attr->query.query_flags || attr->query.attach_flags)
+ return -EINVAL;
+ if (entry) {
+ revision = bpf_mprog_revision(entry);
+ count = bpf_mprog_total(entry);
+ }
+ if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+ return -EFAULT;
+ if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision)))
+ return -EFAULT;
+ if (copy_to_user(&uattr->query.count, &count, sizeof(count)))
+ return -EFAULT;
+ uprog_id = u64_to_user_ptr(attr->query.prog_ids);
+ uprog_flags = u64_to_user_ptr(attr->query.prog_attach_flags);
+ ulink_id = u64_to_user_ptr(attr->query.link_ids);
+ ulink_flags = u64_to_user_ptr(attr->query.link_attach_flags);
+ if (attr->query.count == 0 || !uprog_id || !count)
+ return 0;
+ if (attr->query.count < count) {
+ count = attr->query.count;
+ ret = -ENOSPC;
+ }
+ for (i = 0; i < bpf_mprog_max(); i++) {
+ bpf_mprog_read(entry, i, &fp, &cp);
+ prog = READ_ONCE(fp->prog);
+ if (!prog)
+ break;
+ id = prog->aux->id;
+ if (copy_to_user(uprog_id + i, &id, sizeof(id)))
+ return -EFAULT;
+ if (uprog_flags &&
+ copy_to_user(uprog_flags + i, &flags, sizeof(flags)))
+ return -EFAULT;
+ id = cp->link ? cp->link->id : 0;
+ if (ulink_id &&
+ copy_to_user(ulink_id + i, &id, sizeof(id)))
+ return -EFAULT;
+ if (ulink_flags &&
+ copy_to_user(ulink_flags + i, &flags, sizeof(flags)))
+ return -EFAULT;
+ if (i + 1 == count)
+ break;
+ }
+ return ret;
+}
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 8a26cd8814c1..1a4fec330eaa 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -25,6 +25,7 @@
#include <linux/rhashtable.h>
#include <linux/rtnetlink.h>
#include <linux/rwsem.h>
+#include <net/xdp.h>
/* Protects offdevs, members of bpf_offload_netdev and offload members
* of all progs.
@@ -198,12 +199,14 @@ static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *n
offload->netdev = netdev;
ondev = bpf_offload_find_netdev(offload->netdev);
+ /* When program is offloaded require presence of "true"
+ * bpf_offload_netdev, avoid the one created for !ondev case below.
+ */
+ if (bpf_prog_is_offloaded(prog->aux) && (!ondev || !ondev->offdev)) {
+ err = -EINVAL;
+ goto err_free;
+ }
if (!ondev) {
- if (bpf_prog_is_offloaded(prog->aux)) {
- err = -EINVAL;
- goto err_free;
- }
-
/* When only binding to the device, explicitly
* create an entry in the hashtable.
*/
@@ -231,7 +234,14 @@ int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
attr->prog_type != BPF_PROG_TYPE_XDP)
return -EINVAL;
- if (attr->prog_flags & ~BPF_F_XDP_DEV_BOUND_ONLY)
+ if (attr->prog_flags & ~(BPF_F_XDP_DEV_BOUND_ONLY | BPF_F_XDP_HAS_FRAGS))
+ return -EINVAL;
+
+ /* Frags are allowed only if program is dev-bound-only, but not
+ * if it is requesting bpf offload.
+ */
+ if (attr->prog_flags & BPF_F_XDP_HAS_FRAGS &&
+ !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY))
return -EINVAL;
if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS &&
@@ -844,10 +854,11 @@ void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
if (!ops)
goto out;
- if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_TIMESTAMP))
- p = ops->xmo_rx_timestamp;
- else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_HASH))
- p = ops->xmo_rx_hash;
+#define XDP_METADATA_KFUNC(name, _, __, xmo) \
+ if (func_id == bpf_xdp_metadata_kfunc_id(name)) p = ops->xmo;
+ XDP_METADATA_KFUNC_xxx
+#undef XDP_METADATA_KFUNC
+
out:
up_read(&bpf_devs_lock);
diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile
index 8937dc6bc8d0..b83c2f5e9be1 100644
--- a/kernel/bpf/preload/iterators/Makefile
+++ b/kernel/bpf/preload/iterators/Makefile
@@ -50,7 +50,7 @@ iterators.lskel-%.h: $(OUTPUT)/%/iterators.bpf.o | $(BPFTOOL)
$(OUTPUT)/%/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT)
$(call msg,BPF,$@)
$(Q)mkdir -p $(@D)
- $(Q)$(CLANG) -g -O2 -target bpf -m$* $(INCLUDES) \
+ $(Q)$(CLANG) -g -O2 --target=bpf -m$* $(INCLUDES) \
-c $(filter %.c,$^) -o $@ && \
$(LLVM_STRIP) -g $@
diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c
index 03af863314ea..b78968b63fab 100644
--- a/kernel/bpf/preload/iterators/iterators.bpf.c
+++ b/kernel/bpf/preload/iterators/iterators.bpf.c
@@ -73,6 +73,8 @@ static const char *get_name(struct btf *btf, long btf_id, const char *fallback)
return str + name_off;
}
+__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym;
+
SEC("iter/bpf_map")
int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
{
@@ -84,9 +86,12 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
return 0;
if (seq_num == 0)
- BPF_SEQ_PRINTF(seq, " id name max_entries\n");
+ BPF_SEQ_PRINTF(seq, " id name max_entries cur_entries\n");
+
+ BPF_SEQ_PRINTF(seq, "%4u %-16s %10d %10lld\n",
+ map->id, map->name, map->max_entries,
+ bpf_map_sum_elem_count(map));
- BPF_SEQ_PRINTF(seq, "%4u %-16s%6d\n", map->id, map->name, map->max_entries);
return 0;
}
diff --git a/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
index 70f236a82fe1..5b98ab02025e 100644
--- a/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
+++ b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-/* THIS FILE IS AUTOGENERATED! */
+/* THIS FILE IS AUTOGENERATED BY BPFTOOL! */
#ifndef __ITERATORS_BPF_SKEL_H__
#define __ITERATORS_BPF_SKEL_H__
@@ -18,8 +18,6 @@ struct iterators_bpf {
int dump_bpf_map_fd;
int dump_bpf_prog_fd;
} links;
- struct iterators_bpf__rodata {
- } *rodata;
};
static inline int
@@ -68,7 +66,6 @@ iterators_bpf__destroy(struct iterators_bpf *skel)
iterators_bpf__detach(skel);
skel_closenz(skel->progs.dump_bpf_map.prog_fd);
skel_closenz(skel->progs.dump_bpf_prog.prog_fd);
- skel_free_map_data(skel->rodata, skel->maps.rodata.initial_value, 4096);
skel_closenz(skel->maps.rodata.map_fd);
skel_free(skel);
}
@@ -81,15 +78,6 @@ iterators_bpf__open(void)
if (!skel)
goto cleanup;
skel->ctx.sz = (void *)&skel->links - (void *)skel;
- skel->rodata = skel_prep_map_data((void *)"\
-\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\
-\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\
-\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0", 4096, 98);
- if (!skel->rodata)
- goto cleanup;
- skel->maps.rodata.initial_value = (__u64) (long) skel->rodata;
return skel;
cleanup:
iterators_bpf__destroy(skel);
@@ -103,7 +91,7 @@ iterators_bpf__load(struct iterators_bpf *skel)
int err;
opts.ctx = (struct bpf_loader_ctx *)skel;
- opts.data_sz = 6056;
+ opts.data_sz = 6208;
opts.data = (void *)"\
\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
@@ -138,190 +126,197 @@ iterators_bpf__load(struct iterators_bpf *skel)
\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x9f\xeb\x01\0\
-\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\xf9\x04\0\0\0\0\0\0\0\0\0\x02\x02\0\
+\x18\0\0\0\0\0\0\0\x80\x04\0\0\x80\x04\0\0\x31\x05\0\0\0\0\0\0\0\0\0\x02\x02\0\
\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\0\x04\
\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\0\0\0\0\0\
\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\0\0\0\x20\
-\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\0\0\xb1\0\
-\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\0\0\x80\0\
-\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\0\0\0\0\
-\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x94\x01\0\0\x03\0\0\x04\
-\x18\0\0\0\x9c\x01\0\0\x0e\0\0\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xa4\
-\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb0\x01\0\0\0\0\0\x08\x0f\0\0\0\xb6\x01\0\0\0\0\0\
-\x01\x04\0\0\0\x20\0\0\0\xc3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\
-\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xc8\x01\0\0\0\0\0\x01\x04\0\0\0\
-\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x2c\x02\0\0\x02\0\0\x04\x10\0\0\0\x13\0\
-\0\0\x03\0\0\0\0\0\0\0\x3f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x18\0\
-\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x44\x02\0\0\x01\0\0\x0c\
-\x16\0\0\0\x90\x02\0\0\x01\0\0\x04\x08\0\0\0\x99\x02\0\0\x19\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x02\x1a\0\0\0\xea\x02\0\0\x06\0\0\x04\x38\0\0\0\x9c\x01\0\0\x0e\0\0\
-\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xf7\x02\0\0\x1b\0\0\0\xc0\0\0\0\x08\
-\x03\0\0\x15\0\0\0\0\x01\0\0\x11\x03\0\0\x1d\0\0\0\x40\x01\0\0\x1b\x03\0\0\x1e\
-\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\0\0\0\0\
-\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x65\x03\0\0\x02\0\0\x04\
-\x08\0\0\0\x73\x03\0\0\x0e\0\0\0\0\0\0\0\x7c\x03\0\0\x0e\0\0\0\x20\0\0\0\x1b\
-\x03\0\0\x03\0\0\x04\x18\0\0\0\x86\x03\0\0\x1b\0\0\0\0\0\0\0\x8e\x03\0\0\x21\0\
-\0\0\x40\0\0\0\x94\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\0\0\0\
-\0\0\0\0\0\x02\x24\0\0\0\x98\x03\0\0\x01\0\0\x04\x04\0\0\0\xa3\x03\0\0\x0e\0\0\
-\0\0\0\0\0\x0c\x04\0\0\x01\0\0\x04\x04\0\0\0\x15\x04\0\0\x0e\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x8b\x04\0\0\0\0\0\x0e\x25\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\x9f\x04\
-\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\
-\x20\0\0\0\xb5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\
-\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xca\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe1\x04\0\0\0\0\0\x0e\x2d\0\0\
-\0\x01\0\0\0\xe9\x04\0\0\x04\0\0\x0f\x62\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\0\x28\
-\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\0\0\
-\x11\0\0\0\xf1\x04\0\0\x01\0\0\x0f\x04\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\x62\
-\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\
-\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
-\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x30\
-\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\x65\
-\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\
-\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\
-\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\
-\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\
-\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\
-\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\
-\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\x69\x67\x6e\
-\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\x09\x73\x74\
-\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\
-\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\
-\x29\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x20\x63\
-\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\x3b\0\x30\
-\x3a\x32\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\
-\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\
-\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\
-\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\
-\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\
-\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\
-\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\
-\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\
-\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\
-\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\
-\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\
-\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\
-\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\
-\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\
-\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\
-\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\
-\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\
-\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\
-\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\
-\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\
-\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\
-\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\
-\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\
-\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\
-\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
-\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\
-\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\
-\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\
-\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\
-\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\
-\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\
-\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\
-\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\
-\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\
-\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\
-\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\
-\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\
-\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\
-\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
-\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\
-\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\
-\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
-\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
-\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\
-\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x2d\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\
-\0\x04\0\0\0\x62\0\0\0\x01\0\0\0\x80\x04\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\
-\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x2f\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\
-\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\
-\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\
-\x25\x73\x20\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\
-\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1b\0\0\
-\0\0\0\x79\x11\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\
-\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x23\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\
-\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\
-\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\x7b\x2a\xf0\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\
-\x7b\x1a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\
-\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x23\0\0\0\xb7\x03\0\0\x0e\0\0\0\
-\xb7\x05\0\0\x18\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\
-\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x3c\x01\0\x01\0\0\0\x42\0\0\
-\0\x7b\0\0\0\x24\x3c\x01\0\x02\0\0\0\x42\0\0\0\xee\0\0\0\x1d\x44\x01\0\x03\0\0\
-\0\x42\0\0\0\x0f\x01\0\0\x06\x4c\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\x40\
-\x01\0\x05\0\0\0\x42\0\0\0\x1a\x01\0\0\x1d\x40\x01\0\x06\0\0\0\x42\0\0\0\x43\
-\x01\0\0\x06\x58\x01\0\x08\0\0\0\x42\0\0\0\x56\x01\0\0\x03\x5c\x01\0\x0f\0\0\0\
-\x42\0\0\0\xdc\x01\0\0\x02\x64\x01\0\x1f\0\0\0\x42\0\0\0\x2a\x02\0\0\x01\x6c\
-\x01\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\
-\0\x10\0\0\0\x02\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\
-\x28\0\0\0\x08\0\0\0\x3f\x01\0\0\0\0\0\0\x78\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\
-\x88\0\0\0\x0d\0\0\0\xea\0\0\0\0\0\0\0\xa8\0\0\0\x0d\0\0\0\x3f\x01\0\0\0\0\0\0\
-\x1a\0\0\0\x21\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\
-\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\
-\0\0\0\0\0\x0a\0\0\0\x01\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\
-\0\0\0\0\x79\x12\x08\0\0\0\0\0\x15\x02\x3c\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x79\
-\x27\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\
-\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\
-\x31\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x7b\
-\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xb7\x03\0\0\
-\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\x71\x28\0\0\0\0\0\x79\
-\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\
-\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\0\x03\0\0\0\x0f\x13\0\
-\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\
-\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\
-\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\
-\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\
-\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\
-\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\
-\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\
-\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\x79\xa1\
-\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x51\0\0\0\xb7\x03\0\0\x11\0\0\0\
-\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\
-\0\0\0\0\x17\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x80\x01\0\x01\0\0\0\x42\0\0\
-\0\x7b\0\0\0\x24\x80\x01\0\x02\0\0\0\x42\0\0\0\x60\x02\0\0\x1f\x88\x01\0\x03\0\
-\0\0\x42\0\0\0\x84\x02\0\0\x06\x94\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\
-\x84\x01\0\x05\0\0\0\x42\0\0\0\x9d\x02\0\0\x0e\xa0\x01\0\x06\0\0\0\x42\0\0\0\
-\x1a\x01\0\0\x1d\x84\x01\0\x07\0\0\0\x42\0\0\0\x43\x01\0\0\x06\xa4\x01\0\x09\0\
-\0\0\x42\0\0\0\xaf\x02\0\0\x03\xa8\x01\0\x11\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\
-\xb0\x01\0\x18\0\0\0\x42\0\0\0\x5a\x03\0\0\x06\x04\x01\0\x1b\0\0\0\x42\0\0\0\0\
-\0\0\0\0\0\0\0\x1c\0\0\0\x42\0\0\0\xab\x03\0\0\x0f\x10\x01\0\x1d\0\0\0\x42\0\0\
-\0\xc0\x03\0\0\x2d\x14\x01\0\x1f\0\0\0\x42\0\0\0\xf7\x03\0\0\x0d\x0c\x01\0\x21\
-\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x22\0\0\0\x42\0\0\0\xc0\x03\0\0\x02\x14\x01\0\
-\x25\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x28\0\0\0\x42\0\0\0\0\0\0\0\0\0\
-\0\0\x29\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x1e\x04\
-\0\0\x0d\x18\x01\0\x2d\0\0\0\x42\0\0\0\x4c\x04\0\0\x1b\x1c\x01\0\x2e\0\0\0\x42\
-\0\0\0\x4c\x04\0\0\x06\x1c\x01\0\x2f\0\0\0\x42\0\0\0\x6f\x04\0\0\x0d\x24\x01\0\
-\x31\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\xb0\x01\0\x40\0\0\0\x42\0\0\0\x2a\x02\0\0\
-\x01\xc0\x01\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\
-\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x14\0\0\0\x3e\0\0\0\
-\0\0\0\0\x28\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x30\0\0\0\x08\0\0\0\x3f\x01\0\0\
-\0\0\0\0\x88\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x98\0\0\0\x1a\0\0\0\xea\0\0\0\0\
-\0\0\0\xb0\0\0\0\x1a\0\0\0\x52\x03\0\0\0\0\0\0\xb8\0\0\0\x1a\0\0\0\x56\x03\0\0\
-\0\0\0\0\xc8\0\0\0\x1f\0\0\0\x84\x03\0\0\0\0\0\0\xe0\0\0\0\x20\0\0\0\xea\0\0\0\
-\0\0\0\0\xf8\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x20\x01\0\0\x24\0\0\0\x3e\0\0\0\
-\0\0\0\0\x58\x01\0\0\x1a\0\0\0\xea\0\0\0\0\0\0\0\x68\x01\0\0\x20\0\0\0\x46\x04\
-\0\0\0\0\0\0\x90\x01\0\0\x1a\0\0\0\x3f\x01\0\0\0\0\0\0\xa0\x01\0\0\x1a\0\0\0\
-\x87\x04\0\0\0\0\0\0\xa8\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x42\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\
-\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x1a\0\
-\0\0\x01\0\0\0\0\0\0\0\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\
-\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\
-\0\0\0\0";
- opts.insns_sz = 2216;
+\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xb0\0\0\0\x03\0\0\x04\x18\0\0\0\xbe\0\
+\0\0\x09\0\0\0\0\0\0\0\xc2\0\0\0\x0b\0\0\0\x40\0\0\0\xcd\0\0\0\x0b\0\0\0\x80\0\
+\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xd5\0\0\0\0\0\0\x07\0\0\0\0\xde\0\0\0\0\0\0\
+\x08\x0c\0\0\0\xe4\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\xae\x01\0\0\x03\0\0\x04\
+\x18\0\0\0\xb6\x01\0\0\x0e\0\0\0\0\0\0\0\xb9\x01\0\0\x11\0\0\0\x20\0\0\0\xbe\
+\x01\0\0\x0e\0\0\0\xa0\0\0\0\xca\x01\0\0\0\0\0\x08\x0f\0\0\0\xd0\x01\0\0\0\0\0\
+\x01\x04\0\0\0\x20\0\0\0\xdd\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\
+\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xe2\x01\0\0\0\0\0\x01\x04\0\0\0\
+\x20\0\0\0\0\0\0\0\x01\0\0\x0d\x14\0\0\0\x26\x05\0\0\x04\0\0\0\x2b\x02\0\0\0\0\
+\0\x08\x15\0\0\0\x31\x02\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\x01\x3b\x02\0\0\x01\0\
+\0\x0c\x13\0\0\0\0\0\0\0\0\0\0\x02\x18\0\0\0\x52\x02\0\0\x02\0\0\x04\x10\0\0\0\
+\x13\0\0\0\x03\0\0\0\0\0\0\0\x65\x02\0\0\x19\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
+\x1c\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x17\0\0\0\x6a\x02\0\0\x01\0\
+\0\x0c\x1a\0\0\0\xb6\x02\0\0\x01\0\0\x04\x08\0\0\0\xbf\x02\0\0\x1d\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x02\x1e\0\0\0\x10\x03\0\0\x06\0\0\x04\x38\0\0\0\xb6\x01\0\0\
+\x0e\0\0\0\0\0\0\0\xb9\x01\0\0\x11\0\0\0\x20\0\0\0\x1d\x03\0\0\x1f\0\0\0\xc0\0\
+\0\0\x2e\x03\0\0\x19\0\0\0\0\x01\0\0\x37\x03\0\0\x21\0\0\0\x40\x01\0\0\x41\x03\
+\0\0\x22\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\
+\0\0\0\0\0\0\0\0\0\x02\x23\0\0\0\0\0\0\0\0\0\0\x02\x24\0\0\0\x8b\x03\0\0\x02\0\
+\0\x04\x08\0\0\0\x99\x03\0\0\x0e\0\0\0\0\0\0\0\xa2\x03\0\0\x0e\0\0\0\x20\0\0\0\
+\x41\x03\0\0\x03\0\0\x04\x18\0\0\0\xac\x03\0\0\x1f\0\0\0\0\0\0\0\xb4\x03\0\0\
+\x25\0\0\0\x40\0\0\0\xba\x03\0\0\x27\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x26\0\0\
+\0\0\0\0\0\0\0\0\x02\x28\0\0\0\xbe\x03\0\0\x01\0\0\x04\x04\0\0\0\xc9\x03\0\0\
+\x0e\0\0\0\0\0\0\0\x32\x04\0\0\x01\0\0\x04\x04\0\0\0\x3b\x04\0\0\x0e\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\x12\0\0\0\x30\0\0\0\xb1\x04\0\0\0\0\0\
+\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\x12\0\0\0\x1a\0\0\0\
+\xc5\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\
+\x12\0\0\0\x20\0\0\0\xdb\x04\0\0\0\0\0\x0e\x2d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
+\0\0\0\0\x20\0\0\0\x12\0\0\0\x11\0\0\0\xf0\x04\0\0\0\0\0\x0e\x2f\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\x07\x05\0\0\0\0\0\x0e\
+\x31\0\0\0\x01\0\0\0\x0f\x05\0\0\x01\0\0\x0f\x04\0\0\0\x36\0\0\0\0\0\0\0\x04\0\
+\0\0\x16\x05\0\0\x04\0\0\x0f\x7b\0\0\0\x2a\0\0\0\0\0\0\0\x30\0\0\0\x2c\0\0\0\
+\x30\0\0\0\x1a\0\0\0\x2e\0\0\0\x4a\0\0\0\x20\0\0\0\x30\0\0\0\x6a\0\0\0\x11\0\0\
+\0\x1e\x05\0\0\x01\0\0\x0f\x04\0\0\0\x32\0\0\0\0\0\0\0\x04\0\0\0\x26\x05\0\0\0\
+\0\0\x0e\x06\0\0\0\x01\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\
+\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\
+\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\
+\x62\x70\x66\x5f\x6d\x61\x70\0\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x2f\x61\x73\
+\x70\x73\x6b\x2f\x73\x72\x63\x2f\x62\x70\x66\x2d\x6e\x65\x78\x74\x2f\x6b\x65\
+\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\
+\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\
+\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\
+\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\
+\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\
+\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\
+\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\
+\x69\x67\x6e\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\
+\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\
+\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\
+\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\
+\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\
+\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\
+\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\
+\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\
+\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\
+\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\x6e\
+\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\x6d\
+\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\x73\
+\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\x52\
+\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\x5f\
+\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\
+\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\x31\x30\x64\x20\x20\x20\x25\x31\x30\
+\x6c\x6c\x64\x5c\x6e\x22\x2c\0\x7d\0\x5f\x5f\x73\x36\x34\0\x6c\x6f\x6e\x67\x20\
+\x6c\x6f\x6e\x67\0\x62\x70\x66\x5f\x6d\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\
+\x6d\x5f\x63\x6f\x75\x6e\x74\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\
+\x66\x5f\x70\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
+\x5f\x70\x72\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\
+\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\
+\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\
+\x20\x28\x21\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\
+\x78\0\x09\x61\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\
+\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
+\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\
+\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\
+\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\
+\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\
+\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\
+\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\
+\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\
+\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\
+\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\
+\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\
+\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\
+\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\
+\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\
+\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\
+\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\
+\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\
+\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\
+\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
+\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\
+\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\
+\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\
+\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\
+\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\
+\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
+\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
+\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\
+\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\
+\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x6b\x73\x79\x6d\
+\x73\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x64\x75\x6d\
+\x6d\x79\x5f\x6b\x73\x79\x6d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\xc9\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\0\x04\0\0\0\x7b\0\0\0\x01\0\0\0\
+\x80\0\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\
+\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x34\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\
+\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
+\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\
+\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\
+\x31\x30\x64\x20\x20\x20\x25\x31\x30\x6c\x6c\x64\x0a\0\x20\x20\x69\x64\x20\x6e\
+\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\
+\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
+\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\
+\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1d\0\0\0\0\0\x79\x21\
+\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe0\xff\
+\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\
+\x30\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\
+\xe0\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\
+\x7b\x2a\xe8\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\x7b\x1a\xf0\xff\0\0\0\0\xbf\x71\
+\0\0\0\0\0\0\x85\x20\0\0\0\0\0\0\x7b\x0a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\
+\x07\x04\0\0\xe0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\
+\x30\0\0\0\xb7\x03\0\0\x1a\0\0\0\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\
+\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x88\0\0\0\
+\x1e\x44\x01\0\x01\0\0\0\x42\0\0\0\x88\0\0\0\x24\x44\x01\0\x02\0\0\0\x42\0\0\0\
+\xfb\0\0\0\x1d\x4c\x01\0\x03\0\0\0\x42\0\0\0\x1c\x01\0\0\x06\x54\x01\0\x04\0\0\
+\0\x42\0\0\0\x2b\x01\0\0\x1d\x48\x01\0\x05\0\0\0\x42\0\0\0\x50\x01\0\0\x06\x60\
+\x01\0\x07\0\0\0\x42\0\0\0\x63\x01\0\0\x03\x64\x01\0\x0e\0\0\0\x42\0\0\0\xf6\
+\x01\0\0\x02\x6c\x01\0\x21\0\0\0\x42\0\0\0\x29\x02\0\0\x01\x80\x01\0\0\0\0\0\
+\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\
+\x02\0\0\0\xf7\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x27\x01\0\0\0\0\0\0\x70\0\0\0\
+\x0d\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xf7\0\0\0\0\0\0\0\xa0\0\0\0\
+\x0d\0\0\0\x27\x01\0\0\0\0\0\0\x1a\0\0\0\x23\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\
+\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\
+\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x09\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\
+\x65\x72\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x62\x70\x66\x5f\x6d\
+\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\x6d\x5f\x63\x6f\x75\x6e\x74\0\0\x47\
+\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x11\x08\0\0\0\0\
+\0\x15\x01\x3b\0\0\0\0\0\x79\x17\0\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\
+\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\
+\x18\x62\0\0\0\0\0\0\0\0\0\0\x4a\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x7e\0\0\0\x7b\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\
+\xff\0\0\0\0\xb7\x03\0\0\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\
+\x71\x28\0\0\0\0\0\x79\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\
+\0\0\x0f\x21\0\0\0\0\0\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\
+\0\x03\0\0\0\x0f\x13\0\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\
+\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\
+\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\
+\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\
+\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\
+\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\
+\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\
+\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\
+\xff\xff\xff\x79\xa1\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x6a\0\0\0\xb7\
+\x03\0\0\x11\0\0\0\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\
+\x95\0\0\0\0\0\0\0\0\0\0\0\x1b\0\0\0\0\0\0\0\x42\0\0\0\x88\0\0\0\x1e\x94\x01\0\
+\x01\0\0\0\x42\0\0\0\x88\0\0\0\x24\x94\x01\0\x02\0\0\0\x42\0\0\0\x86\x02\0\0\
+\x1f\x9c\x01\0\x03\0\0\0\x42\0\0\0\xaa\x02\0\0\x06\xa8\x01\0\x04\0\0\0\x42\0\0\
+\0\xc3\x02\0\0\x0e\xb4\x01\0\x05\0\0\0\x42\0\0\0\x2b\x01\0\0\x1d\x98\x01\0\x06\
+\0\0\0\x42\0\0\0\x50\x01\0\0\x06\xb8\x01\0\x08\0\0\0\x42\0\0\0\xd5\x02\0\0\x03\
+\xbc\x01\0\x10\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x17\0\0\0\x42\0\0\0\
+\x80\x03\0\0\x06\x04\x01\0\x1a\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x1b\0\
+\0\0\x42\0\0\0\xd1\x03\0\0\x0f\x10\x01\0\x1c\0\0\0\x42\0\0\0\xe6\x03\0\0\x2d\
+\x14\x01\0\x1e\0\0\0\x42\0\0\0\x1d\x04\0\0\x0d\x0c\x01\0\x20\0\0\0\x42\0\0\0\
+\x45\x03\0\0\x02\xc4\x01\0\x21\0\0\0\x42\0\0\0\xe6\x03\0\0\x02\x14\x01\0\x24\0\
+\0\0\x42\0\0\0\x44\x04\0\0\x0d\x18\x01\0\x27\0\0\0\x42\0\0\0\x45\x03\0\0\x02\
+\xc4\x01\0\x28\0\0\0\x42\0\0\0\x44\x04\0\0\x0d\x18\x01\0\x2b\0\0\0\x42\0\0\0\
+\x44\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x72\x04\0\0\x1b\x1c\x01\0\x2d\0\
+\0\0\x42\0\0\0\x72\x04\0\0\x06\x1c\x01\0\x2e\0\0\0\x42\0\0\0\x95\x04\0\0\x0d\
+\x24\x01\0\x30\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x3f\0\0\0\x42\0\0\0\
+\x29\x02\0\0\x01\xd4\x01\0\0\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\
+\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x18\0\0\0\xf7\0\0\0\0\0\0\0\x20\0\0\0\x1c\0\0\
+\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\0\x27\x01\0\0\0\0\0\0\x80\0\0\0\x1e\0\0\
+\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1e\0\0\0\xf7\0\0\0\0\0\0\0\xa8\0\0\0\x1e\0\0\0\
+\x78\x03\0\0\0\0\0\0\xb0\0\0\0\x1e\0\0\0\x7c\x03\0\0\0\0\0\0\xc0\0\0\0\x23\0\0\
+\0\xaa\x03\0\0\0\0\0\0\xd8\0\0\0\x24\0\0\0\xf7\0\0\0\0\0\0\0\xf0\0\0\0\x24\0\0\
+\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x28\0\0\0\x3e\0\0\0\0\0\0\0\x50\x01\0\0\x1e\0\
+\0\0\xf7\0\0\0\0\0\0\0\x60\x01\0\0\x24\0\0\0\x6c\x04\0\0\0\0\0\0\x88\x01\0\0\
+\x1e\0\0\0\x27\x01\0\0\0\0\0\0\x98\x01\0\0\x1e\0\0\0\xad\x04\0\0\0\0\0\0\xa0\
+\x01\0\0\x1c\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x41\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\
+\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\
+\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x19\0\0\0\x01\0\0\0\0\0\0\0\
+\x12\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\
+\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0";
+ opts.insns_sz = 2456;
opts.insns = (void *)"\
\xbf\x16\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\x78\xff\xff\xff\xb7\x02\0\
\0\x88\0\0\0\xb7\x03\0\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x05\0\x14\0\0\0\0\0\x61\
@@ -331,79 +326,83 @@ iterators_bpf__load(struct iterators_bpf *skel)
\0\0\0\x85\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\
\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xbf\x70\0\0\
\0\0\0\0\x95\0\0\0\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x48\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\
-\0\0\x44\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\
-\0\0\0\0\x38\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\
-\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\
-\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\
+\xe8\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\
+\0\0\xe4\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\
+\0\0\0\0\xd8\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\xd0\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\
+\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xd0\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\
\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\xd4\xff\0\0\0\0\x63\x7a\x78\xff\0\0\0\0\
-\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x0e\0\0\x63\x01\0\0\0\
+\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x0f\0\0\x63\x01\0\0\0\
\0\0\0\x61\x60\x1c\0\0\0\0\0\x15\0\x03\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x5c\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\
-\0\x50\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\
+\xfc\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\
+\0\xf0\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\
\xc5\x07\xc3\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x71\0\0\0\0\0\
-\0\x79\x63\x20\0\0\0\0\0\x15\x03\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x98\
-\x0e\0\0\xb7\x02\0\0\x62\0\0\0\x61\x60\x04\0\0\0\0\0\x45\0\x02\0\x01\0\0\0\x85\
+\0\x79\x63\x20\0\0\0\0\0\x15\x03\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x38\
+\x0f\0\0\xb7\x02\0\0\x7b\0\0\0\x61\x60\x04\0\0\0\0\0\x45\0\x02\0\x01\0\0\0\x85\
\0\0\0\x94\0\0\0\x05\0\x01\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x18\x62\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\x63\
-\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\
-\0\0\x10\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x0e\0\0\
-\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\
-\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\
+\0\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc0\x0f\0\0\x63\
+\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xb8\x0f\0\0\x18\x61\0\0\0\0\0\0\0\
+\0\0\0\xc8\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\xd0\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\
+\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xc0\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\
\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x9f\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\x63\
-\x01\0\0\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\
+\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\x0f\0\0\x63\
+\x01\0\0\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xe0\x0f\0\0\
\xb7\x03\0\0\x04\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x92\xff\
-\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x78\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\x18\
-\x61\0\0\0\0\0\0\0\0\0\0\x70\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
-\0\0\0\x40\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x11\0\0\x7b\x01\0\0\0\0\0\0\
-\x18\x60\0\0\0\0\0\0\0\0\0\0\x48\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc8\x11\0\
-\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x10\0\0\x18\x61\0\0\0\0\
-\0\0\0\0\0\0\xe8\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\
-\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x11\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\
-\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x84\x11\0\0\x63\x01\0\0\0\0\0\0\x79\x60\
-\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\
-\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x11\0\0\x63\x01\0\0\0\0\0\
-\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xf8\x11\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\
+\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
+\x20\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xf0\x0f\0\0\x18\
+\x61\0\0\0\0\0\0\0\0\0\0\x18\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
+\0\0\0\x08\x11\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x60\x12\0\0\x7b\x01\0\0\0\0\0\0\
+\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x11\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x70\x12\0\
+\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xa0\x11\0\0\x18\x61\0\0\0\0\
+\0\0\0\0\0\0\x90\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x12\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\
+\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x12\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\
+\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x2c\x12\0\0\x63\x01\0\0\0\0\0\0\x79\x60\
+\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x12\0\0\x7b\x01\0\0\0\0\0\0\x61\
+\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x58\x12\0\0\x63\x01\0\0\0\0\0\
+\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xa0\x12\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\
\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\
-\x5c\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x68\x11\0\0\x63\x70\x6c\0\0\0\0\0\
-\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\
-\0\0\0\0\0\0\0\0\x68\x11\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\
-\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd8\x11\0\0\x61\x01\0\0\0\0\0\0\xd5\
-\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x4a\xff\0\0\
-\0\0\x63\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x18\x61\0\
-\0\0\0\0\0\0\0\0\0\x10\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\
-\x18\x12\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\
-\x60\0\0\0\0\0\0\0\0\0\0\x28\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x50\x17\0\0\
-\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x14\0\0\x18\x61\0\0\0\0\0\
-\0\0\0\0\0\x60\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x15\
-\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x78\x17\0\0\x7b\x01\0\0\0\0\
-\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x17\0\0\x63\x01\0\0\
-\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x1c\x17\0\0\x63\x01\
-\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\x7b\
-\x01\0\0\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x48\x17\0\
-\0\x63\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x90\x17\0\0\xb7\x02\0\0\x12\
-\0\0\0\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\
-\0\0\0\0\0\xc5\x07\x13\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\x63\
-\x70\x6c\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\
-\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\
-\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x70\x17\0\0\x61\x01\
-\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\
-\x07\x01\xff\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\xd5\x01\
-\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\0\0\0\0\
-\x63\x06\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\x18\x61\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\xb7\0\0\0\
-\0\0\0\0\x95\0\0\0\0\0\0\0";
+\x5c\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x63\x70\x6c\0\0\0\0\0\
+\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\x18\x68\0\0\0\0\0\0\0\0\0\0\xa8\
+\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x12\0\0\xb7\x02\0\0\x17\0\0\0\xb7\x03\
+\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\
+\x07\x4d\xff\0\0\0\0\x75\x07\x03\0\0\0\0\0\x62\x08\x04\0\0\0\0\0\x6a\x08\x02\0\
+\0\0\0\0\x05\0\x0a\0\0\0\0\0\x63\x78\x04\0\0\0\0\0\xbf\x79\0\0\0\0\0\0\x77\x09\
+\0\0\x20\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\x63\x90\0\0\0\0\0\0\x55\
+\x09\x02\0\0\0\0\0\x6a\x08\x02\0\0\0\0\0\x05\0\x01\0\0\0\0\0\x6a\x08\x02\0\x40\
+\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\xb7\x03\0\
+\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\
+\0\0\x01\0\0\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\
+\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x80\x12\0\0\x61\x01\0\0\0\0\0\0\
+\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x2c\xff\
+\0\0\0\0\x63\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x12\0\0\x18\
+\x61\0\0\0\0\0\0\0\0\0\0\xa8\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
+\0\0\0\xd8\x12\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xa0\x17\0\0\x7b\x01\0\0\0\0\0\0\
+\x18\x60\0\0\0\0\0\0\0\0\0\0\xe0\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe8\x17\0\
+\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x14\0\0\x18\x61\0\0\0\0\
+\0\0\0\0\0\0\xf8\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x78\
+\x16\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x18\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x10\x18\0\0\x7b\x01\0\0\
+\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x17\0\0\x63\x01\
+\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb4\x17\0\0\x63\
+\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x17\0\0\
+\x7b\x01\0\0\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\
+\x17\0\0\x63\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x18\0\0\xb7\x02\0\
+\0\x12\0\0\0\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\
+\x07\0\0\0\0\0\0\xc5\x07\xf5\xfe\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x17\0\
+\0\x63\x70\x6c\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\
+\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x98\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\
+\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x08\x18\0\0\
+\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\
+\0\0\xc5\x07\xe3\xfe\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\
+\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\
+\0\0\0\0\x63\x06\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\
+\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0";
err = bpf_load_and_run(&opts);
if (err < 0)
return err;
- skel->rodata = skel_finalize_map_data(&skel->maps.rodata.initial_value,
- 4096, PROT_READ, skel->maps.rodata.map_fd);
- if (!skel->rodata)
- return -ENOMEM;
return 0;
}
@@ -422,4 +421,15 @@ iterators_bpf__open_and_load(void)
return skel;
}
+__attribute__((unused)) static void
+iterators_bpf__assert(struct iterators_bpf *s __attribute__((unused)))
+{
+#ifdef __cplusplus
+#define _Static_assert static_assert
+#endif
+#ifdef __cplusplus
+#undef _Static_assert
+#endif
+}
+
#endif /* __ITERATORS_BPF_SKEL_H__ */
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8d2ddcb7566b..d869f51ea93a 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -98,7 +98,12 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
int err = 0;
void *ptr;
- raw_spin_lock_irqsave(&qs->lock, flags);
+ if (in_nmi()) {
+ if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+ return -EBUSY;
+ } else {
+ raw_spin_lock_irqsave(&qs->lock, flags);
+ }
if (queue_stack_map_is_empty(qs)) {
memset(value, 0, qs->map.value_size);
@@ -128,7 +133,12 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
void *ptr;
u32 index;
- raw_spin_lock_irqsave(&qs->lock, flags);
+ if (in_nmi()) {
+ if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+ return -EBUSY;
+ } else {
+ raw_spin_lock_irqsave(&qs->lock, flags);
+ }
if (queue_stack_map_is_empty(qs)) {
memset(value, 0, qs->map.value_size);
@@ -193,7 +203,12 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
if (flags & BPF_NOEXIST || flags > BPF_EXIST)
return -EINVAL;
- raw_spin_lock_irqsave(&qs->lock, irq_flags);
+ if (in_nmi()) {
+ if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
+ return -EBUSY;
+ } else {
+ raw_spin_lock_irqsave(&qs->lock, irq_flags);
+ }
if (queue_stack_map_is_full(qs)) {
if (!replace) {
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 875ac9b698d9..0ee653a936ea 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -23,15 +23,6 @@
#define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4)
-/* Maximum size of ring buffer area is limited by 32-bit page offset within
- * record header, counted in pages. Reserve 8 bits for extensibility, and take
- * into account few extra pages for consumer/producer pages and
- * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single
- * ring buffer.
- */
-#define RINGBUF_MAX_DATA_SZ \
- (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE)
-
struct bpf_ringbuf {
wait_queue_head_t waitq;
struct irq_work work;
@@ -161,6 +152,17 @@ static void bpf_ringbuf_notify(struct irq_work *work)
wake_up_all(&rb->waitq);
}
+/* Maximum size of ring buffer area is limited by 32-bit page offset within
+ * record header, counted in pages. Reserve 8 bits for extensibility, and
+ * take into account few extra pages for consumer/producer pages and
+ * non-mmap()'able parts, the current maximum size would be:
+ *
+ * (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE)
+ *
+ * This gives 64GB limit, which seems plenty for single ring buffer. Now
+ * considering that the maximum value of data_sz is (4GB - 1), there
+ * will be no overflow, so just note the size limit in the comments.
+ */
static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
{
struct bpf_ringbuf *rb;
@@ -193,12 +195,6 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
!PAGE_ALIGNED(attr->max_entries))
return ERR_PTR(-EINVAL);
-#ifdef CONFIG_64BIT
- /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */
- if (attr->max_entries > RINGBUF_MAX_DATA_SZ)
- return ERR_PTR(-E2BIG);
-#endif
-
rb_map = bpf_map_area_alloc(sizeof(*rb_map), NUMA_NO_NODE);
if (!rb_map)
return ERR_PTR(-ENOMEM);
@@ -774,8 +770,7 @@ schedule_work_return:
/* Prevent the clearing of the busy-bit from being reordered before the
* storing of any rb consumer or producer positions.
*/
- smp_mb__before_atomic();
- atomic_set(&rb->busy, 0);
+ atomic_set_release(&rb->busy, 0);
if (flags & BPF_RB_FORCE_WAKEUP)
irq_work_queue(&rb->work);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 458bb80b14d5..d6b277482085 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -28,7 +28,7 @@ struct bpf_stack_map {
void *elems;
struct pcpu_freelist freelist;
u32 n_buckets;
- struct stack_map_bucket *buckets[];
+ struct stack_map_bucket *buckets[] __counted_by(n_buckets);
};
static inline bool stack_map_use_build_id(struct bpf_map *map)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a2aef900519c..0ed286b8a0f0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -35,7 +35,10 @@
#include <linux/rcupdate_trace.h>
#include <linux/memcontrol.h>
#include <linux/trace_events.h>
+
#include <net/netfilter/nf_bpf_link.h>
+#include <net/netkit.h>
+#include <net/tcx.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -512,6 +515,7 @@ void btf_record_free(struct btf_record *rec)
switch (rec->fields[i].type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
if (rec->fields[i].kptr.module)
module_put(rec->fields[i].kptr.module);
btf_put(rec->fields[i].kptr.btf);
@@ -558,6 +562,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
switch (fields[i].type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
btf_get(fields[i].kptr.btf);
if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) {
ret = -ENXIO;
@@ -622,8 +627,6 @@ void bpf_obj_free_timer(const struct btf_record *rec, void *obj)
bpf_timer_cancel_and_free(obj + rec->timer_off);
}
-extern void __bpf_obj_drop_impl(void *p, const struct btf_record *rec);
-
void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
{
const struct btf_field *fields;
@@ -648,6 +651,7 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
WRITE_ONCE(*(u64 *)field_ptr, 0);
break;
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0);
if (!xchgd_field)
break;
@@ -655,11 +659,10 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
if (!btf_is_kernel(field->kptr.btf)) {
pointee_struct_meta = btf_find_struct_meta(field->kptr.btf,
field->kptr.btf_id);
- WARN_ON_ONCE(!pointee_struct_meta);
migrate_disable();
__bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ?
- pointee_struct_meta->record :
- NULL);
+ pointee_struct_meta->record : NULL,
+ fields[i].type == BPF_KPTR_PERCPU);
migrate_enable();
} else {
field->kptr.dtor(xchgd_field);
@@ -1044,6 +1047,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
case BPF_REFCOUNT:
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
@@ -2441,14 +2445,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
return 0;
default:
return -EINVAL;
@@ -2744,7 +2753,7 @@ free_used_maps:
* period before we can tear down JIT memory since symbols
* are already exposed under kallsyms.
*/
- __bpf_prog_put_noref(prog, prog->aux->func_cnt);
+ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt);
return err;
free_prog_sec:
free_uid(prog->aux->user);
@@ -2813,10 +2822,12 @@ static void bpf_link_free_id(int id)
/* Clean up bpf_link and corresponding anon_inode file and FD. After
* anon_inode is created, bpf_link can't be just kfree()'d due to deferred
- * anon_inode's release() call. This helper marksbpf_link as
+ * anon_inode's release() call. This helper marks bpf_link as
* defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt
* is not decremented, it's the responsibility of a calling code that failed
* to complete bpf_link initialization.
+ * This helper eventually calls link's dealloc callback, but does not call
+ * link's release callback.
*/
void bpf_link_cleanup(struct bpf_link_primer *primer)
{
@@ -3295,6 +3306,25 @@ static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link,
raw_tp_link->btp->tp->name);
}
+static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen,
+ u32 len)
+{
+ if (ulen >= len + 1) {
+ if (copy_to_user(ubuf, buf, len + 1))
+ return -EFAULT;
+ } else {
+ char zero = '\0';
+
+ if (copy_to_user(ubuf, buf, ulen - 1))
+ return -EFAULT;
+ if (put_user(zero, ubuf + ulen - 1))
+ return -EFAULT;
+ return -ENOSPC;
+ }
+
+ return 0;
+}
+
static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
struct bpf_link_info *info)
{
@@ -3313,20 +3343,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
if (!ubuf)
return 0;
- if (ulen >= tp_len + 1) {
- if (copy_to_user(ubuf, tp_name, tp_len + 1))
- return -EFAULT;
- } else {
- char zero = '\0';
-
- if (copy_to_user(ubuf, tp_name, ulen - 1))
- return -EFAULT;
- if (put_user(zero, ubuf + ulen - 1))
- return -EFAULT;
- return -ENOSPC;
- }
-
- return 0;
+ return bpf_copy_to_user(ubuf, tp_name, ulen, tp_len);
}
static const struct bpf_link_ops bpf_raw_tp_link_lops = {
@@ -3358,9 +3375,156 @@ static void bpf_perf_link_dealloc(struct bpf_link *link)
kfree(perf_link);
}
+static int bpf_perf_link_fill_common(const struct perf_event *event,
+ char __user *uname, u32 ulen,
+ u64 *probe_offset, u64 *probe_addr,
+ u32 *fd_type, unsigned long *missed)
+{
+ const char *buf;
+ u32 prog_id;
+ size_t len;
+ int err;
+
+ if (!ulen ^ !uname)
+ return -EINVAL;
+
+ err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
+ probe_offset, probe_addr, missed);
+ if (err)
+ return err;
+ if (!uname)
+ return 0;
+ if (buf) {
+ len = strlen(buf);
+ err = bpf_copy_to_user(uname, buf, ulen, len);
+ if (err)
+ return err;
+ } else {
+ char zero = '\0';
+
+ if (put_user(zero, uname))
+ return -EFAULT;
+ }
+ return 0;
+}
+
+#ifdef CONFIG_KPROBE_EVENTS
+static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
+ struct bpf_link_info *info)
+{
+ unsigned long missed;
+ char __user *uname;
+ u64 addr, offset;
+ u32 ulen, type;
+ int err;
+
+ uname = u64_to_user_ptr(info->perf_event.kprobe.func_name);
+ ulen = info->perf_event.kprobe.name_len;
+ err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+ &type, &missed);
+ if (err)
+ return err;
+ if (type == BPF_FD_TYPE_KRETPROBE)
+ info->perf_event.type = BPF_PERF_EVENT_KRETPROBE;
+ else
+ info->perf_event.type = BPF_PERF_EVENT_KPROBE;
+
+ info->perf_event.kprobe.offset = offset;
+ info->perf_event.kprobe.missed = missed;
+ if (!kallsyms_show_value(current_cred()))
+ addr = 0;
+ info->perf_event.kprobe.addr = addr;
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_UPROBE_EVENTS
+static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
+ struct bpf_link_info *info)
+{
+ char __user *uname;
+ u64 addr, offset;
+ u32 ulen, type;
+ int err;
+
+ uname = u64_to_user_ptr(info->perf_event.uprobe.file_name);
+ ulen = info->perf_event.uprobe.name_len;
+ err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+ &type, NULL);
+ if (err)
+ return err;
+
+ if (type == BPF_FD_TYPE_URETPROBE)
+ info->perf_event.type = BPF_PERF_EVENT_URETPROBE;
+ else
+ info->perf_event.type = BPF_PERF_EVENT_UPROBE;
+ info->perf_event.uprobe.offset = offset;
+ return 0;
+}
+#endif
+
+static int bpf_perf_link_fill_probe(const struct perf_event *event,
+ struct bpf_link_info *info)
+{
+#ifdef CONFIG_KPROBE_EVENTS
+ if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE)
+ return bpf_perf_link_fill_kprobe(event, info);
+#endif
+#ifdef CONFIG_UPROBE_EVENTS
+ if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE)
+ return bpf_perf_link_fill_uprobe(event, info);
+#endif
+ return -EOPNOTSUPP;
+}
+
+static int bpf_perf_link_fill_tracepoint(const struct perf_event *event,
+ struct bpf_link_info *info)
+{
+ char __user *uname;
+ u32 ulen;
+
+ uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name);
+ ulen = info->perf_event.tracepoint.name_len;
+ info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT;
+ return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL);
+}
+
+static int bpf_perf_link_fill_perf_event(const struct perf_event *event,
+ struct bpf_link_info *info)
+{
+ info->perf_event.event.type = event->attr.type;
+ info->perf_event.event.config = event->attr.config;
+ info->perf_event.type = BPF_PERF_EVENT_EVENT;
+ return 0;
+}
+
+static int bpf_perf_link_fill_link_info(const struct bpf_link *link,
+ struct bpf_link_info *info)
+{
+ struct bpf_perf_link *perf_link;
+ const struct perf_event *event;
+
+ perf_link = container_of(link, struct bpf_perf_link, link);
+ event = perf_get_event(perf_link->perf_file);
+ if (IS_ERR(event))
+ return PTR_ERR(event);
+
+ switch (event->prog->type) {
+ case BPF_PROG_TYPE_PERF_EVENT:
+ return bpf_perf_link_fill_perf_event(event, info);
+ case BPF_PROG_TYPE_TRACEPOINT:
+ return bpf_perf_link_fill_tracepoint(event, info);
+ case BPF_PROG_TYPE_KPROBE:
+ return bpf_perf_link_fill_probe(event, info);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static const struct bpf_link_ops bpf_perf_link_lops = {
.release = bpf_perf_link_release,
.dealloc = bpf_perf_link_dealloc,
+ .fill_link_info = bpf_perf_link_fill_link_info,
};
static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
@@ -3502,34 +3666,6 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
return fd;
}
-static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
- enum bpf_attach_type attach_type)
-{
- switch (prog->type) {
- case BPF_PROG_TYPE_CGROUP_SOCK:
- case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
- case BPF_PROG_TYPE_CGROUP_SOCKOPT:
- case BPF_PROG_TYPE_SK_LOOKUP:
- return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
- case BPF_PROG_TYPE_CGROUP_SKB:
- if (!capable(CAP_NET_ADMIN))
- /* cg-skb progs can be loaded by unpriv user.
- * check permissions at attach time.
- */
- return -EPERM;
- return prog->enforce_expected_attach_type &&
- prog->expected_attach_type != attach_type ?
- -EINVAL : 0;
- case BPF_PROG_TYPE_KPROBE:
- if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
- attach_type != BPF_TRACE_KPROBE_MULTI)
- return -EINVAL;
- return 0;
- default:
- return 0;
- }
-}
-
static enum bpf_prog_type
attach_type_to_prog_type(enum bpf_attach_type attach_type)
{
@@ -3546,14 +3682,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
return BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
case BPF_CGROUP_SOCK_OPS:
return BPF_PROG_TYPE_SOCK_OPS;
@@ -3588,15 +3729,87 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
return BPF_PROG_TYPE_XDP;
case BPF_LSM_CGROUP:
return BPF_PROG_TYPE_LSM;
+ case BPF_TCX_INGRESS:
+ case BPF_TCX_EGRESS:
+ case BPF_NETKIT_PRIMARY:
+ case BPF_NETKIT_PEER:
+ return BPF_PROG_TYPE_SCHED_CLS;
default:
return BPF_PROG_TYPE_UNSPEC;
}
}
-#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd
+static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
+ enum bpf_attach_type attach_type)
+{
+ enum bpf_prog_type ptype;
-#define BPF_F_ATTACH_MASK \
- (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE)
+ switch (prog->type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ case BPF_PROG_TYPE_SK_LOOKUP:
+ return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ if (!capable(CAP_NET_ADMIN))
+ /* cg-skb progs can be loaded by unpriv user.
+ * check permissions at attach time.
+ */
+ return -EPERM;
+ return prog->enforce_expected_attach_type &&
+ prog->expected_attach_type != attach_type ?
+ -EINVAL : 0;
+ case BPF_PROG_TYPE_EXT:
+ return 0;
+ case BPF_PROG_TYPE_NETFILTER:
+ if (attach_type != BPF_NETFILTER)
+ return -EINVAL;
+ return 0;
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_TRACEPOINT:
+ if (attach_type != BPF_PERF_EVENT)
+ return -EINVAL;
+ return 0;
+ case BPF_PROG_TYPE_KPROBE:
+ if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
+ attach_type != BPF_TRACE_KPROBE_MULTI)
+ return -EINVAL;
+ if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI &&
+ attach_type != BPF_TRACE_UPROBE_MULTI)
+ return -EINVAL;
+ if (attach_type != BPF_PERF_EVENT &&
+ attach_type != BPF_TRACE_KPROBE_MULTI &&
+ attach_type != BPF_TRACE_UPROBE_MULTI)
+ return -EINVAL;
+ return 0;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ if (attach_type != BPF_TCX_INGRESS &&
+ attach_type != BPF_TCX_EGRESS &&
+ attach_type != BPF_NETKIT_PRIMARY &&
+ attach_type != BPF_NETKIT_PEER)
+ return -EINVAL;
+ return 0;
+ default:
+ ptype = attach_type_to_prog_type(attach_type);
+ if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type)
+ return -EINVAL;
+ return 0;
+ }
+}
+
+#define BPF_PROG_ATTACH_LAST_FIELD expected_revision
+
+#define BPF_F_ATTACH_MASK_BASE \
+ (BPF_F_ALLOW_OVERRIDE | \
+ BPF_F_ALLOW_MULTI | \
+ BPF_F_REPLACE)
+
+#define BPF_F_ATTACH_MASK_MPROG \
+ (BPF_F_REPLACE | \
+ BPF_F_BEFORE | \
+ BPF_F_AFTER | \
+ BPF_F_ID | \
+ BPF_F_LINK)
static int bpf_prog_attach(const union bpf_attr *attr)
{
@@ -3607,12 +3820,19 @@ static int bpf_prog_attach(const union bpf_attr *attr)
if (CHECK_ATTR(BPF_PROG_ATTACH))
return -EINVAL;
- if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
- return -EINVAL;
-
ptype = attach_type_to_prog_type(attr->attach_type);
if (ptype == BPF_PROG_TYPE_UNSPEC)
return -EINVAL;
+ if (bpf_mprog_supported(ptype)) {
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
+ return -EINVAL;
+ } else {
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE)
+ return -EINVAL;
+ if (attr->relative_fd ||
+ attr->expected_revision)
+ return -EINVAL;
+ }
prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
if (IS_ERR(prog))
@@ -3648,6 +3868,13 @@ static int bpf_prog_attach(const union bpf_attr *attr)
else
ret = cgroup_bpf_prog_attach(attr, ptype, prog);
break;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ if (attr->attach_type == BPF_TCX_INGRESS ||
+ attr->attach_type == BPF_TCX_EGRESS)
+ ret = tcx_prog_attach(attr, prog);
+ else
+ ret = netkit_prog_attach(attr, prog);
+ break;
default:
ret = -EINVAL;
}
@@ -3657,25 +3884,45 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return ret;
}
-#define BPF_PROG_DETACH_LAST_FIELD attach_type
+#define BPF_PROG_DETACH_LAST_FIELD expected_revision
static int bpf_prog_detach(const union bpf_attr *attr)
{
+ struct bpf_prog *prog = NULL;
enum bpf_prog_type ptype;
+ int ret;
if (CHECK_ATTR(BPF_PROG_DETACH))
return -EINVAL;
ptype = attach_type_to_prog_type(attr->attach_type);
+ if (bpf_mprog_supported(ptype)) {
+ if (ptype == BPF_PROG_TYPE_UNSPEC)
+ return -EINVAL;
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
+ return -EINVAL;
+ if (attr->attach_bpf_fd) {
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+ }
+ } else if (attr->attach_flags ||
+ attr->relative_fd ||
+ attr->expected_revision) {
+ return -EINVAL;
+ }
switch (ptype) {
case BPF_PROG_TYPE_SK_MSG:
case BPF_PROG_TYPE_SK_SKB:
- return sock_map_prog_detach(attr, ptype);
+ ret = sock_map_prog_detach(attr, ptype);
+ break;
case BPF_PROG_TYPE_LIRC_MODE2:
- return lirc_prog_detach(attr);
+ ret = lirc_prog_detach(attr);
+ break;
case BPF_PROG_TYPE_FLOW_DISSECTOR:
- return netns_bpf_prog_detach(attr, ptype);
+ ret = netns_bpf_prog_detach(attr, ptype);
+ break;
case BPF_PROG_TYPE_CGROUP_DEVICE:
case BPF_PROG_TYPE_CGROUP_SKB:
case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -3684,13 +3931,25 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_LSM:
- return cgroup_bpf_prog_detach(attr, ptype);
+ ret = cgroup_bpf_prog_detach(attr, ptype);
+ break;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ if (attr->attach_type == BPF_TCX_INGRESS ||
+ attr->attach_type == BPF_TCX_EGRESS)
+ ret = tcx_prog_detach(attr, prog);
+ else
+ ret = netkit_prog_detach(attr, prog);
+ break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
+
+ if (prog)
+ bpf_prog_put(prog);
+ return ret;
}
-#define BPF_PROG_QUERY_LAST_FIELD query.prog_attach_flags
+#define BPF_PROG_QUERY_LAST_FIELD query.revision
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
@@ -3713,14 +3972,19 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_INET6_POST_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
case BPF_CGROUP_SYSCTL:
@@ -3738,6 +4002,12 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_SK_MSG_VERDICT:
case BPF_SK_SKB_VERDICT:
return sock_map_bpf_prog_query(attr, uattr);
+ case BPF_TCX_INGRESS:
+ case BPF_TCX_EGRESS:
+ return tcx_prog_query(attr, uattr);
+ case BPF_NETKIT_PRIMARY:
+ case BPF_NETKIT_PEER:
+ return netkit_prog_query(attr, uattr);
default:
return -EINVAL;
}
@@ -4583,7 +4853,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
err = bpf_get_perf_event_info(event, &prog_id, &fd_type,
&buf, &probe_offset,
- &probe_addr);
+ &probe_addr, NULL);
if (!err)
err = bpf_task_fd_query_copy(attr, uattr, prog_id,
fd_type, buf,
@@ -4655,10 +4925,9 @@ err_put:
return err;
}
-#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies
+#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid
static int link_create(union bpf_attr *attr, bpfptr_t uattr)
{
- enum bpf_prog_type ptype;
struct bpf_prog *prog;
int ret;
@@ -4678,38 +4947,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
goto out;
switch (prog->type) {
- case BPF_PROG_TYPE_EXT:
- break;
- case BPF_PROG_TYPE_NETFILTER:
- if (attr->link_create.attach_type != BPF_NETFILTER) {
- ret = -EINVAL;
- goto out;
- }
- break;
- case BPF_PROG_TYPE_PERF_EVENT:
- case BPF_PROG_TYPE_TRACEPOINT:
- if (attr->link_create.attach_type != BPF_PERF_EVENT) {
- ret = -EINVAL;
- goto out;
- }
- break;
- case BPF_PROG_TYPE_KPROBE:
- if (attr->link_create.attach_type != BPF_PERF_EVENT &&
- attr->link_create.attach_type != BPF_TRACE_KPROBE_MULTI) {
- ret = -EINVAL;
- goto out;
- }
- break;
- default:
- ptype = attach_type_to_prog_type(attr->link_create.attach_type);
- if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
- ret = -EINVAL;
- goto out;
- }
- break;
- }
-
- switch (prog->type) {
case BPF_PROG_TYPE_CGROUP_SKB:
case BPF_PROG_TYPE_CGROUP_SOCK:
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
@@ -4751,6 +4988,13 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
case BPF_PROG_TYPE_XDP:
ret = bpf_xdp_link_attach(attr, prog);
break;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ if (attr->link_create.attach_type == BPF_TCX_INGRESS ||
+ attr->link_create.attach_type == BPF_TCX_EGRESS)
+ ret = tcx_link_attach(attr, prog);
+ else
+ ret = netkit_link_attach(attr, prog);
+ break;
case BPF_PROG_TYPE_NETFILTER:
ret = bpf_nf_link_attach(attr, prog);
break;
@@ -4762,8 +5006,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
case BPF_PROG_TYPE_KPROBE:
if (attr->link_create.attach_type == BPF_PERF_EVENT)
ret = bpf_perf_link_attach(attr, prog);
- else
+ else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI)
ret = bpf_kprobe_multi_link_attach(attr, prog);
+ else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI)
+ ret = bpf_uprobe_multi_link_attach(attr, prog);
break;
default:
ret = -EINVAL;
@@ -5304,9 +5550,9 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
}
run_ctx.bpf_cookie = 0;
- run_ctx.saved_run_ctx = NULL;
if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) {
/* recursion detected */
+ __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx);
bpf_prog_put(prog);
return -EBUSY;
}
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index c4ab9d6cdbe9..26082b97894d 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -7,7 +7,9 @@
#include <linux/fs.h>
#include <linux/fdtable.h>
#include <linux/filter.h>
+#include <linux/bpf_mem_alloc.h>
#include <linux/btf_ids.h>
+#include <linux/mm_types.h>
#include "mmap_unlock_work.h"
static const char * const iter_task_type_names[] = {
@@ -35,16 +37,13 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm
u32 *tid,
bool skip_if_dup_files)
{
- struct task_struct *task, *next_task;
+ struct task_struct *task;
struct pid *pid;
- u32 saved_tid;
+ u32 next_tid;
if (!*tid) {
/* The first time, the iterator calls this function. */
pid = find_pid_ns(common->pid, common->ns);
- if (!pid)
- return NULL;
-
task = get_pid_task(pid, PIDTYPE_TGID);
if (!task)
return NULL;
@@ -66,44 +65,27 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm
return task;
}
- pid = find_pid_ns(common->pid_visiting, common->ns);
- if (!pid)
- return NULL;
-
- task = get_pid_task(pid, PIDTYPE_PID);
+ task = find_task_by_pid_ns(common->pid_visiting, common->ns);
if (!task)
return NULL;
retry:
- if (!pid_alive(task)) {
- put_task_struct(task);
- return NULL;
- }
+ task = next_thread(task);
- next_task = next_thread(task);
- put_task_struct(task);
- if (!next_task)
- return NULL;
-
- saved_tid = *tid;
- *tid = __task_pid_nr_ns(next_task, PIDTYPE_PID, common->ns);
- if (!*tid || *tid == common->pid) {
+ next_tid = __task_pid_nr_ns(task, PIDTYPE_PID, common->ns);
+ if (!next_tid || next_tid == common->pid) {
/* Run out of tasks of a process. The tasks of a
* thread_group are linked as circular linked list.
*/
- *tid = saved_tid;
return NULL;
}
- get_task_struct(next_task);
- common->pid_visiting = *tid;
-
- if (skip_if_dup_files && task->files == task->group_leader->files) {
- task = next_task;
+ if (skip_if_dup_files && task->files == task->group_leader->files)
goto retry;
- }
- return next_task;
+ *tid = common->pid_visiting = next_tid;
+ get_task_struct(task);
+ return task;
}
static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *common,
@@ -308,11 +290,9 @@ again:
rcu_read_lock();
for (;; curr_fd++) {
struct file *f;
- f = task_lookup_next_fd_rcu(curr_task, &curr_fd);
+ f = task_lookup_next_fdget_rcu(curr_task, &curr_fd);
if (!f)
break;
- if (!get_file_rcu(f))
- continue;
/* set info->fd */
info->fd = curr_fd;
@@ -724,7 +704,7 @@ static struct bpf_iter_reg task_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task, task),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &task_seq_info,
.fill_link_info = bpf_iter_fill_link_info,
@@ -823,6 +803,244 @@ const struct bpf_func_proto bpf_find_vma_proto = {
.arg5_type = ARG_ANYTHING,
};
+struct bpf_iter_task_vma_kern_data {
+ struct task_struct *task;
+ struct mm_struct *mm;
+ struct mmap_unlock_irq_work *work;
+ struct vma_iterator vmi;
+};
+
+struct bpf_iter_task_vma {
+ /* opaque iterator state; having __u64 here allows to preserve correct
+ * alignment requirements in vmlinux.h, generated from BTF
+ */
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+/* Non-opaque version of bpf_iter_task_vma */
+struct bpf_iter_task_vma_kern {
+ struct bpf_iter_task_vma_kern_data *data;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
+ struct task_struct *task, u64 addr)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+ bool irq_work_busy = false;
+ int err;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma));
+
+ /* is_iter_reg_valid_uninit guarantees that kit hasn't been initialized
+ * before, so non-NULL kit->data doesn't point to previously
+ * bpf_mem_alloc'd bpf_iter_task_vma_kern_data
+ */
+ kit->data = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_iter_task_vma_kern_data));
+ if (!kit->data)
+ return -ENOMEM;
+
+ kit->data->task = get_task_struct(task);
+ kit->data->mm = task->mm;
+ if (!kit->data->mm) {
+ err = -ENOENT;
+ goto err_cleanup_iter;
+ }
+
+ /* kit->data->work == NULL is valid after bpf_mmap_unlock_get_irq_work */
+ irq_work_busy = bpf_mmap_unlock_get_irq_work(&kit->data->work);
+ if (irq_work_busy || !mmap_read_trylock(kit->data->mm)) {
+ err = -EBUSY;
+ goto err_cleanup_iter;
+ }
+
+ vma_iter_init(&kit->data->vmi, kit->data->mm, addr);
+ return 0;
+
+err_cleanup_iter:
+ if (kit->data->task)
+ put_task_struct(kit->data->task);
+ bpf_mem_free(&bpf_global_ma, kit->data);
+ /* NULL kit->data signals failed bpf_iter_task_vma initialization */
+ kit->data = NULL;
+ return err;
+}
+
+__bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+
+ if (!kit->data) /* bpf_iter_task_vma_new failed */
+ return NULL;
+ return vma_next(&kit->data->vmi);
+}
+
+__bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+
+ if (kit->data) {
+ bpf_mmap_unlock_mm(kit->data->work, kit->data->mm);
+ put_task_struct(kit->data->task);
+ bpf_mem_free(&bpf_global_ma, kit->data);
+ }
+}
+
+__bpf_kfunc_end_defs();
+
+#ifdef CONFIG_CGROUPS
+
+struct bpf_iter_css_task {
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_task_kern {
+ struct css_task_iter *css_it;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
+ struct cgroup_subsys_state *css, unsigned int flags)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) !=
+ __alignof__(struct bpf_iter_css_task));
+ kit->css_it = NULL;
+ switch (flags) {
+ case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED:
+ case CSS_TASK_ITER_PROCS:
+ case 0:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter));
+ if (!kit->css_it)
+ return -ENOMEM;
+ css_task_iter_start(css, flags, kit->css_it);
+ return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ if (!kit->css_it)
+ return NULL;
+ return css_task_iter_next(kit->css_it);
+}
+
+__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ if (!kit->css_it)
+ return;
+ css_task_iter_end(kit->css_it);
+ bpf_mem_free(&bpf_global_ma, kit->css_it);
+}
+
+__bpf_kfunc_end_defs();
+
+#endif /* CONFIG_CGROUPS */
+
+struct bpf_iter_task {
+ __u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_task_kern {
+ struct task_struct *task;
+ struct task_struct *pos;
+ unsigned int flags;
+} __attribute__((aligned(8)));
+
+enum {
+ /* all process in the system */
+ BPF_TASK_ITER_ALL_PROCS,
+ /* all threads in the system */
+ BPF_TASK_ITER_ALL_THREADS,
+ /* all threads of a specific process */
+ BPF_TASK_ITER_PROC_THREADS
+};
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
+ struct task_struct *task__nullable, unsigned int flags)
+{
+ struct bpf_iter_task_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_task_kern) > sizeof(struct bpf_iter_task));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) !=
+ __alignof__(struct bpf_iter_task));
+
+ kit->task = kit->pos = NULL;
+ switch (flags) {
+ case BPF_TASK_ITER_ALL_THREADS:
+ case BPF_TASK_ITER_ALL_PROCS:
+ break;
+ case BPF_TASK_ITER_PROC_THREADS:
+ if (!task__nullable)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (flags == BPF_TASK_ITER_PROC_THREADS)
+ kit->task = task__nullable;
+ else
+ kit->task = &init_task;
+ kit->pos = kit->task;
+ kit->flags = flags;
+ return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it)
+{
+ struct bpf_iter_task_kern *kit = (void *)it;
+ struct task_struct *pos;
+ unsigned int flags;
+
+ flags = kit->flags;
+ pos = kit->pos;
+
+ if (!pos)
+ return pos;
+
+ if (flags == BPF_TASK_ITER_ALL_PROCS)
+ goto get_next_task;
+
+ kit->pos = next_thread(kit->pos);
+ if (kit->pos == kit->task) {
+ if (flags == BPF_TASK_ITER_PROC_THREADS) {
+ kit->pos = NULL;
+ return pos;
+ }
+ } else
+ return pos;
+
+get_next_task:
+ kit->pos = next_task(kit->pos);
+ kit->task = kit->pos;
+ if (kit->pos == &init_task)
+ kit->pos = NULL;
+
+ return pos;
+}
+
+__bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it)
+{
+}
+
+__bpf_kfunc_end_defs();
+
DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
static void do_mmap_read_unlock(struct irq_work *entry)
diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c
new file mode 100644
index 000000000000..2e4885e7781f
--- /dev/null
+++ b/kernel/bpf/tcx.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <linux/bpf.h>
+#include <linux/bpf_mprog.h>
+#include <linux/netdevice.h>
+
+#include <net/tcx.h>
+
+int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ bool created, ingress = attr->attach_type == BPF_TCX_INGRESS;
+ struct net *net = current->nsproxy->net_ns;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct bpf_prog *replace_prog = NULL;
+ struct net_device *dev;
+ int ret;
+
+ rtnl_lock();
+ dev = __dev_get_by_index(net, attr->target_ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ if (attr->attach_flags & BPF_F_REPLACE) {
+ replace_prog = bpf_prog_get_type(attr->replace_bpf_fd,
+ prog->type);
+ if (IS_ERR(replace_prog)) {
+ ret = PTR_ERR(replace_prog);
+ replace_prog = NULL;
+ goto out;
+ }
+ }
+ entry = tcx_entry_fetch_or_create(dev, ingress, &created);
+ if (!entry) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog,
+ attr->attach_flags, attr->relative_fd,
+ attr->expected_revision);
+ if (!ret) {
+ if (entry != entry_new) {
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ tcx_skeys_inc(ingress);
+ }
+ bpf_mprog_commit(entry);
+ } else if (created) {
+ tcx_entry_free(entry);
+ }
+out:
+ if (replace_prog)
+ bpf_prog_put(replace_prog);
+ rtnl_unlock();
+ return ret;
+}
+
+int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ bool ingress = attr->attach_type == BPF_TCX_INGRESS;
+ struct net *net = current->nsproxy->net_ns;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct net_device *dev;
+ int ret;
+
+ rtnl_lock();
+ dev = __dev_get_by_index(net, attr->target_ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ entry = tcx_entry_fetch(dev, ingress);
+ if (!entry) {
+ ret = -ENOENT;
+ goto out;
+ }
+ ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags,
+ attr->relative_fd, attr->expected_revision);
+ if (!ret) {
+ if (!tcx_entry_is_active(entry_new))
+ entry_new = NULL;
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ tcx_skeys_dec(ingress);
+ bpf_mprog_commit(entry);
+ if (!entry_new)
+ tcx_entry_free(entry);
+ }
+out:
+ rtnl_unlock();
+ return ret;
+}
+
+void tcx_uninstall(struct net_device *dev, bool ingress)
+{
+ struct bpf_mprog_entry *entry, *entry_new = NULL;
+ struct bpf_tuple tuple = {};
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ bool active;
+
+ entry = tcx_entry_fetch(dev, ingress);
+ if (!entry)
+ return;
+ active = tcx_entry(entry)->miniq_active;
+ if (active)
+ bpf_mprog_clear_all(entry, &entry_new);
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ bpf_mprog_foreach_tuple(entry, fp, cp, tuple) {
+ if (tuple.link)
+ tcx_link(tuple.link)->dev = NULL;
+ else
+ bpf_prog_put(tuple.prog);
+ tcx_skeys_dec(ingress);
+ }
+ if (!active)
+ tcx_entry_free(entry);
+}
+
+int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
+{
+ bool ingress = attr->query.attach_type == BPF_TCX_INGRESS;
+ struct net *net = current->nsproxy->net_ns;
+ struct net_device *dev;
+ int ret;
+
+ rtnl_lock();
+ dev = __dev_get_by_index(net, attr->query.target_ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ ret = bpf_mprog_query(attr, uattr, tcx_entry_fetch(dev, ingress));
+out:
+ rtnl_unlock();
+ return ret;
+}
+
+static int tcx_link_prog_attach(struct bpf_link *link, u32 flags, u32 id_or_fd,
+ u64 revision)
+{
+ struct tcx_link *tcx = tcx_link(link);
+ bool created, ingress = tcx->location == BPF_TCX_INGRESS;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct net_device *dev = tcx->dev;
+ int ret;
+
+ ASSERT_RTNL();
+ entry = tcx_entry_fetch_or_create(dev, ingress, &created);
+ if (!entry)
+ return -ENOMEM;
+ ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags,
+ id_or_fd, revision);
+ if (!ret) {
+ if (entry != entry_new) {
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ tcx_skeys_inc(ingress);
+ }
+ bpf_mprog_commit(entry);
+ } else if (created) {
+ tcx_entry_free(entry);
+ }
+ return ret;
+}
+
+static void tcx_link_release(struct bpf_link *link)
+{
+ struct tcx_link *tcx = tcx_link(link);
+ bool ingress = tcx->location == BPF_TCX_INGRESS;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct net_device *dev;
+ int ret = 0;
+
+ rtnl_lock();
+ dev = tcx->dev;
+ if (!dev)
+ goto out;
+ entry = tcx_entry_fetch(dev, ingress);
+ if (!entry) {
+ ret = -ENOENT;
+ goto out;
+ }
+ ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0);
+ if (!ret) {
+ if (!tcx_entry_is_active(entry_new))
+ entry_new = NULL;
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ tcx_skeys_dec(ingress);
+ bpf_mprog_commit(entry);
+ if (!entry_new)
+ tcx_entry_free(entry);
+ tcx->dev = NULL;
+ }
+out:
+ WARN_ON_ONCE(ret);
+ rtnl_unlock();
+}
+
+static int tcx_link_update(struct bpf_link *link, struct bpf_prog *nprog,
+ struct bpf_prog *oprog)
+{
+ struct tcx_link *tcx = tcx_link(link);
+ bool ingress = tcx->location == BPF_TCX_INGRESS;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct net_device *dev;
+ int ret = 0;
+
+ rtnl_lock();
+ dev = tcx->dev;
+ if (!dev) {
+ ret = -ENOLINK;
+ goto out;
+ }
+ if (oprog && link->prog != oprog) {
+ ret = -EPERM;
+ goto out;
+ }
+ oprog = link->prog;
+ if (oprog == nprog) {
+ bpf_prog_put(nprog);
+ goto out;
+ }
+ entry = tcx_entry_fetch(dev, ingress);
+ if (!entry) {
+ ret = -ENOENT;
+ goto out;
+ }
+ ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog,
+ BPF_F_REPLACE | BPF_F_ID,
+ link->prog->aux->id, 0);
+ if (!ret) {
+ WARN_ON_ONCE(entry != entry_new);
+ oprog = xchg(&link->prog, nprog);
+ bpf_prog_put(oprog);
+ bpf_mprog_commit(entry);
+ }
+out:
+ rtnl_unlock();
+ return ret;
+}
+
+static void tcx_link_dealloc(struct bpf_link *link)
+{
+ kfree(tcx_link(link));
+}
+
+static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq)
+{
+ const struct tcx_link *tcx = tcx_link(link);
+ u32 ifindex = 0;
+
+ rtnl_lock();
+ if (tcx->dev)
+ ifindex = tcx->dev->ifindex;
+ rtnl_unlock();
+
+ seq_printf(seq, "ifindex:\t%u\n", ifindex);
+ seq_printf(seq, "attach_type:\t%u (%s)\n",
+ tcx->location,
+ tcx->location == BPF_TCX_INGRESS ? "ingress" : "egress");
+}
+
+static int tcx_link_fill_info(const struct bpf_link *link,
+ struct bpf_link_info *info)
+{
+ const struct tcx_link *tcx = tcx_link(link);
+ u32 ifindex = 0;
+
+ rtnl_lock();
+ if (tcx->dev)
+ ifindex = tcx->dev->ifindex;
+ rtnl_unlock();
+
+ info->tcx.ifindex = ifindex;
+ info->tcx.attach_type = tcx->location;
+ return 0;
+}
+
+static int tcx_link_detach(struct bpf_link *link)
+{
+ tcx_link_release(link);
+ return 0;
+}
+
+static const struct bpf_link_ops tcx_link_lops = {
+ .release = tcx_link_release,
+ .detach = tcx_link_detach,
+ .dealloc = tcx_link_dealloc,
+ .update_prog = tcx_link_update,
+ .show_fdinfo = tcx_link_fdinfo,
+ .fill_link_info = tcx_link_fill_info,
+};
+
+static int tcx_link_init(struct tcx_link *tcx,
+ struct bpf_link_primer *link_primer,
+ const union bpf_attr *attr,
+ struct net_device *dev,
+ struct bpf_prog *prog)
+{
+ bpf_link_init(&tcx->link, BPF_LINK_TYPE_TCX, &tcx_link_lops, prog);
+ tcx->location = attr->link_create.attach_type;
+ tcx->dev = dev;
+ return bpf_link_prime(&tcx->link, link_primer);
+}
+
+int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ struct net *net = current->nsproxy->net_ns;
+ struct bpf_link_primer link_primer;
+ struct net_device *dev;
+ struct tcx_link *tcx;
+ int ret;
+
+ rtnl_lock();
+ dev = __dev_get_by_index(net, attr->link_create.target_ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ tcx = kzalloc(sizeof(*tcx), GFP_USER);
+ if (!tcx) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = tcx_link_init(tcx, &link_primer, attr, dev, prog);
+ if (ret) {
+ kfree(tcx);
+ goto out;
+ }
+ ret = tcx_link_prog_attach(&tcx->link, attr->link_create.flags,
+ attr->link_create.tcx.relative_fd,
+ attr->link_create.tcx.expected_revision);
+ if (ret) {
+ tcx->dev = NULL;
+ bpf_link_cleanup(&link_primer);
+ goto out;
+ }
+ ret = bpf_link_settle(&link_primer);
+out:
+ rtnl_unlock();
+ return ret;
+}
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 78acf28d4873..e97aeda3a86b 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -415,8 +415,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
goto out;
}
- /* clear all bits except SHARE_IPMODIFY */
- tr->flags &= BPF_TRAMP_F_SHARE_IPMODIFY;
+ /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */
+ tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX);
if (tlinks[BPF_TRAMP_FEXIT].nr_links ||
tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) {
@@ -926,13 +926,12 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
migrate_disable();
might_fault();
+ run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
bpf_prog_inc_misses_counter(prog);
return 0;
}
-
- run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
-
return bpf_prog_start_time();
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 02a021c524ab..af2819d5c8ee 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -25,6 +25,9 @@
#include <linux/btf_ids.h>
#include <linux/poison.h>
#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <linux/bpf_mem_alloc.h>
+#include <net/xdp.h>
#include "disasm.h"
@@ -39,6 +42,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#undef BPF_LINK_TYPE
};
+struct bpf_mem_alloc bpf_global_percpu_ma;
+static bool bpf_global_percpu_ma_set;
+
/* bpf_check() is a static code analyzer that walks eBPF program
* instruction by instruction and updates register/stack state.
* All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -302,7 +308,7 @@ struct bpf_kfunc_call_arg_meta {
/* arg_{btf,btf_id,owning_ref} are used by kfunc-specific handling,
* generally to pass info about user-defined local kptr types to later
* verification logic
- * bpf_obj_drop
+ * bpf_obj_drop/bpf_percpu_obj_drop
* Record the local kptr type to be drop'd
* bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type)
* Record the local kptr type to be refcount_incr'd and use
@@ -334,6 +340,7 @@ struct bpf_kfunc_call_arg_meta {
struct btf *btf_vmlinux;
static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
static const struct bpf_line_info *
find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
@@ -540,12 +547,12 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
return func_id == BPF_FUNC_dynptr_data;
}
-static bool is_callback_calling_kfunc(u32 btf_id);
+static bool is_sync_callback_calling_kfunc(u32 btf_id);
+static bool is_bpf_throw_kfunc(struct bpf_insn *insn);
-static bool is_callback_calling_function(enum bpf_func_id func_id)
+static bool is_sync_callback_calling_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_for_each_map_elem ||
- func_id == BPF_FUNC_timer_set_callback ||
func_id == BPF_FUNC_find_vma ||
func_id == BPF_FUNC_loop ||
func_id == BPF_FUNC_user_ringbuf_drain;
@@ -556,6 +563,18 @@ static bool is_async_callback_calling_function(enum bpf_func_id func_id)
return func_id == BPF_FUNC_timer_set_callback;
}
+static bool is_callback_calling_function(enum bpf_func_id func_id)
+{
+ return is_sync_callback_calling_function(func_id) ||
+ is_async_callback_calling_function(func_id);
+}
+
+static bool is_sync_callback_calling_insn(struct bpf_insn *insn)
+{
+ return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) ||
+ (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm));
+}
+
static bool is_storage_get_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_sk_storage_get ||
@@ -1170,7 +1189,12 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg
static void __mark_reg_known_zero(struct bpf_reg_state *reg);
+static bool in_rcu_cs(struct bpf_verifier_env *env);
+
+static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta);
+
static int mark_stack_slots_iter(struct bpf_verifier_env *env,
+ struct bpf_kfunc_call_arg_meta *meta,
struct bpf_reg_state *reg, int insn_idx,
struct btf *btf, u32 btf_id, int nr_slots)
{
@@ -1191,6 +1215,12 @@ static int mark_stack_slots_iter(struct bpf_verifier_env *env,
__mark_reg_known_zero(st);
st->type = PTR_TO_STACK; /* we don't have dedicated reg type */
+ if (is_kfunc_rcu_protected(meta)) {
+ if (in_rcu_cs(env))
+ st->type |= MEM_RCU;
+ else
+ st->type |= PTR_UNTRUSTED;
+ }
st->live |= REG_LIVE_WRITTEN;
st->ref_obj_id = i == 0 ? id : 0;
st->iter.btf = btf;
@@ -1265,7 +1295,7 @@ static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env,
return true;
}
-static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
struct btf *btf, u32 btf_id, int nr_slots)
{
struct bpf_func_state *state = func(env, reg);
@@ -1273,26 +1303,28 @@ static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_
spi = iter_get_spi(env, reg, nr_slots);
if (spi < 0)
- return false;
+ return -EINVAL;
for (i = 0; i < nr_slots; i++) {
struct bpf_stack_state *slot = &state->stack[spi - i];
struct bpf_reg_state *st = &slot->spilled_ptr;
+ if (st->type & PTR_UNTRUSTED)
+ return -EPROTO;
/* only main (first) slot has ref_obj_id set */
if (i == 0 && !st->ref_obj_id)
- return false;
+ return -EINVAL;
if (i != 0 && st->ref_obj_id)
- return false;
+ return -EINVAL;
if (st->iter.btf != btf || st->iter.btf_id != btf_id)
- return false;
+ return -EINVAL;
for (j = 0; j < BPF_REG_SIZE; j++)
if (slot->slot_type[j] != STACK_ITER)
- return false;
+ return -EINVAL;
}
- return true;
+ return 0;
}
/* Check if given stack slot is "special":
@@ -1339,6 +1371,50 @@ static void scrub_spilled_slot(u8 *stype)
*stype = STACK_MISC;
}
+static void print_scalar_ranges(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ const char **sep)
+{
+ struct {
+ const char *name;
+ u64 val;
+ bool omit;
+ } minmaxs[] = {
+ {"smin", reg->smin_value, reg->smin_value == S64_MIN},
+ {"smax", reg->smax_value, reg->smax_value == S64_MAX},
+ {"umin", reg->umin_value, reg->umin_value == 0},
+ {"umax", reg->umax_value, reg->umax_value == U64_MAX},
+ {"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN},
+ {"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX},
+ {"umin32", reg->u32_min_value, reg->u32_min_value == 0},
+ {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX},
+ }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
+ bool neg1, neg2;
+
+ for (m1 = &minmaxs[0]; m1 < mend; m1++) {
+ if (m1->omit)
+ continue;
+
+ neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
+
+ verbose(env, "%s%s=", *sep, m1->name);
+ *sep = ",";
+
+ for (m2 = m1 + 2; m2 < mend; m2 += 2) {
+ if (m2->omit || m2->val != m1->val)
+ continue;
+ /* don't mix negatives with positives */
+ neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
+ if (neg2 != neg1)
+ continue;
+ m2->omit = true;
+ verbose(env, "%s=", m2->name);
+ }
+
+ verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val);
+ }
+}
+
static void print_verifier_state(struct bpf_verifier_env *env,
const struct bpf_func_state *state,
bool print_all)
@@ -1402,34 +1478,13 @@ static void print_verifier_state(struct bpf_verifier_env *env,
*/
verbose_a("imm=%llx", reg->var_off.value);
} else {
- if (reg->smin_value != reg->umin_value &&
- reg->smin_value != S64_MIN)
- verbose_a("smin=%lld", (long long)reg->smin_value);
- if (reg->smax_value != reg->umax_value &&
- reg->smax_value != S64_MAX)
- verbose_a("smax=%lld", (long long)reg->smax_value);
- if (reg->umin_value != 0)
- verbose_a("umin=%llu", (unsigned long long)reg->umin_value);
- if (reg->umax_value != U64_MAX)
- verbose_a("umax=%llu", (unsigned long long)reg->umax_value);
+ print_scalar_ranges(env, reg, &sep);
if (!tnum_is_unknown(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose_a("var_off=%s", tn_buf);
}
- if (reg->s32_min_value != reg->smin_value &&
- reg->s32_min_value != S32_MIN)
- verbose_a("s32_min=%d", (int)(reg->s32_min_value));
- if (reg->s32_max_value != reg->smax_value &&
- reg->s32_max_value != S32_MAX)
- verbose_a("s32_max=%d", (int)(reg->s32_max_value));
- if (reg->u32_min_value != reg->umin_value &&
- reg->u32_min_value != U32_MIN)
- verbose_a("u32_min=%d", (int)(reg->u32_min_value));
- if (reg->u32_max_value != reg->umax_value &&
- reg->u32_max_value != U32_MAX)
- verbose_a("u32_max=%d", (int)(reg->u32_max_value));
}
#undef verbose_a
@@ -1513,7 +1568,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
if (state->in_async_callback_fn)
verbose(env, " async_cb");
verbose(env, "\n");
- mark_verifier_state_clean(env);
+ if (!print_all)
+ mark_verifier_state_clean(env);
}
static inline u32 vlog_alignment(u32 pos)
@@ -1746,7 +1802,9 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
return -ENOMEM;
dst_state->jmp_history_cnt = src->jmp_history_cnt;
- /* if dst has more stack frames then src frame, free them */
+ /* if dst has more stack frames then src frame, free them, this is also
+ * necessary in case of exceptional exits using bpf_throw.
+ */
for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
free_func_state(dst_state->frame[i]);
dst_state->frame[i] = NULL;
@@ -1760,6 +1818,9 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
dst_state->parent = src->parent;
dst_state->first_insn_idx = src->first_insn_idx;
dst_state->last_insn_idx = src->last_insn_idx;
+ dst_state->dfs_depth = src->dfs_depth;
+ dst_state->callback_unroll_depth = src->callback_unroll_depth;
+ dst_state->used_as_loop_entry = src->used_as_loop_entry;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
@@ -1775,11 +1836,203 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
return 0;
}
+static u32 state_htab_size(struct bpf_verifier_env *env)
+{
+ return env->prog->len;
+}
+
+static struct bpf_verifier_state_list **explored_state(struct bpf_verifier_env *env, int idx)
+{
+ struct bpf_verifier_state *cur = env->cur_state;
+ struct bpf_func_state *state = cur->frame[cur->curframe];
+
+ return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)];
+}
+
+static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_state *b)
+{
+ int fr;
+
+ if (a->curframe != b->curframe)
+ return false;
+
+ for (fr = a->curframe; fr >= 0; fr--)
+ if (a->frame[fr]->callsite != b->frame[fr]->callsite)
+ return false;
+
+ return true;
+}
+
+/* Open coded iterators allow back-edges in the state graph in order to
+ * check unbounded loops that iterators.
+ *
+ * In is_state_visited() it is necessary to know if explored states are
+ * part of some loops in order to decide whether non-exact states
+ * comparison could be used:
+ * - non-exact states comparison establishes sub-state relation and uses
+ * read and precision marks to do so, these marks are propagated from
+ * children states and thus are not guaranteed to be final in a loop;
+ * - exact states comparison just checks if current and explored states
+ * are identical (and thus form a back-edge).
+ *
+ * Paper "A New Algorithm for Identifying Loops in Decompilation"
+ * by Tao Wei, Jian Mao, Wei Zou and Yu Chen [1] presents a convenient
+ * algorithm for loop structure detection and gives an overview of
+ * relevant terminology. It also has helpful illustrations.
+ *
+ * [1] https://api.semanticscholar.org/CorpusID:15784067
+ *
+ * We use a similar algorithm but because loop nested structure is
+ * irrelevant for verifier ours is significantly simpler and resembles
+ * strongly connected components algorithm from Sedgewick's textbook.
+ *
+ * Define topmost loop entry as a first node of the loop traversed in a
+ * depth first search starting from initial state. The goal of the loop
+ * tracking algorithm is to associate topmost loop entries with states
+ * derived from these entries.
+ *
+ * For each step in the DFS states traversal algorithm needs to identify
+ * the following situations:
+ *
+ * initial initial initial
+ * | | |
+ * V V V
+ * ... ... .---------> hdr
+ * | | | |
+ * V V | V
+ * cur .-> succ | .------...
+ * | | | | | |
+ * V | V | V V
+ * succ '-- cur | ... ...
+ * | | |
+ * | V V
+ * | succ <- cur
+ * | |
+ * | V
+ * | ...
+ * | |
+ * '----'
+ *
+ * (A) successor state of cur (B) successor state of cur or it's entry
+ * not yet traversed are in current DFS path, thus cur and succ
+ * are members of the same outermost loop
+ *
+ * initial initial
+ * | |
+ * V V
+ * ... ...
+ * | |
+ * V V
+ * .------... .------...
+ * | | | |
+ * V V V V
+ * .-> hdr ... ... ...
+ * | | | | |
+ * | V V V V
+ * | succ <- cur succ <- cur
+ * | | |
+ * | V V
+ * | ... ...
+ * | | |
+ * '----' exit
+ *
+ * (C) successor state of cur is a part of some loop but this loop
+ * does not include cur or successor state is not in a loop at all.
+ *
+ * Algorithm could be described as the following python code:
+ *
+ * traversed = set() # Set of traversed nodes
+ * entries = {} # Mapping from node to loop entry
+ * depths = {} # Depth level assigned to graph node
+ * path = set() # Current DFS path
+ *
+ * # Find outermost loop entry known for n
+ * def get_loop_entry(n):
+ * h = entries.get(n, None)
+ * while h in entries and entries[h] != h:
+ * h = entries[h]
+ * return h
+ *
+ * # Update n's loop entry if h's outermost entry comes
+ * # before n's outermost entry in current DFS path.
+ * def update_loop_entry(n, h):
+ * n1 = get_loop_entry(n) or n
+ * h1 = get_loop_entry(h) or h
+ * if h1 in path and depths[h1] <= depths[n1]:
+ * entries[n] = h1
+ *
+ * def dfs(n, depth):
+ * traversed.add(n)
+ * path.add(n)
+ * depths[n] = depth
+ * for succ in G.successors(n):
+ * if succ not in traversed:
+ * # Case A: explore succ and update cur's loop entry
+ * # only if succ's entry is in current DFS path.
+ * dfs(succ, depth + 1)
+ * h = get_loop_entry(succ)
+ * update_loop_entry(n, h)
+ * else:
+ * # Case B or C depending on `h1 in path` check in update_loop_entry().
+ * update_loop_entry(n, succ)
+ * path.remove(n)
+ *
+ * To adapt this algorithm for use with verifier:
+ * - use st->branch == 0 as a signal that DFS of succ had been finished
+ * and cur's loop entry has to be updated (case A), handle this in
+ * update_branch_counts();
+ * - use st->branch > 0 as a signal that st is in the current DFS path;
+ * - handle cases B and C in is_state_visited();
+ * - update topmost loop entry for intermediate states in get_loop_entry().
+ */
+static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_state *st)
+{
+ struct bpf_verifier_state *topmost = st->loop_entry, *old;
+
+ while (topmost && topmost->loop_entry && topmost != topmost->loop_entry)
+ topmost = topmost->loop_entry;
+ /* Update loop entries for intermediate states to avoid this
+ * traversal in future get_loop_entry() calls.
+ */
+ while (st && st->loop_entry != topmost) {
+ old = st->loop_entry;
+ st->loop_entry = topmost;
+ st = old;
+ }
+ return topmost;
+}
+
+static void update_loop_entry(struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr)
+{
+ struct bpf_verifier_state *cur1, *hdr1;
+
+ cur1 = get_loop_entry(cur) ?: cur;
+ hdr1 = get_loop_entry(hdr) ?: hdr;
+ /* The head1->branches check decides between cases B and C in
+ * comment for get_loop_entry(). If hdr1->branches == 0 then
+ * head's topmost loop entry is not in current DFS path,
+ * hence 'cur' and 'hdr' are not in the same loop and there is
+ * no need to update cur->loop_entry.
+ */
+ if (hdr1->branches && hdr1->dfs_depth <= cur1->dfs_depth) {
+ cur->loop_entry = hdr;
+ hdr->used_as_loop_entry = true;
+ }
+}
+
static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
{
while (st) {
u32 br = --st->branches;
+ /* br == 0 signals that DFS exploration for 'st' is finished,
+ * thus it is necessary to update parent's loop entry if it
+ * turned out that st is a part of some loop.
+ * This is a part of 'case A' in get_loop_entry() comment.
+ */
+ if (br == 0 && st->parent && st->loop_entry)
+ update_loop_entry(st->parent, st->loop_entry);
+
/* WARN_ON(br > 1) technically makes sense here,
* but see comment in push_stack(), hence:
*/
@@ -2452,6 +2705,68 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
return env->subprog_cnt - 1;
}
+static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env)
+{
+ struct bpf_prog_aux *aux = env->prog->aux;
+ struct btf *btf = aux->btf;
+ const struct btf_type *t;
+ u32 main_btf_id, id;
+ const char *name;
+ int ret, i;
+
+ /* Non-zero func_info_cnt implies valid btf */
+ if (!aux->func_info_cnt)
+ return 0;
+ main_btf_id = aux->func_info[0].type_id;
+
+ t = btf_type_by_id(btf, main_btf_id);
+ if (!t) {
+ verbose(env, "invalid btf id for main subprog in func_info\n");
+ return -EINVAL;
+ }
+
+ name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:");
+ if (IS_ERR(name)) {
+ ret = PTR_ERR(name);
+ /* If there is no tag present, there is no exception callback */
+ if (ret == -ENOENT)
+ ret = 0;
+ else if (ret == -EEXIST)
+ verbose(env, "multiple exception callback tags for main subprog\n");
+ return ret;
+ }
+
+ ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC);
+ if (ret < 0) {
+ verbose(env, "exception callback '%s' could not be found in BTF\n", name);
+ return ret;
+ }
+ id = ret;
+ t = btf_type_by_id(btf, id);
+ if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+ verbose(env, "exception callback '%s' must have global linkage\n", name);
+ return -EINVAL;
+ }
+ ret = 0;
+ for (i = 0; i < aux->func_info_cnt; i++) {
+ if (aux->func_info[i].type_id != id)
+ continue;
+ ret = aux->func_info[i].insn_off;
+ /* Further func_info and subprog checks will also happen
+ * later, so assume this is the right insn_off for now.
+ */
+ if (!ret) {
+ verbose(env, "invalid exception callback insn_off in func_info: 0\n");
+ ret = -EINVAL;
+ }
+ }
+ if (!ret) {
+ verbose(env, "exception callback type id not found in func_info\n");
+ ret = -EINVAL;
+ }
+ return ret;
+}
+
#define MAX_KFUNC_DESCS 256
#define MAX_KFUNC_BTFS 256
@@ -2791,8 +3106,8 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
{
struct bpf_subprog_info *subprog = env->subprog_info;
+ int i, ret, insn_cnt = env->prog->len, ex_cb_insn;
struct bpf_insn *insn = env->prog->insnsi;
- int i, ret, insn_cnt = env->prog->len;
/* Add entry function. */
ret = add_subprog(env, 0);
@@ -2818,6 +3133,26 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
return ret;
}
+ ret = bpf_find_exception_callback_insn_off(env);
+ if (ret < 0)
+ return ret;
+ ex_cb_insn = ret;
+
+ /* If ex_cb_insn > 0, this means that the main program has a subprog
+ * marked using BTF decl tag to serve as the exception callback.
+ */
+ if (ex_cb_insn) {
+ ret = add_subprog(env, ex_cb_insn);
+ if (ret < 0)
+ return ret;
+ for (i = 1; i < env->subprog_cnt; i++) {
+ if (env->subprog_info[i].start != ex_cb_insn)
+ continue;
+ env->exception_callback_subprog = i;
+ break;
+ }
+ }
+
/* Add a fake 'exit' subprog which could simplify subprog iteration
* logic. 'subprog_cnt' should not be increased.
*/
@@ -2854,7 +3189,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
- off = i + insn[i].off + 1;
+ if (code == (BPF_JMP32 | BPF_JA))
+ off = i + insn[i].imm + 1;
+ else
+ off = i + insn[i].off + 1;
if (off < subprog_start || off >= subprog_end) {
verbose(env, "jump out of range from insn %d to %d\n", i, off);
return -EINVAL;
@@ -2863,9 +3201,10 @@ next:
if (i == subprog_end - 1) {
/* to avoid fall-through from one subprog into another
* the last insn of the subprog should be either exit
- * or unconditional jump back
+ * or unconditional jump back or bpf_throw call
*/
if (code != (BPF_JMP | BPF_EXIT) &&
+ code != (BPF_JMP32 | BPF_JA) &&
code != (BPF_JMP | BPF_JA)) {
verbose(env, "last insn is not an exit or jmp\n");
return -EINVAL;
@@ -3011,8 +3350,10 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
}
}
+ if (class == BPF_ALU64 && op == BPF_END && (insn->imm == 16 || insn->imm == 32))
+ return false;
+
if (class == BPF_ALU64 || class == BPF_JMP ||
- /* BPF_END always use BPF_ALU class. */
(class == BPF_ALU && op == BPF_END && insn->imm == 64))
return true;
@@ -3021,7 +3362,7 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
if (class == BPF_LDX) {
if (t != SRC_OP)
- return BPF_SIZE(code) == BPF_DW;
+ return BPF_SIZE(code) == BPF_DW || BPF_MODE(code) == BPF_MEMSX;
/* LDX source must be ptr. */
return true;
}
@@ -3110,13 +3451,11 @@ static void mark_insn_zext(struct bpf_verifier_env *env,
reg->subreg_def = DEF_NOT_SUBREG;
}
-static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
- enum reg_arg_type t)
+static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno,
+ enum reg_arg_type t)
{
- struct bpf_verifier_state *vstate = env->cur_state;
- struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_insn *insn = env->prog->insnsi + env->insn_idx;
- struct bpf_reg_state *reg, *regs = state->regs;
+ struct bpf_reg_state *reg;
bool rw64;
if (regno >= MAX_BPF_REG) {
@@ -3157,6 +3496,15 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
return 0;
}
+static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
+ enum reg_arg_type t)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+
+ return __check_reg_arg(env, state->regs, regno, t);
+}
+
static void mark_jmp_point(struct bpf_verifier_env *env, int idx)
{
env->insn_aux_data[idx].jmp_point = true;
@@ -3192,12 +3540,29 @@ static int push_jmp_history(struct bpf_verifier_env *env,
/* Backtrack one insn at a time. If idx is not at the top of recorded
* history then previous instruction came from straight line execution.
+ * Return -ENOENT if we exhausted all instructions within given state.
+ *
+ * It's legal to have a bit of a looping with the same starting and ending
+ * insn index within the same state, e.g.: 3->4->5->3, so just because current
+ * instruction index is the same as state's first_idx doesn't mean we are
+ * done. If there is still some jump history left, we should keep going. We
+ * need to take into account that we might have a jump history between given
+ * state's parent and itself, due to checkpointing. In this case, we'll have
+ * history entry recording a jump from last instruction of parent state and
+ * first instruction of given state.
*/
static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
u32 *history)
{
u32 cnt = *history;
+ if (i == st->first_insn_idx) {
+ if (cnt == 0)
+ return -ENOENT;
+ if (cnt == 1 && st->jmp_history[0].idx == i)
+ return -ENOENT;
+ }
+
if (cnt && st->jmp_history[cnt - 1].idx == i) {
i = st->jmp_history[cnt - 1].prev_idx;
(*history)--;
@@ -3378,6 +3743,8 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
}
}
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
+
/* For given verifier state backtrack_insn() is called from the last insn to
* the first insn. Its purpose is to compute a bitmask of registers and
* stack slots that needs precision in the parent verifier state.
@@ -3418,9 +3785,14 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
if (class == BPF_ALU || class == BPF_ALU64) {
if (!bt_is_reg_set(bt, dreg))
return 0;
- if (opcode == BPF_MOV) {
+ if (opcode == BPF_END || opcode == BPF_NEG) {
+ /* sreg is reserved and unused
+ * dreg still need precision before this insn
+ */
+ return 0;
+ } else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- /* dreg = sreg
+ /* dreg = sreg or dreg = (s8, s16, s32)sreg
* dreg needs precision after this insn
* sreg needs precision before this insn
*/
@@ -3548,16 +3920,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
return -EFAULT;
return 0;
}
- } else if ((bpf_helper_call(insn) &&
- is_callback_calling_function(insn->imm) &&
- !is_async_callback_calling_function(insn->imm)) ||
- (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) {
- /* callback-calling helper or kfunc call, which means
- * we are exiting from subprog, but unlike the subprog
- * call handling above, we shouldn't propagate
- * precision of r1-r5 (if any requested), as they are
- * not actually arguments passed directly to callback
- * subprogs
+ } else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) {
+ /* exit from callback subprog to callback-calling helper or
+ * kfunc call. Use idx/subseq_idx check to discern it from
+ * straight line code backtracking.
+ * Unlike the subprog call handling above, we shouldn't
+ * propagate precision of r1-r5 (if any requested), as they are
+ * not actually arguments passed directly to callback subprogs
*/
if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
@@ -3592,10 +3961,18 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
} else if (opcode == BPF_EXIT) {
bool r0_precise;
+ /* Backtracking to a nested function call, 'idx' is a part of
+ * the inner frame 'subseq_idx' is a part of the outer frame.
+ * In case of a regular function call, instructions giving
+ * precision to registers R1-R5 should have been found already.
+ * In case of a callback, it is ok to have R1-R5 marked for
+ * backtracking, as these registers are set by the function
+ * invoking callback.
+ */
+ if (subseq_idx >= 0 && calls_callback(env, subseq_idx))
+ for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+ bt_clear_reg(bt, i);
if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
- /* if backtracing was looking for registers R1-R5
- * they should have been found already.
- */
verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
@@ -4039,11 +4416,9 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
bitmap_from_u64(mask, bt_reg_mask(bt));
for_each_set_bit(i, mask, 32) {
reg = &st->frame[0]->regs[i];
- if (reg->type != SCALAR_VALUE) {
- bt_clear_reg(bt, i);
- continue;
- }
- reg->precise = true;
+ bt_clear_reg(bt, i);
+ if (reg->type == SCALAR_VALUE)
+ reg->precise = true;
}
return 0;
}
@@ -4074,10 +4449,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
* Nothing to be tracked further in the parent state.
*/
return 0;
- if (i == first_idx)
- break;
subseq_idx = i;
i = get_prev_insn_idx(st, i, &history);
+ if (i == -ENOENT)
+ break;
if (i >= env->prog->len) {
/* This can happen if backtracking reached insn 0
* and there are still reg_mask or stack_mask
@@ -4352,7 +4727,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
insn->imm != 0 && env->bpf_capable) {
struct bpf_reg_state fake_reg = {};
- __mark_reg_known(&fake_reg, (u32)insn->imm);
+ __mark_reg_known(&fake_reg, insn->imm);
fake_reg.type = SCALAR_VALUE;
save_register_state(state, spi, &fake_reg, size);
} else if (reg && is_spillable_regtype(reg->type)) {
@@ -4982,20 +5357,24 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
struct bpf_reg_state *reg, u32 regno)
{
const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id);
- int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;
+ int perm_flags;
const char *reg_name = "";
- /* Only unreferenced case accepts untrusted pointers */
- if (kptr_field->type == BPF_KPTR_UNREF)
- perm_flags |= PTR_UNTRUSTED;
+ if (btf_is_kernel(reg->btf)) {
+ perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;
+
+ /* Only unreferenced case accepts untrusted pointers */
+ if (kptr_field->type == BPF_KPTR_UNREF)
+ perm_flags |= PTR_UNTRUSTED;
+ } else {
+ perm_flags = PTR_MAYBE_NULL | MEM_ALLOC;
+ if (kptr_field->type == BPF_KPTR_PERCPU)
+ perm_flags |= MEM_PERCPU;
+ }
if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags))
goto bad_type;
- if (!btf_is_kernel(reg->btf)) {
- verbose(env, "R%d must point to kernel BTF\n", regno);
- return -EINVAL;
- }
/* We need to verify reg->type and reg->btf, before accessing reg->btf */
reg_name = btf_type_name(reg->btf, reg->btf_id);
@@ -5008,7 +5387,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
if (__check_ptr_off_reg(env, reg, regno, true))
return -EACCES;
- /* A full type match is needed, as BTF can be vmlinux or module BTF, and
+ /* A full type match is needed, as BTF can be vmlinux, module or prog BTF, and
* we also need to take into account the reg->off.
*
* We want to support cases like:
@@ -5034,7 +5413,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
*/
if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
kptr_field->kptr.btf, kptr_field->kptr.btf_id,
- kptr_field->type == BPF_KPTR_REF))
+ kptr_field->type != BPF_KPTR_UNREF))
goto bad_type;
return 0;
bad_type:
@@ -5054,13 +5433,17 @@ bad_type:
*/
static bool in_rcu_cs(struct bpf_verifier_env *env)
{
- return env->cur_state->active_rcu_lock || !env->prog->aux->sleepable;
+ return env->cur_state->active_rcu_lock ||
+ env->cur_state->active_lock.ptr ||
+ !env->prog->aux->sleepable;
}
/* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
BTF_SET_START(rcu_protected_types)
BTF_ID(struct, prog_test_ref_kfunc)
+#ifdef CONFIG_CGROUPS
BTF_ID(struct, cgroup)
+#endif
BTF_ID(struct, bpf_cpumask)
BTF_ID(struct, task_struct)
BTF_SET_END(rcu_protected_types)
@@ -5076,7 +5459,18 @@ static bool rcu_safe_kptr(const struct btf_field *field)
{
const struct btf_field_kptr *kptr = &field->kptr;
- return field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id);
+ return field->type == BPF_KPTR_PERCPU ||
+ (field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id));
+}
+
+static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field)
+{
+ if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) {
+ if (kptr_field->type != BPF_KPTR_PERCPU)
+ return PTR_MAYBE_NULL | MEM_RCU;
+ return PTR_MAYBE_NULL | MEM_RCU | MEM_PERCPU;
+ }
+ return PTR_MAYBE_NULL | PTR_UNTRUSTED;
}
static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
@@ -5102,7 +5496,8 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
/* We only allow loading referenced kptr, since it will be marked as
* untrusted, similar to unreferenced kptr.
*/
- if (class != BPF_LDX && kptr_field->type == BPF_KPTR_REF) {
+ if (class != BPF_LDX &&
+ (kptr_field->type == BPF_KPTR_REF || kptr_field->type == BPF_KPTR_PERCPU)) {
verbose(env, "store to referenced kptr disallowed\n");
return -EACCES;
}
@@ -5113,10 +5508,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
* value from map as PTR_TO_BTF_ID, with the correct type.
*/
mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf,
- kptr_field->kptr.btf_id,
- rcu_safe_kptr(kptr_field) && in_rcu_cs(env) ?
- PTR_MAYBE_NULL | MEM_RCU :
- PTR_MAYBE_NULL | PTR_UNTRUSTED);
+ kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field));
/* For mark_ptr_or_null_reg */
val_reg->id = ++env->id_gen;
} else if (class == BPF_STX) {
@@ -5170,6 +5562,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
switch (field->type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
if (src != ACCESS_DIRECT) {
verbose(env, "kptr cannot be accessed indirectly by helper\n");
return -EACCES;
@@ -5412,12 +5805,25 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
return reg->type == PTR_TO_FLOW_KEYS;
}
+static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
+#ifdef CONFIG_NET
+ [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
+ [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
+#endif
+ [CONST_PTR_TO_MAP] = btf_bpf_map_id,
+};
+
static bool is_trusted_reg(const struct bpf_reg_state *reg)
{
/* A referenced register is always trusted. */
if (reg->ref_obj_id)
return true;
+ /* Types listed in the reg2btf_ids are always trusted */
+ if (reg2btf_ids[base_type(reg->type)])
+ return true;
+
/* If a register is not referenced, it is trusted if it has the
* MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the
* other type modifiers may be safe, but we elect to take an opt-in
@@ -5624,6 +6030,27 @@ continue_func:
for (; i < subprog_end; i++) {
int next_insn, sidx;
+ if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) {
+ bool err = false;
+
+ if (!is_bpf_throw_kfunc(insn + i))
+ continue;
+ if (subprog[idx].is_cb)
+ err = true;
+ for (int c = 0; c < frame && !err; c++) {
+ if (subprog[ret_prog[c]].is_cb) {
+ err = true;
+ break;
+ }
+ }
+ if (!err)
+ continue;
+ verbose(env,
+ "bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n",
+ i, idx);
+ return -EINVAL;
+ }
+
if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
continue;
/* remember insn and function to return to */
@@ -5646,6 +6073,10 @@ continue_func:
/* async callbacks don't increase bpf prog stack size unless called directly */
if (!bpf_pseudo_call(insn + i))
continue;
+ if (subprog[sidx].is_exception_cb) {
+ verbose(env, "insn %d cannot call exception cb directly\n", i);
+ return -EINVAL;
+ }
}
i = next_insn;
idx = sidx;
@@ -5667,8 +6098,13 @@ continue_func:
* tail call counter throughout bpf2bpf calls combined with tailcalls
*/
if (tail_call_reachable)
- for (j = 0; j < frame; j++)
+ for (j = 0; j < frame; j++) {
+ if (subprog[ret_prog[j]].is_exception_cb) {
+ verbose(env, "cannot tail call within exception cb\n");
+ return -EINVAL;
+ }
subprog[ret_prog[j]].tail_call_reachable = true;
+ }
if (subprog[0].tail_call_reachable)
env->prog->aux->tail_call_reachable = true;
@@ -5813,6 +6249,147 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
__reg_combine_64_into_32(reg);
}
+static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
+{
+ if (size == 1) {
+ reg->smin_value = reg->s32_min_value = S8_MIN;
+ reg->smax_value = reg->s32_max_value = S8_MAX;
+ } else if (size == 2) {
+ reg->smin_value = reg->s32_min_value = S16_MIN;
+ reg->smax_value = reg->s32_max_value = S16_MAX;
+ } else {
+ /* size == 4 */
+ reg->smin_value = reg->s32_min_value = S32_MIN;
+ reg->smax_value = reg->s32_max_value = S32_MAX;
+ }
+ reg->umin_value = reg->u32_min_value = 0;
+ reg->umax_value = U64_MAX;
+ reg->u32_max_value = U32_MAX;
+ reg->var_off = tnum_unknown;
+}
+
+static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+ s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval;
+ u64 top_smax_value, top_smin_value;
+ u64 num_bits = size * 8;
+
+ if (tnum_is_const(reg->var_off)) {
+ u64_cval = reg->var_off.value;
+ if (size == 1)
+ reg->var_off = tnum_const((s8)u64_cval);
+ else if (size == 2)
+ reg->var_off = tnum_const((s16)u64_cval);
+ else
+ /* size == 4 */
+ reg->var_off = tnum_const((s32)u64_cval);
+
+ u64_cval = reg->var_off.value;
+ reg->smax_value = reg->smin_value = u64_cval;
+ reg->umax_value = reg->umin_value = u64_cval;
+ reg->s32_max_value = reg->s32_min_value = u64_cval;
+ reg->u32_max_value = reg->u32_min_value = u64_cval;
+ return;
+ }
+
+ top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits;
+ top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits;
+
+ if (top_smax_value != top_smin_value)
+ goto out;
+
+ /* find the s64_min and s64_min after sign extension */
+ if (size == 1) {
+ init_s64_max = (s8)reg->smax_value;
+ init_s64_min = (s8)reg->smin_value;
+ } else if (size == 2) {
+ init_s64_max = (s16)reg->smax_value;
+ init_s64_min = (s16)reg->smin_value;
+ } else {
+ init_s64_max = (s32)reg->smax_value;
+ init_s64_min = (s32)reg->smin_value;
+ }
+
+ s64_max = max(init_s64_max, init_s64_min);
+ s64_min = min(init_s64_max, init_s64_min);
+
+ /* both of s64_max/s64_min positive or negative */
+ if ((s64_max >= 0) == (s64_min >= 0)) {
+ reg->smin_value = reg->s32_min_value = s64_min;
+ reg->smax_value = reg->s32_max_value = s64_max;
+ reg->umin_value = reg->u32_min_value = s64_min;
+ reg->umax_value = reg->u32_max_value = s64_max;
+ reg->var_off = tnum_range(s64_min, s64_max);
+ return;
+ }
+
+out:
+ set_sext64_default_val(reg, size);
+}
+
+static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
+{
+ if (size == 1) {
+ reg->s32_min_value = S8_MIN;
+ reg->s32_max_value = S8_MAX;
+ } else {
+ /* size == 2 */
+ reg->s32_min_value = S16_MIN;
+ reg->s32_max_value = S16_MAX;
+ }
+ reg->u32_min_value = 0;
+ reg->u32_max_value = U32_MAX;
+}
+
+static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+ s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val;
+ u32 top_smax_value, top_smin_value;
+ u32 num_bits = size * 8;
+
+ if (tnum_is_const(reg->var_off)) {
+ u32_val = reg->var_off.value;
+ if (size == 1)
+ reg->var_off = tnum_const((s8)u32_val);
+ else
+ reg->var_off = tnum_const((s16)u32_val);
+
+ u32_val = reg->var_off.value;
+ reg->s32_min_value = reg->s32_max_value = u32_val;
+ reg->u32_min_value = reg->u32_max_value = u32_val;
+ return;
+ }
+
+ top_smax_value = ((u32)reg->s32_max_value >> num_bits) << num_bits;
+ top_smin_value = ((u32)reg->s32_min_value >> num_bits) << num_bits;
+
+ if (top_smax_value != top_smin_value)
+ goto out;
+
+ /* find the s32_min and s32_min after sign extension */
+ if (size == 1) {
+ init_s32_max = (s8)reg->s32_max_value;
+ init_s32_min = (s8)reg->s32_min_value;
+ } else {
+ /* size == 2 */
+ init_s32_max = (s16)reg->s32_max_value;
+ init_s32_min = (s16)reg->s32_min_value;
+ }
+ s32_max = max(init_s32_max, init_s32_min);
+ s32_min = min(init_s32_max, init_s32_min);
+
+ if ((s32_min >= 0) == (s32_max >= 0)) {
+ reg->s32_min_value = s32_min;
+ reg->s32_max_value = s32_max;
+ reg->u32_min_value = (u32)s32_min;
+ reg->u32_max_value = (u32)s32_max;
+ return;
+ }
+
+out:
+ set_sext32_default_val(reg, size);
+}
+
static bool bpf_map_is_rdonly(const struct bpf_map *map)
{
/* A map is considered read-only if the following condition are true:
@@ -5833,7 +6410,8 @@ static bool bpf_map_is_rdonly(const struct bpf_map *map)
!bpf_map_write_active(map);
}
-static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
+static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val,
+ bool is_ldsx)
{
void *ptr;
u64 addr;
@@ -5846,13 +6424,13 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
switch (size) {
case sizeof(u8):
- *val = (u64)*(u8 *)ptr;
+ *val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr;
break;
case sizeof(u16):
- *val = (u64)*(u16 *)ptr;
+ *val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr;
break;
case sizeof(u32):
- *val = (u64)*(u32 *)ptr;
+ *val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr;
break;
case sizeof(u64):
*val = *(u64 *)ptr;
@@ -6042,7 +6620,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
}
if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) &&
- !reg->ref_obj_id) {
+ !(reg->type & MEM_RCU) && !reg->ref_obj_id) {
verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n");
return -EFAULT;
}
@@ -6085,6 +6663,11 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
type_is_rcu_or_null(env, reg, field_name, btf_id)) {
/* __rcu tagged pointers can be NULL */
flag |= MEM_RCU | PTR_MAYBE_NULL;
+
+ /* We always trust them */
+ if (type_is_rcu_or_null(env, reg, field_name, btf_id) &&
+ flag & PTR_UNTRUSTED)
+ flag &= ~PTR_UNTRUSTED;
} else if (flag & (MEM_PERCPU | MEM_USER)) {
/* keep as-is */
} else {
@@ -6266,7 +6849,7 @@ static int check_stack_access_within_bounds(
*/
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
int off, int bpf_size, enum bpf_access_type t,
- int value_regno, bool strict_alignment_once)
+ int value_regno, bool strict_alignment_once, bool is_ldsx)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
@@ -6327,7 +6910,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
u64 val = 0;
err = bpf_map_direct_read(map, map_off, size,
- &val);
+ &val, is_ldsx);
if (err)
return err;
@@ -6497,8 +7080,11 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
regs[value_regno].type == SCALAR_VALUE) {
- /* b/h/w load zero-extends, mark upper bits as known 0 */
- coerce_reg_to_size(&regs[value_regno], size);
+ if (!is_ldsx)
+ /* b/h/w load zero-extends, mark upper bits as known 0 */
+ coerce_reg_to_size(&regs[value_regno], size);
+ else
+ coerce_reg_to_size_sx(&regs[value_regno], size);
}
return err;
}
@@ -6590,17 +7176,17 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
* case to simulate the register fill.
*/
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_READ, -1, true);
+ BPF_SIZE(insn->code), BPF_READ, -1, true, false);
if (!err && load_reg >= 0)
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, load_reg,
- true);
+ true, false);
if (err)
return err;
/* Check whether we can write into the same memory. */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+ BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
if (err)
return err;
@@ -6846,7 +7432,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
return zero_size_allowed ? 0 : -EACCES;
return check_mem_access(env, env->insn_idx, regno, offset, BPF_B,
- atype, -1, false);
+ atype, -1, false, false);
}
fallthrough;
@@ -7145,7 +7731,7 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno,
verbose(env, "off=%d doesn't point to kptr\n", kptr_off);
return -EACCES;
}
- if (kptr_field->type != BPF_KPTR_REF) {
+ if (kptr_field->type != BPF_KPTR_REF && kptr_field->type != BPF_KPTR_PERCPU) {
verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off);
return -EACCES;
}
@@ -7218,7 +7804,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
/* we write BPF_DW bits (8 bytes) at a time */
for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) {
err = check_mem_access(env, insn_idx, regno,
- i, BPF_DW, BPF_WRITE, -1, false);
+ i, BPF_DW, BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -7311,20 +7897,29 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) {
err = check_mem_access(env, insn_idx, regno,
- i, BPF_DW, BPF_WRITE, -1, false);
+ i, BPF_DW, BPF_WRITE, -1, false, false);
if (err)
return err;
}
- err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots);
+ err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots);
if (err)
return err;
} else {
/* iter_next() or iter_destroy() expect initialized iter state*/
- if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) {
+ err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots);
+ switch (err) {
+ case 0:
+ break;
+ case -EINVAL:
verbose(env, "expected an initialized iter_%s as arg #%d\n",
iter_type_str(meta->btf, btf_id), regno);
- return -EINVAL;
+ return err;
+ case -EPROTO:
+ verbose(env, "expected an RCU CS when using %s\n", meta->func_name);
+ return err;
+ default:
+ return err;
}
spi = iter_get_spi(env, reg, nr_slots);
@@ -7350,6 +7945,81 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
return 0;
}
+/* Look for a previous loop entry at insn_idx: nearest parent state
+ * stopped at insn_idx with callsites matching those in cur->frame.
+ */
+static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *cur,
+ int insn_idx)
+{
+ struct bpf_verifier_state_list *sl;
+ struct bpf_verifier_state *st;
+
+ /* Explored states are pushed in stack order, most recent states come first */
+ sl = *explored_state(env, insn_idx);
+ for (; sl; sl = sl->next) {
+ /* If st->branches != 0 state is a part of current DFS verification path,
+ * hence cur & st for a loop.
+ */
+ st = &sl->state;
+ if (st->insn_idx == insn_idx && st->branches && same_callsites(st, cur) &&
+ st->dfs_depth < cur->dfs_depth)
+ return st;
+ }
+
+ return NULL;
+}
+
+static void reset_idmap_scratch(struct bpf_verifier_env *env);
+static bool regs_exact(const struct bpf_reg_state *rold,
+ const struct bpf_reg_state *rcur,
+ struct bpf_idmap *idmap);
+
+static void maybe_widen_reg(struct bpf_verifier_env *env,
+ struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
+ struct bpf_idmap *idmap)
+{
+ if (rold->type != SCALAR_VALUE)
+ return;
+ if (rold->type != rcur->type)
+ return;
+ if (rold->precise || rcur->precise || regs_exact(rold, rcur, idmap))
+ return;
+ __mark_reg_unknown(env, rcur);
+}
+
+static int widen_imprecise_scalars(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *old,
+ struct bpf_verifier_state *cur)
+{
+ struct bpf_func_state *fold, *fcur;
+ int i, fr;
+
+ reset_idmap_scratch(env);
+ for (fr = old->curframe; fr >= 0; fr--) {
+ fold = old->frame[fr];
+ fcur = cur->frame[fr];
+
+ for (i = 0; i < MAX_BPF_REG; i++)
+ maybe_widen_reg(env,
+ &fold->regs[i],
+ &fcur->regs[i],
+ &env->idmap_scratch);
+
+ for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; i++) {
+ if (!is_spilled_reg(&fold->stack[i]) ||
+ !is_spilled_reg(&fcur->stack[i]))
+ continue;
+
+ maybe_widen_reg(env,
+ &fold->stack[i].spilled_ptr,
+ &fcur->stack[i].spilled_ptr,
+ &env->idmap_scratch);
+ }
+ }
+ return 0;
+}
+
/* process_iter_next_call() is called when verifier gets to iterator's next
* "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer
* to it as just "iter_next()" in comments below.
@@ -7391,25 +8061,47 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
* is some statically known limit on number of iterations (e.g., if there is
* an explicit `if n > 100 then break;` statement somewhere in the loop).
*
- * One very subtle but very important aspect is that we *always* simulate NULL
- * condition first (as the current state) before we simulate non-NULL case.
- * This has to do with intricacies of scalar precision tracking. By simulating
- * "exit condition" of iter_next() returning NULL first, we make sure all the
- * relevant precision marks *that will be set **after** we exit iterator loop*
- * are propagated backwards to common parent state of NULL and non-NULL
- * branches. Thanks to that, state equivalence checks done later in forked
- * state, when reaching iter_next() for ACTIVE iterator, can assume that
- * precision marks are finalized and won't change. Because simulating another
- * ACTIVE iterator iteration won't change them (because given same input
- * states we'll end up with exactly same output states which we are currently
- * comparing; and verification after the loop already propagated back what
- * needs to be **additionally** tracked as precise). It's subtle, grok
- * precision tracking for more intuitive understanding.
+ * Iteration convergence logic in is_state_visited() relies on exact
+ * states comparison, which ignores read and precision marks.
+ * This is necessary because read and precision marks are not finalized
+ * while in the loop. Exact comparison might preclude convergence for
+ * simple programs like below:
+ *
+ * i = 0;
+ * while(iter_next(&it))
+ * i++;
+ *
+ * At each iteration step i++ would produce a new distinct state and
+ * eventually instruction processing limit would be reached.
+ *
+ * To avoid such behavior speculatively forget (widen) range for
+ * imprecise scalar registers, if those registers were not precise at the
+ * end of the previous iteration and do not match exactly.
+ *
+ * This is a conservative heuristic that allows to verify wide range of programs,
+ * however it precludes verification of programs that conjure an
+ * imprecise value on the first loop iteration and use it as precise on a second.
+ * For example, the following safe program would fail to verify:
+ *
+ * struct bpf_num_iter it;
+ * int arr[10];
+ * int i = 0, a = 0;
+ * bpf_iter_num_new(&it, 0, 10);
+ * while (bpf_iter_num_next(&it)) {
+ * if (a == 0) {
+ * a = 1;
+ * i = 7; // Because i changed verifier would forget
+ * // it's range on second loop entry.
+ * } else {
+ * arr[i] = 42; // This would fail to verify.
+ * }
+ * }
+ * bpf_iter_num_destroy(&it);
*/
static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
struct bpf_kfunc_call_arg_meta *meta)
{
- struct bpf_verifier_state *cur_st = env->cur_state, *queued_st;
+ struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st;
struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr;
struct bpf_reg_state *cur_iter, *queued_iter;
int iter_frameno = meta->iter.frameno;
@@ -7427,6 +8119,19 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
}
if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) {
+ /* Because iter_next() call is a checkpoint is_state_visitied()
+ * should guarantee parent state with same call sites and insn_idx.
+ */
+ if (!cur_st->parent || cur_st->parent->insn_idx != insn_idx ||
+ !same_callsites(cur_st->parent, cur_st)) {
+ verbose(env, "bug: bad parent state for iter next call");
+ return -EFAULT;
+ }
+ /* Note cur_st->parent in the call below, it is necessary to skip
+ * checkpoint created for cur_st by is_state_visited()
+ * right at this instruction.
+ */
+ prev_st = find_prev_entry(env, cur_st->parent, insn_idx);
/* branch out active iter state */
queued_st = push_stack(env, insn_idx + 1, insn_idx, false);
if (!queued_st)
@@ -7435,6 +8140,8 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
queued_iter = &queued_st->frame[iter_frameno]->stack[iter_spi].spilled_ptr;
queued_iter->iter.state = BPF_ITER_STATE_ACTIVE;
queued_iter->iter.depth++;
+ if (prev_st)
+ widen_imprecise_scalars(env, prev_st, queued_st);
queued_fr = queued_st->frame[queued_st->curframe];
mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]);
@@ -7578,6 +8285,7 @@ static const struct bpf_reg_types btf_ptr_types = {
static const struct bpf_reg_types percpu_btf_ptr_types = {
.types = {
PTR_TO_BTF_ID | MEM_PERCPU,
+ PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU,
PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED,
}
};
@@ -7656,8 +8364,10 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
if (base_type(arg_type) == ARG_PTR_TO_MEM)
type &= ~DYNPTR_TYPE_FLAG_MASK;
- if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type))
+ if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type)) {
type &= ~MEM_ALLOC;
+ type &= ~MEM_PERCPU;
+ }
for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
expected = compatible->types[i];
@@ -7740,14 +8450,19 @@ found:
break;
}
case PTR_TO_BTF_ID | MEM_ALLOC:
+ case PTR_TO_BTF_ID | MEM_PERCPU | MEM_ALLOC:
if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock &&
meta->func_id != BPF_FUNC_kptr_xchg) {
verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n");
return -EFAULT;
}
- /* Handled by helper specific checks */
+ if (meta->func_id == BPF_FUNC_kptr_xchg) {
+ if (map_kptr_match_type(env, meta->kptr_field, reg, regno))
+ return -EACCES;
+ }
break;
case PTR_TO_BTF_ID | MEM_PERCPU:
+ case PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU:
case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED:
/* Handled by helper specific checks */
break;
@@ -7797,17 +8512,6 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK)
return 0;
- if ((type_is_ptr_alloc_obj(type) || type_is_non_owning_ref(type)) && reg->off) {
- if (reg_find_field_offset(reg, reg->off, BPF_GRAPH_NODE_OR_ROOT))
- return __check_ptr_off_reg(env, reg, regno, true);
-
- verbose(env, "R%d must have zero offset when passed to release func\n",
- regno);
- verbose(env, "No graph node or root found at R%d type:%s off:%d\n", regno,
- btf_type_name(reg->btf, reg->btf_id), reg->off);
- return -EINVAL;
- }
-
/* Doing check_ptr_off_reg check for the offset will catch this
* because fixed_off_ok is false, but checking here allows us
* to give the user a better error message.
@@ -7842,6 +8546,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
case PTR_TO_BTF_ID | PTR_TRUSTED:
case PTR_TO_BTF_ID | MEM_RCU:
case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF:
+ case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU:
/* When referenced PTR_TO_BTF_ID is passed to release function,
* its fixed offset must be 0. In the other cases, fixed offset
* can be non-zero. This was already checked above. So pass
@@ -8671,7 +9376,7 @@ static void clear_caller_saved_regs(struct bpf_verifier_env *env,
/* after the call registers r0 - r5 were scratched */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
- check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+ __check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK);
}
}
@@ -8684,11 +9389,10 @@ static int set_callee_state(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee, int insn_idx);
-static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
- int *insn_idx, int subprog,
- set_callee_state_fn set_callee_state_cb)
+static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite,
+ set_callee_state_fn set_callee_state_cb,
+ struct bpf_verifier_state *state)
{
- struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_state *caller, *callee;
int err;
@@ -8698,53 +9402,72 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return -E2BIG;
}
- caller = state->frame[state->curframe];
if (state->frame[state->curframe + 1]) {
verbose(env, "verifier bug. Frame %d already allocated\n",
state->curframe + 1);
return -EFAULT;
}
+ caller = state->frame[state->curframe];
+ callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+ if (!callee)
+ return -ENOMEM;
+ state->frame[state->curframe + 1] = callee;
+
+ /* callee cannot access r0, r6 - r9 for reading and has to write
+ * into its own stack before reading from it.
+ * callee can read/write into caller's stack
+ */
+ init_func_state(env, callee,
+ /* remember the callsite, it will be used by bpf_exit */
+ callsite,
+ state->curframe + 1 /* frameno within this callchain */,
+ subprog /* subprog number within this prog */);
+ /* Transfer references to the callee */
+ err = copy_reference_state(callee, caller);
+ err = err ?: set_callee_state_cb(env, caller, callee, callsite);
+ if (err)
+ goto err_out;
+
+ /* only increment it after check_reg_arg() finished */
+ state->curframe++;
+
+ return 0;
+
+err_out:
+ free_func_state(callee);
+ state->frame[state->curframe + 1] = NULL;
+ return err;
+}
+
+static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+ int insn_idx, int subprog,
+ set_callee_state_fn set_callee_state_cb)
+{
+ struct bpf_verifier_state *state = env->cur_state, *callback_state;
+ struct bpf_func_state *caller, *callee;
+ int err;
+
+ caller = state->frame[state->curframe];
err = btf_check_subprog_call(env, subprog, caller->regs);
if (err == -EFAULT)
return err;
- if (subprog_is_global(env, subprog)) {
- if (err) {
- verbose(env, "Caller passes invalid args into func#%d\n",
- subprog);
- return err;
- } else {
- if (env->log.level & BPF_LOG_LEVEL)
- verbose(env,
- "Func#%d is global and valid. Skipping.\n",
- subprog);
- clear_caller_saved_regs(env, caller->regs);
-
- /* All global functions return a 64-bit SCALAR_VALUE */
- mark_reg_unknown(env, caller->regs, BPF_REG_0);
- caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
-
- /* continue with next insn after call */
- return 0;
- }
- }
/* set_callee_state is used for direct subprog calls, but we are
* interested in validating only BPF helpers that can call subprogs as
* callbacks
*/
- if (set_callee_state_cb != set_callee_state) {
- if (bpf_pseudo_kfunc_call(insn) &&
- !is_callback_calling_kfunc(insn->imm)) {
- verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
- func_id_name(insn->imm), insn->imm);
- return -EFAULT;
- } else if (!bpf_pseudo_kfunc_call(insn) &&
- !is_callback_calling_function(insn->imm)) { /* helper */
- verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
- func_id_name(insn->imm), insn->imm);
- return -EFAULT;
- }
+ env->subprog_info[subprog].is_cb = true;
+ if (bpf_pseudo_kfunc_call(insn) &&
+ !is_sync_callback_calling_kfunc(insn->imm)) {
+ verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
+ func_id_name(insn->imm), insn->imm);
+ return -EFAULT;
+ } else if (!bpf_pseudo_kfunc_call(insn) &&
+ !is_callback_calling_function(insn->imm)) { /* helper */
+ verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
+ func_id_name(insn->imm), insn->imm);
+ return -EFAULT;
}
if (insn->code == (BPF_JMP | BPF_CALL) &&
@@ -8755,53 +9478,83 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
/* there is no real recursion here. timer callbacks are async */
env->subprog_info[subprog].is_async_cb = true;
async_cb = push_async_cb(env, env->subprog_info[subprog].start,
- *insn_idx, subprog);
+ insn_idx, subprog);
if (!async_cb)
return -EFAULT;
callee = async_cb->frame[0];
callee->async_entry_cnt = caller->async_entry_cnt + 1;
/* Convert bpf_timer_set_callback() args into timer callback args */
- err = set_callee_state_cb(env, caller, callee, *insn_idx);
+ err = set_callee_state_cb(env, caller, callee, insn_idx);
if (err)
return err;
+ return 0;
+ }
+
+ /* for callback functions enqueue entry to callback and
+ * proceed with next instruction within current frame.
+ */
+ callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false);
+ if (!callback_state)
+ return -ENOMEM;
+
+ err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb,
+ callback_state);
+ if (err)
+ return err;
+
+ callback_state->callback_unroll_depth++;
+ callback_state->frame[callback_state->curframe - 1]->callback_depth++;
+ caller->callback_depth = 0;
+ return 0;
+}
+
+static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+ int *insn_idx)
+{
+ struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_func_state *caller;
+ int err, subprog, target_insn;
+
+ target_insn = *insn_idx + insn->imm + 1;
+ subprog = find_subprog(env, target_insn);
+ if (subprog < 0) {
+ verbose(env, "verifier bug. No program starts at insn %d\n", target_insn);
+ return -EFAULT;
+ }
+
+ caller = state->frame[state->curframe];
+ err = btf_check_subprog_call(env, subprog, caller->regs);
+ if (err == -EFAULT)
+ return err;
+ if (subprog_is_global(env, subprog)) {
+ if (err) {
+ verbose(env, "Caller passes invalid args into func#%d\n", subprog);
+ return err;
+ }
+
+ if (env->log.level & BPF_LOG_LEVEL)
+ verbose(env, "Func#%d is global and valid. Skipping.\n", subprog);
clear_caller_saved_regs(env, caller->regs);
+
+ /* All global functions return a 64-bit SCALAR_VALUE */
mark_reg_unknown(env, caller->regs, BPF_REG_0);
caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
+
/* continue with next insn after call */
return 0;
}
- callee = kzalloc(sizeof(*callee), GFP_KERNEL);
- if (!callee)
- return -ENOMEM;
- state->frame[state->curframe + 1] = callee;
-
- /* callee cannot access r0, r6 - r9 for reading and has to write
- * into its own stack before reading from it.
- * callee can read/write into caller's stack
+ /* for regular function entry setup new frame and continue
+ * from that frame.
*/
- init_func_state(env, callee,
- /* remember the callsite, it will be used by bpf_exit */
- *insn_idx /* callsite */,
- state->curframe + 1 /* frameno within this callchain */,
- subprog /* subprog number within this prog */);
-
- /* Transfer references to the callee */
- err = copy_reference_state(callee, caller);
+ err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state);
if (err)
- goto err_out;
-
- err = set_callee_state_cb(env, caller, callee, *insn_idx);
- if (err)
- goto err_out;
+ return err;
clear_caller_saved_regs(env, caller->regs);
- /* only increment it after check_reg_arg() finished */
- state->curframe++;
-
/* and go analyze first insn of the callee */
*insn_idx = env->subprog_info[subprog].start - 1;
@@ -8809,14 +9562,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
verbose(env, "caller:\n");
print_verifier_state(env, caller, true);
verbose(env, "callee:\n");
- print_verifier_state(env, callee, true);
+ print_verifier_state(env, state->frame[state->curframe], true);
}
- return 0;
-err_out:
- free_func_state(callee);
- state->frame[state->curframe + 1] = NULL;
- return err;
+ return 0;
}
int map_set_for_each_callback_args(struct bpf_verifier_env *env,
@@ -8860,22 +9609,6 @@ static int set_callee_state(struct bpf_verifier_env *env,
return 0;
}
-static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
- int *insn_idx)
-{
- int subprog, target_insn;
-
- target_insn = *insn_idx + insn->imm + 1;
- subprog = find_subprog(env, target_insn);
- if (subprog < 0) {
- verbose(env, "verifier bug. No program starts at insn %d\n",
- target_insn);
- return -EFAULT;
- }
-
- return __check_func_call(env, insn, insn_idx, subprog, set_callee_state);
-}
-
static int set_map_elem_callback_state(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee,
@@ -9068,9 +9801,10 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
- struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_verifier_state *state = env->cur_state, *prev_st;
struct bpf_func_state *caller, *callee;
struct bpf_reg_state *r0;
+ bool in_callback_fn;
int err;
callee = state->frame[state->curframe];
@@ -9099,6 +9833,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
return -EINVAL;
}
+ if (!calls_callback(env, callee->callsite)) {
+ verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n",
+ *insn_idx, callee->callsite);
+ return -EFAULT;
+ }
} else {
/* return to the caller whatever r0 had in the callee */
caller->regs[BPF_REG_0] = *r0;
@@ -9116,16 +9855,44 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
return err;
}
- *insn_idx = callee->callsite + 1;
+ /* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite,
+ * there function call logic would reschedule callback visit. If iteration
+ * converges is_state_visited() would prune that visit eventually.
+ */
+ in_callback_fn = callee->in_callback_fn;
+ if (in_callback_fn)
+ *insn_idx = callee->callsite;
+ else
+ *insn_idx = callee->callsite + 1;
+
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "returning from callee:\n");
print_verifier_state(env, callee, true);
verbose(env, "to caller at %d:\n", *insn_idx);
print_verifier_state(env, caller, true);
}
- /* clear everything in the callee */
+ /* clear everything in the callee. In case of exceptional exits using
+ * bpf_throw, this will be done by copy_verifier_state for extra frames. */
free_func_state(callee);
state->frame[state->curframe--] = NULL;
+
+ /* for callbacks widen imprecise scalars to make programs like below verify:
+ *
+ * struct ctx { int i; }
+ * void cb(int idx, struct ctx *ctx) { ctx->i++; ... }
+ * ...
+ * struct ctx = { .i = 0; }
+ * bpf_loop(100, cb, &ctx, 0);
+ *
+ * This is similar to what is done in process_iter_next_call() for open
+ * coded iterators.
+ */
+ prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL;
+ if (prev_st) {
+ err = widen_imprecise_scalars(env, prev_st, state);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -9135,19 +9902,33 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
{
struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
- if (ret_type != RET_INTEGER ||
- (func_id != BPF_FUNC_get_stack &&
- func_id != BPF_FUNC_get_task_stack &&
- func_id != BPF_FUNC_probe_read_str &&
- func_id != BPF_FUNC_probe_read_kernel_str &&
- func_id != BPF_FUNC_probe_read_user_str))
+ if (ret_type != RET_INTEGER)
return;
- ret_reg->smax_value = meta->msize_max_value;
- ret_reg->s32_max_value = meta->msize_max_value;
- ret_reg->smin_value = -MAX_ERRNO;
- ret_reg->s32_min_value = -MAX_ERRNO;
- reg_bounds_sync(ret_reg);
+ switch (func_id) {
+ case BPF_FUNC_get_stack:
+ case BPF_FUNC_get_task_stack:
+ case BPF_FUNC_probe_read_str:
+ case BPF_FUNC_probe_read_kernel_str:
+ case BPF_FUNC_probe_read_user_str:
+ ret_reg->smax_value = meta->msize_max_value;
+ ret_reg->s32_max_value = meta->msize_max_value;
+ ret_reg->smin_value = -MAX_ERRNO;
+ ret_reg->s32_min_value = -MAX_ERRNO;
+ reg_bounds_sync(ret_reg);
+ break;
+ case BPF_FUNC_get_smp_processor_id:
+ ret_reg->umax_value = nr_cpu_ids - 1;
+ ret_reg->u32_max_value = nr_cpu_ids - 1;
+ ret_reg->smax_value = nr_cpu_ids - 1;
+ ret_reg->s32_max_value = nr_cpu_ids - 1;
+ ret_reg->umin_value = 0;
+ ret_reg->u32_min_value = 0;
+ ret_reg->smin_value = 0;
+ ret_reg->s32_min_value = 0;
+ reg_bounds_sync(ret_reg);
+ break;
+ }
}
static int
@@ -9233,17 +10014,17 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
return 0;
}
-static int check_reference_leak(struct bpf_verifier_env *env)
+static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit)
{
struct bpf_func_state *state = cur_func(env);
bool refs_lingering = false;
int i;
- if (state->frameno && !state->in_callback_fn)
+ if (!exception_exit && state->frameno && !state->in_callback_fn)
return 0;
for (i = 0; i < state->acquired_refs; i++) {
- if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
+ if (!exception_exit && state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
continue;
verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
state->refs[i].id, state->refs[i].insn_idx);
@@ -9350,6 +10131,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
int *insn_idx_p)
{
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+ bool returns_cpu_specific_alloc_ptr = false;
const struct bpf_func_proto *fn = NULL;
enum bpf_return_type ret_type;
enum bpf_type_flag ret_flag;
@@ -9441,7 +10223,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
*/
for (i = 0; i < meta.access_size; i++) {
err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
- BPF_WRITE, -1, false);
+ BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -9460,6 +10242,26 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return -EFAULT;
}
err = unmark_stack_slots_dynptr(env, &regs[meta.release_regno]);
+ } else if (func_id == BPF_FUNC_kptr_xchg && meta.ref_obj_id) {
+ u32 ref_obj_id = meta.ref_obj_id;
+ bool in_rcu = in_rcu_cs(env);
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+
+ err = release_reference_state(cur_func(env), ref_obj_id);
+ if (!err) {
+ bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ if (reg->ref_obj_id == ref_obj_id) {
+ if (in_rcu && (reg->type & MEM_ALLOC) && (reg->type & MEM_PERCPU)) {
+ reg->ref_obj_id = 0;
+ reg->type &= ~MEM_ALLOC;
+ reg->type |= MEM_RCU;
+ } else {
+ mark_reg_invalid(env, reg);
+ }
+ }
+ }));
+ }
} else if (meta.ref_obj_id) {
err = release_reference(env, meta.ref_obj_id);
} else if (register_is_null(&regs[meta.release_regno])) {
@@ -9477,7 +10279,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
switch (func_id) {
case BPF_FUNC_tail_call:
- err = check_reference_leak(env);
+ err = check_reference_leak(env, false);
if (err) {
verbose(env, "tail_call would lead to reference leak\n");
return err;
@@ -9493,24 +10295,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
}
break;
case BPF_FUNC_for_each_map_elem:
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_map_elem_callback_state);
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_map_elem_callback_state);
break;
case BPF_FUNC_timer_set_callback:
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_timer_callback_state);
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_timer_callback_state);
break;
case BPF_FUNC_find_vma:
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_find_vma_callback_state);
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_find_vma_callback_state);
break;
case BPF_FUNC_snprintf:
err = check_bpf_snprintf_call(env, regs);
break;
case BPF_FUNC_loop:
update_loop_inline_state(env, meta.subprogno);
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_loop_callback_state);
+ /* Verifier relies on R1 value to determine if bpf_loop() iteration
+ * is finished, thus mark it precise.
+ */
+ err = mark_chain_precision(env, BPF_REG_1);
+ if (err)
+ return err;
+ if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) {
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_loop_callback_state);
+ } else {
+ cur_func(env)->callback_depth = 0;
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "frame%d bpf_loop iteration limit reached\n",
+ env->cur_state->curframe);
+ }
break;
case BPF_FUNC_dynptr_from_mem:
if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) {
@@ -9588,9 +10403,26 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
break;
}
+ case BPF_FUNC_per_cpu_ptr:
+ case BPF_FUNC_this_cpu_ptr:
+ {
+ struct bpf_reg_state *reg = &regs[BPF_REG_1];
+ const struct btf_type *type;
+
+ if (reg->type & MEM_RCU) {
+ type = btf_type_by_id(reg->btf, reg->btf_id);
+ if (!type || !btf_type_is_struct(type)) {
+ verbose(env, "Helper has invalid btf/btf_id in R1\n");
+ return -EFAULT;
+ }
+ returns_cpu_specific_alloc_ptr = true;
+ env->insn_aux_data[insn_idx].call_with_percpu_alloc_ptr = true;
+ }
+ break;
+ }
case BPF_FUNC_user_ringbuf_drain:
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_user_ringbuf_callback_state);
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_user_ringbuf_callback_state);
break;
}
@@ -9677,14 +10509,18 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
regs[BPF_REG_0].mem_size = tsize;
} else {
- /* MEM_RDONLY may be carried from ret_flag, but it
- * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
- * it will confuse the check of PTR_TO_BTF_ID in
- * check_mem_access().
- */
- ret_flag &= ~MEM_RDONLY;
+ if (returns_cpu_specific_alloc_ptr) {
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC | MEM_RCU;
+ } else {
+ /* MEM_RDONLY may be carried from ret_flag, but it
+ * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
+ * it will confuse the check of PTR_TO_BTF_ID in
+ * check_mem_access().
+ */
+ ret_flag &= ~MEM_RDONLY;
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
+ }
- regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
regs[BPF_REG_0].btf = meta.ret_btf;
regs[BPF_REG_0].btf_id = meta.ret_btf_id;
}
@@ -9700,8 +10536,11 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (func_id == BPF_FUNC_kptr_xchg) {
ret_btf = meta.kptr_field->kptr.btf;
ret_btf_id = meta.kptr_field->kptr.btf_id;
- if (!btf_is_kernel(ret_btf))
+ if (!btf_is_kernel(ret_btf)) {
regs[BPF_REG_0].type |= MEM_ALLOC;
+ if (meta.kptr_field->type == BPF_KPTR_PERCPU)
+ regs[BPF_REG_0].type |= MEM_PERCPU;
+ }
} else {
if (fn->ret_btf_id == BPF_PTR_POISON) {
verbose(env, "verifier internal error:");
@@ -9848,6 +10687,11 @@ static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta)
return meta->kfunc_flags & KF_RCU;
}
+static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta)
+{
+ return meta->kfunc_flags & KF_RCU_PROTECTED;
+}
+
static bool __kfunc_param_match_suffix(const struct btf *btf,
const struct btf_param *arg,
const char *suffix)
@@ -9922,6 +10766,11 @@ static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf
return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr");
}
+static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg)
+{
+ return __kfunc_param_match_suffix(btf, arg, "__nullable");
+}
+
static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
const struct btf_param *arg,
const char *name)
@@ -10050,15 +10899,6 @@ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env,
return true;
}
-
-static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
-#ifdef CONFIG_NET
- [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
- [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
- [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
-#endif
-};
-
enum kfunc_ptr_arg_type {
KF_ARG_PTR_TO_CTX,
KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */
@@ -10073,6 +10913,7 @@ enum kfunc_ptr_arg_type {
KF_ARG_PTR_TO_CALLBACK,
KF_ARG_PTR_TO_RB_ROOT,
KF_ARG_PTR_TO_RB_NODE,
+ KF_ARG_PTR_TO_NULL,
};
enum special_kfunc_type {
@@ -10095,6 +10936,10 @@ enum special_kfunc_type {
KF_bpf_dynptr_slice,
KF_bpf_dynptr_slice_rdwr,
KF_bpf_dynptr_clone,
+ KF_bpf_percpu_obj_new_impl,
+ KF_bpf_percpu_obj_drop_impl,
+ KF_bpf_throw,
+ KF_bpf_iter_css_task_new,
};
BTF_SET_START(special_kfunc_set)
@@ -10115,6 +10960,12 @@ BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
BTF_ID(func, bpf_dynptr_clone)
+BTF_ID(func, bpf_percpu_obj_new_impl)
+BTF_ID(func, bpf_percpu_obj_drop_impl)
+BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
+BTF_ID(func, bpf_iter_css_task_new)
+#endif
BTF_SET_END(special_kfunc_set)
BTF_ID_LIST(special_kfunc_list)
@@ -10137,6 +10988,14 @@ BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
BTF_ID(func, bpf_dynptr_clone)
+BTF_ID(func, bpf_percpu_obj_new_impl)
+BTF_ID(func, bpf_percpu_obj_drop_impl)
+BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
+BTF_ID(func, bpf_iter_css_task_new)
+#else
+BTF_ID_UNUSED
+#endif
static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
{
@@ -10217,6 +11076,8 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
if (is_kfunc_arg_callback(env, meta->btf, &args[argno]))
return KF_ARG_PTR_TO_CALLBACK;
+ if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg))
+ return KF_ARG_PTR_TO_NULL;
if (argno + 1 < nargs &&
(is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1]) ||
@@ -10303,6 +11164,7 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env,
static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
struct bpf_verifier_state *state = env->cur_state;
+ struct btf_record *rec = reg_btf_record(reg);
if (!state->active_lock.ptr) {
verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n");
@@ -10315,6 +11177,9 @@ static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state
}
reg->type |= NON_OWN_REF;
+ if (rec->refcount_off >= 0)
+ reg->type |= MEM_RCU;
+
return 0;
}
@@ -10445,11 +11310,17 @@ static bool is_bpf_graph_api_kfunc(u32 btf_id)
btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl];
}
-static bool is_callback_calling_kfunc(u32 btf_id)
+static bool is_sync_callback_calling_kfunc(u32 btf_id)
{
return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl];
}
+static bool is_bpf_throw_kfunc(struct bpf_insn *insn)
+{
+ return bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
+ insn->imm == special_kfunc_list[KF_bpf_throw];
+}
+
static bool is_rbtree_lock_required_kfunc(u32 btf_id)
{
return is_bpf_rbtree_api_kfunc(btf_id);
@@ -10657,6 +11528,28 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
&meta->arg_rbtree_root.field);
}
+/*
+ * css_task iter allowlist is needed to avoid dead locking on css_set_lock.
+ * LSM hooks and iters (both sleepable and non-sleepable) are safe.
+ * Any sleepable progs are also safe since bpf_check_attach_target() enforce
+ * them can only be attached to some specific hook points.
+ */
+static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
+{
+ enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+
+ switch (prog_type) {
+ case BPF_PROG_TYPE_LSM:
+ return true;
+ case BPF_PROG_TYPE_TRACING:
+ if (env->prog->expected_attach_type == BPF_TRACE_ITER)
+ return true;
+ fallthrough;
+ default:
+ return env->prog->aux->sleepable;
+ }
+}
+
static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta,
int insn_idx)
{
@@ -10743,7 +11636,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
}
if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) &&
- (register_is_null(reg) || type_may_be_null(reg->type))) {
+ (register_is_null(reg) || type_may_be_null(reg->type)) &&
+ !is_kfunc_arg_nullable(meta->btf, &args[i])) {
verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i);
return -EACCES;
}
@@ -10768,6 +11662,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
return kf_arg_type;
switch (kf_arg_type) {
+ case KF_ARG_PTR_TO_NULL:
+ continue;
case KF_ARG_PTR_TO_ALLOC_BTF_ID:
case KF_ARG_PTR_TO_BTF_ID:
if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta))
@@ -10827,7 +11723,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
}
break;
case KF_ARG_PTR_TO_ALLOC_BTF_ID:
- if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) {
+ if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) {
+ if (meta->func_id != special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ verbose(env, "arg#%d expected for bpf_obj_drop_impl()\n", i);
+ return -EINVAL;
+ }
+ } else if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC | MEM_PERCPU)) {
+ if (meta->func_id != special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) {
+ verbose(env, "arg#%d expected for bpf_percpu_obj_drop_impl()\n", i);
+ return -EINVAL;
+ }
+ } else {
verbose(env, "arg#%d expected pointer to allocated object\n", i);
return -EINVAL;
}
@@ -10835,8 +11741,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
verbose(env, "allocated object must be referenced\n");
return -EINVAL;
}
- if (meta->btf == btf_vmlinux &&
- meta->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ if (meta->btf == btf_vmlinux) {
meta->arg_btf = reg->btf;
meta->arg_btf_id = reg->btf_id;
}
@@ -10898,6 +11803,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
break;
}
case KF_ARG_PTR_TO_ITER:
+ if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
+ if (!check_css_task_iter_allowlist(env)) {
+ verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n");
+ return -EINVAL;
+ }
+ }
ret = process_iter_arg(env, regno, insn_idx, meta);
if (ret < 0)
return ret;
@@ -11027,6 +11938,10 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
break;
}
case KF_ARG_PTR_TO_CALLBACK:
+ if (reg->type != PTR_TO_FUNC) {
+ verbose(env, "arg%d expected pointer to func\n", i);
+ return -EINVAL;
+ }
meta->subprogno = reg->subprogno;
break;
case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
@@ -11047,10 +11962,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
verbose(env, "arg#%d doesn't point to a type with bpf_refcount field\n", i);
return -EINVAL;
}
- if (rec->refcount_off >= 0) {
- verbose(env, "bpf_refcount_acquire calls are disabled for now\n");
- return -EINVAL;
- }
+
meta->arg_btf = reg->btf;
meta->arg_btf_id = reg->btf_id;
break;
@@ -11108,6 +12020,8 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env,
return 0;
}
+static int check_return_code(struct bpf_verifier_env *env, int regno);
+
static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx_p)
{
@@ -11148,18 +12062,39 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EACCES;
}
+ /* Check the arguments */
+ err = check_kfunc_args(env, &meta, insn_idx);
+ if (err < 0)
+ return err;
+
+ if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_rbtree_add_callback_state);
+ if (err) {
+ verbose(env, "kfunc %s#%d failed callback verification\n",
+ func_name, meta.func_id);
+ return err;
+ }
+ }
+
rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta);
rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta);
if (env->cur_state->active_rcu_lock) {
struct bpf_func_state *state;
struct bpf_reg_state *reg;
+ u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER);
+
+ if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) {
+ verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n");
+ return -EACCES;
+ }
if (rcu_lock) {
verbose(env, "nested rcu read lock (kernel function %s)\n", func_name);
return -EINVAL;
} else if (rcu_unlock) {
- bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({
if (reg->type & MEM_RCU) {
reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL);
reg->type |= PTR_UNTRUSTED;
@@ -11177,10 +12112,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EINVAL;
}
- /* Check the arguments */
- err = check_kfunc_args(env, &meta, insn_idx);
- if (err < 0)
- return err;
/* In case of release function, we get register number of refcounted
* PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now.
*/
@@ -11214,13 +12145,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
}
}
- if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_rbtree_add_callback_state);
- if (err) {
- verbose(env, "kfunc %s#%d failed callback verification\n",
+ if (meta.func_id == special_kfunc_list[KF_bpf_throw]) {
+ if (!bpf_jit_supports_exceptions()) {
+ verbose(env, "JIT does not support calling kfunc %s#%d\n",
func_name, meta.func_id);
- return err;
+ return -ENOTSUPP;
+ }
+ env->seen_exception = true;
+
+ /* In the case of the default callback, the cookie value passed
+ * to bpf_throw becomes the return value of the program.
+ */
+ if (!env->exception_callback_subprog) {
+ err = check_return_code(env, BPF_REG_1);
+ if (err < 0)
+ return err;
}
}
@@ -11234,6 +12173,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
/* Only exception is bpf_obj_new_impl */
if (meta.btf != btf_vmlinux ||
(meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl] &&
+ meta.func_id != special_kfunc_list[KF_bpf_percpu_obj_new_impl] &&
meta.func_id != special_kfunc_list[KF_bpf_refcount_acquire_impl])) {
verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
return -EINVAL;
@@ -11247,13 +12187,29 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id);
if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
- if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] ||
+ meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ struct btf_struct_meta *struct_meta;
struct btf *ret_btf;
u32 ret_btf_id;
- if (unlikely(!bpf_global_ma_set))
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
return -ENOMEM;
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ if (!bpf_global_percpu_ma_set) {
+ mutex_lock(&bpf_percpu_ma_lock);
+ if (!bpf_global_percpu_ma_set) {
+ err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
+ if (!err)
+ bpf_global_percpu_ma_set = true;
+ }
+ mutex_unlock(&bpf_percpu_ma_lock);
+ if (err)
+ return err;
+ }
+ }
+
if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
return -EINVAL;
@@ -11264,24 +12220,38 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
/* This may be NULL due to user not supplying a BTF */
if (!ret_btf) {
- verbose(env, "bpf_obj_new requires prog BTF\n");
+ verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n");
return -EINVAL;
}
ret_t = btf_type_by_id(ret_btf, ret_btf_id);
if (!ret_t || !__btf_type_is_struct(ret_t)) {
- verbose(env, "bpf_obj_new type ID argument must be of a struct\n");
+ verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n");
return -EINVAL;
}
+ struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
+ verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n");
+ return -EINVAL;
+ }
+
+ if (struct_meta) {
+ verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n");
+ return -EINVAL;
+ }
+ }
+
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
regs[BPF_REG_0].btf = ret_btf;
regs[BPF_REG_0].btf_id = ret_btf_id;
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl])
+ regs[BPF_REG_0].type |= MEM_PERCPU;
insn_aux->obj_new_size = ret_t->size;
- insn_aux->kptr_struct_meta =
- btf_find_struct_meta(ret_btf, ret_btf_id);
+ insn_aux->kptr_struct_meta = struct_meta;
} else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
@@ -11418,7 +12388,8 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
regs[BPF_REG_0].id = ++env->id_gen;
} else if (btf_type_is_void(t)) {
if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
- if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl] ||
+ meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) {
insn_aux->kptr_struct_meta =
btf_find_struct_meta(meta.arg_btf,
meta.arg_btf_id);
@@ -12907,7 +13878,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
(insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
- BPF_CLASS(insn->code) == BPF_ALU64) {
+ (BPF_CLASS(insn->code) == BPF_ALU64 &&
+ BPF_SRC(insn->code) != BPF_TO_LE)) {
verbose(env, "BPF_END uses reserved fields\n");
return -EINVAL;
}
@@ -12932,11 +13904,24 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0 || insn->off != 0) {
+ if (insn->imm != 0) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
+ if (BPF_CLASS(insn->code) == BPF_ALU) {
+ if (insn->off != 0 && insn->off != 8 && insn->off != 16) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ } else {
+ if (insn->off != 0 && insn->off != 8 && insn->off != 16 &&
+ insn->off != 32) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ }
+
/* check src operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
@@ -12960,18 +13945,42 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
!tnum_is_const(src_reg->var_off);
if (BPF_CLASS(insn->code) == BPF_ALU64) {
- /* case: R1 = R2
- * copy register state to dest reg
- */
- if (need_id)
- /* Assign src and dst registers the same ID
- * that will be used by find_equal_scalars()
- * to propagate min/max range.
+ if (insn->off == 0) {
+ /* case: R1 = R2
+ * copy register state to dest reg
*/
- src_reg->id = ++env->id_gen;
- copy_register_state(dst_reg, src_reg);
- dst_reg->live |= REG_LIVE_WRITTEN;
- dst_reg->subreg_def = DEF_NOT_SUBREG;
+ if (need_id)
+ /* Assign src and dst registers the same ID
+ * that will be used by find_equal_scalars()
+ * to propagate min/max range.
+ */
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
+ } else {
+ /* case: R1 = (s8, s16 s32)R2 */
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose(env,
+ "R%d sign-extension part of pointer\n",
+ insn->src_reg);
+ return -EACCES;
+ } else if (src_reg->type == SCALAR_VALUE) {
+ bool no_sext;
+
+ no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+ if (no_sext && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ if (!no_sext)
+ dst_reg->id = 0;
+ coerce_reg_to_size_sx(dst_reg, insn->off >> 3);
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
+ } else {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ }
+ }
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
@@ -12980,19 +13989,33 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
insn->src_reg);
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
- bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
-
- if (is_src_reg_u32 && need_id)
- src_reg->id = ++env->id_gen;
- copy_register_state(dst_reg, src_reg);
- /* Make sure ID is cleared if src_reg is not in u32 range otherwise
- * dst_reg min/max could be incorrectly
- * propagated into src_reg by find_equal_scalars()
- */
- if (!is_src_reg_u32)
- dst_reg->id = 0;
- dst_reg->live |= REG_LIVE_WRITTEN;
- dst_reg->subreg_def = env->insn_idx + 1;
+ if (insn->off == 0) {
+ bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
+
+ if (is_src_reg_u32 && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ /* Make sure ID is cleared if src_reg is not in u32
+ * range otherwise dst_reg min/max could be incorrectly
+ * propagated into src_reg by find_equal_scalars()
+ */
+ if (!is_src_reg_u32)
+ dst_reg->id = 0;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
+ } else {
+ /* case: W1 = (s8, s16)W2 */
+ bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+
+ if (no_sext && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ if (!no_sext)
+ dst_reg->id = 0;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
+ coerce_subreg_to_size_sx(dst_reg, insn->off >> 3);
+ }
} else {
mark_reg_unknown(env, regs,
insn->dst_reg);
@@ -13023,7 +14046,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else { /* all other ALU ops: and, sub, xor, add, ... */
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0 || insn->off != 0) {
+ if (insn->imm != 0 || insn->off > 1 ||
+ (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
@@ -13032,7 +14056,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (err)
return err;
} else {
- if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+ if (insn->src_reg != BPF_REG_0 || insn->off > 1 ||
+ (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
@@ -13160,12 +14185,16 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
return !!tnum_equals_const(subreg, val);
else if (val < reg->u32_min_value || val > reg->u32_max_value)
return 0;
+ else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
+ return 0;
break;
case BPF_JNE:
if (tnum_is_const(subreg))
return !tnum_equals_const(subreg, val);
else if (val < reg->u32_min_value || val > reg->u32_max_value)
return 1;
+ else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
+ return 1;
break;
case BPF_JSET:
if ((~subreg.mask & subreg.value) & val)
@@ -13237,12 +14266,16 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return !!tnum_equals_const(reg->var_off, val);
else if (val < reg->umin_value || val > reg->umax_value)
return 0;
+ else if (sval < reg->smin_value || sval > reg->smax_value)
+ return 0;
break;
case BPF_JNE:
if (tnum_is_const(reg->var_off))
return !tnum_equals_const(reg->var_off, val);
else if (val < reg->umin_value || val > reg->umax_value)
return 1;
+ else if (sval < reg->smin_value || sval > reg->smax_value)
+ return 1;
break;
case BPF_JSET:
if ((~reg->var_off.mask & reg->var_off.value) & val)
@@ -13817,6 +14850,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return -EINVAL;
}
+ /* check src2 operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ dst_reg = &regs[insn->dst_reg];
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0) {
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -13828,12 +14867,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
if (err)
return err;
- if (is_pointer_value(env, insn->src_reg)) {
+ src_reg = &regs[insn->src_reg];
+ if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) &&
+ is_pointer_value(env, insn->src_reg)) {
verbose(env, "R%d pointer comparison prohibited\n",
insn->src_reg);
return -EACCES;
}
- src_reg = &regs[insn->src_reg];
} else {
if (insn->src_reg != BPF_REG_0) {
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -13841,12 +14881,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
}
}
- /* check src2 operand */
- err = check_reg_arg(env, insn->dst_reg, SRC_OP);
- if (err)
- return err;
-
- dst_reg = &regs[insn->dst_reg];
is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
if (BPF_SRC(insn->code) == BPF_K) {
@@ -13903,6 +14937,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
!sanitize_speculative_path(env, insn, *insn_idx + 1,
*insn_idx))
return -EFAULT;
+ if (env->log.level & BPF_LOG_LEVEL)
+ print_insn_state(env, this_branch->frame[this_branch->curframe]);
*insn_idx += insn->off;
return 0;
} else if (pred == 0) {
@@ -13915,6 +14951,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
*insn_idx + insn->off + 1,
*insn_idx))
return -EFAULT;
+ if (env->log.level & BPF_LOG_LEVEL)
+ print_insn_state(env, this_branch->frame[this_branch->curframe]);
return 0;
}
@@ -14193,7 +15231,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
* gen_ld_abs() may terminate the program at runtime, leading to
* reference leak.
*/
- err = check_reference_leak(env);
+ err = check_reference_leak(env, false);
if (err) {
verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n");
return err;
@@ -14242,19 +15280,19 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return 0;
}
-static int check_return_code(struct bpf_verifier_env *env)
+static int check_return_code(struct bpf_verifier_env *env, int regno)
{
struct tnum enforce_attach_type_range = tnum_unknown;
const struct bpf_prog *prog = env->prog;
struct bpf_reg_state *reg;
- struct tnum range = tnum_range(0, 1);
+ struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0);
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
int err;
struct bpf_func_state *frame = env->cur_state->frame[0];
const bool is_subprog = frame->subprogno;
/* LSM and struct_ops func-ptr's return type could be "void" */
- if (!is_subprog) {
+ if (!is_subprog || frame->in_exception_callback_fn) {
switch (prog_type) {
case BPF_PROG_TYPE_LSM:
if (prog->expected_attach_type == BPF_LSM_CGROUP)
@@ -14276,36 +15314,36 @@ static int check_return_code(struct bpf_verifier_env *env)
* of bpf_exit, which means that program wrote
* something into it earlier
*/
- err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ err = check_reg_arg(env, regno, SRC_OP);
if (err)
return err;
- if (is_pointer_value(env, BPF_REG_0)) {
- verbose(env, "R0 leaks addr as return value\n");
+ if (is_pointer_value(env, regno)) {
+ verbose(env, "R%d leaks addr as return value\n", regno);
return -EACCES;
}
- reg = cur_regs(env) + BPF_REG_0;
+ reg = cur_regs(env) + regno;
if (frame->in_async_callback_fn) {
/* enforce return zero from async callbacks like timer */
if (reg->type != SCALAR_VALUE) {
- verbose(env, "In async callback the register R0 is not a known value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "In async callback the register R%d is not a known value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
- if (!tnum_in(tnum_const(0), reg->var_off)) {
- verbose_invalid_scalar(env, reg, &range, "async callback", "R0");
+ if (!tnum_in(const_0, reg->var_off)) {
+ verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0");
return -EINVAL;
}
return 0;
}
- if (is_subprog) {
+ if (is_subprog && !frame->in_exception_callback_fn) {
if (reg->type != SCALAR_VALUE) {
- verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "At subprogram exit the register R%d is not a scalar value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
return 0;
@@ -14315,10 +15353,13 @@ static int check_return_code(struct bpf_verifier_env *env)
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG ||
env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
- env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
+ env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME)
range = tnum_range(1, 1);
if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)
@@ -14387,8 +15428,8 @@ static int check_return_code(struct bpf_verifier_env *env)
}
if (reg->type != SCALAR_VALUE) {
- verbose(env, "At program exit the register R0 is not a known value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "At program exit the register R%d is not a known value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
@@ -14447,21 +15488,6 @@ enum {
BRANCH = 2,
};
-static u32 state_htab_size(struct bpf_verifier_env *env)
-{
- return env->prog->len;
-}
-
-static struct bpf_verifier_state_list **explored_state(
- struct bpf_verifier_env *env,
- int idx)
-{
- struct bpf_verifier_state *cur = env->cur_state;
- struct bpf_func_state *state = cur->frame[cur->curframe];
-
- return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)];
-}
-
static void mark_prune_point(struct bpf_verifier_env *env, int idx)
{
env->insn_aux_data[idx].prune_point = true;
@@ -14482,6 +15508,15 @@ static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx)
return env->insn_aux_data[insn_idx].force_checkpoint;
}
+static void mark_calls_callback(struct bpf_verifier_env *env, int idx)
+{
+ env->insn_aux_data[idx].calls_callback = true;
+}
+
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx)
+{
+ return env->insn_aux_data[insn_idx].calls_callback;
+}
enum {
DONE_EXPLORING = 0,
@@ -14493,8 +15528,7 @@ enum {
* w - next instruction
* e - edge
*/
-static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
- bool loop_ok)
+static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
{
int *insn_stack = env->cfg.insn_stack;
int *insn_state = env->cfg.insn_state;
@@ -14526,7 +15560,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
insn_stack[env->cfg.cur_stack++] = w;
return KEEP_EXPLORING;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
- if (loop_ok && env->bpf_capable)
+ if (env->bpf_capable)
return DONE_EXPLORING;
verbose_linfo(env, t, "%d: ", t);
verbose_linfo(env, w, "%d: ", w);
@@ -14546,24 +15580,20 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
struct bpf_verifier_env *env,
bool visit_callee)
{
- int ret;
+ int ret, insn_sz;
- ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
+ insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
+ ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
if (ret)
return ret;
- mark_prune_point(env, t + 1);
+ mark_prune_point(env, t + insn_sz);
/* when we exit from subprog, we need to record non-linear history */
- mark_jmp_point(env, t + 1);
+ mark_jmp_point(env, t + insn_sz);
if (visit_callee) {
mark_prune_point(env, t);
- ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env,
- /* It's ok to allow recursion from CFG point of
- * view. __check_func_call() will do the actual
- * check.
- */
- bpf_pseudo_func(insns + t));
+ ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
}
return ret;
}
@@ -14576,15 +15606,17 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
static int visit_insn(int t, struct bpf_verifier_env *env)
{
struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
- int ret;
+ int ret, off, insn_sz;
if (bpf_pseudo_func(insn))
return visit_func_call_insn(t, insns, env, true);
/* All non-branch instructions have a single fall-through edge. */
if (BPF_CLASS(insn->code) != BPF_JMP &&
- BPF_CLASS(insn->code) != BPF_JMP32)
- return push_insn(t, t + 1, FALLTHROUGH, env, false);
+ BPF_CLASS(insn->code) != BPF_JMP32) {
+ insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
+ return push_insn(t, t + insn_sz, FALLTHROUGH, env);
+ }
switch (BPF_OP(insn->code)) {
case BPF_EXIT:
@@ -14598,6 +15630,21 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
* async state will be pushed for further exploration.
*/
mark_prune_point(env, t);
+ /* For functions that invoke callbacks it is not known how many times
+ * callback would be called. Verifier models callback calling functions
+ * by repeatedly visiting callback bodies and returning to origin call
+ * instruction.
+ * In order to stop such iteration verifier needs to identify when a
+ * state identical some state from a previous iteration is reached.
+ * Check below forces creation of checkpoint before callback calling
+ * instruction to allow search for such identical states.
+ */
+ if (is_sync_callback_calling_insn(insn)) {
+ mark_calls_callback(env, t);
+ mark_force_checkpoint(env, t);
+ mark_prune_point(env, t);
+ mark_jmp_point(env, t);
+ }
if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
struct bpf_kfunc_call_arg_meta meta;
@@ -14624,14 +15671,18 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
if (BPF_SRC(insn->code) != BPF_K)
return -EINVAL;
+ if (BPF_CLASS(insn->code) == BPF_JMP)
+ off = insn->off;
+ else
+ off = insn->imm;
+
/* unconditional jump with single edge */
- ret = push_insn(t, t + insn->off + 1, FALLTHROUGH, env,
- true);
+ ret = push_insn(t, t + off + 1, FALLTHROUGH, env);
if (ret)
return ret;
- mark_prune_point(env, t + insn->off + 1);
- mark_jmp_point(env, t + insn->off + 1);
+ mark_prune_point(env, t + off + 1);
+ mark_jmp_point(env, t + off + 1);
return ret;
@@ -14639,11 +15690,11 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
/* conditional jump with two edges */
mark_prune_point(env, t);
- ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
+ ret = push_insn(t, t + 1, FALLTHROUGH, env);
if (ret)
return ret;
- return push_insn(t, t + insn->off + 1, BRANCH, env, true);
+ return push_insn(t, t + insn->off + 1, BRANCH, env);
}
}
@@ -14654,8 +15705,8 @@ static int check_cfg(struct bpf_verifier_env *env)
{
int insn_cnt = env->prog->len;
int *insn_stack, *insn_state;
- int ret = 0;
- int i;
+ int ex_insn_beg, i, ret = 0;
+ bool ex_done = false;
insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
@@ -14671,6 +15722,7 @@ static int check_cfg(struct bpf_verifier_env *env)
insn_stack[0] = 0; /* 0 is the first instruction */
env->cfg.cur_stack = 1;
+walk_cfg:
while (env->cfg.cur_stack > 0) {
int t = insn_stack[env->cfg.cur_stack - 1];
@@ -14697,12 +15749,32 @@ static int check_cfg(struct bpf_verifier_env *env)
goto err_free;
}
+ if (env->exception_callback_subprog && !ex_done) {
+ ex_insn_beg = env->subprog_info[env->exception_callback_subprog].start;
+
+ insn_state[ex_insn_beg] = DISCOVERED;
+ insn_stack[0] = ex_insn_beg;
+ env->cfg.cur_stack = 1;
+ ex_done = true;
+ goto walk_cfg;
+ }
+
for (i = 0; i < insn_cnt; i++) {
+ struct bpf_insn *insn = &env->prog->insnsi[i];
+
if (insn_state[i] != EXPLORED) {
verbose(env, "unreachable insn %d\n", i);
ret = -EINVAL;
goto err_free;
}
+ if (bpf_is_ldimm64(insn)) {
+ if (insn_state[i + 1] != 0) {
+ verbose(env, "jump into the middle of ldimm64 insn %d\n", i);
+ ret = -EINVAL;
+ goto err_free;
+ }
+ i++; /* skip second half of ldimm64 */
+ }
}
ret = 0; /* cfg looks good */
@@ -14734,20 +15806,18 @@ static int check_abnormal_return(struct bpf_verifier_env *env)
#define MIN_BPF_FUNCINFO_SIZE 8
#define MAX_FUNCINFO_REC_SIZE 252
-static int check_btf_func(struct bpf_verifier_env *env,
- const union bpf_attr *attr,
- bpfptr_t uattr)
+static int check_btf_func_early(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
{
- const struct btf_type *type, *func_proto, *ret_type;
- u32 i, nfuncs, urec_size, min_size;
u32 krec_size = sizeof(struct bpf_func_info);
+ const struct btf_type *type, *func_proto;
+ u32 i, nfuncs, urec_size, min_size;
struct bpf_func_info *krecord;
- struct bpf_func_info_aux *info_aux = NULL;
struct bpf_prog *prog;
const struct btf *btf;
- bpfptr_t urecord;
u32 prev_offset = 0;
- bool scalar_return;
+ bpfptr_t urecord;
int ret = -ENOMEM;
nfuncs = attr->func_info_cnt;
@@ -14757,11 +15827,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
return 0;
}
- if (nfuncs != env->subprog_cnt) {
- verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
- return -EINVAL;
- }
-
urec_size = attr->func_info_rec_size;
if (urec_size < MIN_BPF_FUNCINFO_SIZE ||
urec_size > MAX_FUNCINFO_REC_SIZE ||
@@ -14779,9 +15844,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
if (!krecord)
return -ENOMEM;
- info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
- if (!info_aux)
- goto err_free;
for (i = 0; i < nfuncs; i++) {
ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
@@ -14820,11 +15882,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
goto err_free;
}
- if (env->subprog_info[i].start != krecord[i].insn_off) {
- verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
- goto err_free;
- }
-
/* check type_id */
type = btf_type_by_id(btf, krecord[i].type_id);
if (!type || !btf_type_is_func(type)) {
@@ -14832,12 +15889,77 @@ static int check_btf_func(struct bpf_verifier_env *env,
krecord[i].type_id);
goto err_free;
}
- info_aux[i].linkage = BTF_INFO_VLEN(type->info);
func_proto = btf_type_by_id(btf, type->type);
if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
/* btf_func_check() already verified it during BTF load */
goto err_free;
+
+ prev_offset = krecord[i].insn_off;
+ bpfptr_add(&urecord, urec_size);
+ }
+
+ prog->aux->func_info = krecord;
+ prog->aux->func_info_cnt = nfuncs;
+ return 0;
+
+err_free:
+ kvfree(krecord);
+ return ret;
+}
+
+static int check_btf_func(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
+{
+ const struct btf_type *type, *func_proto, *ret_type;
+ u32 i, nfuncs, urec_size;
+ struct bpf_func_info *krecord;
+ struct bpf_func_info_aux *info_aux = NULL;
+ struct bpf_prog *prog;
+ const struct btf *btf;
+ bpfptr_t urecord;
+ bool scalar_return;
+ int ret = -ENOMEM;
+
+ nfuncs = attr->func_info_cnt;
+ if (!nfuncs) {
+ if (check_abnormal_return(env))
+ return -EINVAL;
+ return 0;
+ }
+ if (nfuncs != env->subprog_cnt) {
+ verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
+ return -EINVAL;
+ }
+
+ urec_size = attr->func_info_rec_size;
+
+ prog = env->prog;
+ btf = prog->aux->btf;
+
+ urecord = make_bpfptr(attr->func_info, uattr.is_kernel);
+
+ krecord = prog->aux->func_info;
+ info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
+ if (!info_aux)
+ return -ENOMEM;
+
+ for (i = 0; i < nfuncs; i++) {
+ /* check insn_off */
+ ret = -EINVAL;
+
+ if (env->subprog_info[i].start != krecord[i].insn_off) {
+ verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
+ goto err_free;
+ }
+
+ /* Already checked type_id */
+ type = btf_type_by_id(btf, krecord[i].type_id);
+ info_aux[i].linkage = BTF_INFO_VLEN(type->info);
+ /* Already checked func_proto */
+ func_proto = btf_type_by_id(btf, type->type);
+
ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
scalar_return =
btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type);
@@ -14850,17 +15972,13 @@ static int check_btf_func(struct bpf_verifier_env *env,
goto err_free;
}
- prev_offset = krecord[i].insn_off;
bpfptr_add(&urecord, urec_size);
}
- prog->aux->func_info = krecord;
- prog->aux->func_info_cnt = nfuncs;
prog->aux->func_info_aux = info_aux;
return 0;
err_free:
- kvfree(krecord);
kfree(info_aux);
return ret;
}
@@ -14873,7 +15991,8 @@ static void adjust_btf_func(struct bpf_verifier_env *env)
if (!aux->func_info)
return;
- for (i = 0; i < env->subprog_cnt; i++)
+ /* func_info is not available for hidden subprogs */
+ for (i = 0; i < env->subprog_cnt - env->hidden_subprog_cnt; i++)
aux->func_info[i].insn_off = env->subprog_info[i].start;
}
@@ -15077,9 +16196,9 @@ static int check_core_relo(struct bpf_verifier_env *env,
return err;
}
-static int check_btf_info(struct bpf_verifier_env *env,
- const union bpf_attr *attr,
- bpfptr_t uattr)
+static int check_btf_info_early(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
{
struct btf *btf;
int err;
@@ -15099,6 +16218,24 @@ static int check_btf_info(struct bpf_verifier_env *env,
}
env->prog->aux->btf = btf;
+ err = check_btf_func_early(env, attr, uattr);
+ if (err)
+ return err;
+ return 0;
+}
+
+static int check_btf_info(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
+{
+ int err;
+
+ if (!attr->func_info_cnt && !attr->line_info_cnt) {
+ if (check_abnormal_return(env))
+ return -EINVAL;
+ return 0;
+ }
+
err = check_btf_func(env, attr, uattr);
if (err)
return err;
@@ -15257,18 +16394,14 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn,
struct bpf_verifier_state *cur)
{
struct bpf_verifier_state_list *sl;
- int i;
sl = *explored_state(env, insn);
while (sl) {
if (sl->state.branches)
goto next;
if (sl->state.insn_idx != insn ||
- sl->state.curframe != cur->curframe)
+ !same_callsites(&sl->state, cur))
goto next;
- for (i = 0; i <= cur->curframe; i++)
- if (sl->state.frame[i]->callsite != cur->frame[i]->callsite)
- goto next;
clean_verifier_state(env, &sl->state);
next:
sl = sl->next;
@@ -15286,8 +16419,11 @@ static bool regs_exact(const struct bpf_reg_state *rold,
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
- struct bpf_reg_state *rcur, struct bpf_idmap *idmap)
+ struct bpf_reg_state *rcur, struct bpf_idmap *idmap, bool exact)
{
+ if (exact)
+ return regs_exact(rold, rcur, idmap);
+
if (!(rold->live & REG_LIVE_READ))
/* explored state didn't use this */
return true;
@@ -15404,7 +16540,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
}
static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
- struct bpf_func_state *cur, struct bpf_idmap *idmap)
+ struct bpf_func_state *cur, struct bpf_idmap *idmap, bool exact)
{
int i, spi;
@@ -15417,7 +16553,12 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
spi = i / BPF_REG_SIZE;
- if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) {
+ if (exact &&
+ old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+ cur->stack[spi].slot_type[i % BPF_REG_SIZE])
+ return false;
+
+ if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) && !exact) {
i += BPF_REG_SIZE - 1;
/* explored state didn't use this */
continue;
@@ -15467,7 +16608,7 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
* return false to continue verification of this path
*/
if (!regsafe(env, &old->stack[spi].spilled_ptr,
- &cur->stack[spi].spilled_ptr, idmap))
+ &cur->stack[spi].spilled_ptr, idmap, exact))
return false;
break;
case STACK_DYNPTR:
@@ -15549,16 +16690,16 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur,
* the current state will reach 'bpf_exit' instruction safely
*/
static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old,
- struct bpf_func_state *cur)
+ struct bpf_func_state *cur, bool exact)
{
int i;
for (i = 0; i < MAX_BPF_REG; i++)
if (!regsafe(env, &old->regs[i], &cur->regs[i],
- &env->idmap_scratch))
+ &env->idmap_scratch, exact))
return false;
- if (!stacksafe(env, old, cur, &env->idmap_scratch))
+ if (!stacksafe(env, old, cur, &env->idmap_scratch, exact))
return false;
if (!refsafe(old, cur, &env->idmap_scratch))
@@ -15567,17 +16708,23 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
return true;
}
+static void reset_idmap_scratch(struct bpf_verifier_env *env)
+{
+ env->idmap_scratch.tmp_id_gen = env->id_gen;
+ memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map));
+}
+
static bool states_equal(struct bpf_verifier_env *env,
struct bpf_verifier_state *old,
- struct bpf_verifier_state *cur)
+ struct bpf_verifier_state *cur,
+ bool exact)
{
int i;
if (old->curframe != cur->curframe)
return false;
- env->idmap_scratch.tmp_id_gen = env->id_gen;
- memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map));
+ reset_idmap_scratch(env);
/* Verification state from speculative execution simulation
* must never prune a non-speculative execution one.
@@ -15607,7 +16754,7 @@ static bool states_equal(struct bpf_verifier_env *env,
for (i = 0; i <= old->curframe; i++) {
if (old->frame[i]->callsite != cur->frame[i]->callsite)
return false;
- if (!func_states_equal(env, old->frame[i], cur->frame[i]))
+ if (!func_states_equal(env, old->frame[i], cur->frame[i], exact))
return false;
}
return true;
@@ -15861,10 +17008,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
struct bpf_verifier_state_list *sl, **pprev;
- struct bpf_verifier_state *cur = env->cur_state, *new;
- int i, j, err, states_cnt = 0;
+ struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry;
+ int i, j, n, err, states_cnt = 0;
bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx);
bool add_new_state = force_new_state;
+ bool force_exact;
/* bpf progs typically have pruning point every 4 instructions
* http://vger.kernel.org/bpfconf2019.html#session-1
@@ -15917,9 +17065,33 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
* It's safe to assume that iterator loop will finish, taking into
* account iter_next() contract of eventually returning
* sticky NULL result.
+ *
+ * Note, that states have to be compared exactly in this case because
+ * read and precision marks might not be finalized inside the loop.
+ * E.g. as in the program below:
+ *
+ * 1. r7 = -16
+ * 2. r6 = bpf_get_prandom_u32()
+ * 3. while (bpf_iter_num_next(&fp[-8])) {
+ * 4. if (r6 != 42) {
+ * 5. r7 = -32
+ * 6. r6 = bpf_get_prandom_u32()
+ * 7. continue
+ * 8. }
+ * 9. r0 = r10
+ * 10. r0 += r7
+ * 11. r8 = *(u64 *)(r0 + 0)
+ * 12. r6 = bpf_get_prandom_u32()
+ * 13. }
+ *
+ * Here verifier would first visit path 1-3, create a checkpoint at 3
+ * with r7=-16, continue to 4-7,3. Existing checkpoint at 3 does
+ * not have read or precision mark for r7 yet, thus inexact states
+ * comparison would discard current state with r7=-32
+ * => unsafe memory access at 11 would not be caught.
*/
if (is_iter_next_insn(env, insn_idx)) {
- if (states_equal(env, &sl->state, cur)) {
+ if (states_equal(env, &sl->state, cur, true)) {
struct bpf_func_state *cur_frame;
struct bpf_reg_state *iter_state, *iter_reg;
int spi;
@@ -15935,17 +17107,29 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
*/
spi = __get_spi(iter_reg->off + iter_reg->var_off.value);
iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr;
- if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE)
+ if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) {
+ update_loop_entry(cur, &sl->state);
goto hit;
+ }
}
goto skip_inf_loop_check;
}
+ if (calls_callback(env, insn_idx)) {
+ if (states_equal(env, &sl->state, cur, true))
+ goto hit;
+ goto skip_inf_loop_check;
+ }
/* attempt to detect infinite loop to avoid unnecessary doomed work */
if (states_maybe_looping(&sl->state, cur) &&
- states_equal(env, &sl->state, cur) &&
- !iter_active_depths_differ(&sl->state, cur)) {
+ states_equal(env, &sl->state, cur, false) &&
+ !iter_active_depths_differ(&sl->state, cur) &&
+ sl->state.callback_unroll_depth == cur->callback_unroll_depth) {
verbose_linfo(env, insn_idx, "; ");
verbose(env, "infinite loop detected at insn %d\n", insn_idx);
+ verbose(env, "cur state:");
+ print_verifier_state(env, cur->frame[cur->curframe], true);
+ verbose(env, "old state:");
+ print_verifier_state(env, sl->state.frame[cur->curframe], true);
return -EINVAL;
}
/* if the verifier is processing a loop, avoid adding new state
@@ -15967,7 +17151,36 @@ skip_inf_loop_check:
add_new_state = false;
goto miss;
}
- if (states_equal(env, &sl->state, cur)) {
+ /* If sl->state is a part of a loop and this loop's entry is a part of
+ * current verification path then states have to be compared exactly.
+ * 'force_exact' is needed to catch the following case:
+ *
+ * initial Here state 'succ' was processed first,
+ * | it was eventually tracked to produce a
+ * V state identical to 'hdr'.
+ * .---------> hdr All branches from 'succ' had been explored
+ * | | and thus 'succ' has its .branches == 0.
+ * | V
+ * | .------... Suppose states 'cur' and 'succ' correspond
+ * | | | to the same instruction + callsites.
+ * | V V In such case it is necessary to check
+ * | ... ... if 'succ' and 'cur' are states_equal().
+ * | | | If 'succ' and 'cur' are a part of the
+ * | V V same loop exact flag has to be set.
+ * | succ <- cur To check if that is the case, verify
+ * | | if loop entry of 'succ' is in current
+ * | V DFS path.
+ * | ...
+ * | |
+ * '----'
+ *
+ * Additional details are in the comment before get_loop_entry().
+ */
+ loop_entry = get_loop_entry(&sl->state);
+ force_exact = loop_entry && loop_entry->branches > 0;
+ if (states_equal(env, &sl->state, cur, force_exact)) {
+ if (force_exact)
+ update_loop_entry(cur, loop_entry);
hit:
sl->hit_cnt++;
/* reached equivalent register/stack state,
@@ -16006,13 +17219,18 @@ miss:
* to keep checking from state equivalence point of view.
* Higher numbers increase max_states_per_insn and verification time,
* but do not meaningfully decrease insn_processed.
+ * 'n' controls how many times state could miss before eviction.
+ * Use bigger 'n' for checkpoints because evicting checkpoint states
+ * too early would hinder iterator convergence.
*/
- if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
+ n = is_force_checkpoint(env, insn_idx) && sl->state.branches > 0 ? 64 : 3;
+ if (sl->miss_cnt > sl->hit_cnt * n + n) {
/* the state is unlikely to be useful. Remove it to
* speed up verification
*/
*pprev = sl->next;
- if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) {
+ if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE &&
+ !sl->state.used_as_loop_entry) {
u32 br = sl->state.branches;
WARN_ONCE(br,
@@ -16081,6 +17299,7 @@ next:
cur->parent = new;
cur->first_insn_idx = insn_idx;
+ cur->dfs_depth = new->dfs_depth + 1;
clear_jmp_history(cur);
new_sl->next = *explored_state(env, insn_idx);
*explored_state(env, insn_idx) = new_sl;
@@ -16178,7 +17397,7 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
* Have to support a use case when one path through
* the program yields TRUSTED pointer while another
* is UNTRUSTED. Fallback to UNTRUSTED to generate
- * BPF_PROBE_MEM.
+ * BPF_PROBE_MEM/BPF_PROBE_MEMSX.
*/
*prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
} else {
@@ -16201,6 +17420,7 @@ static int do_check(struct bpf_verifier_env *env)
int prev_insn_idx = -1;
for (;;) {
+ bool exception_exit = false;
struct bpf_insn *insn;
u8 class;
int err;
@@ -16319,7 +17539,8 @@ static int do_check(struct bpf_verifier_env *env)
*/
err = check_mem_access(env, env->insn_idx, insn->src_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_READ, insn->dst_reg, false);
+ BPF_READ, insn->dst_reg, false,
+ BPF_MODE(insn->code) == BPF_MEMSX);
if (err)
return err;
@@ -16356,7 +17577,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, insn->src_reg, false);
+ BPF_WRITE, insn->src_reg, false, false);
if (err)
return err;
@@ -16381,7 +17602,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, -1, false);
+ BPF_WRITE, -1, false, false);
if (err)
return err;
@@ -16414,27 +17635,35 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
}
- if (insn->src_reg == BPF_PSEUDO_CALL)
+ if (insn->src_reg == BPF_PSEUDO_CALL) {
err = check_func_call(env, insn, &env->insn_idx);
- else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
+ } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
err = check_kfunc_call(env, insn, &env->insn_idx);
- else
+ if (!err && is_bpf_throw_kfunc(insn)) {
+ exception_exit = true;
+ goto process_bpf_exit_full;
+ }
+ } else {
err = check_helper_call(env, insn, &env->insn_idx);
+ }
if (err)
return err;
mark_reg_scratched(env, BPF_REG_0);
} else if (opcode == BPF_JA) {
if (BPF_SRC(insn->code) != BPF_K ||
- insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0 ||
- class == BPF_JMP32) {
+ (class == BPF_JMP && insn->imm != 0) ||
+ (class == BPF_JMP32 && insn->off != 0)) {
verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
- env->insn_idx += insn->off + 1;
+ if (class == BPF_JMP)
+ env->insn_idx += insn->off + 1;
+ else
+ env->insn_idx += insn->imm + 1;
continue;
} else if (opcode == BPF_EXIT) {
@@ -16446,14 +17675,15 @@ static int do_check(struct bpf_verifier_env *env)
verbose(env, "BPF_EXIT uses reserved fields\n");
return -EINVAL;
}
-
+process_bpf_exit_full:
if (env->cur_state->active_lock.ptr &&
!in_rbtree_lock_required_cb(env)) {
verbose(env, "bpf_spin_unlock is missing\n");
return -EINVAL;
}
- if (env->cur_state->active_rcu_lock) {
+ if (env->cur_state->active_rcu_lock &&
+ !in_rbtree_lock_required_cb(env)) {
verbose(env, "bpf_rcu_read_unlock is missing\n");
return -EINVAL;
}
@@ -16464,10 +17694,23 @@ static int do_check(struct bpf_verifier_env *env)
* function, for which reference_state must
* match caller reference state when it exits.
*/
- err = check_reference_leak(env);
+ err = check_reference_leak(env, exception_exit);
if (err)
return err;
+ /* The side effect of the prepare_func_exit
+ * which is being skipped is that it frees
+ * bpf_func_state. Typically, process_bpf_exit
+ * will only be hit with outermost exit.
+ * copy_verifier_state in pop_stack will handle
+ * freeing of any extra bpf_func_state left over
+ * from not processing all nested function
+ * exits. We also skip return code checks as
+ * they are not needed for exceptional exits.
+ */
+ if (exception_exit)
+ goto process_bpf_exit;
+
if (state->curframe) {
/* exit from nested function */
err = prepare_func_exit(env, &env->insn_idx);
@@ -16477,7 +17720,7 @@ static int do_check(struct bpf_verifier_env *env)
continue;
}
- err = check_return_code(env);
+ err = check_return_code(env, BPF_REG_0);
if (err)
return err;
process_bpf_exit:
@@ -16733,11 +17976,6 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
return -EINVAL;
}
-
- if (prog->aux->sleepable) {
- verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n");
- return -EINVAL;
- }
}
if (btf_record_has_field(map->record, BPF_TIMER)) {
@@ -16809,7 +18047,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
- (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
+ ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) ||
+ insn->imm != 0)) {
verbose(env, "BPF_LDX uses reserved fields\n");
return -EINVAL;
}
@@ -17280,13 +18519,13 @@ static bool insn_is_cond_jump(u8 code)
{
u8 op;
+ op = BPF_OP(code);
if (BPF_CLASS(code) == BPF_JMP32)
- return true;
+ return op != BPF_JA;
if (BPF_CLASS(code) != BPF_JMP)
return false;
- op = BPF_OP(code);
return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
}
@@ -17503,11 +18742,15 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
+ u8 mode;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) {
type = BPF_READ;
} else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
@@ -17566,8 +18809,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
*/
case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
if (type == BPF_READ) {
- insn->code = BPF_LDX | BPF_PROBE_MEM |
- BPF_SIZE((insn)->code);
+ if (BPF_MODE(insn->code) == BPF_MEM)
+ insn->code = BPF_LDX | BPF_PROBE_MEM |
+ BPF_SIZE((insn)->code);
+ else
+ insn->code = BPF_LDX | BPF_PROBE_MEMSX |
+ BPF_SIZE((insn)->code);
env->prog->aux->num_exentries++;
}
continue;
@@ -17577,6 +18824,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
size = BPF_LDST_BYTES(insn);
+ mode = BPF_MODE(insn->code);
/* If the read access is a narrower load of the field,
* convert to a 4/8-byte load, to minimum program type specific
@@ -17636,6 +18884,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
(1ULL << size * 8) - 1);
}
}
+ if (mode == BPF_MEMSX)
+ insn_buf[cnt++] = BPF_RAW_INSN(BPF_ALU64 | BPF_MOV | BPF_X,
+ insn->dst_reg, insn->dst_reg,
+ size * 8, 0);
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
@@ -17755,11 +19007,15 @@ static int jit_subprogs(struct bpf_verifier_env *env)
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
- BPF_MODE(insn->code) == BPF_PROBE_MEM)
+ (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEMSX))
num_exentries++;
}
func[i]->aux->num_exentries = num_exentries;
func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
+ func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb;
+ if (!i)
+ func[i]->aux->exception_boundary = env->seen_exception;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
err = -ENOTSUPP;
@@ -17799,7 +19055,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
* the call instruction, as an index for this list
*/
func[i]->aux->func = func;
- func[i]->aux->func_cnt = env->subprog_cnt;
+ func[i]->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt;
+ func[i]->aux->real_func_cnt = env->subprog_cnt;
}
for (i = 0; i < env->subprog_cnt; i++) {
old_bpf_func = func[i]->bpf_func;
@@ -17845,7 +19102,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
prog->aux->extable = func[0]->aux->extable;
prog->aux->num_exentries = func[0]->aux->num_exentries;
prog->aux->func = func;
- prog->aux->func_cnt = env->subprog_cnt;
+ prog->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt;
+ prog->aux->real_func_cnt = env->subprog_cnt;
+ prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func;
+ prog->aux->exception_boundary = func[0]->aux->exception_boundary;
bpf_prog_jit_attempt_done(prog);
return 0;
out_free:
@@ -18012,21 +19272,42 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
insn->imm = BPF_CALL_IMM(desc->addr);
if (insn->off)
return 0;
- if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
+ if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl] ||
+ desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size;
+ if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && kptr_struct_meta) {
+ verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size);
insn_buf[1] = addr[0];
insn_buf[2] = addr[1];
insn_buf[3] = *insn;
*cnt = 4;
} else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl] ||
+ desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
+ if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] && kptr_struct_meta) {
+ verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
+ if (desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] &&
+ !kptr_struct_meta) {
+ verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
insn_buf[0] = addr[0];
insn_buf[1] = addr[1];
insn_buf[2] = *insn;
@@ -18034,6 +19315,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
} else if (desc->func_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_list_push_front_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+ struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
int struct_meta_reg = BPF_REG_3;
int node_offset_reg = BPF_REG_4;
@@ -18043,6 +19325,12 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
node_offset_reg = BPF_REG_5;
}
+ if (!kptr_struct_meta) {
+ verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
__fixup_collection_insert_kfunc(&env->insn_aux_data[insn_idx], struct_meta_reg,
node_offset_reg, insn, insn_buf, cnt);
} else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] ||
@@ -18053,6 +19341,33 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return 0;
}
+/* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */
+static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len)
+{
+ struct bpf_subprog_info *info = env->subprog_info;
+ int cnt = env->subprog_cnt;
+ struct bpf_prog *prog;
+
+ /* We only reserve one slot for hidden subprogs in subprog_info. */
+ if (env->hidden_subprog_cnt) {
+ verbose(env, "verifier internal error: only one hidden subprog supported\n");
+ return -EFAULT;
+ }
+ /* We're not patching any existing instruction, just appending the new
+ * ones for the hidden subprog. Hence all of the adjustment operations
+ * in bpf_patch_insn_data are no-ops.
+ */
+ prog = bpf_patch_insn_data(env, env->prog->len - 1, patch, len);
+ if (!prog)
+ return -ENOMEM;
+ env->prog = prog;
+ info[cnt + 1].start = info[cnt].start;
+ info[cnt].start = prog->len - len + 1;
+ env->subprog_cnt++;
+ env->hidden_subprog_cnt++;
+ return 0;
+}
+
/* Do various post-verification rewrites in a single program pass.
* These rewrites simplify JIT and interpreter implementations.
*/
@@ -18071,6 +19386,26 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
struct bpf_map *map_ptr;
int i, ret, cnt, delta = 0;
+ if (env->seen_exception && !env->exception_callback_subprog) {
+ struct bpf_insn patch[] = {
+ env->prog->insnsi[insn_cnt - 1],
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ };
+
+ ret = add_hidden_subprog(env, patch, ARRAY_SIZE(patch));
+ if (ret < 0)
+ return ret;
+ prog = env->prog;
+ insn = prog->insnsi;
+
+ env->exception_callback_subprog = env->subprog_cnt - 1;
+ /* Don't update insn_cnt, as add_hidden_subprog always appends insns */
+ env->subprog_info[env->exception_callback_subprog].is_cb = true;
+ env->subprog_info[env->exception_callback_subprog].is_async_cb = true;
+ env->subprog_info[env->exception_callback_subprog].is_exception_cb = true;
+ }
+
for (i = 0; i < insn_cnt; i++, insn++) {
/* Make divide-by-zero exceptions impossible. */
if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
@@ -18340,6 +19675,25 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
goto patch_call_imm;
}
+ /* bpf_per_cpu_ptr() and bpf_this_cpu_ptr() */
+ if (env->insn_aux_data[i + delta].call_with_percpu_alloc_ptr) {
+ /* patch with 'r1 = *(u64 *)(r1 + 0)' since for percpu data,
+ * bpf_mem_alloc() returns a ptr to the percpu data ptr.
+ */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+ insn_buf[1] = *insn;
+ cnt = 2;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ goto patch_call_imm;
+ }
+
/* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
* and other inlining handlers are currently limited to 64 bit
* only.
@@ -18749,7 +20103,7 @@ static void free_states(struct bpf_verifier_env *env)
}
}
-static int do_check_common(struct bpf_verifier_env *env, int subprog)
+static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
struct bpf_verifier_state *state;
@@ -18780,7 +20134,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
regs = state->frame[state->curframe]->regs;
if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
- ret = btf_prepare_func_args(env, subprog, regs);
+ ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb);
if (ret)
goto out;
for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
@@ -18796,6 +20150,12 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
regs[i].id = ++env->id_gen;
}
}
+ if (is_ex_cb) {
+ state->frame[0]->in_exception_callback_fn = true;
+ env->subprog_info[subprog].is_cb = true;
+ env->subprog_info[subprog].is_async_cb = true;
+ env->subprog_info[subprog].is_exception_cb = true;
+ }
} else {
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
@@ -18860,7 +20220,7 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
continue;
env->insn_idx = env->subprog_info[i].start;
WARN_ON_ONCE(env->insn_idx == 0);
- ret = do_check_common(env, i);
+ ret = do_check_common(env, i, env->exception_callback_subprog == i);
if (ret) {
return ret;
} else if (env->log.level & BPF_LOG_LEVEL) {
@@ -18877,7 +20237,7 @@ static int do_check_main(struct bpf_verifier_env *env)
int ret;
env->insn_idx = 0;
- ret = do_check_common(env, 0);
+ ret = do_check_common(env, 0, false);
if (!ret)
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return ret;
@@ -19046,6 +20406,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
bpf_log(log, "Subprog %s doesn't exist\n", tname);
return -EINVAL;
}
+ if (aux->func && aux->func[subprog]->aux->exception_cb) {
+ bpf_log(log,
+ "%s programs cannot attach to exception callback\n",
+ prog_extension ? "Extension" : "FENTRY/FEXIT");
+ return -EINVAL;
+ }
conservative = aux->func_info_aux[subprog].unreliable;
if (prog_extension) {
if (conservative) {
@@ -19375,6 +20741,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
if (!tr)
return -ENOMEM;
+ if (tgt_prog && tgt_prog->aux->tail_call_reachable)
+ tr->flags = BPF_TRAMP_F_TAIL_CALL_CTX;
+
prog->aux->dst_trampoline = tr;
return 0;
}
@@ -19470,6 +20839,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (!env->explored_states)
goto skip_full_check;
+ ret = check_btf_info_early(env, attr, uattr);
+ if (ret < 0)
+ goto skip_full_check;
+
ret = add_subprog_and_kfunc(env);
if (ret < 0)
goto skip_full_check;
diff --git a/kernel/capability.c b/kernel/capability.c
index 1a2795102ae4..dac4df77e376 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -112,7 +112,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
int ret;
if (pid && (pid != task_pid_vnr(current))) {
- struct task_struct *target;
+ const struct task_struct *target;
rcu_read_lock();
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 83044312bc41..76db6c67e39a 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -360,10 +360,9 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
}
css_task_iter_end(&it);
length = n;
- /* now sort & (if procs) strip out duplicates */
+ /* now sort & strip out duplicates (tgids or recycled thread PIDs) */
sort(array, length, sizeof(pid_t), cmppid, NULL);
- if (type == CGROUP_FILE_PROCS)
- length = pidlist_uniq(array, length);
+ length = pidlist_uniq(array, length);
l = cgroup_pidlist_find_create(cgrp, type);
if (!l) {
@@ -431,7 +430,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
if (l->list[mid] == pid) {
index = mid;
break;
- } else if (l->list[mid] <= pid)
+ } else if (l->list[mid] < pid)
index = mid + 1;
else
end = mid;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index f55a40db065f..4b9ff41ca603 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -207,6 +207,8 @@ static u16 have_exit_callback __read_mostly;
static u16 have_release_callback __read_mostly;
static u16 have_canfork_callback __read_mostly;
+static bool have_favordynmods __ro_after_init = IS_ENABLED(CONFIG_CGROUP_FAVOR_DYNMODS);
+
/* cgroup namespace for init task */
struct cgroup_namespace init_cgroup_ns = {
.ns.count = REFCOUNT_INIT(2),
@@ -493,28 +495,6 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
}
/**
- * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem
- * @cgrp: the cgroup of interest
- * @ss: the subsystem of interest
- *
- * Find and get @cgrp's css associated with @ss. If the css doesn't exist
- * or is offline, %NULL is returned.
- */
-static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
- struct cgroup_subsys *ss)
-{
- struct cgroup_subsys_state *css;
-
- rcu_read_lock();
- css = cgroup_css(cgrp, ss);
- if (css && !css_tryget_online(css))
- css = NULL;
- rcu_read_unlock();
-
- return css;
-}
-
-/**
* cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss
* @cgrp: the cgroup of interest
* @ss: the subsystem of interest (%NULL returns @cgrp->self)
@@ -679,7 +659,7 @@ EXPORT_SYMBOL_GPL(of_css);
* @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
* @cgrp: the target cgroup to iterate css's of
*
- * Should be called under cgroup_[tree_]mutex.
+ * Should be called under cgroup_mutex.
*/
#define for_each_css(css, ssid, cgrp) \
for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
@@ -929,7 +909,7 @@ static void css_set_move_task(struct task_struct *task,
#define CSS_SET_HASH_BITS 7
static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS);
-static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
+static unsigned long css_set_hash(struct cgroup_subsys_state **css)
{
unsigned long key = 0UL;
struct cgroup_subsys *ss;
@@ -1070,7 +1050,7 @@ static bool compare_css_sets(struct css_set *cset,
*/
static struct css_set *find_existing_css_set(struct css_set *old_cset,
struct cgroup *cgrp,
- struct cgroup_subsys_state *template[])
+ struct cgroup_subsys_state **template)
{
struct cgroup_root *root = cgrp->root;
struct cgroup_subsys *ss;
@@ -1372,7 +1352,9 @@ static void cgroup_destroy_root(struct cgroup_root *root)
cgroup_root_count--;
}
- cgroup_favor_dynmods(root, false);
+ if (!have_favordynmods)
+ cgroup_favor_dynmods(root, false);
+
cgroup_exit_root_id(root);
cgroup_unlock();
@@ -1736,25 +1718,27 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
struct cftype *cfts, *failed_cfts;
int ret;
- if ((css->flags & CSS_VISIBLE) || !cgrp->kn)
+ if (css->flags & CSS_VISIBLE)
return 0;
if (!css->ss) {
if (cgroup_on_dfl(cgrp)) {
- ret = cgroup_addrm_files(&cgrp->self, cgrp,
+ ret = cgroup_addrm_files(css, cgrp,
cgroup_base_files, true);
if (ret < 0)
return ret;
if (cgroup_psi_enabled()) {
- ret = cgroup_addrm_files(&cgrp->self, cgrp,
+ ret = cgroup_addrm_files(css, cgrp,
cgroup_psi_files, true);
if (ret < 0)
return ret;
}
} else {
- cgroup_addrm_files(css, cgrp,
- cgroup1_base_files, true);
+ ret = cgroup_addrm_files(css, cgrp,
+ cgroup1_base_files, true);
+ if (ret < 0)
+ return ret;
}
} else {
list_for_each_entry(cfts, &css->ss->cfts, node) {
@@ -1924,6 +1908,7 @@ enum cgroup2_param {
Opt_favordynmods,
Opt_memory_localevents,
Opt_memory_recursiveprot,
+ Opt_memory_hugetlb_accounting,
nr__cgroup2_params
};
@@ -1932,6 +1917,7 @@ static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
fsparam_flag("favordynmods", Opt_favordynmods),
fsparam_flag("memory_localevents", Opt_memory_localevents),
fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot),
+ fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting),
{}
};
@@ -1958,6 +1944,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
case Opt_memory_recursiveprot:
ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
return 0;
+ case Opt_memory_hugetlb_accounting:
+ ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+ return 0;
}
return -EINVAL;
}
@@ -1982,6 +1971,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
else
cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT;
+
+ if (root_flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)
+ cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+ else
+ cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
}
}
@@ -1995,6 +1989,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
seq_puts(seq, ",memory_localevents");
if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
seq_puts(seq, ",memory_recursiveprot");
+ if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)
+ seq_puts(seq, ",memory_hugetlb_accounting");
return 0;
}
@@ -2265,9 +2261,9 @@ static int cgroup_init_fs_context(struct fs_context *fc)
fc->user_ns = get_user_ns(ctx->ns->user_ns);
fc->global = true;
-#ifdef CONFIG_CGROUP_FAVOR_DYNMODS
- ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
-#endif
+ if (have_favordynmods)
+ ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
+
return 0;
}
@@ -2499,7 +2495,7 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
/*
* This function may be called both before and
- * after cgroup_taskset_migrate(). The two cases
+ * after cgroup_migrate_execute(). The two cases
* can be distinguished by looking at whether @cset
* has its ->mg_dst_cset set.
*/
@@ -3654,9 +3650,32 @@ static int cgroup_stat_show(struct seq_file *seq, void *v)
return 0;
}
-static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq,
- struct cgroup *cgrp, int ssid)
+#ifdef CONFIG_CGROUP_SCHED
+/**
+ * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest
+ *
+ * Find and get @cgrp's css associated with @ss. If the css doesn't exist
+ * or is offline, %NULL is returned.
+ */
+static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
+ struct cgroup_subsys *ss)
+{
+ struct cgroup_subsys_state *css;
+
+ rcu_read_lock();
+ css = cgroup_css(cgrp, ss);
+ if (css && !css_tryget_online(css))
+ css = NULL;
+ rcu_read_unlock();
+
+ return css;
+}
+
+static int cgroup_extra_stat_show(struct seq_file *seq, int ssid)
{
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
struct cgroup_subsys *ss = cgroup_subsys[ssid];
struct cgroup_subsys_state *css;
int ret;
@@ -3673,14 +3692,44 @@ static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq,
return ret;
}
+static int cgroup_local_stat_show(struct seq_file *seq,
+ struct cgroup *cgrp, int ssid)
+{
+ struct cgroup_subsys *ss = cgroup_subsys[ssid];
+ struct cgroup_subsys_state *css;
+ int ret;
+
+ if (!ss->css_local_stat_show)
+ return 0;
+
+ css = cgroup_tryget_css(cgrp, ss);
+ if (!css)
+ return 0;
+
+ ret = ss->css_local_stat_show(seq, css);
+ css_put(css);
+ return ret;
+}
+#endif
+
static int cpu_stat_show(struct seq_file *seq, void *v)
{
- struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup;
int ret = 0;
cgroup_base_stat_cputime_show(seq);
#ifdef CONFIG_CGROUP_SCHED
- ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id);
+ ret = cgroup_extra_stat_show(seq, cpu_cgrp_id);
+#endif
+ return ret;
+}
+
+static int cpu_local_stat_show(struct seq_file *seq, void *v)
+{
+ struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup;
+ int ret = 0;
+
+#ifdef CONFIG_CGROUP_SCHED
+ ret = cgroup_local_stat_show(seq, cgrp, cpu_cgrp_id);
#endif
return ret;
}
@@ -3836,14 +3885,6 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
}
-static int cgroup_pressure_open(struct kernfs_open_file *of)
-{
- if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
- return -EPERM;
-
- return 0;
-}
-
static void cgroup_pressure_release(struct kernfs_open_file *of)
{
struct cgroup_file_ctx *ctx = of->priv;
@@ -4320,14 +4361,13 @@ static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
return ret;
}
-static int cgroup_rm_cftypes_locked(struct cftype *cfts)
+static void cgroup_rm_cftypes_locked(struct cftype *cfts)
{
lockdep_assert_held(&cgroup_mutex);
list_del(&cfts->node);
cgroup_apply_cftypes(cfts, false);
cgroup_exit_cftypes(cfts);
- return 0;
}
/**
@@ -4343,8 +4383,6 @@ static int cgroup_rm_cftypes_locked(struct cftype *cfts)
*/
int cgroup_rm_cftypes(struct cftype *cfts)
{
- int ret;
-
if (!cfts || cfts[0].name[0] == '\0')
return 0;
@@ -4352,9 +4390,9 @@ int cgroup_rm_cftypes(struct cftype *cfts)
return -ENOENT;
cgroup_lock();
- ret = cgroup_rm_cftypes_locked(cfts);
+ cgroup_rm_cftypes_locked(cfts);
cgroup_unlock();
- return ret;
+ return 0;
}
/**
@@ -4889,9 +4927,11 @@ repeat:
void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
struct css_task_iter *it)
{
+ unsigned long irqflags;
+
memset(it, 0, sizeof(*it));
- spin_lock_irq(&css_set_lock);
+ spin_lock_irqsave(&css_set_lock, irqflags);
it->ss = css->ss;
it->flags = flags;
@@ -4905,7 +4945,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
css_task_iter_advance(it);
- spin_unlock_irq(&css_set_lock);
+ spin_unlock_irqrestore(&css_set_lock, irqflags);
}
/**
@@ -4918,12 +4958,14 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
*/
struct task_struct *css_task_iter_next(struct css_task_iter *it)
{
+ unsigned long irqflags;
+
if (it->cur_task) {
put_task_struct(it->cur_task);
it->cur_task = NULL;
}
- spin_lock_irq(&css_set_lock);
+ spin_lock_irqsave(&css_set_lock, irqflags);
/* @it may be half-advanced by skips, finish advancing */
if (it->flags & CSS_TASK_ITER_SKIPPED)
@@ -4936,7 +4978,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
css_task_iter_advance(it);
}
- spin_unlock_irq(&css_set_lock);
+ spin_unlock_irqrestore(&css_set_lock, irqflags);
return it->cur_task;
}
@@ -4949,11 +4991,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
*/
void css_task_iter_end(struct css_task_iter *it)
{
+ unsigned long irqflags;
+
if (it->cur_cset) {
- spin_lock_irq(&css_set_lock);
+ spin_lock_irqsave(&css_set_lock, irqflags);
list_del(&it->iters_node);
put_css_set_locked(it->cur_cset);
- spin_unlock_irq(&css_set_lock);
+ spin_unlock_irqrestore(&css_set_lock, irqflags);
}
if (it->cur_dcset)
@@ -5235,6 +5279,10 @@ static struct cftype cgroup_base_files[] = {
.name = "cpu.stat",
.seq_show = cpu_stat_show,
},
+ {
+ .name = "cpu.stat.local",
+ .seq_show = cpu_local_stat_show,
+ },
{ } /* terminate */
};
@@ -5243,7 +5291,6 @@ static struct cftype cgroup_psi_files[] = {
{
.name = "io.pressure",
.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
- .open = cgroup_pressure_open,
.seq_show = cgroup_io_pressure_show,
.write = cgroup_io_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5252,7 +5299,6 @@ static struct cftype cgroup_psi_files[] = {
{
.name = "memory.pressure",
.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
- .open = cgroup_pressure_open,
.seq_show = cgroup_memory_pressure_show,
.write = cgroup_memory_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5261,7 +5307,6 @@ static struct cftype cgroup_psi_files[] = {
{
.name = "cpu.pressure",
.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
- .open = cgroup_pressure_open,
.seq_show = cgroup_cpu_pressure_show,
.write = cgroup_cpu_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5271,7 +5316,6 @@ static struct cftype cgroup_psi_files[] = {
{
.name = "irq.pressure",
.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
- .open = cgroup_pressure_open,
.seq_show = cgroup_irq_pressure_show,
.write = cgroup_irq_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5303,7 +5347,7 @@ static struct cftype cgroup_psi_files[] = {
* RCU callback.
*
* 4. After the grace period, the css can be freed. Implemented in
- * css_free_work_fn().
+ * css_free_rwork_fn().
*
* It is actually hairier because both step 2 and 4 require process context
* and thus involve punting to css->destroy_work adding two additional
@@ -5547,8 +5591,7 @@ err_free_css:
/*
* The returned cgroup is fully initialized including its control mask, but
- * it isn't associated with its kernfs_node and doesn't have the control
- * mask applied.
+ * it doesn't have the control mask applied.
*/
static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
umode_t mode)
@@ -5874,7 +5917,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
/*
* Mark @cgrp and the associated csets dead. The former prevents
* further task migration and child creation by disabling
- * cgroup_lock_live_group(). The latter makes the csets ignored by
+ * cgroup_kn_lock_live(). The latter makes the csets ignored by
* the migration path.
*/
cgrp->self.flags &= ~CSS_ONLINE;
@@ -5896,7 +5939,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
parent->nr_threaded_children--;
spin_lock_irq(&css_set_lock);
- for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) {
+ for (tcgrp = parent; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
tcgrp->nr_descendants--;
tcgrp->nr_dying_descendants++;
/*
@@ -6089,8 +6132,8 @@ int __init cgroup_init(void)
continue;
if (cgroup1_ssid_disabled(ssid))
- printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n",
- ss->name);
+ pr_info("Disabling %s control group subsystem in v1 mounts\n",
+ ss->legacy_name);
cgrp_dfl_root.subsys_mask |= 1 << ss->id;
@@ -6733,6 +6776,12 @@ static int __init enable_cgroup_debug(char *str)
}
__setup("cgroup_debug", enable_cgroup_debug);
+static int __init cgroup_favordynmods_setup(char *str)
+{
+ return (kstrtobool(str, &have_favordynmods) == 0);
+}
+__setup("cgroup_favordynmods=", cgroup_favordynmods_setup);
+
/**
* css_tryget_online_from_dir - get corresponding css from a cgroup dentry
* @dentry: directory dentry of interest
@@ -7019,7 +7068,8 @@ static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
"nsdelegate\n"
"favordynmods\n"
"memory_localevents\n"
- "memory_recursiveprot\n");
+ "memory_recursiveprot\n"
+ "memory_hugetlb_accounting\n");
}
static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 58e6f18f01c1..615daaf87f1f 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -75,16 +75,18 @@ enum prs_errcode {
PERR_NOCPUS,
PERR_HOTPLUG,
PERR_CPUSEMPTY,
+ PERR_HKEEPING,
};
static const char * const perr_strings[] = {
- [PERR_INVCPUS] = "Invalid cpu list in cpuset.cpus",
+ [PERR_INVCPUS] = "Invalid cpu list in cpuset.cpus.exclusive",
[PERR_INVPARENT] = "Parent is an invalid partition root",
[PERR_NOTPART] = "Parent is not a partition root",
[PERR_NOTEXCL] = "Cpu list in cpuset.cpus not exclusive",
[PERR_NOCPUS] = "Parent unable to distribute cpu downstream",
[PERR_HOTPLUG] = "No cpu available due to hotplug",
[PERR_CPUSEMPTY] = "cpuset.cpus is empty",
+ [PERR_HKEEPING] = "partition config conflicts with housekeeping setup",
};
struct cpuset {
@@ -121,14 +123,23 @@ struct cpuset {
nodemask_t effective_mems;
/*
- * CPUs allocated to child sub-partitions (default hierarchy only)
- * - CPUs granted by the parent = effective_cpus U subparts_cpus
- * - effective_cpus and subparts_cpus are mutually exclusive.
+ * Exclusive CPUs dedicated to current cgroup (default hierarchy only)
*
- * effective_cpus contains only onlined CPUs, but subparts_cpus
- * may have offlined ones.
+ * This exclusive CPUs must be a subset of cpus_allowed. A parent
+ * cgroup can only grant exclusive CPUs to one of its children.
+ *
+ * When the cgroup becomes a valid partition root, effective_xcpus
+ * defaults to cpus_allowed if not set. The effective_cpus of a valid
+ * partition root comes solely from its effective_xcpus and some of the
+ * effective_xcpus may be distributed to sub-partitions below & hence
+ * excluded from its effective_cpus.
+ */
+ cpumask_var_t effective_xcpus;
+
+ /*
+ * Exclusive CPUs as requested by the user (default hierarchy only)
*/
- cpumask_var_t subparts_cpus;
+ cpumask_var_t exclusive_cpus;
/*
* This is old Memory Nodes tasks took on.
@@ -156,8 +167,8 @@ struct cpuset {
/* for custom sched domain */
int relax_domain_level;
- /* number of CPUs in subparts_cpus */
- int nr_subparts_cpus;
+ /* number of valid sub-partitions */
+ int nr_subparts;
/* partition root state */
int partition_root_state;
@@ -183,9 +194,20 @@ struct cpuset {
/* Handle for cpuset.cpus.partition */
struct cgroup_file partition_file;
+
+ /* Remote partition silbling list anchored at remote_children */
+ struct list_head remote_sibling;
};
/*
+ * Exclusive CPUs distributed out to sub-partitions of top_cpuset
+ */
+static cpumask_var_t subpartitions_cpus;
+
+/* List of remote partition root children */
+static struct list_head remote_children;
+
+/*
* Partition root states:
*
* 0 - member (not a partition root)
@@ -312,7 +334,7 @@ static inline int is_partition_invalid(const struct cpuset *cs)
*/
static inline void make_partition_invalid(struct cpuset *cs)
{
- if (is_partition_valid(cs))
+ if (cs->partition_root_state > 0)
cs->partition_root_state = -cs->partition_root_state;
}
@@ -334,6 +356,7 @@ static struct cpuset top_cpuset = {
.flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) |
(1 << CS_MEM_EXCLUSIVE)),
.partition_root_state = PRS_ROOT,
+ .remote_sibling = LIST_HEAD_INIT(top_cpuset.remote_sibling),
};
/**
@@ -469,7 +492,7 @@ static inline bool partition_is_populated(struct cpuset *cs,
if (cs->css.cgroup->nr_populated_csets)
return true;
- if (!excluded_child && !cs->nr_subparts_cpus)
+ if (!excluded_child && !cs->nr_subparts)
return cgroup_is_populated(cs->css.cgroup);
rcu_read_lock();
@@ -596,16 +619,18 @@ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
*/
static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
{
- cpumask_var_t *pmask1, *pmask2, *pmask3;
+ cpumask_var_t *pmask1, *pmask2, *pmask3, *pmask4;
if (cs) {
pmask1 = &cs->cpus_allowed;
pmask2 = &cs->effective_cpus;
- pmask3 = &cs->subparts_cpus;
+ pmask3 = &cs->effective_xcpus;
+ pmask4 = &cs->exclusive_cpus;
} else {
pmask1 = &tmp->new_cpus;
pmask2 = &tmp->addmask;
pmask3 = &tmp->delmask;
+ pmask4 = NULL;
}
if (!zalloc_cpumask_var(pmask1, GFP_KERNEL))
@@ -617,8 +642,14 @@ static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
if (!zalloc_cpumask_var(pmask3, GFP_KERNEL))
goto free_two;
+ if (pmask4 && !zalloc_cpumask_var(pmask4, GFP_KERNEL))
+ goto free_three;
+
+
return 0;
+free_three:
+ free_cpumask_var(*pmask3);
free_two:
free_cpumask_var(*pmask2);
free_one:
@@ -636,7 +667,8 @@ static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
if (cs) {
free_cpumask_var(cs->cpus_allowed);
free_cpumask_var(cs->effective_cpus);
- free_cpumask_var(cs->subparts_cpus);
+ free_cpumask_var(cs->effective_xcpus);
+ free_cpumask_var(cs->exclusive_cpus);
}
if (tmp) {
free_cpumask_var(tmp->new_cpus);
@@ -664,6 +696,8 @@ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs)
cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
cpumask_copy(trial->effective_cpus, cs->effective_cpus);
+ cpumask_copy(trial->effective_xcpus, cs->effective_xcpus);
+ cpumask_copy(trial->exclusive_cpus, cs->exclusive_cpus);
return trial;
}
@@ -677,6 +711,28 @@ static inline void free_cpuset(struct cpuset *cs)
kfree(cs);
}
+static inline struct cpumask *fetch_xcpus(struct cpuset *cs)
+{
+ return !cpumask_empty(cs->exclusive_cpus) ? cs->exclusive_cpus :
+ cpumask_empty(cs->effective_xcpus) ? cs->cpus_allowed
+ : cs->effective_xcpus;
+}
+
+/*
+ * cpusets_are_exclusive() - check if two cpusets are exclusive
+ *
+ * Return true if exclusive, false if not
+ */
+static inline bool cpusets_are_exclusive(struct cpuset *cs1, struct cpuset *cs2)
+{
+ struct cpumask *xcpus1 = fetch_xcpus(cs1);
+ struct cpumask *xcpus2 = fetch_xcpus(cs2);
+
+ if (cpumask_intersects(xcpus1, xcpus2))
+ return false;
+ return true;
+}
+
/*
* validate_change_legacy() - Validate conditions specific to legacy (v1)
* behavior.
@@ -776,9 +832,10 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
ret = -EINVAL;
cpuset_for_each_child(c, css, par) {
if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
- c != cur &&
- cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
- goto out;
+ c != cur) {
+ if (!cpusets_are_exclusive(trial, c))
+ goto out;
+ }
if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
c != cur &&
nodes_intersects(trial->mems_allowed, c->mems_allowed))
@@ -908,7 +965,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
csa = NULL;
/* Special case for the 99% of systems with one, full, sched domain */
- if (root_load_balance && !top_cpuset.nr_subparts_cpus) {
+ if (root_load_balance && !top_cpuset.nr_subparts) {
ndoms = 1;
doms = alloc_sched_domains(ndoms);
if (!doms)
@@ -1159,7 +1216,7 @@ static void rebuild_sched_domains_locked(void)
* should be the same as the active CPUs, so checking only top_cpuset
* is enough to detect racing CPU offlines.
*/
- if (!top_cpuset.nr_subparts_cpus &&
+ if (cpumask_empty(subpartitions_cpus) &&
!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
return;
@@ -1168,7 +1225,7 @@ static void rebuild_sched_domains_locked(void)
* root should be only a subset of the active CPUs. Since a CPU in any
* partition root could be offlined, all must be checked.
*/
- if (top_cpuset.nr_subparts_cpus) {
+ if (top_cpuset.nr_subparts) {
rcu_read_lock();
cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
if (!is_partition_valid(cs)) {
@@ -1230,9 +1287,9 @@ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
/*
* Percpu kthreads in top_cpuset are ignored
*/
- if ((task->flags & PF_KTHREAD) && kthread_is_per_cpu(task))
+ if (kthread_is_per_cpu(task))
continue;
- cpumask_andnot(new_cpus, possible_mask, cs->subparts_cpus);
+ cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus);
} else {
cpumask_and(new_cpus, possible_mask, cs->effective_cpus);
}
@@ -1247,38 +1304,372 @@ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
* @cs: the cpuset the need to recompute the new effective_cpus mask
* @parent: the parent cpuset
*
- * If the parent has subpartition CPUs, include them in the list of
- * allowable CPUs in computing the new effective_cpus mask. Since offlined
- * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask
- * to mask those out.
+ * The result is valid only if the given cpuset isn't a partition root.
*/
static void compute_effective_cpumask(struct cpumask *new_cpus,
struct cpuset *cs, struct cpuset *parent)
{
- if (parent->nr_subparts_cpus) {
- cpumask_or(new_cpus, parent->effective_cpus,
- parent->subparts_cpus);
- cpumask_and(new_cpus, new_cpus, cs->cpus_allowed);
- cpumask_and(new_cpus, new_cpus, cpu_active_mask);
- } else {
- cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus);
- }
+ cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus);
}
/*
- * Commands for update_parent_subparts_cpumask
+ * Commands for update_parent_effective_cpumask
*/
-enum subparts_cmd {
- partcmd_enable, /* Enable partition root */
- partcmd_disable, /* Disable partition root */
- partcmd_update, /* Update parent's subparts_cpus */
- partcmd_invalidate, /* Make partition invalid */
+enum partition_cmd {
+ partcmd_enable, /* Enable partition root */
+ partcmd_disable, /* Disable partition root */
+ partcmd_update, /* Update parent's effective_cpus */
+ partcmd_invalidate, /* Make partition invalid */
};
static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
int turning_on);
+static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
+ struct tmpmasks *tmp);
+
+/*
+ * Update partition exclusive flag
+ *
+ * Return: 0 if successful, an error code otherwise
+ */
+static int update_partition_exclusive(struct cpuset *cs, int new_prs)
+{
+ bool exclusive = (new_prs > 0);
+
+ if (exclusive && !is_cpu_exclusive(cs)) {
+ if (update_flag(CS_CPU_EXCLUSIVE, cs, 1))
+ return PERR_NOTEXCL;
+ } else if (!exclusive && is_cpu_exclusive(cs)) {
+ /* Turning off CS_CPU_EXCLUSIVE will not return error */
+ update_flag(CS_CPU_EXCLUSIVE, cs, 0);
+ }
+ return 0;
+}
+
+/*
+ * Update partition load balance flag and/or rebuild sched domain
+ *
+ * Changing load balance flag will automatically call
+ * rebuild_sched_domains_locked().
+ * This function is for cgroup v2 only.
+ */
+static void update_partition_sd_lb(struct cpuset *cs, int old_prs)
+{
+ int new_prs = cs->partition_root_state;
+ bool rebuild_domains = (new_prs > 0) || (old_prs > 0);
+ bool new_lb;
+
+ /*
+ * If cs is not a valid partition root, the load balance state
+ * will follow its parent.
+ */
+ if (new_prs > 0) {
+ new_lb = (new_prs != PRS_ISOLATED);
+ } else {
+ new_lb = is_sched_load_balance(parent_cs(cs));
+ }
+ if (new_lb != !!is_sched_load_balance(cs)) {
+ rebuild_domains = true;
+ if (new_lb)
+ set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
+ else
+ clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
+ }
+
+ if (rebuild_domains)
+ rebuild_sched_domains_locked();
+}
+
+/*
+ * tasks_nocpu_error - Return true if tasks will have no effective_cpus
+ */
+static bool tasks_nocpu_error(struct cpuset *parent, struct cpuset *cs,
+ struct cpumask *xcpus)
+{
+ /*
+ * A populated partition (cs or parent) can't have empty effective_cpus
+ */
+ return (cpumask_subset(parent->effective_cpus, xcpus) &&
+ partition_is_populated(parent, cs)) ||
+ (!cpumask_intersects(xcpus, cpu_active_mask) &&
+ partition_is_populated(cs, NULL));
+}
+
+static void reset_partition_data(struct cpuset *cs)
+{
+ struct cpuset *parent = parent_cs(cs);
+
+ if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
+ return;
+
+ lockdep_assert_held(&callback_lock);
+
+ cs->nr_subparts = 0;
+ if (cpumask_empty(cs->exclusive_cpus)) {
+ cpumask_clear(cs->effective_xcpus);
+ if (is_cpu_exclusive(cs))
+ clear_bit(CS_CPU_EXCLUSIVE, &cs->flags);
+ }
+ if (!cpumask_and(cs->effective_cpus,
+ parent->effective_cpus, cs->cpus_allowed)) {
+ cs->use_parent_ecpus = true;
+ parent->child_ecpus_count++;
+ cpumask_copy(cs->effective_cpus, parent->effective_cpus);
+ }
+}
+
+/*
+ * compute_effective_exclusive_cpumask - compute effective exclusive CPUs
+ * @cs: cpuset
+ * @xcpus: effective exclusive CPUs value to be set
+ * Return: true if xcpus is not empty, false otherwise.
+ *
+ * Starting with exclusive_cpus (cpus_allowed if exclusive_cpus is not set),
+ * it must be a subset of cpus_allowed and parent's effective_xcpus.
+ */
+static bool compute_effective_exclusive_cpumask(struct cpuset *cs,
+ struct cpumask *xcpus)
+{
+ struct cpuset *parent = parent_cs(cs);
+
+ if (!xcpus)
+ xcpus = cs->effective_xcpus;
+
+ if (!cpumask_empty(cs->exclusive_cpus))
+ cpumask_and(xcpus, cs->exclusive_cpus, cs->cpus_allowed);
+ else
+ cpumask_copy(xcpus, cs->cpus_allowed);
+
+ return cpumask_and(xcpus, xcpus, parent->effective_xcpus);
+}
+
+static inline bool is_remote_partition(struct cpuset *cs)
+{
+ return !list_empty(&cs->remote_sibling);
+}
+
+static inline bool is_local_partition(struct cpuset *cs)
+{
+ return is_partition_valid(cs) && !is_remote_partition(cs);
+}
+
+/*
+ * remote_partition_enable - Enable current cpuset as a remote partition root
+ * @cs: the cpuset to update
+ * @tmp: temparary masks
+ * Return: 1 if successful, 0 if error
+ *
+ * Enable the current cpuset to become a remote partition root taking CPUs
+ * directly from the top cpuset. cpuset_mutex must be held by the caller.
+ */
+static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
+{
+ /*
+ * The user must have sysadmin privilege.
+ */
+ if (!capable(CAP_SYS_ADMIN))
+ return 0;
+
+ /*
+ * The requested exclusive_cpus must not be allocated to other
+ * partitions and it can't use up all the root's effective_cpus.
+ *
+ * Note that if there is any local partition root above it or
+ * remote partition root underneath it, its exclusive_cpus must
+ * have overlapped with subpartitions_cpus.
+ */
+ compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
+ if (cpumask_empty(tmp->new_cpus) ||
+ cpumask_intersects(tmp->new_cpus, subpartitions_cpus) ||
+ cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
+ return 0;
+
+ spin_lock_irq(&callback_lock);
+ cpumask_andnot(top_cpuset.effective_cpus,
+ top_cpuset.effective_cpus, tmp->new_cpus);
+ cpumask_or(subpartitions_cpus,
+ subpartitions_cpus, tmp->new_cpus);
+
+ if (cs->use_parent_ecpus) {
+ struct cpuset *parent = parent_cs(cs);
+
+ cs->use_parent_ecpus = false;
+ parent->child_ecpus_count--;
+ }
+ list_add(&cs->remote_sibling, &remote_children);
+ spin_unlock_irq(&callback_lock);
+
+ /*
+ * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
+ */
+ update_tasks_cpumask(&top_cpuset, tmp->new_cpus);
+ update_sibling_cpumasks(&top_cpuset, NULL, tmp);
+
+ return 1;
+}
+
+/*
+ * remote_partition_disable - Remove current cpuset from remote partition list
+ * @cs: the cpuset to update
+ * @tmp: temparary masks
+ *
+ * The effective_cpus is also updated.
+ *
+ * cpuset_mutex must be held by the caller.
+ */
+static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
+{
+ compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
+ WARN_ON_ONCE(!is_remote_partition(cs));
+ WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, subpartitions_cpus));
+
+ spin_lock_irq(&callback_lock);
+ cpumask_andnot(subpartitions_cpus,
+ subpartitions_cpus, tmp->new_cpus);
+ cpumask_and(tmp->new_cpus,
+ tmp->new_cpus, cpu_active_mask);
+ cpumask_or(top_cpuset.effective_cpus,
+ top_cpuset.effective_cpus, tmp->new_cpus);
+ list_del_init(&cs->remote_sibling);
+ cs->partition_root_state = -cs->partition_root_state;
+ if (!cs->prs_err)
+ cs->prs_err = PERR_INVCPUS;
+ reset_partition_data(cs);
+ spin_unlock_irq(&callback_lock);
+
+ /*
+ * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
+ */
+ update_tasks_cpumask(&top_cpuset, tmp->new_cpus);
+ update_sibling_cpumasks(&top_cpuset, NULL, tmp);
+}
+
+/*
+ * remote_cpus_update - cpus_exclusive change of remote partition
+ * @cs: the cpuset to be updated
+ * @newmask: the new effective_xcpus mask
+ * @tmp: temparary masks
+ *
+ * top_cpuset and subpartitions_cpus will be updated or partition can be
+ * invalidated.
+ */
+static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
+ struct tmpmasks *tmp)
+{
+ bool adding, deleting;
+
+ if (WARN_ON_ONCE(!is_remote_partition(cs)))
+ return;
+
+ WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
+
+ if (cpumask_empty(newmask))
+ goto invalidate;
+
+ adding = cpumask_andnot(tmp->addmask, newmask, cs->effective_xcpus);
+ deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, newmask);
+
+ /*
+ * Additions of remote CPUs is only allowed if those CPUs are
+ * not allocated to other partitions and there are effective_cpus
+ * left in the top cpuset.
+ */
+ if (adding && (!capable(CAP_SYS_ADMIN) ||
+ cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
+ cpumask_subset(top_cpuset.effective_cpus, tmp->addmask)))
+ goto invalidate;
+
+ spin_lock_irq(&callback_lock);
+ if (adding) {
+ cpumask_or(subpartitions_cpus,
+ subpartitions_cpus, tmp->addmask);
+ cpumask_andnot(top_cpuset.effective_cpus,
+ top_cpuset.effective_cpus, tmp->addmask);
+ }
+ if (deleting) {
+ cpumask_andnot(subpartitions_cpus,
+ subpartitions_cpus, tmp->delmask);
+ cpumask_and(tmp->delmask,
+ tmp->delmask, cpu_active_mask);
+ cpumask_or(top_cpuset.effective_cpus,
+ top_cpuset.effective_cpus, tmp->delmask);
+ }
+ spin_unlock_irq(&callback_lock);
+
+ /*
+ * Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
+ */
+ update_tasks_cpumask(&top_cpuset, tmp->new_cpus);
+ update_sibling_cpumasks(&top_cpuset, NULL, tmp);
+ return;
+
+invalidate:
+ remote_partition_disable(cs, tmp);
+}
+
+/*
+ * remote_partition_check - check if a child remote partition needs update
+ * @cs: the cpuset to be updated
+ * @newmask: the new effective_xcpus mask
+ * @delmask: temporary mask for deletion (not in tmp)
+ * @tmp: temparary masks
+ *
+ * This should be called before the given cs has updated its cpus_allowed
+ * and/or effective_xcpus.
+ */
+static void remote_partition_check(struct cpuset *cs, struct cpumask *newmask,
+ struct cpumask *delmask, struct tmpmasks *tmp)
+{
+ struct cpuset *child, *next;
+ int disable_cnt = 0;
+
+ /*
+ * Compute the effective exclusive CPUs that will be deleted.
+ */
+ if (!cpumask_andnot(delmask, cs->effective_xcpus, newmask) ||
+ !cpumask_intersects(delmask, subpartitions_cpus))
+ return; /* No deletion of exclusive CPUs in partitions */
+
+ /*
+ * Searching the remote children list to look for those that will
+ * be impacted by the deletion of exclusive CPUs.
+ *
+ * Since a cpuset must be removed from the remote children list
+ * before it can go offline and holding cpuset_mutex will prevent
+ * any change in cpuset status. RCU read lock isn't needed.
+ */
+ lockdep_assert_held(&cpuset_mutex);
+ list_for_each_entry_safe(child, next, &remote_children, remote_sibling)
+ if (cpumask_intersects(child->effective_cpus, delmask)) {
+ remote_partition_disable(child, tmp);
+ disable_cnt++;
+ }
+ if (disable_cnt)
+ rebuild_sched_domains_locked();
+}
+
+/*
+ * prstate_housekeeping_conflict - check for partition & housekeeping conflicts
+ * @prstate: partition root state to be checked
+ * @new_cpus: cpu mask
+ * Return: true if there is conflict, false otherwise
+ *
+ * CPUs outside of housekeeping_cpumask(HK_TYPE_DOMAIN) can only be used in
+ * an isolated partition.
+ */
+static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
+{
+ const struct cpumask *hk_domain = housekeeping_cpumask(HK_TYPE_DOMAIN);
+ bool all_in_hk = cpumask_subset(new_cpus, hk_domain);
+
+ if (!all_in_hk && (prstate != PRS_ISOLATED))
+ return true;
+
+ return false;
+}
+
/**
- * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset
+ * update_parent_effective_cpumask - update effective_cpus mask of parent cpuset
* @cs: The cpuset that requests change in partition root state
* @cmd: Partition root state change command
* @newmask: Optional new cpumask for partcmd_update
@@ -1286,21 +1677,20 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
* Return: 0 or a partition root state error code
*
* For partcmd_enable, the cpuset is being transformed from a non-partition
- * root to a partition root. The cpus_allowed mask of the given cpuset will
- * be put into parent's subparts_cpus and taken away from parent's
+ * root to a partition root. The effective_xcpus (cpus_allowed if effective_xcpus
+ * not set) mask of the given cpuset will be taken away from parent's
* effective_cpus. The function will return 0 if all the CPUs listed in
- * cpus_allowed can be granted or an error code will be returned.
+ * effective_xcpus can be granted or an error code will be returned.
*
* For partcmd_disable, the cpuset is being transformed from a partition
- * root back to a non-partition root. Any CPUs in cpus_allowed that are in
- * parent's subparts_cpus will be taken away from that cpumask and put back
- * into parent's effective_cpus. 0 will always be returned.
+ * root back to a non-partition root. Any CPUs in effective_xcpus will be
+ * given back to parent's effective_cpus. 0 will always be returned.
*
* For partcmd_update, if the optional newmask is specified, the cpu list is
- * to be changed from cpus_allowed to newmask. Otherwise, cpus_allowed is
+ * to be changed from effective_xcpus to newmask. Otherwise, effective_xcpus is
* assumed to remain the same. The cpuset should either be a valid or invalid
* partition root. The partition root state may change from valid to invalid
- * or vice versa. An error code will only be returned if transitioning from
+ * or vice versa. An error code will be returned if transitioning from
* invalid to valid violates the exclusivity rule.
*
* For partcmd_invalidate, the current partition will be made invalid.
@@ -1315,19 +1705,48 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
* check for error and so partition_root_state and prs_error will be updated
* directly.
*/
-static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
- struct cpumask *newmask,
- struct tmpmasks *tmp)
+static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
+ struct cpumask *newmask,
+ struct tmpmasks *tmp)
{
struct cpuset *parent = parent_cs(cs);
- int adding; /* Moving cpus from effective_cpus to subparts_cpus */
- int deleting; /* Moving cpus from subparts_cpus to effective_cpus */
+ int adding; /* Adding cpus to parent's effective_cpus */
+ int deleting; /* Deleting cpus from parent's effective_cpus */
int old_prs, new_prs;
int part_error = PERR_NONE; /* Partition error? */
+ int subparts_delta = 0;
+ struct cpumask *xcpus; /* cs effective_xcpus */
+ bool nocpu;
lockdep_assert_held(&cpuset_mutex);
/*
+ * new_prs will only be changed for the partcmd_update and
+ * partcmd_invalidate commands.
+ */
+ adding = deleting = false;
+ old_prs = new_prs = cs->partition_root_state;
+ xcpus = !cpumask_empty(cs->exclusive_cpus)
+ ? cs->effective_xcpus : cs->cpus_allowed;
+
+ if (cmd == partcmd_invalidate) {
+ if (is_prs_invalid(old_prs))
+ return 0;
+
+ /*
+ * Make the current partition invalid.
+ */
+ if (is_partition_valid(parent))
+ adding = cpumask_and(tmp->addmask,
+ xcpus, parent->effective_xcpus);
+ if (old_prs > 0) {
+ new_prs = -old_prs;
+ subparts_delta--;
+ }
+ goto write_error;
+ }
+
+ /*
* The parent must be a partition root.
* The new cpumask, if present, or the current cpus_allowed must
* not be empty.
@@ -1336,123 +1755,141 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
return is_partition_invalid(parent)
? PERR_INVPARENT : PERR_NOTPART;
}
- if ((newmask && cpumask_empty(newmask)) ||
- (!newmask && cpumask_empty(cs->cpus_allowed)))
+ if (!newmask && cpumask_empty(cs->cpus_allowed))
return PERR_CPUSEMPTY;
- /*
- * new_prs will only be changed for the partcmd_update and
- * partcmd_invalidate commands.
- */
- adding = deleting = false;
- old_prs = new_prs = cs->partition_root_state;
+ nocpu = tasks_nocpu_error(parent, cs, xcpus);
+
if (cmd == partcmd_enable) {
/*
- * Enabling partition root is not allowed if cpus_allowed
- * doesn't overlap parent's cpus_allowed.
+ * Enabling partition root is not allowed if its
+ * effective_xcpus is empty or doesn't overlap with
+ * parent's effective_xcpus.
*/
- if (!cpumask_intersects(cs->cpus_allowed, parent->cpus_allowed))
+ if (cpumask_empty(xcpus) ||
+ !cpumask_intersects(xcpus, parent->effective_xcpus))
return PERR_INVCPUS;
+ if (prstate_housekeeping_conflict(new_prs, xcpus))
+ return PERR_HKEEPING;
+
/*
* A parent can be left with no CPU as long as there is no
* task directly associated with the parent partition.
*/
- if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) &&
- partition_is_populated(parent, cs))
+ if (nocpu)
return PERR_NOCPUS;
- cpumask_copy(tmp->addmask, cs->cpus_allowed);
- adding = true;
+ cpumask_copy(tmp->delmask, xcpus);
+ deleting = true;
+ subparts_delta++;
} else if (cmd == partcmd_disable) {
/*
- * Need to remove cpus from parent's subparts_cpus for valid
- * partition root.
+ * May need to add cpus to parent's effective_cpus for
+ * valid partition root.
*/
- deleting = !is_prs_invalid(old_prs) &&
- cpumask_and(tmp->delmask, cs->cpus_allowed,
- parent->subparts_cpus);
- } else if (cmd == partcmd_invalidate) {
- if (is_prs_invalid(old_prs))
- return 0;
-
+ adding = !is_prs_invalid(old_prs) &&
+ cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus);
+ if (adding)
+ subparts_delta--;
+ } else if (newmask) {
/*
- * Make the current partition invalid. It is assumed that
- * invalidation is caused by violating cpu exclusivity rule.
+ * Empty cpumask is not allowed
*/
- deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
- parent->subparts_cpus);
- if (old_prs > 0) {
- new_prs = -old_prs;
- part_error = PERR_NOTEXCL;
+ if (cpumask_empty(newmask)) {
+ part_error = PERR_CPUSEMPTY;
+ goto write_error;
}
- } else if (newmask) {
+
/*
* partcmd_update with newmask:
*
- * Compute add/delete mask to/from subparts_cpus
+ * Compute add/delete mask to/from effective_cpus
+ *
+ * For valid partition:
+ * addmask = exclusive_cpus & ~newmask
+ * & parent->effective_xcpus
+ * delmask = newmask & ~exclusive_cpus
+ * & parent->effective_xcpus
*
- * delmask = cpus_allowed & ~newmask & parent->subparts_cpus
- * addmask = newmask & parent->cpus_allowed
- * & ~parent->subparts_cpus
+ * For invalid partition:
+ * delmask = newmask & parent->effective_xcpus
*/
- cpumask_andnot(tmp->delmask, cs->cpus_allowed, newmask);
- deleting = cpumask_and(tmp->delmask, tmp->delmask,
- parent->subparts_cpus);
+ if (is_prs_invalid(old_prs)) {
+ adding = false;
+ deleting = cpumask_and(tmp->delmask,
+ newmask, parent->effective_xcpus);
+ } else {
+ cpumask_andnot(tmp->addmask, xcpus, newmask);
+ adding = cpumask_and(tmp->addmask, tmp->addmask,
+ parent->effective_xcpus);
- cpumask_and(tmp->addmask, newmask, parent->cpus_allowed);
- adding = cpumask_andnot(tmp->addmask, tmp->addmask,
- parent->subparts_cpus);
+ cpumask_andnot(tmp->delmask, newmask, xcpus);
+ deleting = cpumask_and(tmp->delmask, tmp->delmask,
+ parent->effective_xcpus);
+ }
/*
* Make partition invalid if parent's effective_cpus could
* become empty and there are tasks in the parent.
*/
- if (adding &&
- cpumask_subset(parent->effective_cpus, tmp->addmask) &&
- !cpumask_intersects(tmp->delmask, cpu_active_mask) &&
- partition_is_populated(parent, cs)) {
+ if (nocpu && (!adding ||
+ !cpumask_intersects(tmp->addmask, cpu_active_mask))) {
part_error = PERR_NOCPUS;
- adding = false;
- deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
- parent->subparts_cpus);
+ deleting = false;
+ adding = cpumask_and(tmp->addmask,
+ xcpus, parent->effective_xcpus);
}
} else {
/*
- * partcmd_update w/o newmask:
+ * partcmd_update w/o newmask
+ *
+ * delmask = effective_xcpus & parent->effective_cpus
+ *
+ * This can be called from:
+ * 1) update_cpumasks_hier()
+ * 2) cpuset_hotplug_update_tasks()
*
- * delmask = cpus_allowed & parent->subparts_cpus
- * addmask = cpus_allowed & parent->cpus_allowed
- * & ~parent->subparts_cpus
+ * Check to see if it can be transitioned from valid to
+ * invalid partition or vice versa.
*
- * This gets invoked either due to a hotplug event or from
- * update_cpumasks_hier(). This can cause the state of a
- * partition root to transition from valid to invalid or vice
- * versa. So we still need to compute the addmask and delmask.
-
- * A partition error happens when:
- * 1) Cpuset is valid partition, but parent does not distribute
- * out any CPUs.
- * 2) Parent has tasks and all its effective CPUs will have
- * to be distributed out.
+ * A partition error happens when parent has tasks and all
+ * its effective CPUs will have to be distributed out.
*/
- cpumask_and(tmp->addmask, cs->cpus_allowed,
- parent->cpus_allowed);
- adding = cpumask_andnot(tmp->addmask, tmp->addmask,
- parent->subparts_cpus);
-
- if ((is_partition_valid(cs) && !parent->nr_subparts_cpus) ||
- (adding &&
- cpumask_subset(parent->effective_cpus, tmp->addmask) &&
- partition_is_populated(parent, cs))) {
+ WARN_ON_ONCE(!is_partition_valid(parent));
+ if (nocpu) {
part_error = PERR_NOCPUS;
- adding = false;
- }
+ if (is_partition_valid(cs))
+ adding = cpumask_and(tmp->addmask,
+ xcpus, parent->effective_xcpus);
+ } else if (is_partition_invalid(cs) &&
+ cpumask_subset(xcpus, parent->effective_xcpus)) {
+ struct cgroup_subsys_state *css;
+ struct cpuset *child;
+ bool exclusive = true;
- if (part_error && is_partition_valid(cs) &&
- parent->nr_subparts_cpus)
- deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
- parent->subparts_cpus);
+ /*
+ * Convert invalid partition to valid has to
+ * pass the cpu exclusivity test.
+ */
+ rcu_read_lock();
+ cpuset_for_each_child(child, css, parent) {
+ if (child == cs)
+ continue;
+ if (!cpusets_are_exclusive(cs, child)) {
+ exclusive = false;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ if (exclusive)
+ deleting = cpumask_and(tmp->delmask,
+ xcpus, parent->effective_cpus);
+ else
+ part_error = PERR_NOTEXCL;
+ }
}
+
+write_error:
if (part_error)
WRITE_ONCE(cs->prs_err, part_error);
@@ -1464,13 +1901,17 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
switch (cs->partition_root_state) {
case PRS_ROOT:
case PRS_ISOLATED:
- if (part_error)
+ if (part_error) {
new_prs = -old_prs;
+ subparts_delta--;
+ }
break;
case PRS_INVALID_ROOT:
case PRS_INVALID_ISOLATED:
- if (!part_error)
+ if (!part_error) {
new_prs = -old_prs;
+ subparts_delta++;
+ }
break;
}
}
@@ -1480,63 +1921,154 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
/*
* Transitioning between invalid to valid or vice versa may require
- * changing CS_CPU_EXCLUSIVE and CS_SCHED_LOAD_BALANCE.
+ * changing CS_CPU_EXCLUSIVE. In the case of partcmd_update,
+ * validate_change() has already been successfully called and
+ * CPU lists in cs haven't been updated yet. So defer it to later.
*/
- if (old_prs != new_prs) {
- if (is_prs_invalid(old_prs) && !is_cpu_exclusive(cs) &&
- (update_flag(CS_CPU_EXCLUSIVE, cs, 1) < 0))
- return PERR_NOTEXCL;
- if (is_prs_invalid(new_prs) && is_cpu_exclusive(cs))
- update_flag(CS_CPU_EXCLUSIVE, cs, 0);
+ if ((old_prs != new_prs) && (cmd != partcmd_update)) {
+ int err = update_partition_exclusive(cs, new_prs);
+
+ if (err)
+ return err;
}
/*
- * Change the parent's subparts_cpus.
+ * Change the parent's effective_cpus & effective_xcpus (top cpuset
+ * only).
+ *
* Newly added CPUs will be removed from effective_cpus and
* newly deleted ones will be added back to effective_cpus.
*/
spin_lock_irq(&callback_lock);
if (adding) {
- cpumask_or(parent->subparts_cpus,
- parent->subparts_cpus, tmp->addmask);
- cpumask_andnot(parent->effective_cpus,
- parent->effective_cpus, tmp->addmask);
- }
- if (deleting) {
- cpumask_andnot(parent->subparts_cpus,
- parent->subparts_cpus, tmp->delmask);
+ if (parent == &top_cpuset)
+ cpumask_andnot(subpartitions_cpus,
+ subpartitions_cpus, tmp->addmask);
/*
- * Some of the CPUs in subparts_cpus might have been offlined.
+ * Some of the CPUs in effective_xcpus might have been offlined.
*/
- cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask);
cpumask_or(parent->effective_cpus,
- parent->effective_cpus, tmp->delmask);
+ parent->effective_cpus, tmp->addmask);
+ cpumask_and(parent->effective_cpus,
+ parent->effective_cpus, cpu_active_mask);
+ }
+ if (deleting) {
+ if (parent == &top_cpuset)
+ cpumask_or(subpartitions_cpus,
+ subpartitions_cpus, tmp->delmask);
+ cpumask_andnot(parent->effective_cpus,
+ parent->effective_cpus, tmp->delmask);
}
- parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);
+ if (is_partition_valid(parent)) {
+ parent->nr_subparts += subparts_delta;
+ WARN_ON_ONCE(parent->nr_subparts < 0);
+ }
- if (old_prs != new_prs)
+ if (old_prs != new_prs) {
cs->partition_root_state = new_prs;
+ if (new_prs <= 0)
+ cs->nr_subparts = 0;
+ }
spin_unlock_irq(&callback_lock);
- if (adding || deleting)
+ if ((old_prs != new_prs) && (cmd == partcmd_update))
+ update_partition_exclusive(cs, new_prs);
+
+ if (adding || deleting) {
update_tasks_cpumask(parent, tmp->addmask);
+ update_sibling_cpumasks(parent, cs, tmp);
+ }
/*
- * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
- * rebuild_sched_domains_locked() may be called.
+ * For partcmd_update without newmask, it is being called from
+ * cpuset_hotplug_workfn() where cpus_read_lock() wasn't taken.
+ * Update the load balance flag and scheduling domain if
+ * cpus_read_trylock() is successful.
*/
- if (old_prs != new_prs) {
- if (old_prs == PRS_ISOLATED)
- update_flag(CS_SCHED_LOAD_BALANCE, cs, 1);
- else if (new_prs == PRS_ISOLATED)
- update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
+ if ((cmd == partcmd_update) && !newmask && cpus_read_trylock()) {
+ update_partition_sd_lb(cs, old_prs);
+ cpus_read_unlock();
}
+
notify_partition_change(cs, old_prs);
return 0;
}
+/**
+ * compute_partition_effective_cpumask - compute effective_cpus for partition
+ * @cs: partition root cpuset
+ * @new_ecpus: previously computed effective_cpus to be updated
+ *
+ * Compute the effective_cpus of a partition root by scanning effective_xcpus
+ * of child partition roots and excluding their effective_xcpus.
+ *
+ * This has the side effect of invalidating valid child partition roots,
+ * if necessary. Since it is called from either cpuset_hotplug_update_tasks()
+ * or update_cpumasks_hier() where parent and children are modified
+ * successively, we don't need to call update_parent_effective_cpumask()
+ * and the child's effective_cpus will be updated in later iterations.
+ *
+ * Note that rcu_read_lock() is assumed to be held.
+ */
+static void compute_partition_effective_cpumask(struct cpuset *cs,
+ struct cpumask *new_ecpus)
+{
+ struct cgroup_subsys_state *css;
+ struct cpuset *child;
+ bool populated = partition_is_populated(cs, NULL);
+
+ /*
+ * Check child partition roots to see if they should be
+ * invalidated when
+ * 1) child effective_xcpus not a subset of new
+ * excluisve_cpus
+ * 2) All the effective_cpus will be used up and cp
+ * has tasks
+ */
+ compute_effective_exclusive_cpumask(cs, new_ecpus);
+ cpumask_and(new_ecpus, new_ecpus, cpu_active_mask);
+
+ rcu_read_lock();
+ cpuset_for_each_child(child, css, cs) {
+ if (!is_partition_valid(child))
+ continue;
+
+ child->prs_err = 0;
+ if (!cpumask_subset(child->effective_xcpus,
+ cs->effective_xcpus))
+ child->prs_err = PERR_INVCPUS;
+ else if (populated &&
+ cpumask_subset(new_ecpus, child->effective_xcpus))
+ child->prs_err = PERR_NOCPUS;
+
+ if (child->prs_err) {
+ int old_prs = child->partition_root_state;
+
+ /*
+ * Invalidate child partition
+ */
+ spin_lock_irq(&callback_lock);
+ make_partition_invalid(child);
+ cs->nr_subparts--;
+ child->nr_subparts = 0;
+ spin_unlock_irq(&callback_lock);
+ notify_partition_change(child, old_prs);
+ continue;
+ }
+ cpumask_andnot(new_ecpus, new_ecpus,
+ child->effective_xcpus);
+ }
+ rcu_read_unlock();
+}
+
+/*
+ * update_cpumasks_hier() flags
+ */
+#define HIER_CHECKALL 0x01 /* Check all cpusets with no skipping */
+#define HIER_NO_SD_REBUILD 0x02 /* Don't rebuild sched domains */
+
/*
* update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
* @cs: the cpuset to consider
@@ -1551,7 +2083,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
* Called with cpuset_mutex held
*/
static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
- bool force)
+ int flags)
{
struct cpuset *cp;
struct cgroup_subsys_state *pos_css;
@@ -1561,9 +2093,44 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
rcu_read_lock();
cpuset_for_each_descendant_pre(cp, pos_css, cs) {
struct cpuset *parent = parent_cs(cp);
+ bool remote = is_remote_partition(cp);
bool update_parent = false;
- compute_effective_cpumask(tmp->new_cpus, cp, parent);
+ /*
+ * Skip descendent remote partition that acquires CPUs
+ * directly from top cpuset unless it is cs.
+ */
+ if (remote && (cp != cs)) {
+ pos_css = css_rightmost_descendant(pos_css);
+ continue;
+ }
+
+ /*
+ * Update effective_xcpus if exclusive_cpus set.
+ * The case when exclusive_cpus isn't set is handled later.
+ */
+ if (!cpumask_empty(cp->exclusive_cpus) && (cp != cs)) {
+ spin_lock_irq(&callback_lock);
+ compute_effective_exclusive_cpumask(cp, NULL);
+ spin_unlock_irq(&callback_lock);
+ }
+
+ old_prs = new_prs = cp->partition_root_state;
+ if (remote || (is_partition_valid(parent) &&
+ is_partition_valid(cp)))
+ compute_partition_effective_cpumask(cp, tmp->new_cpus);
+ else
+ compute_effective_cpumask(tmp->new_cpus, cp, parent);
+
+ /*
+ * A partition with no effective_cpus is allowed as long as
+ * there is no task associated with it. Call
+ * update_parent_effective_cpumask() to check it.
+ */
+ if (is_partition_valid(cp) && cpumask_empty(tmp->new_cpus)) {
+ update_parent = true;
+ goto update_parent_effective;
+ }
/*
* If it becomes empty, inherit the effective mask of the
@@ -1571,11 +2138,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
* it is a partition root that has explicitly distributed
* out all its CPUs.
*/
- if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) {
- if (is_partition_valid(cp) &&
- cpumask_equal(cp->cpus_allowed, cp->subparts_cpus))
- goto update_parent_subparts;
-
+ if (is_in_v2_mode() && !remote && cpumask_empty(tmp->new_cpus)) {
cpumask_copy(tmp->new_cpus, parent->effective_cpus);
if (!cp->use_parent_ecpus) {
cp->use_parent_ecpus = true;
@@ -1587,24 +2150,31 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
parent->child_ecpus_count--;
}
+ if (remote)
+ goto get_css;
+
/*
- * Skip the whole subtree if the cpumask remains the same
- * and has no partition root state and force flag not set.
+ * Skip the whole subtree if
+ * 1) the cpumask remains the same,
+ * 2) has no partition root state,
+ * 3) HIER_CHECKALL flag not set, and
+ * 4) for v2 load balance state same as its parent.
*/
- if (!cp->partition_root_state && !force &&
- cpumask_equal(tmp->new_cpus, cp->effective_cpus)) {
+ if (!cp->partition_root_state && !(flags & HIER_CHECKALL) &&
+ cpumask_equal(tmp->new_cpus, cp->effective_cpus) &&
+ (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
+ (is_sched_load_balance(parent) == is_sched_load_balance(cp)))) {
pos_css = css_rightmost_descendant(pos_css);
continue;
}
-update_parent_subparts:
+update_parent_effective:
/*
- * update_parent_subparts_cpumask() should have been called
+ * update_parent_effective_cpumask() should have been called
* for cs already in update_cpumask(). We should also call
* update_tasks_cpumask() again for tasks in the parent
- * cpuset if the parent's subparts_cpus changes.
+ * cpuset if the parent's effective_cpus changes.
*/
- old_prs = new_prs = cp->partition_root_state;
if ((cp != cs) && old_prs) {
switch (parent->partition_root_state) {
case PRS_ROOT:
@@ -1626,14 +2196,13 @@ update_parent_subparts:
break;
}
}
-
+get_css:
if (!css_tryget_online(&cp->css))
continue;
rcu_read_unlock();
if (update_parent) {
- update_parent_subparts_cpumask(cp, partcmd_update, NULL,
- tmp);
+ update_parent_effective_cpumask(cp, partcmd_update, NULL, tmp);
/*
* The cpuset partition_root_state may become
* invalid. Capture it.
@@ -1642,30 +2211,17 @@ update_parent_subparts:
}
spin_lock_irq(&callback_lock);
-
- if (cp->nr_subparts_cpus && !is_partition_valid(cp)) {
- /*
- * Put all active subparts_cpus back to effective_cpus.
- */
- cpumask_or(tmp->new_cpus, tmp->new_cpus,
- cp->subparts_cpus);
- cpumask_and(tmp->new_cpus, tmp->new_cpus,
- cpu_active_mask);
- cp->nr_subparts_cpus = 0;
- cpumask_clear(cp->subparts_cpus);
- }
-
cpumask_copy(cp->effective_cpus, tmp->new_cpus);
- if (cp->nr_subparts_cpus) {
- /*
- * Make sure that effective_cpus & subparts_cpus
- * are mutually exclusive.
- */
- cpumask_andnot(cp->effective_cpus, cp->effective_cpus,
- cp->subparts_cpus);
- }
-
cp->partition_root_state = new_prs;
+ /*
+ * Make sure effective_xcpus is properly set for a valid
+ * partition root.
+ */
+ if ((new_prs > 0) && cpumask_empty(cp->exclusive_cpus))
+ cpumask_and(cp->effective_xcpus,
+ cp->cpus_allowed, parent->effective_xcpus);
+ else if (new_prs < 0)
+ reset_partition_data(cp);
spin_unlock_irq(&callback_lock);
notify_partition_change(cp, old_prs);
@@ -1673,7 +2229,21 @@ update_parent_subparts:
WARN_ON(!is_in_v2_mode() &&
!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
- update_tasks_cpumask(cp, tmp->new_cpus);
+ update_tasks_cpumask(cp, cp->effective_cpus);
+
+ /*
+ * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE
+ * from parent if current cpuset isn't a valid partition root
+ * and their load balance states differ.
+ */
+ if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+ !is_partition_valid(cp) &&
+ (is_sched_load_balance(parent) != is_sched_load_balance(cp))) {
+ if (is_sched_load_balance(parent))
+ set_bit(CS_SCHED_LOAD_BALANCE, &cp->flags);
+ else
+ clear_bit(CS_SCHED_LOAD_BALANCE, &cp->flags);
+ }
/*
* On legacy hierarchy, if the effective cpumask of any non-
@@ -1692,7 +2262,7 @@ update_parent_subparts:
}
rcu_read_unlock();
- if (need_rebuild_sched_domains)
+ if (need_rebuild_sched_domains && !(flags & HIER_NO_SD_REBUILD))
rebuild_sched_domains_locked();
}
@@ -1712,23 +2282,35 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
/*
* Check all its siblings and call update_cpumasks_hier()
- * if their use_parent_ecpus flag is set in order for them
- * to use the right effective_cpus value.
+ * if their effective_cpus will need to be changed.
+ *
+ * With the addition of effective_xcpus which is a subset of
+ * cpus_allowed. It is possible a change in parent's effective_cpus
+ * due to a change in a child partition's effective_xcpus will impact
+ * its siblings even if they do not inherit parent's effective_cpus
+ * directly.
*
* The update_cpumasks_hier() function may sleep. So we have to
- * release the RCU read lock before calling it.
+ * release the RCU read lock before calling it. HIER_NO_SD_REBUILD
+ * flag is used to suppress rebuild of sched domains as the callers
+ * will take care of that.
*/
rcu_read_lock();
cpuset_for_each_child(sibling, pos_css, parent) {
if (sibling == cs)
continue;
- if (!sibling->use_parent_ecpus)
- continue;
+ if (!sibling->use_parent_ecpus &&
+ !is_partition_valid(sibling)) {
+ compute_effective_cpumask(tmp->new_cpus, sibling,
+ parent);
+ if (cpumask_equal(tmp->new_cpus, sibling->effective_cpus))
+ continue;
+ }
if (!css_tryget_online(&sibling->css))
continue;
rcu_read_unlock();
- update_cpumasks_hier(sibling, tmp, false);
+ update_cpumasks_hier(sibling, tmp, HIER_NO_SD_REBUILD);
rcu_read_lock();
css_put(&sibling->css);
}
@@ -1746,7 +2328,10 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
{
int retval;
struct tmpmasks tmp;
+ struct cpuset *parent = parent_cs(cs);
bool invalidate = false;
+ int hier_flags = 0;
+ int old_prs = cs->partition_root_state;
/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
if (cs == &top_cpuset)
@@ -1760,6 +2345,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
*/
if (!*buf) {
cpumask_clear(trialcs->cpus_allowed);
+ cpumask_clear(trialcs->effective_xcpus);
} else {
retval = cpulist_parse(buf, trialcs->cpus_allowed);
if (retval < 0)
@@ -1768,30 +2354,50 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (!cpumask_subset(trialcs->cpus_allowed,
top_cpuset.cpus_allowed))
return -EINVAL;
+
+ /*
+ * When exclusive_cpus isn't explicitly set, it is constrainted
+ * by cpus_allowed and parent's effective_xcpus. Otherwise,
+ * trialcs->effective_xcpus is used as a temporary cpumask
+ * for checking validity of the partition root.
+ */
+ if (!cpumask_empty(trialcs->exclusive_cpus) || is_partition_valid(cs))
+ compute_effective_exclusive_cpumask(trialcs, NULL);
}
/* Nothing to do if the cpus didn't change */
if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
return 0;
-#ifdef CONFIG_CPUMASK_OFFSTACK
+ if (alloc_cpumasks(NULL, &tmp))
+ return -ENOMEM;
+
+ if (old_prs) {
+ if (is_partition_valid(cs) &&
+ cpumask_empty(trialcs->effective_xcpus)) {
+ invalidate = true;
+ cs->prs_err = PERR_INVCPUS;
+ } else if (prstate_housekeeping_conflict(old_prs, trialcs->effective_xcpus)) {
+ invalidate = true;
+ cs->prs_err = PERR_HKEEPING;
+ } else if (tasks_nocpu_error(parent, cs, trialcs->effective_xcpus)) {
+ invalidate = true;
+ cs->prs_err = PERR_NOCPUS;
+ }
+ }
+
/*
- * Use the cpumasks in trialcs for tmpmasks when they are pointers
- * to allocated cpumasks.
- *
- * Note that update_parent_subparts_cpumask() uses only addmask &
- * delmask, but not new_cpus.
+ * Check all the descendants in update_cpumasks_hier() if
+ * effective_xcpus is to be changed.
*/
- tmp.addmask = trialcs->subparts_cpus;
- tmp.delmask = trialcs->effective_cpus;
- tmp.new_cpus = NULL;
-#endif
+ if (!cpumask_equal(cs->effective_xcpus, trialcs->effective_xcpus))
+ hier_flags = HIER_CHECKALL;
retval = validate_change(cs, trialcs);
if ((retval == -EINVAL) && cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
- struct cpuset *cp, *parent;
struct cgroup_subsys_state *css;
+ struct cpuset *cp;
/*
* The -EINVAL error code indicates that partition sibling
@@ -1802,71 +2408,169 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
*/
invalidate = true;
rcu_read_lock();
- parent = parent_cs(cs);
- cpuset_for_each_child(cp, css, parent)
+ cpuset_for_each_child(cp, css, parent) {
+ struct cpumask *xcpus = fetch_xcpus(trialcs);
+
if (is_partition_valid(cp) &&
- cpumask_intersects(trialcs->cpus_allowed, cp->cpus_allowed)) {
+ cpumask_intersects(xcpus, cp->effective_xcpus)) {
rcu_read_unlock();
- update_parent_subparts_cpumask(cp, partcmd_invalidate, NULL, &tmp);
+ update_parent_effective_cpumask(cp, partcmd_invalidate, NULL, &tmp);
rcu_read_lock();
}
+ }
rcu_read_unlock();
retval = 0;
}
+
if (retval < 0)
- return retval;
+ goto out_free;
+
+ if (is_partition_valid(cs) ||
+ (is_partition_invalid(cs) && !invalidate)) {
+ struct cpumask *xcpus = trialcs->effective_xcpus;
- if (cs->partition_root_state) {
- if (invalidate)
- update_parent_subparts_cpumask(cs, partcmd_invalidate,
- NULL, &tmp);
+ if (cpumask_empty(xcpus) && is_partition_invalid(cs))
+ xcpus = trialcs->cpus_allowed;
+
+ /*
+ * Call remote_cpus_update() to handle valid remote partition
+ */
+ if (is_remote_partition(cs))
+ remote_cpus_update(cs, xcpus, &tmp);
+ else if (invalidate)
+ update_parent_effective_cpumask(cs, partcmd_invalidate,
+ NULL, &tmp);
else
- update_parent_subparts_cpumask(cs, partcmd_update,
- trialcs->cpus_allowed, &tmp);
+ update_parent_effective_cpumask(cs, partcmd_update,
+ xcpus, &tmp);
+ } else if (!cpumask_empty(cs->exclusive_cpus)) {
+ /*
+ * Use trialcs->effective_cpus as a temp cpumask
+ */
+ remote_partition_check(cs, trialcs->effective_xcpus,
+ trialcs->effective_cpus, &tmp);
}
- compute_effective_cpumask(trialcs->effective_cpus, trialcs,
- parent_cs(cs));
spin_lock_irq(&callback_lock);
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
+ cpumask_copy(cs->effective_xcpus, trialcs->effective_xcpus);
+ if ((old_prs > 0) && !is_partition_valid(cs))
+ reset_partition_data(cs);
+ spin_unlock_irq(&callback_lock);
+
+ /* effective_cpus/effective_xcpus will be updated here */
+ update_cpumasks_hier(cs, &tmp, hier_flags);
+
+ /* Update CS_SCHED_LOAD_BALANCE and/or sched_domains, if necessary */
+ if (cs->partition_root_state)
+ update_partition_sd_lb(cs, old_prs);
+out_free:
+ free_cpumasks(NULL, &tmp);
+ return 0;
+}
+
+/**
+ * update_exclusive_cpumask - update the exclusive_cpus mask of a cpuset
+ * @cs: the cpuset to consider
+ * @trialcs: trial cpuset
+ * @buf: buffer of cpu numbers written to this cpuset
+ *
+ * The tasks' cpumask will be updated if cs is a valid partition root.
+ */
+static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
+ const char *buf)
+{
+ int retval;
+ struct tmpmasks tmp;
+ struct cpuset *parent = parent_cs(cs);
+ bool invalidate = false;
+ int hier_flags = 0;
+ int old_prs = cs->partition_root_state;
+
+ if (!*buf) {
+ cpumask_clear(trialcs->exclusive_cpus);
+ cpumask_clear(trialcs->effective_xcpus);
+ } else {
+ retval = cpulist_parse(buf, trialcs->exclusive_cpus);
+ if (retval < 0)
+ return retval;
+ if (!is_cpu_exclusive(cs))
+ set_bit(CS_CPU_EXCLUSIVE, &trialcs->flags);
+ }
+
+ /* Nothing to do if the CPUs didn't change */
+ if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus))
+ return 0;
+
+ if (alloc_cpumasks(NULL, &tmp))
+ return -ENOMEM;
+
+ if (*buf)
+ compute_effective_exclusive_cpumask(trialcs, NULL);
/*
- * Make sure that subparts_cpus, if not empty, is a subset of
- * cpus_allowed. Clear subparts_cpus if partition not valid or
- * empty effective cpus with tasks.
+ * Check all the descendants in update_cpumasks_hier() if
+ * effective_xcpus is to be changed.
*/
- if (cs->nr_subparts_cpus) {
- if (!is_partition_valid(cs) ||
- (cpumask_subset(trialcs->effective_cpus, cs->subparts_cpus) &&
- partition_is_populated(cs, NULL))) {
- cs->nr_subparts_cpus = 0;
- cpumask_clear(cs->subparts_cpus);
+ if (!cpumask_equal(cs->effective_xcpus, trialcs->effective_xcpus))
+ hier_flags = HIER_CHECKALL;
+
+ retval = validate_change(cs, trialcs);
+ if (retval)
+ return retval;
+
+ if (old_prs) {
+ if (cpumask_empty(trialcs->effective_xcpus)) {
+ invalidate = true;
+ cs->prs_err = PERR_INVCPUS;
+ } else if (prstate_housekeeping_conflict(old_prs, trialcs->effective_xcpus)) {
+ invalidate = true;
+ cs->prs_err = PERR_HKEEPING;
+ } else if (tasks_nocpu_error(parent, cs, trialcs->effective_xcpus)) {
+ invalidate = true;
+ cs->prs_err = PERR_NOCPUS;
+ }
+
+ if (is_remote_partition(cs)) {
+ if (invalidate)
+ remote_partition_disable(cs, &tmp);
+ else
+ remote_cpus_update(cs, trialcs->effective_xcpus,
+ &tmp);
+ } else if (invalidate) {
+ update_parent_effective_cpumask(cs, partcmd_invalidate,
+ NULL, &tmp);
} else {
- cpumask_and(cs->subparts_cpus, cs->subparts_cpus,
- cs->cpus_allowed);
- cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
+ update_parent_effective_cpumask(cs, partcmd_update,
+ trialcs->effective_xcpus, &tmp);
}
+ } else if (!cpumask_empty(trialcs->exclusive_cpus)) {
+ /*
+ * Use trialcs->effective_cpus as a temp cpumask
+ */
+ remote_partition_check(cs, trialcs->effective_xcpus,
+ trialcs->effective_cpus, &tmp);
}
+ spin_lock_irq(&callback_lock);
+ cpumask_copy(cs->exclusive_cpus, trialcs->exclusive_cpus);
+ cpumask_copy(cs->effective_xcpus, trialcs->effective_xcpus);
+ if ((old_prs > 0) && !is_partition_valid(cs))
+ reset_partition_data(cs);
spin_unlock_irq(&callback_lock);
-#ifdef CONFIG_CPUMASK_OFFSTACK
- /* Now trialcs->cpus_allowed is available */
- tmp.new_cpus = trialcs->cpus_allowed;
-#endif
-
- /* effective_cpus will be updated here */
- update_cpumasks_hier(cs, &tmp, false);
+ /*
+ * Call update_cpumasks_hier() to update effective_cpus/effective_xcpus
+ * of the subtree when it is a valid partition root or effective_xcpus
+ * is updated.
+ */
+ if (is_partition_valid(cs) || hier_flags)
+ update_cpumasks_hier(cs, &tmp, hier_flags);
- if (cs->partition_root_state) {
- struct cpuset *parent = parent_cs(cs);
+ /* Update CS_SCHED_LOAD_BALANCE and/or sched_domains, if necessary */
+ if (cs->partition_root_state)
+ update_partition_sd_lb(cs, old_prs);
- /*
- * For partition root, update the cpumasks of sibling
- * cpusets if they use parent's effective_cpus.
- */
- if (parent->child_ecpus_count)
- update_sibling_cpumasks(parent, cs, &tmp);
- }
+ free_cpumasks(NULL, &tmp);
return 0;
}
@@ -2242,7 +2946,6 @@ out:
static int update_prstate(struct cpuset *cs, int new_prs)
{
int err = PERR_NONE, old_prs = cs->partition_root_state;
- bool sched_domain_rebuilt = false;
struct cpuset *parent = parent_cs(cs);
struct tmpmasks tmpmask;
@@ -2250,108 +2953,89 @@ static int update_prstate(struct cpuset *cs, int new_prs)
return 0;
/*
- * For a previously invalid partition root, leave it at being
- * invalid if new_prs is not "member".
+ * Treat a previously invalid partition root as if it is a "member".
*/
- if (new_prs && is_prs_invalid(old_prs)) {
- cs->partition_root_state = -new_prs;
- return 0;
- }
+ if (new_prs && is_prs_invalid(old_prs))
+ old_prs = PRS_MEMBER;
if (alloc_cpumasks(NULL, &tmpmask))
return -ENOMEM;
+ /*
+ * Setup effective_xcpus if not properly set yet, it will be cleared
+ * later if partition becomes invalid.
+ */
+ if ((new_prs > 0) && cpumask_empty(cs->exclusive_cpus)) {
+ spin_lock_irq(&callback_lock);
+ cpumask_and(cs->effective_xcpus,
+ cs->cpus_allowed, parent->effective_xcpus);
+ spin_unlock_irq(&callback_lock);
+ }
+
+ err = update_partition_exclusive(cs, new_prs);
+ if (err)
+ goto out;
+
if (!old_prs) {
/*
- * Turning on partition root requires setting the
- * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed
- * cannot be empty.
+ * cpus_allowed cannot be empty.
*/
if (cpumask_empty(cs->cpus_allowed)) {
err = PERR_CPUSEMPTY;
goto out;
}
- err = update_flag(CS_CPU_EXCLUSIVE, cs, 1);
- if (err) {
- err = PERR_NOTEXCL;
- goto out;
- }
-
- err = update_parent_subparts_cpumask(cs, partcmd_enable,
- NULL, &tmpmask);
- if (err) {
- update_flag(CS_CPU_EXCLUSIVE, cs, 0);
- goto out;
- }
-
- if (new_prs == PRS_ISOLATED) {
- /*
- * Disable the load balance flag should not return an
- * error unless the system is running out of memory.
- */
- update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
- sched_domain_rebuilt = true;
- }
+ err = update_parent_effective_cpumask(cs, partcmd_enable,
+ NULL, &tmpmask);
+ /*
+ * If an attempt to become local partition root fails,
+ * try to become a remote partition root instead.
+ */
+ if (err && remote_partition_enable(cs, &tmpmask))
+ err = 0;
} else if (old_prs && new_prs) {
/*
* A change in load balance state only, no change in cpumasks.
*/
- update_flag(CS_SCHED_LOAD_BALANCE, cs, (new_prs != PRS_ISOLATED));
- sched_domain_rebuilt = true;
- goto out; /* Sched domain is rebuilt in update_flag() */
+ ;
} else {
/*
* Switching back to member is always allowed even if it
* disables child partitions.
*/
- update_parent_subparts_cpumask(cs, partcmd_disable, NULL,
- &tmpmask);
+ if (is_remote_partition(cs))
+ remote_partition_disable(cs, &tmpmask);
+ else
+ update_parent_effective_cpumask(cs, partcmd_disable,
+ NULL, &tmpmask);
/*
- * If there are child partitions, they will all become invalid.
+ * Invalidation of child partitions will be done in
+ * update_cpumasks_hier().
*/
- if (unlikely(cs->nr_subparts_cpus)) {
- spin_lock_irq(&callback_lock);
- cs->nr_subparts_cpus = 0;
- cpumask_clear(cs->subparts_cpus);
- compute_effective_cpumask(cs->effective_cpus, cs, parent);
- spin_unlock_irq(&callback_lock);
- }
-
- /* Turning off CS_CPU_EXCLUSIVE will not return error */
- update_flag(CS_CPU_EXCLUSIVE, cs, 0);
-
- if (!is_sched_load_balance(cs)) {
- /* Make sure load balance is on */
- update_flag(CS_SCHED_LOAD_BALANCE, cs, 1);
- sched_domain_rebuilt = true;
- }
}
-
- update_tasks_cpumask(parent, tmpmask.new_cpus);
-
- if (parent->child_ecpus_count)
- update_sibling_cpumasks(parent, cs, &tmpmask);
-
- if (!sched_domain_rebuilt)
- rebuild_sched_domains_locked();
out:
/*
- * Make partition invalid if an error happen
+ * Make partition invalid & disable CS_CPU_EXCLUSIVE if an error
+ * happens.
*/
- if (err)
+ if (err) {
new_prs = -new_prs;
+ update_partition_exclusive(cs, new_prs);
+ }
+
spin_lock_irq(&callback_lock);
cs->partition_root_state = new_prs;
WRITE_ONCE(cs->prs_err, err);
+ if (!is_partition_valid(cs))
+ reset_partition_data(cs);
spin_unlock_irq(&callback_lock);
- /*
- * Update child cpusets, if present.
- * Force update if switching back to member.
- */
- if (!list_empty(&cs->css.children))
- update_cpumasks_hier(cs, &tmpmask, !new_prs);
+
+ /* Force update if switching back to member */
+ update_cpumasks_hier(cs, &tmpmask, !new_prs ? HIER_CHECKALL : 0);
+
+ /* Update sched domains and load balance flag */
+ update_partition_sd_lb(cs, old_prs);
notify_partition_change(cs, old_prs);
free_cpumasks(NULL, &tmpmask);
@@ -2487,6 +3171,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
struct cgroup_subsys_state *css;
struct cpuset *cs, *oldcs;
struct task_struct *task;
+ bool cpus_updated, mems_updated;
int ret;
/* used later by cpuset_attach() */
@@ -2501,13 +3186,25 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
if (ret)
goto out_unlock;
+ cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus);
+ mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems);
+
cgroup_taskset_for_each(task, css, tset) {
ret = task_can_attach(task);
if (ret)
goto out_unlock;
- ret = security_task_setscheduler(task);
- if (ret)
- goto out_unlock;
+
+ /*
+ * Skip rights over task check in v2 when nothing changes,
+ * migration permission derives from hierarchy ownership in
+ * cgroup_procs_write_permission()).
+ */
+ if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
+ (cpus_updated || mems_updated)) {
+ ret = security_task_setscheduler(task);
+ if (ret)
+ goto out_unlock;
+ }
if (dl_task(task)) {
cs->nr_migrate_dl_tasks++;
@@ -2584,7 +3281,7 @@ static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task)
guarantee_online_cpus(task, cpus_attach);
else
cpumask_andnot(cpus_attach, task_cpu_possible_mask(task),
- cs->subparts_cpus);
+ subpartitions_cpus);
/*
* can_attach beforehand should guarantee that this doesn't
* fail. TODO: have a better way to handle failure here
@@ -2687,6 +3384,8 @@ typedef enum {
FILE_EFFECTIVE_CPULIST,
FILE_EFFECTIVE_MEMLIST,
FILE_SUBPARTS_CPULIST,
+ FILE_EXCLUSIVE_CPULIST,
+ FILE_EFFECTIVE_XCPULIST,
FILE_CPU_EXCLUSIVE,
FILE_MEM_EXCLUSIVE,
FILE_MEM_HARDWALL,
@@ -2824,6 +3523,9 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
case FILE_CPULIST:
retval = update_cpumask(cs, trialcs, buf);
break;
+ case FILE_EXCLUSIVE_CPULIST:
+ retval = update_exclusive_cpumask(cs, trialcs, buf);
+ break;
case FILE_MEMLIST:
retval = update_nodemask(cs, trialcs, buf);
break;
@@ -2871,8 +3573,14 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
case FILE_EFFECTIVE_MEMLIST:
seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
break;
+ case FILE_EXCLUSIVE_CPULIST:
+ seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->exclusive_cpus));
+ break;
+ case FILE_EFFECTIVE_XCPULIST:
+ seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_xcpus));
+ break;
case FILE_SUBPARTS_CPULIST:
- seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus));
+ seq_printf(sf, "%*pbl\n", cpumask_pr_args(subpartitions_cpus));
break;
default:
ret = -EINVAL;
@@ -3145,10 +3853,26 @@ static struct cftype dfl_files[] = {
},
{
+ .name = "cpus.exclusive",
+ .seq_show = cpuset_common_seq_show,
+ .write = cpuset_write_resmask,
+ .max_write_len = (100U + 6 * NR_CPUS),
+ .private = FILE_EXCLUSIVE_CPULIST,
+ .flags = CFTYPE_NOT_ON_ROOT,
+ },
+
+ {
+ .name = "cpus.exclusive.effective",
+ .seq_show = cpuset_common_seq_show,
+ .private = FILE_EFFECTIVE_XCPULIST,
+ .flags = CFTYPE_NOT_ON_ROOT,
+ },
+
+ {
.name = "cpus.subpartitions",
.seq_show = cpuset_common_seq_show,
.private = FILE_SUBPARTS_CPULIST,
- .flags = CFTYPE_DEBUG,
+ .flags = CFTYPE_ONLY_ON_ROOT | CFTYPE_DEBUG,
},
{ } /* terminate */
@@ -3186,6 +3910,7 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
nodes_clear(cs->effective_mems);
fmeter_init(&cs->fmeter);
cs->relax_domain_level = -1;
+ INIT_LIST_HEAD(&cs->remote_sibling);
/* Set CS_MEMORY_MIGRATE for default hierarchy */
if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
@@ -3221,7 +3946,20 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
cs->effective_mems = parent->effective_mems;
cs->use_parent_ecpus = true;
parent->child_ecpus_count++;
+ /*
+ * Clear CS_SCHED_LOAD_BALANCE if parent is isolated
+ */
+ if (!is_sched_load_balance(parent))
+ clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
}
+
+ /*
+ * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated
+ */
+ if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+ !is_sched_load_balance(parent))
+ clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
+
spin_unlock_irq(&callback_lock);
if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
@@ -3314,6 +4052,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
if (is_in_v2_mode()) {
cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
+ cpumask_copy(top_cpuset.effective_xcpus, cpu_possible_mask);
top_cpuset.mems_allowed = node_possible_map;
} else {
cpumask_copy(top_cpuset.cpus_allowed,
@@ -3452,16 +4191,21 @@ int __init cpuset_init(void)
{
BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL));
BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL));
- BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_xcpus, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL));
+ BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL));
cpumask_setall(top_cpuset.cpus_allowed);
nodes_setall(top_cpuset.mems_allowed);
cpumask_setall(top_cpuset.effective_cpus);
+ cpumask_setall(top_cpuset.effective_xcpus);
+ cpumask_setall(top_cpuset.exclusive_cpus);
nodes_setall(top_cpuset.effective_mems);
fmeter_init(&top_cpuset.fmeter);
set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
top_cpuset.relax_domain_level = -1;
+ INIT_LIST_HEAD(&remote_children);
BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL));
@@ -3521,17 +4265,16 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
is_empty = cpumask_empty(cs->cpus_allowed) ||
nodes_empty(cs->mems_allowed);
- mutex_unlock(&cpuset_mutex);
-
/*
* Move tasks to the nearest ancestor with execution resources,
* This is full cgroup operation which will also call back into
* cpuset. Should be done outside any lock.
*/
- if (is_empty)
+ if (is_empty) {
+ mutex_unlock(&cpuset_mutex);
remove_tasks_in_empty_cpuset(cs);
-
- mutex_lock(&cpuset_mutex);
+ mutex_lock(&cpuset_mutex);
+ }
}
static void
@@ -3578,6 +4321,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
static nodemask_t new_mems;
bool cpus_updated;
bool mems_updated;
+ bool remote;
struct cpuset *parent;
retry:
wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
@@ -3597,29 +4341,23 @@ retry:
compute_effective_cpumask(&new_cpus, cs, parent);
nodes_and(new_mems, cs->mems_allowed, parent->effective_mems);
- if (cs->nr_subparts_cpus)
- /*
- * Make sure that CPUs allocated to child partitions
- * do not show up in effective_cpus.
- */
- cpumask_andnot(&new_cpus, &new_cpus, cs->subparts_cpus);
-
if (!tmp || !cs->partition_root_state)
goto update_tasks;
/*
- * In the unlikely event that a partition root has empty
- * effective_cpus with tasks, we will have to invalidate child
- * partitions, if present, by setting nr_subparts_cpus to 0 to
- * reclaim their cpus.
+ * Compute effective_cpus for valid partition root, may invalidate
+ * child partition roots if necessary.
*/
- if (cs->nr_subparts_cpus && is_partition_valid(cs) &&
- cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) {
- spin_lock_irq(&callback_lock);
- cs->nr_subparts_cpus = 0;
- cpumask_clear(cs->subparts_cpus);
- spin_unlock_irq(&callback_lock);
+ remote = is_remote_partition(cs);
+ if (remote || (is_partition_valid(cs) && is_partition_valid(parent)))
+ compute_partition_effective_cpumask(cs, &new_cpus);
+
+ if (remote && cpumask_empty(&new_cpus) &&
+ partition_is_populated(cs, NULL)) {
+ remote_partition_disable(cs, tmp);
compute_effective_cpumask(&new_cpus, cs, parent);
+ remote = false;
+ cpuset_force_rebuild();
}
/*
@@ -3629,44 +4367,22 @@ retry:
* 2) parent is invalid or doesn't grant any cpus to child
* partitions.
*/
- if (is_partition_valid(cs) && (!parent->nr_subparts_cpus ||
- (cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)))) {
- int old_prs, parent_prs;
-
- update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp);
- if (cs->nr_subparts_cpus) {
- spin_lock_irq(&callback_lock);
- cs->nr_subparts_cpus = 0;
- cpumask_clear(cs->subparts_cpus);
- spin_unlock_irq(&callback_lock);
- compute_effective_cpumask(&new_cpus, cs, parent);
- }
-
- old_prs = cs->partition_root_state;
- parent_prs = parent->partition_root_state;
- if (is_partition_valid(cs)) {
- spin_lock_irq(&callback_lock);
- make_partition_invalid(cs);
- spin_unlock_irq(&callback_lock);
- if (is_prs_invalid(parent_prs))
- WRITE_ONCE(cs->prs_err, PERR_INVPARENT);
- else if (!parent_prs)
- WRITE_ONCE(cs->prs_err, PERR_NOTPART);
- else
- WRITE_ONCE(cs->prs_err, PERR_HOTPLUG);
- notify_partition_change(cs, old_prs);
- }
+ if (is_local_partition(cs) && (!is_partition_valid(parent) ||
+ tasks_nocpu_error(parent, cs, &new_cpus))) {
+ update_parent_effective_cpumask(cs, partcmd_invalidate, NULL, tmp);
+ compute_effective_cpumask(&new_cpus, cs, parent);
cpuset_force_rebuild();
}
-
/*
* On the other hand, an invalid partition root may be transitioned
* back to a regular one.
*/
else if (is_partition_valid(parent) && is_partition_invalid(cs)) {
- update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp);
- if (is_partition_valid(cs))
+ update_parent_effective_cpumask(cs, partcmd_update, NULL, tmp);
+ if (is_partition_valid(cs)) {
+ compute_partition_effective_cpumask(cs, &new_cpus);
cpuset_force_rebuild();
+ }
}
update_tasks:
@@ -3691,6 +4407,7 @@ unlock:
/**
* cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset
+ * @work: unused
*
* This function is called after either CPU or memory configuration has
* changed and updates cpuset accordingly. The top_cpuset is always
@@ -3723,21 +4440,22 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
new_mems = node_states[N_MEMORY];
/*
- * If subparts_cpus is populated, it is likely that the check below
- * will produce a false positive on cpus_updated when the cpu list
- * isn't changed. It is extra work, but it is better to be safe.
+ * If subpartitions_cpus is populated, it is likely that the check
+ * below will produce a false positive on cpus_updated when the cpu
+ * list isn't changed. It is extra work, but it is better to be safe.
*/
- cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus);
+ cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus) ||
+ !cpumask_empty(subpartitions_cpus);
mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems);
/*
- * In the rare case that hotplug removes all the cpus in subparts_cpus,
- * we assumed that cpus are updated.
+ * In the rare case that hotplug removes all the cpus in
+ * subpartitions_cpus, we assumed that cpus are updated.
*/
- if (!cpus_updated && top_cpuset.nr_subparts_cpus)
+ if (!cpus_updated && top_cpuset.nr_subparts)
cpus_updated = true;
- /* synchronize cpus_allowed to cpu_active_mask */
+ /* For v1, synchronize cpus_allowed to cpu_active_mask */
if (cpus_updated) {
spin_lock_irq(&callback_lock);
if (!on_dfl)
@@ -3745,17 +4463,16 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
/*
* Make sure that CPUs allocated to child partitions
* do not show up in effective_cpus. If no CPU is left,
- * we clear the subparts_cpus & let the child partitions
+ * we clear the subpartitions_cpus & let the child partitions
* fight for the CPUs again.
*/
- if (top_cpuset.nr_subparts_cpus) {
- if (cpumask_subset(&new_cpus,
- top_cpuset.subparts_cpus)) {
- top_cpuset.nr_subparts_cpus = 0;
- cpumask_clear(top_cpuset.subparts_cpus);
+ if (!cpumask_empty(subpartitions_cpus)) {
+ if (cpumask_subset(&new_cpus, subpartitions_cpus)) {
+ top_cpuset.nr_subparts = 0;
+ cpumask_clear(subpartitions_cpus);
} else {
cpumask_andnot(&new_cpus, &new_cpus,
- top_cpuset.subparts_cpus);
+ subpartitions_cpus);
}
}
cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
@@ -3887,7 +4604,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
* We first exclude cpus allocated to partitions. If there is no
* allowable online cpu left, we fall back to all possible cpus.
*/
- cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus);
+ cpumask_andnot(pmask, possible_mask, subpartitions_cpus);
if (!cpumask_intersects(pmask, cpu_online_mask))
cpumask_copy(pmask, possible_mask);
}
@@ -4073,6 +4790,7 @@ bool cpuset_node_allowed(int node, gfp_t gfp_mask)
/**
* cpuset_spread_node() - On which node to begin search for a page
+ * @rotor: round robin rotor
*
* If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for
* tasks in a cpuset with is_spread_page or is_spread_slab set),
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 122dacb3a443..66d1708042a7 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -66,9 +66,15 @@ static struct freezer *parent_freezer(struct freezer *freezer)
bool cgroup_freezing(struct task_struct *task)
{
bool ret;
+ unsigned int state;
rcu_read_lock();
- ret = task_freezer(task)->state & CGROUP_FREEZING;
+ /* Check if the cgroup is still FREEZING, but not FROZEN. The extra
+ * !FROZEN check is required, because the FREEZING bit is not cleared
+ * when the state FROZEN is reached.
+ */
+ state = task_freezer(task)->state;
+ ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN);
rcu_read_unlock();
return ret;
diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c
index ae2f4dd47508..79a3717a5803 100644
--- a/kernel/cgroup/misc.c
+++ b/kernel/cgroup/misc.c
@@ -14,7 +14,7 @@
#include <linux/misc_cgroup.h>
#define MAX_STR "max"
-#define MAX_NUM ULONG_MAX
+#define MAX_NUM U64_MAX
/* Miscellaneous res name, keep it in sync with enum misc_res_type */
static const char *const misc_res_name[] = {
@@ -37,7 +37,7 @@ static struct misc_cg root_cg;
* more than the actual capacity. We are using Limits resource distribution
* model of cgroup for miscellaneous controller.
*/
-static unsigned long misc_res_capacity[MISC_CG_RES_TYPES];
+static u64 misc_res_capacity[MISC_CG_RES_TYPES];
/**
* parent_misc() - Get the parent of the passed misc cgroup.
@@ -74,10 +74,10 @@ static inline bool valid_type(enum misc_res_type type)
* Context: Any context.
* Return: Current total usage of the resource.
*/
-unsigned long misc_cg_res_total_usage(enum misc_res_type type)
+u64 misc_cg_res_total_usage(enum misc_res_type type)
{
if (valid_type(type))
- return atomic_long_read(&root_cg.res[type].usage);
+ return atomic64_read(&root_cg.res[type].usage);
return 0;
}
@@ -95,7 +95,7 @@ EXPORT_SYMBOL_GPL(misc_cg_res_total_usage);
* * %0 - Successfully registered the capacity.
* * %-EINVAL - If @type is invalid.
*/
-int misc_cg_set_capacity(enum misc_res_type type, unsigned long capacity)
+int misc_cg_set_capacity(enum misc_res_type type, u64 capacity)
{
if (!valid_type(type))
return -EINVAL;
@@ -114,9 +114,9 @@ EXPORT_SYMBOL_GPL(misc_cg_set_capacity);
* Context: Any context.
*/
static void misc_cg_cancel_charge(enum misc_res_type type, struct misc_cg *cg,
- unsigned long amount)
+ u64 amount)
{
- WARN_ONCE(atomic_long_add_negative(-amount, &cg->res[type].usage),
+ WARN_ONCE(atomic64_add_negative(-amount, &cg->res[type].usage),
"misc cgroup resource %s became less than 0",
misc_res_name[type]);
}
@@ -137,13 +137,12 @@ static void misc_cg_cancel_charge(enum misc_res_type type, struct misc_cg *cg,
* * -EBUSY - If max limit will be crossed or total usage will be more than the
* capacity.
*/
-int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg,
- unsigned long amount)
+int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, u64 amount)
{
struct misc_cg *i, *j;
int ret;
struct misc_res *res;
- int new_usage;
+ u64 new_usage;
if (!(valid_type(type) && cg && READ_ONCE(misc_res_capacity[type])))
return -EINVAL;
@@ -154,7 +153,7 @@ int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg,
for (i = cg; i; i = parent_misc(i)) {
res = &i->res[type];
- new_usage = atomic_long_add_return(amount, &res->usage);
+ new_usage = atomic64_add_return(amount, &res->usage);
if (new_usage > READ_ONCE(res->max) ||
new_usage > READ_ONCE(misc_res_capacity[type])) {
ret = -EBUSY;
@@ -165,7 +164,7 @@ int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg,
err_charge:
for (j = i; j; j = parent_misc(j)) {
- atomic_long_inc(&j->res[type].events);
+ atomic64_inc(&j->res[type].events);
cgroup_file_notify(&j->events_file);
}
@@ -184,8 +183,7 @@ EXPORT_SYMBOL_GPL(misc_cg_try_charge);
*
* Context: Any context.
*/
-void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg,
- unsigned long amount)
+void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg, u64 amount)
{
struct misc_cg *i;
@@ -209,7 +207,7 @@ static int misc_cg_max_show(struct seq_file *sf, void *v)
{
int i;
struct misc_cg *cg = css_misc(seq_css(sf));
- unsigned long max;
+ u64 max;
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
if (READ_ONCE(misc_res_capacity[i])) {
@@ -217,7 +215,7 @@ static int misc_cg_max_show(struct seq_file *sf, void *v)
if (max == MAX_NUM)
seq_printf(sf, "%s max\n", misc_res_name[i]);
else
- seq_printf(sf, "%s %lu\n", misc_res_name[i],
+ seq_printf(sf, "%s %llu\n", misc_res_name[i],
max);
}
}
@@ -241,13 +239,13 @@ static int misc_cg_max_show(struct seq_file *sf, void *v)
* Return:
* * >= 0 - Number of bytes processed in the input.
* * -EINVAL - If buf is not valid.
- * * -ERANGE - If number is bigger than the unsigned long capacity.
+ * * -ERANGE - If number is bigger than the u64 capacity.
*/
static ssize_t misc_cg_max_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct misc_cg *cg;
- unsigned long max;
+ u64 max;
int ret = 0, i;
enum misc_res_type type = MISC_CG_RES_TYPES;
char *token;
@@ -271,7 +269,7 @@ static ssize_t misc_cg_max_write(struct kernfs_open_file *of, char *buf,
if (!strcmp(MAX_STR, buf)) {
max = MAX_NUM;
} else {
- ret = kstrtoul(buf, 0, &max);
+ ret = kstrtou64(buf, 0, &max);
if (ret)
return ret;
}
@@ -297,13 +295,13 @@ static ssize_t misc_cg_max_write(struct kernfs_open_file *of, char *buf,
static int misc_cg_current_show(struct seq_file *sf, void *v)
{
int i;
- unsigned long usage;
+ u64 usage;
struct misc_cg *cg = css_misc(seq_css(sf));
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
- usage = atomic_long_read(&cg->res[i].usage);
+ usage = atomic64_read(&cg->res[i].usage);
if (READ_ONCE(misc_res_capacity[i]) || usage)
- seq_printf(sf, "%s %lu\n", misc_res_name[i], usage);
+ seq_printf(sf, "%s %llu\n", misc_res_name[i], usage);
}
return 0;
@@ -322,12 +320,12 @@ static int misc_cg_current_show(struct seq_file *sf, void *v)
static int misc_cg_capacity_show(struct seq_file *sf, void *v)
{
int i;
- unsigned long cap;
+ u64 cap;
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
cap = READ_ONCE(misc_res_capacity[i]);
if (cap)
- seq_printf(sf, "%s %lu\n", misc_res_name[i], cap);
+ seq_printf(sf, "%s %llu\n", misc_res_name[i], cap);
}
return 0;
@@ -336,12 +334,13 @@ static int misc_cg_capacity_show(struct seq_file *sf, void *v)
static int misc_events_show(struct seq_file *sf, void *v)
{
struct misc_cg *cg = css_misc(seq_css(sf));
- unsigned long events, i;
+ u64 events;
+ int i;
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
- events = atomic_long_read(&cg->res[i].events);
+ events = atomic64_read(&cg->res[i].events);
if (READ_ONCE(misc_res_capacity[i]) || events)
- seq_printf(sf, "%s.max %lu\n", misc_res_name[i], events);
+ seq_printf(sf, "%s.max %llu\n", misc_res_name[i], events);
}
return 0;
}
@@ -397,7 +396,7 @@ misc_cg_alloc(struct cgroup_subsys_state *parent_css)
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
WRITE_ONCE(cg->res[i].max, MAX_NUM);
- atomic_long_set(&cg->res[i].usage, 0);
+ atomic64_set(&cg->res[i].usage, 0);
}
return &cg->css;
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index 0d5c29879a50..144a464e45c6 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -149,9 +149,3 @@ const struct proc_ns_operations cgroupns_operations = {
.install = cgroupns_install,
.owner = cgroupns_owner,
};
-
-static __init int cgroup_namespaces_init(void)
-{
- return 0;
-}
-subsys_initcall(cgroup_namespaces_init);
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 2542c21b6b6d..c0adb7254b45 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -156,19 +156,16 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
* optimize away the callsite. Therefore, __weak is needed to ensure that the
* call is still emitted, by telling the compiler that we don't know what the
* function might eventually be.
- *
- * __diag_* below are needed to dismiss the missing prototype warning.
*/
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "kfuncs which will be used in BPF programs");
+
+__bpf_hook_start();
__weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
struct cgroup *parent, int cpu)
{
}
-__diag_pop();
+__bpf_hook_end();
/* see cgroup_rstat_flush() */
static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
@@ -344,6 +341,7 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
{
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
struct cgroup *parent = cgroup_parent(cgrp);
+ struct cgroup_rstat_cpu *prstatc;
struct cgroup_base_stat delta;
unsigned seq;
@@ -357,17 +355,24 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
delta = rstatc->bstat;
} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
- /* propagate percpu delta to global */
+ /* propagate per-cpu delta to cgroup and per-cpu global statistics */
cgroup_base_stat_sub(&delta, &rstatc->last_bstat);
cgroup_base_stat_add(&cgrp->bstat, &delta);
cgroup_base_stat_add(&rstatc->last_bstat, &delta);
+ cgroup_base_stat_add(&rstatc->subtree_bstat, &delta);
- /* propagate global delta to parent (unless that's root) */
+ /* propagate cgroup and per-cpu global delta to parent (unless that's root) */
if (cgroup_parent(parent)) {
delta = cgrp->bstat;
cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
cgroup_base_stat_add(&parent->bstat, &delta);
cgroup_base_stat_add(&cgrp->last_bstat, &delta);
+
+ delta = rstatc->subtree_bstat;
+ prstatc = cgroup_rstat_cpu(parent, cpu);
+ cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat);
+ cgroup_base_stat_add(&prstatc->subtree_bstat, &delta);
+ cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta);
}
}
diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config
index e8db8d938661..4722b998a324 100644
--- a/kernel/configs/debug.config
+++ b/kernel/configs/debug.config
@@ -1,3 +1,5 @@
+# Help: Debugging for CI systems and finding regressions
+#
# The config is based on running daily CI for enterprise Linux distros to
# seek regressions on linux-next builds on different bare-metal and virtual
# platforms. It can be used for example,
diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config
new file mode 100644
index 000000000000..95a400f042b1
--- /dev/null
+++ b/kernel/configs/hardening.config
@@ -0,0 +1,98 @@
+# Help: Basic kernel hardening options
+#
+# These are considered the basic kernel hardening, self-protection, and
+# attack surface reduction options. They are expected to have low (or
+# no) performance impact on most workloads, and have a reasonable level
+# of legacy API removals.
+
+# Make sure reporting of various hardening actions is possible.
+CONFIG_BUG=y
+
+# Basic kernel memory permission enforcement.
+CONFIG_STRICT_KERNEL_RWX=y
+CONFIG_STRICT_MODULE_RWX=y
+CONFIG_VMAP_STACK=y
+
+# Kernel image and memory ASLR.
+CONFIG_RANDOMIZE_BASE=y
+CONFIG_RANDOMIZE_MEMORY=y
+
+# Randomize allocator freelists, harden metadata.
+CONFIG_SLAB_FREELIST_RANDOM=y
+CONFIG_SLAB_FREELIST_HARDENED=y
+CONFIG_SHUFFLE_PAGE_ALLOCATOR=y
+CONFIG_RANDOM_KMALLOC_CACHES=y
+
+# Randomize kernel stack offset on syscall entry.
+CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT=y
+
+# Basic stack frame overflow protection.
+CONFIG_STACKPROTECTOR=y
+CONFIG_STACKPROTECTOR_STRONG=y
+
+# Basic buffer length bounds checking.
+CONFIG_HARDENED_USERCOPY=y
+CONFIG_FORTIFY_SOURCE=y
+
+# Basic array index bounds checking.
+CONFIG_UBSAN=y
+CONFIG_UBSAN_TRAP=y
+CONFIG_UBSAN_BOUNDS=y
+# CONFIG_UBSAN_SHIFT is not set
+# CONFIG_UBSAN_DIV_ZERO
+# CONFIG_UBSAN_UNREACHABLE
+# CONFIG_UBSAN_BOOL
+# CONFIG_UBSAN_ENUM
+# CONFIG_UBSAN_ALIGNMENT
+CONFIG_UBSAN_SANITIZE_ALL=y
+
+# Linked list integrity checking.
+CONFIG_LIST_HARDENED=y
+
+# Initialize all heap variables to zero on allocation.
+CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y
+
+# Initialize all stack variables to zero on function entry.
+CONFIG_INIT_STACK_ALL_ZERO=y
+
+# Wipe RAM at reboot via EFI. For more details, see:
+# https://trustedcomputinggroup.org/resource/pc-client-work-group-platform-reset-attack-mitigation-specification/
+# https://bugzilla.redhat.com/show_bug.cgi?id=1532058
+CONFIG_RESET_ATTACK_MITIGATION=y
+
+# Disable DMA between EFI hand-off and the kernel's IOMMU setup.
+CONFIG_EFI_DISABLE_PCI_DMA=y
+
+# Force IOMMU TLB invalidation so devices will never be able to access stale
+# data content.
+CONFIG_IOMMU_SUPPORT=y
+CONFIG_IOMMU_DEFAULT_DMA_STRICT=y
+
+# Do not allow direct physical memory access to non-device memory.
+CONFIG_STRICT_DEVMEM=y
+CONFIG_IO_STRICT_DEVMEM=y
+
+# Provide userspace with seccomp BPF API for syscall attack surface reduction.
+CONFIG_SECCOMP=y
+CONFIG_SECCOMP_FILTER=y
+
+# Provides some protections against SYN flooding.
+CONFIG_SYN_COOKIES=y
+
+# Attack surface reduction: do not autoload TTY line disciplines.
+# CONFIG_LDISC_AUTOLOAD is not set
+
+# Dangerous; enabling this disables userspace brk ASLR.
+# CONFIG_COMPAT_BRK is not set
+
+# Dangerous; exposes kernel text image layout.
+# CONFIG_PROC_KCORE is not set
+
+# Dangerous; enabling this disables userspace VDSO ASLR.
+# CONFIG_COMPAT_VDSO is not set
+
+# Attack surface reduction: Use the modern PTY interface (devpts) only.
+# CONFIG_LEGACY_PTYS is not set
+
+# Attack surface reduction: Use only modesetting video drivers.
+# CONFIG_DRM_LEGACY is not set
diff --git a/kernel/configs/kvm_guest.config b/kernel/configs/kvm_guest.config
index 208481d91090..d0877063d925 100644
--- a/kernel/configs/kvm_guest.config
+++ b/kernel/configs/kvm_guest.config
@@ -1,3 +1,4 @@
+# Help: Bootable as a KVM guest
CONFIG_NET=y
CONFIG_NET_CORE=y
CONFIG_NETDEVICES=y
diff --git a/kernel/configs/nopm.config b/kernel/configs/nopm.config
index 81ff07863576..ebfdc3d8aa9a 100644
--- a/kernel/configs/nopm.config
+++ b/kernel/configs/nopm.config
@@ -1,3 +1,5 @@
+# Help: Disable Power Management
+
CONFIG_PM=n
CONFIG_SUSPEND=n
CONFIG_HIBERNATION=n
diff --git a/kernel/configs/rust.config b/kernel/configs/rust.config
index 38a7c5362c9c..2c6e001a7284 100644
--- a/kernel/configs/rust.config
+++ b/kernel/configs/rust.config
@@ -1 +1,2 @@
+# Help: Enable Rust
CONFIG_RUST=y
diff --git a/kernel/configs/tiny-base.config b/kernel/configs/tiny-base.config
index 2f0e6bf6db2c..ffb9dcafca26 100644
--- a/kernel/configs/tiny-base.config
+++ b/kernel/configs/tiny-base.config
@@ -1 +1 @@
-CONFIG_EMBEDDED=y
+CONFIG_EXPERT=y
diff --git a/kernel/configs/x86_debug.config b/kernel/configs/x86_debug.config
index 6fac5b405334..35f48671b8d5 100644
--- a/kernel/configs/x86_debug.config
+++ b/kernel/configs/x86_debug.config
@@ -1,3 +1,4 @@
+# Help: Debugging options for tip tree testing
CONFIG_X86_DEBUG_FPU=y
CONFIG_LOCK_STAT=y
CONFIG_DEBUG_VM=y
diff --git a/kernel/configs/xen.config b/kernel/configs/xen.config
index 436f806aa1ed..6878b9a49be8 100644
--- a/kernel/configs/xen.config
+++ b/kernel/configs/xen.config
@@ -1,3 +1,5 @@
+# Help: Bootable as a Xen guest
+#
# global stuff - these enable us to allow some
# of the not so generic stuff below for xen
CONFIG_PARAVIRT=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 88a7ede322bd..a86972a91991 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -592,7 +592,10 @@ static void lockdep_release_cpus_lock(void)
void __weak arch_smt_update(void) { }
#ifdef CONFIG_HOTPLUG_SMT
+
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+static unsigned int cpu_smt_max_threads __ro_after_init;
+unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX;
void __init cpu_smt_disable(bool force)
{
@@ -606,16 +609,33 @@ void __init cpu_smt_disable(bool force)
pr_info("SMT: disabled\n");
cpu_smt_control = CPU_SMT_DISABLED;
}
+ cpu_smt_num_threads = 1;
}
/*
* The decision whether SMT is supported can only be done after the full
* CPU identification. Called from architecture code.
*/
-void __init cpu_smt_check_topology(void)
+void __init cpu_smt_set_num_threads(unsigned int num_threads,
+ unsigned int max_threads)
{
- if (!topology_smt_supported())
+ WARN_ON(!num_threads || (num_threads > max_threads));
+
+ if (max_threads == 1)
cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+
+ cpu_smt_max_threads = max_threads;
+
+ /*
+ * If SMT has been disabled via the kernel command line or SMT is
+ * not supported, set cpu_smt_num_threads to 1 for consistency.
+ * If enabled, take the architecture requested number of threads
+ * to bring up into account.
+ */
+ if (cpu_smt_control != CPU_SMT_ENABLED)
+ cpu_smt_num_threads = 1;
+ else if (num_threads < cpu_smt_num_threads)
+ cpu_smt_num_threads = num_threads;
}
static int __init smt_cmdline_disable(char *str)
@@ -625,9 +645,31 @@ static int __init smt_cmdline_disable(char *str)
}
early_param("nosmt", smt_cmdline_disable);
-static inline bool cpu_smt_allowed(unsigned int cpu)
+/*
+ * For Archicture supporting partial SMT states check if the thread is allowed.
+ * Otherwise this has already been checked through cpu_smt_max_threads when
+ * setting the SMT level.
+ */
+static inline bool cpu_smt_thread_allowed(unsigned int cpu)
{
- if (cpu_smt_control == CPU_SMT_ENABLED)
+#ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC
+ return topology_smt_thread_allowed(cpu);
+#else
+ return true;
+#endif
+}
+
+static inline bool cpu_bootable(unsigned int cpu)
+{
+ if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu))
+ return true;
+
+ /* All CPUs are bootable if controls are not configured */
+ if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED)
+ return true;
+
+ /* All CPUs are bootable if CPU is not SMT capable */
+ if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
return true;
if (topology_is_primary_thread(cpu))
@@ -642,7 +684,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu)
return !cpumask_test_cpu(cpu, &cpus_booted_once_mask);
}
-/* Returns true if SMT is not supported of forcefully (irreversibly) disabled */
+/* Returns true if SMT is supported and not forcefully (irreversibly) disabled */
bool cpu_smt_possible(void)
{
return cpu_smt_control != CPU_SMT_FORCE_DISABLED &&
@@ -650,22 +692,8 @@ bool cpu_smt_possible(void)
}
EXPORT_SYMBOL_GPL(cpu_smt_possible);
-static inline bool cpuhp_smt_aware(void)
-{
- return topology_smt_supported();
-}
-
-static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
-{
- return cpu_primary_thread_mask;
-}
#else
-static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
-static inline bool cpuhp_smt_aware(void) { return false; }
-static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
-{
- return cpu_present_mask;
-}
+static inline bool cpu_bootable(unsigned int cpu) { return true; }
#endif
static inline enum cpuhp_state
@@ -768,10 +796,10 @@ static int bringup_wait_for_ap_online(unsigned int cpu)
* SMT soft disabling on X86 requires to bring the CPU out of the
* BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The
* CPU marked itself as booted_once in notify_cpu_starting() so the
- * cpu_smt_allowed() check will now return false if this is not the
+ * cpu_bootable() check will now return false if this is not the
* primary sibling.
*/
- if (!cpu_smt_allowed(cpu))
+ if (!cpu_bootable(cpu))
return -ECANCELED;
return 0;
}
@@ -1352,7 +1380,14 @@ static int takedown_cpu(unsigned int cpu)
cpuhp_bp_sync_dead(cpu);
tick_cleanup_dead_cpu(cpu);
+
+ /*
+ * Callbacks must be re-integrated right away to the RCU state machine.
+ * Otherwise an RCU callback could block a further teardown function
+ * waiting for its completion.
+ */
rcutree_migrate_callbacks(cpu);
+
return 0;
}
@@ -1368,10 +1403,10 @@ void cpuhp_report_idle_dead(void)
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
BUG_ON(st->state != CPUHP_AP_OFFLINE);
- rcu_report_dead(smp_processor_id());
+ rcutree_report_cpu_dead();
st->state = CPUHP_AP_IDLE_DEAD;
/*
- * We cannot call complete after rcu_report_dead() so we delegate it
+ * We cannot call complete after rcutree_report_cpu_dead() so we delegate it
* to an online cpu.
*/
smp_call_function_single(cpumask_first(cpu_online_mask),
@@ -1467,8 +1502,22 @@ out:
return ret;
}
+struct cpu_down_work {
+ unsigned int cpu;
+ enum cpuhp_state target;
+};
+
+static long __cpu_down_maps_locked(void *arg)
+{
+ struct cpu_down_work *work = arg;
+
+ return _cpu_down(work->cpu, 0, work->target);
+}
+
static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
{
+ struct cpu_down_work work = { .cpu = cpu, .target = target, };
+
/*
* If the platform does not support hotplug, report it explicitly to
* differentiate it from a transient offlining failure.
@@ -1477,7 +1526,18 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
return -EOPNOTSUPP;
if (cpu_hotplug_disabled)
return -EBUSY;
- return _cpu_down(cpu, 0, target);
+
+ /*
+ * Ensure that the control task does not run on the to be offlined
+ * CPU to prevent a deadlock against cfs_b->period_timer.
+ * Also keep at least one housekeeping cpu onlined to avoid generating
+ * an empty sched_domain span.
+ */
+ for_each_cpu_and(cpu, cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) {
+ if (cpu != work.cpu)
+ return work_on_cpu(cpu, __cpu_down_maps_locked, &work);
+ }
+ return -EBUSY;
}
static int cpu_down(unsigned int cpu, enum cpuhp_state target)
@@ -1575,7 +1635,7 @@ void notify_cpu_starting(unsigned int cpu)
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
- rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
+ rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
cpumask_set_cpu(cpu, &cpus_booted_once_mask);
/*
@@ -1683,9 +1743,6 @@ static int cpu_up(unsigned int cpu, enum cpuhp_state target)
if (!cpu_possible(cpu)) {
pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
cpu);
-#if defined(CONFIG_IA64)
- pr_err("please check additional_cpus= boot parameter\n");
-#endif
return -EINVAL;
}
@@ -1699,7 +1756,7 @@ static int cpu_up(unsigned int cpu, enum cpuhp_state target)
err = -EBUSY;
goto out;
}
- if (!cpu_smt_allowed(cpu)) {
+ if (!cpu_bootable(cpu)) {
err = -EPERM;
goto out;
}
@@ -1793,6 +1850,16 @@ static int __init parallel_bringup_parse_param(char *arg)
}
early_param("cpuhp.parallel", parallel_bringup_parse_param);
+static inline bool cpuhp_smt_aware(void)
+{
+ return cpu_smt_max_threads > 1;
+}
+
+static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
+{
+ return cpu_primary_thread_mask;
+}
+
/*
* On architectures which have enabled parallel bringup this invokes all BP
* prepare states for each of the to be onlined APs first. The last state
@@ -2046,7 +2113,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
[CPUHP_HRTIMERS_PREPARE] = {
.name = "hrtimers:prepare",
.startup.single = hrtimers_prepare_cpu,
- .teardown.single = hrtimers_dead_cpu,
+ .teardown.single = NULL,
},
[CPUHP_SMPCFD_PREPARE] = {
.name = "smpcfd:prepare",
@@ -2138,6 +2205,12 @@ static struct cpuhp_step cpuhp_hp_states[] = {
.startup.single = NULL,
.teardown.single = smpcfd_dying_cpu,
},
+ [CPUHP_AP_HRTIMERS_DYING] = {
+ .name = "hrtimers:dying",
+ .startup.single = NULL,
+ .teardown.single = hrtimers_cpu_dying,
+ },
+
/* Entry state on starting. Interrupts enabled from here on. Transient
* state for synchronsization */
[CPUHP_AP_ONLINE] = {
@@ -2626,6 +2699,12 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
for_each_online_cpu(cpu) {
if (topology_is_primary_thread(cpu))
continue;
+ /*
+ * Disable can be called with CPU_SMT_ENABLED when changing
+ * from a higher to lower number of SMT threads per core.
+ */
+ if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu))
+ continue;
ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
if (ret)
break;
@@ -2660,6 +2739,8 @@ int cpuhp_smt_enable(void)
/* Skip online CPUs and CPUs on offline nodes */
if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
continue;
+ if (!cpu_smt_thread_allowed(cpu))
+ continue;
ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
if (ret)
break;
@@ -2838,20 +2919,19 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
#ifdef CONFIG_HOTPLUG_SMT
+static bool cpu_smt_num_threads_valid(unsigned int threads)
+{
+ if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC))
+ return threads >= 1 && threads <= cpu_smt_max_threads;
+ return threads == 1 || threads == cpu_smt_max_threads;
+}
+
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
- int ctrlval, ret;
-
- if (sysfs_streq(buf, "on"))
- ctrlval = CPU_SMT_ENABLED;
- else if (sysfs_streq(buf, "off"))
- ctrlval = CPU_SMT_DISABLED;
- else if (sysfs_streq(buf, "forceoff"))
- ctrlval = CPU_SMT_FORCE_DISABLED;
- else
- return -EINVAL;
+ int ctrlval, ret, num_threads, orig_threads;
+ bool force_off;
if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
return -EPERM;
@@ -2859,21 +2939,39 @@ __store_smt_control(struct device *dev, struct device_attribute *attr,
if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
return -ENODEV;
+ if (sysfs_streq(buf, "on")) {
+ ctrlval = CPU_SMT_ENABLED;
+ num_threads = cpu_smt_max_threads;
+ } else if (sysfs_streq(buf, "off")) {
+ ctrlval = CPU_SMT_DISABLED;
+ num_threads = 1;
+ } else if (sysfs_streq(buf, "forceoff")) {
+ ctrlval = CPU_SMT_FORCE_DISABLED;
+ num_threads = 1;
+ } else if (kstrtoint(buf, 10, &num_threads) == 0) {
+ if (num_threads == 1)
+ ctrlval = CPU_SMT_DISABLED;
+ else if (cpu_smt_num_threads_valid(num_threads))
+ ctrlval = CPU_SMT_ENABLED;
+ else
+ return -EINVAL;
+ } else {
+ return -EINVAL;
+ }
+
ret = lock_device_hotplug_sysfs();
if (ret)
return ret;
- if (ctrlval != cpu_smt_control) {
- switch (ctrlval) {
- case CPU_SMT_ENABLED:
- ret = cpuhp_smt_enable();
- break;
- case CPU_SMT_DISABLED:
- case CPU_SMT_FORCE_DISABLED:
- ret = cpuhp_smt_disable(ctrlval);
- break;
- }
- }
+ orig_threads = cpu_smt_num_threads;
+ cpu_smt_num_threads = num_threads;
+
+ force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED;
+
+ if (num_threads > orig_threads)
+ ret = cpuhp_smt_enable();
+ else if (num_threads < orig_threads || force_off)
+ ret = cpuhp_smt_disable(ctrlval);
unlock_device_hotplug();
return ret ? ret : count;
@@ -2901,6 +2999,17 @@ static ssize_t control_show(struct device *dev,
{
const char *state = smt_states[cpu_smt_control];
+#ifdef CONFIG_HOTPLUG_SMT
+ /*
+ * If SMT is enabled but not all threads are enabled then show the
+ * number of threads. If all threads are enabled show "on". Otherwise
+ * show the state name.
+ */
+ if (cpu_smt_control == CPU_SMT_ENABLED &&
+ cpu_smt_num_threads != cpu_smt_max_threads)
+ return sysfs_emit(buf, "%d\n", cpu_smt_num_threads);
+#endif
+
return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
}
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 90ce1dfd591c..d4313b53837e 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -5,11 +5,16 @@
*/
#include <linux/buildid.h>
-#include <linux/crash_core.h>
#include <linux/init.h>
#include <linux/utsname.h>
#include <linux/vmalloc.h>
#include <linux/sizes.h>
+#include <linux/kexec.h>
+#include <linux/memory.h>
+#include <linux/cpuhotplug.h>
+#include <linux/memblock.h>
+#include <linux/kexec.h>
+#include <linux/kmemleak.h>
#include <asm/page.h>
#include <asm/sections.h>
@@ -17,6 +22,10 @@
#include <crypto/sha1.h>
#include "kallsyms_internal.h"
+#include "kexec_internal.h"
+
+/* Per cpu memory for storing cpu states in case of system crash. */
+note_buf_t __percpu *crash_notes;
/* vmcoreinfo stuff */
unsigned char *vmcoreinfo_data;
@@ -26,6 +35,22 @@ u32 *vmcoreinfo_note;
/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */
static unsigned char *vmcoreinfo_data_safecopy;
+/* Location of the reserved area for the crash kernel */
+struct resource crashk_res = {
+ .name = "Crash kernel",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
+ .desc = IORES_DESC_CRASH_KERNEL
+};
+struct resource crashk_low_res = {
+ .name = "Crash kernel",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
+ .desc = IORES_DESC_CRASH_KERNEL
+};
+
/*
* parsing the "crashkernel" commandline
*
@@ -174,7 +199,7 @@ static __initdata char *suffix_tbl[] = {
* It returns 0 on success and -EINVAL on failure.
*/
static int __init parse_crashkernel_suffix(char *cmdline,
- unsigned long long *crash_size,
+ unsigned long long *crash_size,
const char *suffix)
{
char *cur = cmdline;
@@ -241,11 +266,11 @@ static int __init __parse_crashkernel(char *cmdline,
unsigned long long system_ram,
unsigned long long *crash_size,
unsigned long long *crash_base,
- const char *name,
const char *suffix)
{
- char *first_colon, *first_space;
- char *ck_cmdline;
+ char *first_colon, *first_space;
+ char *ck_cmdline;
+ char *name = "crashkernel=";
BUG_ON(!crash_size || !crash_base);
*crash_size = 0;
@@ -276,32 +301,53 @@ static int __init __parse_crashkernel(char *cmdline,
/*
* That function is the entry point for command line parsing and should be
* called from the arch-specific code.
+ *
+ * If crashkernel=,high|low is supported on architecture, non-NULL values
+ * should be passed to parameters 'low_size' and 'high'.
*/
int __init parse_crashkernel(char *cmdline,
unsigned long long system_ram,
unsigned long long *crash_size,
- unsigned long long *crash_base)
+ unsigned long long *crash_base,
+ unsigned long long *low_size,
+ bool *high)
{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", NULL);
-}
+ int ret;
-int __init parse_crashkernel_high(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", suffix_tbl[SUFFIX_HIGH]);
-}
+ /* crashkernel=X[@offset] */
+ ret = __parse_crashkernel(cmdline, system_ram, crash_size,
+ crash_base, NULL);
+#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+ /*
+ * If non-NULL 'high' passed in and no normal crashkernel
+ * setting detected, try parsing crashkernel=,high|low.
+ */
+ if (high && ret == -ENOENT) {
+ ret = __parse_crashkernel(cmdline, 0, crash_size,
+ crash_base, suffix_tbl[SUFFIX_HIGH]);
+ if (ret || !*crash_size)
+ return -EINVAL;
-int __init parse_crashkernel_low(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", suffix_tbl[SUFFIX_LOW]);
+ /*
+ * crashkernel=Y,low can be specified or not, but invalid value
+ * is not allowed.
+ */
+ ret = __parse_crashkernel(cmdline, 0, low_size,
+ crash_base, suffix_tbl[SUFFIX_LOW]);
+ if (ret == -ENOENT) {
+ *low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+ ret = 0;
+ } else if (ret) {
+ return ret;
+ }
+
+ *high = true;
+ }
+#endif
+ if (!*crash_size)
+ ret = -EINVAL;
+
+ return ret;
}
/*
@@ -314,6 +360,290 @@ static int __init parse_crashkernel_dummy(char *arg)
}
early_param("crashkernel", parse_crashkernel_dummy);
+#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+static int __init reserve_crashkernel_low(unsigned long long low_size)
+{
+#ifdef CONFIG_64BIT
+ unsigned long long low_base;
+
+ low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX);
+ if (!low_base) {
+ pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size);
+ return -ENOMEM;
+ }
+
+ pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n",
+ low_base, low_base + low_size, low_size >> 20);
+
+ crashk_low_res.start = low_base;
+ crashk_low_res.end = low_base + low_size - 1;
+ insert_resource(&iomem_resource, &crashk_low_res);
+#endif
+ return 0;
+}
+
+void __init reserve_crashkernel_generic(char *cmdline,
+ unsigned long long crash_size,
+ unsigned long long crash_base,
+ unsigned long long crash_low_size,
+ bool high)
+{
+ unsigned long long search_end = CRASH_ADDR_LOW_MAX, search_base = 0;
+ bool fixed_base = false;
+
+ /* User specifies base address explicitly. */
+ if (crash_base) {
+ fixed_base = true;
+ search_base = crash_base;
+ search_end = crash_base + crash_size;
+ } else if (high) {
+ search_base = CRASH_ADDR_LOW_MAX;
+ search_end = CRASH_ADDR_HIGH_MAX;
+ }
+
+retry:
+ crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN,
+ search_base, search_end);
+ if (!crash_base) {
+ /*
+ * For crashkernel=size[KMG]@offset[KMG], print out failure
+ * message if can't reserve the specified region.
+ */
+ if (fixed_base) {
+ pr_warn("crashkernel reservation failed - memory is in use.\n");
+ return;
+ }
+
+ /*
+ * For crashkernel=size[KMG], if the first attempt was for
+ * low memory, fall back to high memory, the minimum required
+ * low memory will be reserved later.
+ */
+ if (!high && search_end == CRASH_ADDR_LOW_MAX) {
+ search_end = CRASH_ADDR_HIGH_MAX;
+ search_base = CRASH_ADDR_LOW_MAX;
+ crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+ goto retry;
+ }
+
+ /*
+ * For crashkernel=size[KMG],high, if the first attempt was
+ * for high memory, fall back to low memory.
+ */
+ if (high && search_end == CRASH_ADDR_HIGH_MAX) {
+ search_end = CRASH_ADDR_LOW_MAX;
+ search_base = 0;
+ goto retry;
+ }
+ pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
+ crash_size);
+ return;
+ }
+
+ if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
+ crash_low_size && reserve_crashkernel_low(crash_low_size)) {
+ memblock_phys_free(crash_base, crash_size);
+ return;
+ }
+
+ pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+ crash_base, crash_base + crash_size, crash_size >> 20);
+
+ /*
+ * The crashkernel memory will be removed from the kernel linear
+ * map. Inform kmemleak so that it won't try to access it.
+ */
+ kmemleak_ignore_phys(crash_base);
+ if (crashk_low_res.end)
+ kmemleak_ignore_phys(crashk_low_res.start);
+
+ crashk_res.start = crash_base;
+ crashk_res.end = crash_base + crash_size - 1;
+ insert_resource(&iomem_resource, &crashk_res);
+}
+#endif
+
+int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
+ void **addr, unsigned long *sz)
+{
+ Elf64_Ehdr *ehdr;
+ Elf64_Phdr *phdr;
+ unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
+ unsigned char *buf;
+ unsigned int cpu, i;
+ unsigned long long notes_addr;
+ unsigned long mstart, mend;
+
+ /* extra phdr for vmcoreinfo ELF note */
+ nr_phdr = nr_cpus + 1;
+ nr_phdr += mem->nr_ranges;
+
+ /*
+ * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
+ * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64).
+ * I think this is required by tools like gdb. So same physical
+ * memory will be mapped in two ELF headers. One will contain kernel
+ * text virtual addresses and other will have __va(physical) addresses.
+ */
+
+ nr_phdr++;
+ elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
+ elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
+
+ buf = vzalloc(elf_sz);
+ if (!buf)
+ return -ENOMEM;
+
+ ehdr = (Elf64_Ehdr *)buf;
+ phdr = (Elf64_Phdr *)(ehdr + 1);
+ memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
+ ehdr->e_ident[EI_CLASS] = ELFCLASS64;
+ ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
+ ehdr->e_ident[EI_VERSION] = EV_CURRENT;
+ ehdr->e_ident[EI_OSABI] = ELF_OSABI;
+ memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
+ ehdr->e_type = ET_CORE;
+ ehdr->e_machine = ELF_ARCH;
+ ehdr->e_version = EV_CURRENT;
+ ehdr->e_phoff = sizeof(Elf64_Ehdr);
+ ehdr->e_ehsize = sizeof(Elf64_Ehdr);
+ ehdr->e_phentsize = sizeof(Elf64_Phdr);
+
+ /* Prepare one phdr of type PT_NOTE for each possible CPU */
+ for_each_possible_cpu(cpu) {
+ phdr->p_type = PT_NOTE;
+ notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
+ phdr->p_offset = phdr->p_paddr = notes_addr;
+ phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
+ (ehdr->e_phnum)++;
+ phdr++;
+ }
+
+ /* Prepare one PT_NOTE header for vmcoreinfo */
+ phdr->p_type = PT_NOTE;
+ phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
+ phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
+ (ehdr->e_phnum)++;
+ phdr++;
+
+ /* Prepare PT_LOAD type program header for kernel text region */
+ if (need_kernel_map) {
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R|PF_W|PF_X;
+ phdr->p_vaddr = (unsigned long) _text;
+ phdr->p_filesz = phdr->p_memsz = _end - _text;
+ phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
+ ehdr->e_phnum++;
+ phdr++;
+ }
+
+ /* Go through all the ranges in mem->ranges[] and prepare phdr */
+ for (i = 0; i < mem->nr_ranges; i++) {
+ mstart = mem->ranges[i].start;
+ mend = mem->ranges[i].end;
+
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R|PF_W|PF_X;
+ phdr->p_offset = mstart;
+
+ phdr->p_paddr = mstart;
+ phdr->p_vaddr = (unsigned long) __va(mstart);
+ phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
+ phdr->p_align = 0;
+ ehdr->e_phnum++;
+ pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
+ phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
+ ehdr->e_phnum, phdr->p_offset);
+ phdr++;
+ }
+
+ *addr = buf;
+ *sz = elf_sz;
+ return 0;
+}
+
+int crash_exclude_mem_range(struct crash_mem *mem,
+ unsigned long long mstart, unsigned long long mend)
+{
+ int i, j;
+ unsigned long long start, end, p_start, p_end;
+ struct range temp_range = {0, 0};
+
+ for (i = 0; i < mem->nr_ranges; i++) {
+ start = mem->ranges[i].start;
+ end = mem->ranges[i].end;
+ p_start = mstart;
+ p_end = mend;
+
+ if (mstart > end || mend < start)
+ continue;
+
+ /* Truncate any area outside of range */
+ if (mstart < start)
+ p_start = start;
+ if (mend > end)
+ p_end = end;
+
+ /* Found completely overlapping range */
+ if (p_start == start && p_end == end) {
+ mem->ranges[i].start = 0;
+ mem->ranges[i].end = 0;
+ if (i < mem->nr_ranges - 1) {
+ /* Shift rest of the ranges to left */
+ for (j = i; j < mem->nr_ranges - 1; j++) {
+ mem->ranges[j].start =
+ mem->ranges[j+1].start;
+ mem->ranges[j].end =
+ mem->ranges[j+1].end;
+ }
+
+ /*
+ * Continue to check if there are another overlapping ranges
+ * from the current position because of shifting the above
+ * mem ranges.
+ */
+ i--;
+ mem->nr_ranges--;
+ continue;
+ }
+ mem->nr_ranges--;
+ return 0;
+ }
+
+ if (p_start > start && p_end < end) {
+ /* Split original range */
+ mem->ranges[i].end = p_start - 1;
+ temp_range.start = p_end + 1;
+ temp_range.end = end;
+ } else if (p_start != start)
+ mem->ranges[i].end = p_start - 1;
+ else
+ mem->ranges[i].start = p_end + 1;
+ break;
+ }
+
+ /* If a split happened, add the split to array */
+ if (!temp_range.end)
+ return 0;
+
+ /* Split happened */
+ if (i == mem->max_nr_ranges - 1)
+ return -ENOMEM;
+
+ /* Location where new range should go */
+ j = i + 1;
+ if (j < mem->nr_ranges) {
+ /* Move over all ranges one slot towards the end */
+ for (i = mem->nr_ranges - 1; i >= j; i--)
+ mem->ranges[i + 1] = mem->ranges[i];
+ }
+
+ mem->ranges[j].start = temp_range.start;
+ mem->ranges[j].end = temp_range.end;
+ mem->nr_ranges++;
+ return 0;
+}
+
Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
void *data, size_t data_len)
{
@@ -455,8 +785,6 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_OFFSET(page, lru);
VMCOREINFO_OFFSET(page, _mapcount);
VMCOREINFO_OFFSET(page, private);
- VMCOREINFO_OFFSET(folio, _folio_dtor);
- VMCOREINFO_OFFSET(folio, _folio_order);
VMCOREINFO_OFFSET(page, compound_head);
VMCOREINFO_OFFSET(pglist_data, node_zones);
VMCOREINFO_OFFSET(pglist_data, nr_zones);
@@ -490,7 +818,7 @@ static int __init crash_save_vmcoreinfo_init(void)
#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy)
VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
#ifdef CONFIG_HUGETLB_PAGE
- VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
+ VMCOREINFO_NUMBER(PG_hugetlb);
#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline)
VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE);
#endif
@@ -515,3 +843,223 @@ static int __init crash_save_vmcoreinfo_init(void)
}
subsys_initcall(crash_save_vmcoreinfo_init);
+
+static int __init crash_notes_memory_init(void)
+{
+ /* Allocate memory for saving cpu registers. */
+ size_t size, align;
+
+ /*
+ * crash_notes could be allocated across 2 vmalloc pages when percpu
+ * is vmalloc based . vmalloc doesn't guarantee 2 continuous vmalloc
+ * pages are also on 2 continuous physical pages. In this case the
+ * 2nd part of crash_notes in 2nd page could be lost since only the
+ * starting address and size of crash_notes are exported through sysfs.
+ * Here round up the size of crash_notes to the nearest power of two
+ * and pass it to __alloc_percpu as align value. This can make sure
+ * crash_notes is allocated inside one physical page.
+ */
+ size = sizeof(note_buf_t);
+ align = min(roundup_pow_of_two(sizeof(note_buf_t)), PAGE_SIZE);
+
+ /*
+ * Break compile if size is bigger than PAGE_SIZE since crash_notes
+ * definitely will be in 2 pages with that.
+ */
+ BUILD_BUG_ON(size > PAGE_SIZE);
+
+ crash_notes = __alloc_percpu(size, align);
+ if (!crash_notes) {
+ pr_warn("Memory allocation for saving cpu register states failed\n");
+ return -ENOMEM;
+ }
+ return 0;
+}
+subsys_initcall(crash_notes_memory_init);
+
+#ifdef CONFIG_CRASH_HOTPLUG
+#undef pr_fmt
+#define pr_fmt(fmt) "crash hp: " fmt
+
+/*
+ * Different than kexec/kdump loading/unloading/jumping/shrinking which
+ * usually rarely happen, there will be many crash hotplug events notified
+ * during one short period, e.g one memory board is hot added and memory
+ * regions are online. So mutex lock __crash_hotplug_lock is used to
+ * serialize the crash hotplug handling specifically.
+ */
+DEFINE_MUTEX(__crash_hotplug_lock);
+#define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock)
+#define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock)
+
+/*
+ * This routine utilized when the crash_hotplug sysfs node is read.
+ * It reflects the kernel's ability/permission to update the crash
+ * elfcorehdr directly.
+ */
+int crash_check_update_elfcorehdr(void)
+{
+ int rc = 0;
+
+ crash_hotplug_lock();
+ /* Obtain lock while reading crash information */
+ if (!kexec_trylock()) {
+ pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+ crash_hotplug_unlock();
+ return 0;
+ }
+ if (kexec_crash_image) {
+ if (kexec_crash_image->file_mode)
+ rc = 1;
+ else
+ rc = kexec_crash_image->update_elfcorehdr;
+ }
+ /* Release lock now that update complete */
+ kexec_unlock();
+ crash_hotplug_unlock();
+
+ return rc;
+}
+
+/*
+ * To accurately reflect hot un/plug changes of cpu and memory resources
+ * (including onling and offlining of those resources), the elfcorehdr
+ * (which is passed to the crash kernel via the elfcorehdr= parameter)
+ * must be updated with the new list of CPUs and memories.
+ *
+ * In order to make changes to elfcorehdr, two conditions are needed:
+ * First, the segment containing the elfcorehdr must be large enough
+ * to permit a growing number of resources; the elfcorehdr memory size
+ * is based on NR_CPUS_DEFAULT and CRASH_MAX_MEMORY_RANGES.
+ * Second, purgatory must explicitly exclude the elfcorehdr from the
+ * list of segments it checks (since the elfcorehdr changes and thus
+ * would require an update to purgatory itself to update the digest).
+ */
+static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
+{
+ struct kimage *image;
+
+ crash_hotplug_lock();
+ /* Obtain lock while changing crash information */
+ if (!kexec_trylock()) {
+ pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+ crash_hotplug_unlock();
+ return;
+ }
+
+ /* Check kdump is not loaded */
+ if (!kexec_crash_image)
+ goto out;
+
+ image = kexec_crash_image;
+
+ /* Check that updating elfcorehdr is permitted */
+ if (!(image->file_mode || image->update_elfcorehdr))
+ goto out;
+
+ if (hp_action == KEXEC_CRASH_HP_ADD_CPU ||
+ hp_action == KEXEC_CRASH_HP_REMOVE_CPU)
+ pr_debug("hp_action %u, cpu %u\n", hp_action, cpu);
+ else
+ pr_debug("hp_action %u\n", hp_action);
+
+ /*
+ * The elfcorehdr_index is set to -1 when the struct kimage
+ * is allocated. Find the segment containing the elfcorehdr,
+ * if not already found.
+ */
+ if (image->elfcorehdr_index < 0) {
+ unsigned long mem;
+ unsigned char *ptr;
+ unsigned int n;
+
+ for (n = 0; n < image->nr_segments; n++) {
+ mem = image->segment[n].mem;
+ ptr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT));
+ if (ptr) {
+ /* The segment containing elfcorehdr */
+ if (memcmp(ptr, ELFMAG, SELFMAG) == 0)
+ image->elfcorehdr_index = (int)n;
+ kunmap_local(ptr);
+ }
+ }
+ }
+
+ if (image->elfcorehdr_index < 0) {
+ pr_err("unable to locate elfcorehdr segment");
+ goto out;
+ }
+
+ /* Needed in order for the segments to be updated */
+ arch_kexec_unprotect_crashkres();
+
+ /* Differentiate between normal load and hotplug update */
+ image->hp_action = hp_action;
+
+ /* Now invoke arch-specific update handler */
+ arch_crash_handle_hotplug_event(image);
+
+ /* No longer handling a hotplug event */
+ image->hp_action = KEXEC_CRASH_HP_NONE;
+ image->elfcorehdr_updated = true;
+
+ /* Change back to read-only */
+ arch_kexec_protect_crashkres();
+
+ /* Errors in the callback is not a reason to rollback state */
+out:
+ /* Release lock now that update complete */
+ kexec_unlock();
+ crash_hotplug_unlock();
+}
+
+static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)
+{
+ switch (val) {
+ case MEM_ONLINE:
+ crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY,
+ KEXEC_CRASH_HP_INVALID_CPU);
+ break;
+
+ case MEM_OFFLINE:
+ crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY,
+ KEXEC_CRASH_HP_INVALID_CPU);
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block crash_memhp_nb = {
+ .notifier_call = crash_memhp_notifier,
+ .priority = 0
+};
+
+static int crash_cpuhp_online(unsigned int cpu)
+{
+ crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu);
+ return 0;
+}
+
+static int crash_cpuhp_offline(unsigned int cpu)
+{
+ crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu);
+ return 0;
+}
+
+static int __init crash_hotplug_init(void)
+{
+ int result = 0;
+
+ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+ register_memory_notifier(&crash_memhp_nb);
+
+ if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
+ result = cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN,
+ "crash/cpuhp", crash_cpuhp_online, crash_cpuhp_offline);
+ }
+
+ return result;
+}
+
+subsys_initcall(crash_hotplug_init);
+#endif
diff --git a/kernel/cred.c b/kernel/cred.c
index 811ad654abd1..c033a201c808 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -4,6 +4,9 @@
* Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
+
+#define pr_fmt(fmt) "CRED: " fmt
+
#include <linux/export.h>
#include <linux/cred.h>
#include <linux/slab.h>
@@ -33,17 +36,13 @@ do { \
static struct kmem_cache *cred_jar;
/* init to 2 - one for init_task, one to ensure it is never freed */
-static struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
+static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) };
/*
* The initial credentials for the initial task
*/
struct cred init_cred = {
.usage = ATOMIC_INIT(4),
-#ifdef CONFIG_DEBUG_CREDENTIALS
- .subscribers = ATOMIC_INIT(2),
- .magic = CRED_MAGIC,
-#endif
.uid = GLOBAL_ROOT_UID,
.gid = GLOBAL_ROOT_GID,
.suid = GLOBAL_ROOT_UID,
@@ -63,31 +62,6 @@ struct cred init_cred = {
.ucounts = &init_ucounts,
};
-static inline void set_cred_subscribers(struct cred *cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- atomic_set(&cred->subscribers, n);
-#endif
-}
-
-static inline int read_cred_subscribers(const struct cred *cred)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- return atomic_read(&cred->subscribers);
-#else
- return 0;
-#endif
-}
-
-static inline void alter_cred_subscribers(const struct cred *_cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- struct cred *cred = (struct cred *) _cred;
-
- atomic_add(n, &cred->subscribers);
-#endif
-}
-
/*
* The RCU callback to actually dispose of a set of credentials
*/
@@ -97,20 +71,9 @@ static void put_cred_rcu(struct rcu_head *rcu)
kdebug("put_cred_rcu(%p)", cred);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- if (cred->magic != CRED_MAGIC_DEAD ||
- atomic_read(&cred->usage) != 0 ||
- read_cred_subscribers(cred) != 0)
- panic("CRED: put_cred_rcu() sees %p with"
- " mag %x, put %p, usage %d, subscr %d\n",
- cred, cred->magic, cred->put_addr,
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
-#else
- if (atomic_read(&cred->usage) != 0)
- panic("CRED: put_cred_rcu() sees %p with usage %d\n",
- cred, atomic_read(&cred->usage));
-#endif
+ if (atomic_long_read(&cred->usage) != 0)
+ panic("CRED: put_cred_rcu() sees %p with usage %ld\n",
+ cred, atomic_long_read(&cred->usage));
security_cred_free(cred);
key_put(cred->session_keyring);
@@ -134,16 +97,10 @@ static void put_cred_rcu(struct rcu_head *rcu)
*/
void __put_cred(struct cred *cred)
{
- kdebug("__put_cred(%p{%d,%d})", cred,
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
-
- BUG_ON(atomic_read(&cred->usage) != 0);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(cred) != 0);
- cred->magic = CRED_MAGIC_DEAD;
- cred->put_addr = __builtin_return_address(0);
-#endif
+ kdebug("__put_cred(%p{%ld})", cred,
+ atomic_long_read(&cred->usage));
+
+ BUG_ON(atomic_long_read(&cred->usage) != 0);
BUG_ON(cred == current->cred);
BUG_ON(cred == current->real_cred);
@@ -159,23 +116,23 @@ EXPORT_SYMBOL(__put_cred);
*/
void exit_creds(struct task_struct *tsk)
{
- struct cred *cred;
+ struct cred *real_cred, *cred;
- kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred,
- atomic_read(&tsk->cred->usage),
- read_cred_subscribers(tsk->cred));
+ kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred,
+ atomic_long_read(&tsk->cred->usage));
- cred = (struct cred *) tsk->real_cred;
+ real_cred = (struct cred *) tsk->real_cred;
tsk->real_cred = NULL;
- validate_creds(cred);
- alter_cred_subscribers(cred, -1);
- put_cred(cred);
cred = (struct cred *) tsk->cred;
tsk->cred = NULL;
- validate_creds(cred);
- alter_cred_subscribers(cred, -1);
- put_cred(cred);
+
+ if (real_cred == cred) {
+ put_cred_many(cred, 2);
+ } else {
+ put_cred(real_cred);
+ put_cred(cred);
+ }
#ifdef CONFIG_KEYS_REQUEST_CACHE
key_put(tsk->cached_requested_key);
@@ -221,10 +178,7 @@ struct cred *cred_alloc_blank(void)
if (!new)
return NULL;
- atomic_set(&new->usage, 1);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- new->magic = CRED_MAGIC;
-#endif
+ atomic_long_set(&new->usage, 1);
if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
@@ -255,8 +209,6 @@ struct cred *prepare_creds(void)
const struct cred *old;
struct cred *new;
- validate_process_creds();
-
new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
if (!new)
return NULL;
@@ -267,8 +219,7 @@ struct cred *prepare_creds(void)
memcpy(new, old, sizeof(struct cred));
new->non_rcu = 0;
- atomic_set(&new->usage, 1);
- set_cred_subscribers(new, 0);
+ atomic_long_set(&new->usage, 1);
get_group_info(new->group_info);
get_uid(new->user);
get_user_ns(new->user_ns);
@@ -291,7 +242,6 @@ struct cred *prepare_creds(void)
if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
- validate_creds(new);
return new;
error:
@@ -352,12 +302,9 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
#endif
clone_flags & CLONE_THREAD
) {
- p->real_cred = get_cred(p->cred);
- get_cred(p->cred);
- alter_cred_subscribers(p->cred, 2);
- kdebug("share_creds(%p{%d,%d})",
- p->cred, atomic_read(&p->cred->usage),
- read_cred_subscribers(p->cred));
+ p->real_cred = get_cred_many(p->cred, 2);
+ kdebug("share_creds(%p{%ld})",
+ p->cred, atomic_long_read(&p->cred->usage));
inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
return 0;
}
@@ -396,8 +343,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
p->cred = p->real_cred = get_cred(new);
inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
- alter_cred_subscribers(new, 2);
- validate_creds(new);
return 0;
error_put:
@@ -449,17 +394,11 @@ int commit_creds(struct cred *new)
struct task_struct *task = current;
const struct cred *old = task->real_cred;
- kdebug("commit_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
+ kdebug("commit_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
BUG_ON(task->cred != old);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(old) < 2);
- validate_creds(old);
- validate_creds(new);
-#endif
- BUG_ON(atomic_read(&new->usage) < 1);
+ BUG_ON(atomic_long_read(&new->usage) < 1);
get_cred(new); /* we will require a ref for the subj creds too */
@@ -494,14 +433,12 @@ int commit_creds(struct cred *new)
* RLIMIT_NPROC limits on user->processes have already been checked
* in set_user().
*/
- alter_cred_subscribers(new, 2);
if (new->user != old->user || new->user_ns != old->user_ns)
inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
rcu_assign_pointer(task->real_cred, new);
rcu_assign_pointer(task->cred, new);
if (new->user != old->user || new->user_ns != old->user_ns)
dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
- alter_cred_subscribers(old, -2);
/* send notifications */
if (!uid_eq(new->uid, old->uid) ||
@@ -517,8 +454,7 @@ int commit_creds(struct cred *new)
proc_id_connector(task, PROC_EVENT_GID);
/* release the old obj and subj refs both */
- put_cred(old);
- put_cred(old);
+ put_cred_many(old, 2);
return 0;
}
EXPORT_SYMBOL(commit_creds);
@@ -532,14 +468,10 @@ EXPORT_SYMBOL(commit_creds);
*/
void abort_creds(struct cred *new)
{
- kdebug("abort_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
+ kdebug("abort_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(new) != 0);
-#endif
- BUG_ON(atomic_read(&new->usage) < 1);
+ BUG_ON(atomic_long_read(&new->usage) < 1);
put_cred(new);
}
EXPORT_SYMBOL(abort_creds);
@@ -555,12 +487,8 @@ const struct cred *override_creds(const struct cred *new)
{
const struct cred *old = current->cred;
- kdebug("override_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
-
- validate_creds(old);
- validate_creds(new);
+ kdebug("override_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
/*
* NOTE! This uses 'get_new_cred()' rather than 'get_cred()'.
@@ -569,18 +497,12 @@ const struct cred *override_creds(const struct cred *new)
* we are only installing the cred into the thread-synchronous
* '->cred' pointer, not the '->real_cred' pointer that is
* visible to other threads under RCU.
- *
- * Also note that we did validate_creds() manually, not depending
- * on the validation in 'get_cred()'.
*/
get_new_cred((struct cred *)new);
- alter_cred_subscribers(new, 1);
rcu_assign_pointer(current->cred, new);
- alter_cred_subscribers(old, -1);
- kdebug("override_creds() = %p{%d,%d}", old,
- atomic_read(&old->usage),
- read_cred_subscribers(old));
+ kdebug("override_creds() = %p{%ld}", old,
+ atomic_long_read(&old->usage));
return old;
}
EXPORT_SYMBOL(override_creds);
@@ -596,15 +518,10 @@ void revert_creds(const struct cred *old)
{
const struct cred *override = current->cred;
- kdebug("revert_creds(%p{%d,%d})", old,
- atomic_read(&old->usage),
- read_cred_subscribers(old));
+ kdebug("revert_creds(%p{%ld})", old,
+ atomic_long_read(&old->usage));
- validate_creds(old);
- validate_creds(override);
- alter_cred_subscribers(old, 1);
rcu_assign_pointer(current->cred, old);
- alter_cred_subscribers(override, -1);
put_cred(override);
}
EXPORT_SYMBOL(revert_creds);
@@ -724,12 +641,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
kdebug("prepare_kernel_cred() alloc %p", new);
old = get_task_cred(daemon);
- validate_creds(old);
*new = *old;
new->non_rcu = 0;
- atomic_set(&new->usage, 1);
- set_cred_subscribers(new, 0);
+ atomic_long_set(&new->usage, 1);
get_uid(new->user);
get_user_ns(new->user_ns);
get_group_info(new->group_info);
@@ -753,7 +668,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
goto error;
put_cred(old);
- validate_creds(new);
return new;
error:
@@ -818,109 +732,3 @@ int set_create_files_as(struct cred *new, struct inode *inode)
return security_kernel_create_files_as(new, inode);
}
EXPORT_SYMBOL(set_create_files_as);
-
-#ifdef CONFIG_DEBUG_CREDENTIALS
-
-bool creds_are_invalid(const struct cred *cred)
-{
- if (cred->magic != CRED_MAGIC)
- return true;
- return false;
-}
-EXPORT_SYMBOL(creds_are_invalid);
-
-/*
- * dump invalid credentials
- */
-static void dump_invalid_creds(const struct cred *cred, const char *label,
- const struct task_struct *tsk)
-{
- printk(KERN_ERR "CRED: %s credentials: %p %s%s%s\n",
- label, cred,
- cred == &init_cred ? "[init]" : "",
- cred == tsk->real_cred ? "[real]" : "",
- cred == tsk->cred ? "[eff]" : "");
- printk(KERN_ERR "CRED: ->magic=%x, put_addr=%p\n",
- cred->magic, cred->put_addr);
- printk(KERN_ERR "CRED: ->usage=%d, subscr=%d\n",
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
- printk(KERN_ERR "CRED: ->*uid = { %d,%d,%d,%d }\n",
- from_kuid_munged(&init_user_ns, cred->uid),
- from_kuid_munged(&init_user_ns, cred->euid),
- from_kuid_munged(&init_user_ns, cred->suid),
- from_kuid_munged(&init_user_ns, cred->fsuid));
- printk(KERN_ERR "CRED: ->*gid = { %d,%d,%d,%d }\n",
- from_kgid_munged(&init_user_ns, cred->gid),
- from_kgid_munged(&init_user_ns, cred->egid),
- from_kgid_munged(&init_user_ns, cred->sgid),
- from_kgid_munged(&init_user_ns, cred->fsgid));
-#ifdef CONFIG_SECURITY
- printk(KERN_ERR "CRED: ->security is %p\n", cred->security);
- if ((unsigned long) cred->security >= PAGE_SIZE &&
- (((unsigned long) cred->security & 0xffffff00) !=
- (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)))
- printk(KERN_ERR "CRED: ->security {%x, %x}\n",
- ((u32*)cred->security)[0],
- ((u32*)cred->security)[1]);
-#endif
-}
-
-/*
- * report use of invalid credentials
- */
-void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line)
-{
- printk(KERN_ERR "CRED: Invalid credentials\n");
- printk(KERN_ERR "CRED: At %s:%u\n", file, line);
- dump_invalid_creds(cred, "Specified", current);
- BUG();
-}
-EXPORT_SYMBOL(__invalid_creds);
-
-/*
- * check the credentials on a process
- */
-void __validate_process_creds(struct task_struct *tsk,
- const char *file, unsigned line)
-{
- if (tsk->cred == tsk->real_cred) {
- if (unlikely(read_cred_subscribers(tsk->cred) < 2 ||
- creds_are_invalid(tsk->cred)))
- goto invalid_creds;
- } else {
- if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 ||
- read_cred_subscribers(tsk->cred) < 1 ||
- creds_are_invalid(tsk->real_cred) ||
- creds_are_invalid(tsk->cred)))
- goto invalid_creds;
- }
- return;
-
-invalid_creds:
- printk(KERN_ERR "CRED: Invalid process credentials\n");
- printk(KERN_ERR "CRED: At %s:%u\n", file, line);
-
- dump_invalid_creds(tsk->real_cred, "Real", tsk);
- if (tsk->cred != tsk->real_cred)
- dump_invalid_creds(tsk->cred, "Effective", tsk);
- else
- printk(KERN_ERR "CRED: Effective creds == Real creds\n");
- BUG();
-}
-EXPORT_SYMBOL(__validate_process_creds);
-
-/*
- * check creds for do_exit()
- */
-void validate_creds_for_do_exit(struct task_struct *tsk)
-{
- kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})",
- tsk->real_cred, tsk->cred,
- atomic_read(&tsk->cred->usage),
- read_cred_subscribers(tsk->cred));
-
- __validate_process_creds(tsk, __FILE__, __LINE__);
-}
-
-#endif /* CONFIG_DEBUG_CREDENTIALS */
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index d5e9ccde3ab8..ce1bb2301c06 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -968,7 +968,7 @@ static int __init opt_kgdb_con(char *str)
early_param("kgdbcon", opt_kgdb_con);
#ifdef CONFIG_MAGIC_SYSRQ
-static void sysrq_handle_dbg(int key)
+static void sysrq_handle_dbg(u8 key)
{
if (!dbg_io_ops) {
pr_crit("ERROR: No KGDB I/O module available\n");
@@ -1006,6 +1006,9 @@ void kgdb_panic(const char *msg)
if (panic_timeout)
return;
+ debug_locks_off();
+ console_flush_on_panic(CONSOLE_FLUSH_PENDING);
+
if (dbg_kdb_mode)
kdb_printf("PANIC: %s\n", msg);
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 813cb6cf72d6..9443bc63c5a2 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -590,6 +590,8 @@ static void kdb_msg_write(const char *msg, int msg_len)
continue;
if (c == dbg_io_ops->cons)
continue;
+ if (!c->write)
+ continue;
/*
* Set oops_in_progress to encourage the console drivers to
* disregard their internal spin locks: in the current calling
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 438b868cbfa9..6b213c8252d6 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -272,11 +272,10 @@ char *kdbgetenv(const char *match)
* kdballocenv - This function is used to allocate bytes for
* environment entries.
* Parameters:
- * match A character string representing a numeric value
- * Outputs:
- * *value the unsigned long representation of the env variable 'match'
+ * bytes The number of bytes to allocate in the static buffer.
* Returns:
- * Zero on success, a kdb diagnostic on failure.
+ * A pointer to the allocated space in the buffer on success.
+ * NULL if bytes > size available in the envbuffer.
* Remarks:
* We use a static environment buffer (envbuffer) to hold the values
* of dynamically generated environment variables (see kdb_set). Buffer
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 11d077003205..d62f5957f36b 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -90,6 +90,19 @@ config SWIOTLB
bool
select NEED_DMA_MAP_STATE
+config SWIOTLB_DYNAMIC
+ bool "Dynamic allocation of DMA bounce buffers"
+ default n
+ depends on SWIOTLB
+ help
+ This enables dynamic resizing of the software IO TLB. The kernel
+ starts with one memory pool at boot and it will allocate additional
+ pools as needed. To reduce run-time kernel memory requirements, you
+ may have to specify a smaller size of the initial pool using
+ "swiotlb=" on the kernel command line.
+
+ If unsure, say N.
+
config DMA_BOUNCE_UNALIGNED_KMALLOC
bool
depends on SWIOTLB
@@ -122,6 +135,8 @@ config DMA_COHERENT_POOL
config DMA_GLOBAL_POOL
select DMA_DECLARE_COHERENT
+ depends on !ARCH_HAS_DMA_SET_UNCACHED
+ depends on !DMA_DIRECT_REMAP
bool
config DMA_DIRECT_REMAP
@@ -129,6 +144,15 @@ config DMA_DIRECT_REMAP
select DMA_COHERENT_POOL
select DMA_NONCOHERENT_MMAP
+#
+# Fallback to arch code for DMA allocations. This should eventually go away.
+#
+config ARCH_HAS_DMA_ALLOC
+ depends on !ARCH_HAS_DMA_SET_UNCACHED
+ depends on !DMA_DIRECT_REMAP
+ depends on !DMA_GLOBAL_POOL
+ bool
+
config DMA_CMA
bool "DMA Contiguous Memory Allocator"
depends on HAVE_DMA_CONTIGUOUS && CMA
@@ -145,15 +169,16 @@ config DMA_CMA
if DMA_CMA
-config DMA_PERNUMA_CMA
- bool "Enable separate DMA Contiguous Memory Area for each NUMA Node"
- default NUMA && ARM64
+config DMA_NUMA_CMA
+ bool "Enable separate DMA Contiguous Memory Area for NUMA Node"
+ depends on NUMA
help
- Enable this option to get pernuma CMA areas so that devices like
- ARM64 SMMU can get local memory by DMA coherent APIs.
+ Enable this option to get numa CMA areas so that NUMA devices
+ can get local memory by DMA coherent APIs.
You can set the size of pernuma CMA by specifying "cma_pernuma=size"
- on the kernel's command line.
+ or set the node id and its size of CMA by specifying "numa_cma=
+ <node>:size[,<node>:size]" on the kernel's command line.
comment "Default contiguous memory area size:"
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 6ea80ae42622..f005c66f378c 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -50,6 +50,7 @@
#include <linux/sizes.h>
#include <linux/dma-map-ops.h>
#include <linux/cma.h>
+#include <linux/nospec.h>
#ifdef CONFIG_CMA_SIZE_MBYTES
#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
@@ -96,11 +97,44 @@ static int __init early_cma(char *p)
}
early_param("cma", early_cma);
-#ifdef CONFIG_DMA_PERNUMA_CMA
+#ifdef CONFIG_DMA_NUMA_CMA
+static struct cma *dma_contiguous_numa_area[MAX_NUMNODES];
+static phys_addr_t numa_cma_size[MAX_NUMNODES] __initdata;
static struct cma *dma_contiguous_pernuma_area[MAX_NUMNODES];
static phys_addr_t pernuma_size_bytes __initdata;
+static int __init early_numa_cma(char *p)
+{
+ int nid, count = 0;
+ unsigned long tmp;
+ char *s = p;
+
+ while (*s) {
+ if (sscanf(s, "%lu%n", &tmp, &count) != 1)
+ break;
+
+ if (s[count] == ':') {
+ if (tmp >= MAX_NUMNODES)
+ break;
+ nid = array_index_nospec(tmp, MAX_NUMNODES);
+
+ s += count + 1;
+ tmp = memparse(s, &s);
+ numa_cma_size[nid] = tmp;
+
+ if (*s == ',')
+ s++;
+ else
+ break;
+ } else
+ break;
+ }
+
+ return 0;
+}
+early_param("numa_cma", early_numa_cma);
+
static int __init early_cma_pernuma(char *p)
{
pernuma_size_bytes = memparse(p, &p);
@@ -127,32 +161,49 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
#endif
-#ifdef CONFIG_DMA_PERNUMA_CMA
-void __init dma_pernuma_cma_reserve(void)
+#ifdef CONFIG_DMA_NUMA_CMA
+static void __init dma_numa_cma_reserve(void)
{
int nid;
- if (!pernuma_size_bytes)
- return;
-
- for_each_online_node(nid) {
+ for_each_node(nid) {
int ret;
char name[CMA_MAX_NAME];
- struct cma **cma = &dma_contiguous_pernuma_area[nid];
-
- snprintf(name, sizeof(name), "pernuma%d", nid);
- ret = cma_declare_contiguous_nid(0, pernuma_size_bytes, 0, 0,
- 0, false, name, cma, nid);
- if (ret) {
- pr_warn("%s: reservation failed: err %d, node %d", __func__,
- ret, nid);
+ struct cma **cma;
+
+ if (!node_online(nid)) {
+ if (pernuma_size_bytes || numa_cma_size[nid])
+ pr_warn("invalid node %d specified\n", nid);
continue;
}
- pr_debug("%s: reserved %llu MiB on node %d\n", __func__,
- (unsigned long long)pernuma_size_bytes / SZ_1M, nid);
+ if (pernuma_size_bytes) {
+
+ cma = &dma_contiguous_pernuma_area[nid];
+ snprintf(name, sizeof(name), "pernuma%d", nid);
+ ret = cma_declare_contiguous_nid(0, pernuma_size_bytes, 0, 0,
+ 0, false, name, cma, nid);
+ if (ret)
+ pr_warn("%s: reservation failed: err %d, node %d", __func__,
+ ret, nid);
+ }
+
+ if (numa_cma_size[nid]) {
+
+ cma = &dma_contiguous_numa_area[nid];
+ snprintf(name, sizeof(name), "numa%d", nid);
+ ret = cma_declare_contiguous_nid(0, numa_cma_size[nid], 0, 0, 0, false,
+ name, cma, nid);
+ if (ret)
+ pr_warn("%s: reservation failed: err %d, node %d", __func__,
+ ret, nid);
+ }
}
}
+#else
+static inline void __init dma_numa_cma_reserve(void)
+{
+}
#endif
/**
@@ -171,6 +222,8 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
phys_addr_t selected_limit = limit;
bool fixed = false;
+ dma_numa_cma_reserve();
+
pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
if (size_cmdline != -1) {
@@ -303,7 +356,7 @@ static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp)
*/
struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
{
-#ifdef CONFIG_DMA_PERNUMA_CMA
+#ifdef CONFIG_DMA_NUMA_CMA
int nid = dev_to_node(dev);
#endif
@@ -315,7 +368,7 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
if (size <= PAGE_SIZE)
return NULL;
-#ifdef CONFIG_DMA_PERNUMA_CMA
+#ifdef CONFIG_DMA_NUMA_CMA
if (nid != NUMA_NO_NODE && !(gfp & (GFP_DMA | GFP_DMA32))) {
struct cma *cma = dma_contiguous_pernuma_area[nid];
struct page *page;
@@ -325,6 +378,13 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
if (page)
return page;
}
+
+ cma = dma_contiguous_numa_area[nid];
+ if (cma) {
+ page = cma_alloc_aligned(cma, size, gfp);
+ if (page)
+ return page;
+ }
}
#endif
if (!dma_contiguous_default_area)
@@ -356,10 +416,13 @@ void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
/*
* otherwise, page is from either per-numa cma or default cma
*/
-#ifdef CONFIG_DMA_PERNUMA_CMA
+#ifdef CONFIG_DMA_NUMA_CMA
if (cma_release(dma_contiguous_pernuma_area[page_to_nid(page)],
page, count))
return;
+ if (cma_release(dma_contiguous_numa_area[page_to_nid(page)],
+ page, count))
+ return;
#endif
if (cma_release(dma_contiguous_default_area, page, count))
return;
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index f190651bcadd..3de494375b7b 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -139,7 +139,7 @@ static const char *const maperr2str[] = {
static const char *type2name[] = {
[dma_debug_single] = "single",
- [dma_debug_sg] = "scather-gather",
+ [dma_debug_sg] = "scatter-gather",
[dma_debug_coherent] = "coherent",
[dma_debug_resource] = "resource",
};
@@ -637,15 +637,19 @@ static struct dma_debug_entry *__dma_entry_alloc(void)
return entry;
}
-static void __dma_entry_alloc_check_leak(void)
+/*
+ * This should be called outside of free_entries_lock scope to avoid potential
+ * deadlocks with serial consoles that use DMA.
+ */
+static void __dma_entry_alloc_check_leak(u32 nr_entries)
{
- u32 tmp = nr_total_entries % nr_prealloc_entries;
+ u32 tmp = nr_entries % nr_prealloc_entries;
/* Shout each time we tick over some multiple of the initial pool */
if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) {
pr_info("dma_debug_entry pool grown to %u (%u00%%)\n",
- nr_total_entries,
- (nr_total_entries / nr_prealloc_entries));
+ nr_entries,
+ (nr_entries / nr_prealloc_entries));
}
}
@@ -656,8 +660,10 @@ static void __dma_entry_alloc_check_leak(void)
*/
static struct dma_debug_entry *dma_entry_alloc(void)
{
+ bool alloc_check_leak = false;
struct dma_debug_entry *entry;
unsigned long flags;
+ u32 nr_entries;
spin_lock_irqsave(&free_entries_lock, flags);
if (num_free_entries == 0) {
@@ -667,13 +673,17 @@ static struct dma_debug_entry *dma_entry_alloc(void)
pr_err("debugging out of memory - disabling\n");
return NULL;
}
- __dma_entry_alloc_check_leak();
+ alloc_check_leak = true;
+ nr_entries = nr_total_entries;
}
entry = __dma_entry_alloc();
spin_unlock_irqrestore(&free_entries_lock, flags);
+ if (alloc_check_leak)
+ __dma_entry_alloc_check_leak(nr_entries);
+
#ifdef CONFIG_STACKTRACE
entry->stack_len = stack_trace_save(entry->stack_entries,
ARRAY_SIZE(entry->stack_entries),
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index d29cade048db..73c95815789a 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -66,7 +66,7 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 *phys_limit)
return 0;
}
-static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
{
dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
@@ -220,13 +220,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
return dma_direct_alloc_no_mapping(dev, size, dma_handle, gfp);
if (!dev_is_dma_coherent(dev)) {
- /*
- * Fallback to the arch handler if it exists. This should
- * eventually go away.
- */
- if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
- !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
- !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
+ if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_ALLOC) &&
!is_swiotlb_for_alloc(dev))
return arch_dma_alloc(dev, size, dma_handle, gfp,
attrs);
@@ -240,27 +234,24 @@ void *dma_direct_alloc(struct device *dev, size_t size,
dma_handle);
/*
- * Otherwise remap if the architecture is asking for it. But
- * given that remapping memory is a blocking operation we'll
- * instead have to dip into the atomic pools.
+ * Otherwise we require the architecture to either be able to
+ * mark arbitrary parts of the kernel direct mapping uncached,
+ * or remapped it uncached.
*/
+ set_uncached = IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED);
remap = IS_ENABLED(CONFIG_DMA_DIRECT_REMAP);
- if (remap) {
- if (dma_direct_use_pool(dev, gfp))
- return dma_direct_alloc_from_pool(dev, size,
- dma_handle, gfp);
- } else {
- if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED))
- return NULL;
- set_uncached = true;
+ if (!set_uncached && !remap) {
+ pr_warn_once("coherent DMA allocations not supported on this platform.\n");
+ return NULL;
}
}
/*
- * Decrypting memory may block, so allocate the memory from the atomic
- * pools if we can't block.
+ * Remapping or decrypting memory may block, allocate the memory from
+ * the atomic pools instead if we aren't allowed block.
*/
- if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp))
+ if ((remap || force_dma_unencrypted(dev)) &&
+ dma_direct_use_pool(dev, gfp))
return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
/* we always manually zero the memory once we are done */
@@ -330,9 +321,7 @@ void dma_direct_free(struct device *dev, size_t size,
return;
}
- if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
- !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
- !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
+ if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_ALLOC) &&
!dev_is_dma_coherent(dev) &&
!is_swiotlb_for_alloc(dev)) {
arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
@@ -598,6 +587,46 @@ int dma_direct_supported(struct device *dev, u64 mask)
return mask >= phys_to_dma_unencrypted(dev, min_mask);
}
+/*
+ * To check whether all ram resource ranges are covered by dma range map
+ * Returns 0 when further check is needed
+ * Returns 1 if there is some RAM range can't be covered by dma_range_map
+ */
+static int check_ram_in_range_map(unsigned long start_pfn,
+ unsigned long nr_pages, void *data)
+{
+ unsigned long end_pfn = start_pfn + nr_pages;
+ const struct bus_dma_region *bdr = NULL;
+ const struct bus_dma_region *m;
+ struct device *dev = data;
+
+ while (start_pfn < end_pfn) {
+ for (m = dev->dma_range_map; PFN_DOWN(m->size); m++) {
+ unsigned long cpu_start_pfn = PFN_DOWN(m->cpu_start);
+
+ if (start_pfn >= cpu_start_pfn &&
+ start_pfn - cpu_start_pfn < PFN_DOWN(m->size)) {
+ bdr = m;
+ break;
+ }
+ }
+ if (!bdr)
+ return 1;
+
+ start_pfn = PFN_DOWN(bdr->cpu_start) + PFN_DOWN(bdr->size);
+ }
+
+ return 0;
+}
+
+bool dma_direct_all_ram_mapped(struct device *dev)
+{
+ if (!dev->dma_range_map)
+ return true;
+ return !walk_system_ram_range(0, PFN_DOWN(ULONG_MAX) + 1, dev,
+ check_ram_in_range_map);
+}
+
size_t dma_direct_max_mapping_size(struct device *dev)
{
/* If SWIOTLB is active, use its maximum mapping size */
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index 97ec892ea0b5..18d346118fe8 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -20,6 +20,7 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
enum dma_data_direction dir, unsigned long attrs);
+bool dma_direct_all_ram_mapped(struct device *dev);
size_t dma_direct_max_mapping_size(struct device *dev);
#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 9a4db5cce600..58db8fd70471 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -760,12 +760,6 @@ bool dma_pci_p2pdma_supported(struct device *dev)
}
EXPORT_SYMBOL_GPL(dma_pci_p2pdma_supported);
-#ifdef CONFIG_ARCH_HAS_DMA_SET_MASK
-void arch_dma_set_mask(struct device *dev, u64 mask);
-#else
-#define arch_dma_set_mask(dev, mask) do { } while (0)
-#endif
-
int dma_set_mask(struct device *dev, u64 mask)
{
/*
@@ -799,6 +793,28 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
}
EXPORT_SYMBOL(dma_set_coherent_mask);
+/**
+ * dma_addressing_limited - return if the device is addressing limited
+ * @dev: device to check
+ *
+ * Return %true if the devices DMA mask is too small to address all memory in
+ * the system, else %false. Lack of addressing bits is the prime reason for
+ * bounce buffering, but might not be the only one.
+ */
+bool dma_addressing_limited(struct device *dev)
+{
+ const struct dma_map_ops *ops = get_dma_ops(dev);
+
+ if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
+ dma_get_required_mask(dev))
+ return true;
+
+ if (unlikely(ops))
+ return false;
+ return !dma_direct_all_ram_mapped(dev);
+}
+EXPORT_SYMBOL_GPL(dma_addressing_limited);
+
size_t dma_max_mapping_size(struct device *dev)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 1acec2e22827..b481c48a31a6 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -135,9 +135,9 @@ encrypt_mapping:
remove_mapping:
#ifdef CONFIG_DMA_DIRECT_REMAP
dma_common_free_remap(addr, pool_size);
-#endif
-free_page: __maybe_unused
+free_page:
__free_pages(page, order);
+#endif
out:
return ret;
}
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 2b83e3ad9dca..33d942615be5 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -35,6 +35,7 @@
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/pfn.h>
+#include <linux/rculist.h>
#include <linux/scatterlist.h>
#include <linux/set_memory.h>
#include <linux/spinlock.h>
@@ -62,6 +63,13 @@
#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
+/**
+ * struct io_tlb_slot - IO TLB slot descriptor
+ * @orig_addr: The original address corresponding to a mapped entry.
+ * @alloc_size: Size of the allocated buffer.
+ * @list: The free list describing the number of free entries available
+ * from each index.
+ */
struct io_tlb_slot {
phys_addr_t orig_addr;
size_t alloc_size;
@@ -71,7 +79,22 @@ struct io_tlb_slot {
static bool swiotlb_force_bounce;
static bool swiotlb_force_disable;
-struct io_tlb_mem io_tlb_default_mem;
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+
+static void swiotlb_dyn_alloc(struct work_struct *work);
+
+static struct io_tlb_mem io_tlb_default_mem = {
+ .lock = __SPIN_LOCK_UNLOCKED(io_tlb_default_mem.lock),
+ .pools = LIST_HEAD_INIT(io_tlb_default_mem.pools),
+ .dyn_alloc = __WORK_INITIALIZER(io_tlb_default_mem.dyn_alloc,
+ swiotlb_dyn_alloc),
+};
+
+#else /* !CONFIG_SWIOTLB_DYNAMIC */
+
+static struct io_tlb_mem io_tlb_default_mem;
+
+#endif /* CONFIG_SWIOTLB_DYNAMIC */
static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
static unsigned long default_nareas;
@@ -202,7 +225,7 @@ void __init swiotlb_adjust_size(unsigned long size)
void swiotlb_print_info(void)
{
- struct io_tlb_mem *mem = &io_tlb_default_mem;
+ struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
if (!mem->nslabs) {
pr_warn("No low mem\n");
@@ -231,7 +254,7 @@ static inline unsigned long nr_slots(u64 val)
*/
void __init swiotlb_update_mem_attributes(void)
{
- struct io_tlb_mem *mem = &io_tlb_default_mem;
+ struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long bytes;
if (!mem->nslabs || mem->late_alloc)
@@ -240,9 +263,8 @@ void __init swiotlb_update_mem_attributes(void)
set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT);
}
-static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
- unsigned long nslabs, unsigned int flags,
- bool late_alloc, unsigned int nareas)
+static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start,
+ unsigned long nslabs, bool late_alloc, unsigned int nareas)
{
void *vaddr = phys_to_virt(start);
unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
@@ -254,8 +276,6 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
mem->nareas = nareas;
mem->area_nslabs = nslabs / mem->nareas;
- mem->force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE);
-
for (i = 0; i < mem->nareas; i++) {
spin_lock_init(&mem->areas[i].lock);
mem->areas[i].index = 0;
@@ -263,7 +283,8 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
}
for (i = 0; i < mem->nslabs; i++) {
- mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
+ mem->slots[i].list = min(IO_TLB_SEGSIZE - io_tlb_offset(i),
+ mem->nslabs - i);
mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
mem->slots[i].alloc_size = 0;
}
@@ -273,6 +294,23 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
return;
}
+/**
+ * add_mem_pool() - add a memory pool to the allocator
+ * @mem: Software IO TLB allocator.
+ * @pool: Memory pool to be added.
+ */
+static void add_mem_pool(struct io_tlb_mem *mem, struct io_tlb_pool *pool)
+{
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ spin_lock(&mem->lock);
+ list_add_rcu(&pool->node, &mem->pools);
+ mem->nslabs += pool->nslabs;
+ spin_unlock(&mem->lock);
+#else
+ mem->nslabs = pool->nslabs;
+#endif
+}
+
static void __init *swiotlb_memblock_alloc(unsigned long nslabs,
unsigned int flags,
int (*remap)(void *tlb, unsigned long nslabs))
@@ -312,7 +350,7 @@ static void __init *swiotlb_memblock_alloc(unsigned long nslabs,
void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
int (*remap)(void *tlb, unsigned long nslabs))
{
- struct io_tlb_mem *mem = &io_tlb_default_mem;
+ struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long nslabs;
unsigned int nareas;
size_t alloc_size;
@@ -323,6 +361,18 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
if (swiotlb_force_disable)
return;
+ io_tlb_default_mem.force_bounce =
+ swiotlb_force_bounce || (flags & SWIOTLB_FORCE);
+
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ if (!remap)
+ io_tlb_default_mem.can_grow = true;
+ if (flags & SWIOTLB_ANY)
+ io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1);
+ else
+ io_tlb_default_mem.phys_limit = ARCH_LOW_ADDRESS_LIMIT;
+#endif
+
if (!default_nareas)
swiotlb_adjust_nareas(num_possible_cpus());
@@ -350,14 +400,14 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
}
mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
- default_nareas), SMP_CACHE_BYTES);
+ nareas), SMP_CACHE_BYTES);
if (!mem->areas) {
pr_warn("%s: Failed to allocate mem->areas.\n", __func__);
return;
}
- swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false,
- default_nareas);
+ swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, nareas);
+ add_mem_pool(&io_tlb_default_mem, mem);
if (flags & SWIOTLB_VERBOSE)
swiotlb_print_info();
@@ -376,7 +426,7 @@ void __init swiotlb_init(bool addressing_limit, unsigned int flags)
int swiotlb_init_late(size_t size, gfp_t gfp_mask,
int (*remap)(void *tlb, unsigned long nslabs))
{
- struct io_tlb_mem *mem = &io_tlb_default_mem;
+ struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
unsigned int nareas;
unsigned char *vstart = NULL;
@@ -384,9 +434,25 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
bool retried = false;
int rc = 0;
+ if (io_tlb_default_mem.nslabs)
+ return 0;
+
if (swiotlb_force_disable)
return 0;
+ io_tlb_default_mem.force_bounce = swiotlb_force_bounce;
+
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ if (!remap)
+ io_tlb_default_mem.can_grow = true;
+ if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp_mask & __GFP_DMA))
+ io_tlb_default_mem.phys_limit = DMA_BIT_MASK(zone_dma_bits);
+ else if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp_mask & __GFP_DMA32))
+ io_tlb_default_mem.phys_limit = DMA_BIT_MASK(32);
+ else
+ io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1);
+#endif
+
if (!default_nareas)
swiotlb_adjust_nareas(num_possible_cpus());
@@ -438,8 +504,9 @@ retry:
set_memory_decrypted((unsigned long)vstart,
(nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
- swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true,
- nareas);
+ swiotlb_init_io_tlb_pool(mem, virt_to_phys(vstart), nslabs, true,
+ nareas);
+ add_mem_pool(&io_tlb_default_mem, mem);
swiotlb_print_info();
return 0;
@@ -453,7 +520,7 @@ error_area:
void __init swiotlb_exit(void)
{
- struct io_tlb_mem *mem = &io_tlb_default_mem;
+ struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long tbl_vaddr;
size_t tbl_size, slots_size;
unsigned int area_order;
@@ -486,6 +553,274 @@ void __init swiotlb_exit(void)
memset(mem, 0, sizeof(*mem));
}
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+
+/**
+ * alloc_dma_pages() - allocate pages to be used for DMA
+ * @gfp: GFP flags for the allocation.
+ * @bytes: Size of the buffer.
+ * @phys_limit: Maximum allowed physical address of the buffer.
+ *
+ * Allocate pages from the buddy allocator. If successful, make the allocated
+ * pages decrypted that they can be used for DMA.
+ *
+ * Return: Decrypted pages, %NULL on allocation failure, or ERR_PTR(-EAGAIN)
+ * if the allocated physical address was above @phys_limit.
+ */
+static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit)
+{
+ unsigned int order = get_order(bytes);
+ struct page *page;
+ phys_addr_t paddr;
+ void *vaddr;
+
+ page = alloc_pages(gfp, order);
+ if (!page)
+ return NULL;
+
+ paddr = page_to_phys(page);
+ if (paddr + bytes - 1 > phys_limit) {
+ __free_pages(page, order);
+ return ERR_PTR(-EAGAIN);
+ }
+
+ vaddr = phys_to_virt(paddr);
+ if (set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes)))
+ goto error;
+ return page;
+
+error:
+ /* Intentional leak if pages cannot be encrypted again. */
+ if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
+ __free_pages(page, order);
+ return NULL;
+}
+
+/**
+ * swiotlb_alloc_tlb() - allocate a dynamic IO TLB buffer
+ * @dev: Device for which a memory pool is allocated.
+ * @bytes: Size of the buffer.
+ * @phys_limit: Maximum allowed physical address of the buffer.
+ * @gfp: GFP flags for the allocation.
+ *
+ * Return: Allocated pages, or %NULL on allocation failure.
+ */
+static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
+ u64 phys_limit, gfp_t gfp)
+{
+ struct page *page;
+
+ /*
+ * Allocate from the atomic pools if memory is encrypted and
+ * the allocation is atomic, because decrypting may block.
+ */
+ if (!gfpflags_allow_blocking(gfp) && dev && force_dma_unencrypted(dev)) {
+ void *vaddr;
+
+ if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
+ return NULL;
+
+ return dma_alloc_from_pool(dev, bytes, &vaddr, gfp,
+ dma_coherent_ok);
+ }
+
+ gfp &= ~GFP_ZONEMASK;
+ if (phys_limit <= DMA_BIT_MASK(zone_dma_bits))
+ gfp |= __GFP_DMA;
+ else if (phys_limit <= DMA_BIT_MASK(32))
+ gfp |= __GFP_DMA32;
+
+ while (IS_ERR(page = alloc_dma_pages(gfp, bytes, phys_limit))) {
+ if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+ phys_limit < DMA_BIT_MASK(64) &&
+ !(gfp & (__GFP_DMA32 | __GFP_DMA)))
+ gfp |= __GFP_DMA32;
+ else if (IS_ENABLED(CONFIG_ZONE_DMA) &&
+ !(gfp & __GFP_DMA))
+ gfp = (gfp & ~__GFP_DMA32) | __GFP_DMA;
+ else
+ return NULL;
+ }
+
+ return page;
+}
+
+/**
+ * swiotlb_free_tlb() - free a dynamically allocated IO TLB buffer
+ * @vaddr: Virtual address of the buffer.
+ * @bytes: Size of the buffer.
+ */
+static void swiotlb_free_tlb(void *vaddr, size_t bytes)
+{
+ if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+ dma_free_from_pool(NULL, vaddr, bytes))
+ return;
+
+ /* Intentional leak if pages cannot be encrypted again. */
+ if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
+ __free_pages(virt_to_page(vaddr), get_order(bytes));
+}
+
+/**
+ * swiotlb_alloc_pool() - allocate a new IO TLB memory pool
+ * @dev: Device for which a memory pool is allocated.
+ * @minslabs: Minimum number of slabs.
+ * @nslabs: Desired (maximum) number of slabs.
+ * @nareas: Number of areas.
+ * @phys_limit: Maximum DMA buffer physical address.
+ * @gfp: GFP flags for the allocations.
+ *
+ * Allocate and initialize a new IO TLB memory pool. The actual number of
+ * slabs may be reduced if allocation of @nslabs fails. If even
+ * @minslabs cannot be allocated, this function fails.
+ *
+ * Return: New memory pool, or %NULL on allocation failure.
+ */
+static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
+ unsigned long minslabs, unsigned long nslabs,
+ unsigned int nareas, u64 phys_limit, gfp_t gfp)
+{
+ struct io_tlb_pool *pool;
+ unsigned int slot_order;
+ struct page *tlb;
+ size_t pool_size;
+ size_t tlb_size;
+
+ if (nslabs > SLABS_PER_PAGE << MAX_ORDER) {
+ nslabs = SLABS_PER_PAGE << MAX_ORDER;
+ nareas = limit_nareas(nareas, nslabs);
+ }
+
+ pool_size = sizeof(*pool) + array_size(sizeof(*pool->areas), nareas);
+ pool = kzalloc(pool_size, gfp);
+ if (!pool)
+ goto error;
+ pool->areas = (void *)pool + sizeof(*pool);
+
+ tlb_size = nslabs << IO_TLB_SHIFT;
+ while (!(tlb = swiotlb_alloc_tlb(dev, tlb_size, phys_limit, gfp))) {
+ if (nslabs <= minslabs)
+ goto error_tlb;
+ nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+ nareas = limit_nareas(nareas, nslabs);
+ tlb_size = nslabs << IO_TLB_SHIFT;
+ }
+
+ slot_order = get_order(array_size(sizeof(*pool->slots), nslabs));
+ pool->slots = (struct io_tlb_slot *)
+ __get_free_pages(gfp, slot_order);
+ if (!pool->slots)
+ goto error_slots;
+
+ swiotlb_init_io_tlb_pool(pool, page_to_phys(tlb), nslabs, true, nareas);
+ return pool;
+
+error_slots:
+ swiotlb_free_tlb(page_address(tlb), tlb_size);
+error_tlb:
+ kfree(pool);
+error:
+ return NULL;
+}
+
+/**
+ * swiotlb_dyn_alloc() - dynamic memory pool allocation worker
+ * @work: Pointer to dyn_alloc in struct io_tlb_mem.
+ */
+static void swiotlb_dyn_alloc(struct work_struct *work)
+{
+ struct io_tlb_mem *mem =
+ container_of(work, struct io_tlb_mem, dyn_alloc);
+ struct io_tlb_pool *pool;
+
+ pool = swiotlb_alloc_pool(NULL, IO_TLB_MIN_SLABS, default_nslabs,
+ default_nareas, mem->phys_limit, GFP_KERNEL);
+ if (!pool) {
+ pr_warn_ratelimited("Failed to allocate new pool");
+ return;
+ }
+
+ add_mem_pool(mem, pool);
+}
+
+/**
+ * swiotlb_dyn_free() - RCU callback to free a memory pool
+ * @rcu: RCU head in the corresponding struct io_tlb_pool.
+ */
+static void swiotlb_dyn_free(struct rcu_head *rcu)
+{
+ struct io_tlb_pool *pool = container_of(rcu, struct io_tlb_pool, rcu);
+ size_t slots_size = array_size(sizeof(*pool->slots), pool->nslabs);
+ size_t tlb_size = pool->end - pool->start;
+
+ free_pages((unsigned long)pool->slots, get_order(slots_size));
+ swiotlb_free_tlb(pool->vaddr, tlb_size);
+ kfree(pool);
+}
+
+/**
+ * swiotlb_find_pool() - find the IO TLB pool for a physical address
+ * @dev: Device which has mapped the DMA buffer.
+ * @paddr: Physical address within the DMA buffer.
+ *
+ * Find the IO TLB memory pool descriptor which contains the given physical
+ * address, if any.
+ *
+ * Return: Memory pool which contains @paddr, or %NULL if none.
+ */
+struct io_tlb_pool *swiotlb_find_pool(struct device *dev, phys_addr_t paddr)
+{
+ struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+ struct io_tlb_pool *pool;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(pool, &mem->pools, node) {
+ if (paddr >= pool->start && paddr < pool->end)
+ goto out;
+ }
+
+ list_for_each_entry_rcu(pool, &dev->dma_io_tlb_pools, node) {
+ if (paddr >= pool->start && paddr < pool->end)
+ goto out;
+ }
+ pool = NULL;
+out:
+ rcu_read_unlock();
+ return pool;
+}
+
+/**
+ * swiotlb_del_pool() - remove an IO TLB pool from a device
+ * @dev: Owning device.
+ * @pool: Memory pool to be removed.
+ */
+static void swiotlb_del_pool(struct device *dev, struct io_tlb_pool *pool)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->dma_io_tlb_lock, flags);
+ list_del_rcu(&pool->node);
+ spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
+
+ call_rcu(&pool->rcu, swiotlb_dyn_free);
+}
+
+#endif /* CONFIG_SWIOTLB_DYNAMIC */
+
+/**
+ * swiotlb_dev_init() - initialize swiotlb fields in &struct device
+ * @dev: Device to be initialized.
+ */
+void swiotlb_dev_init(struct device *dev)
+{
+ dev->dma_io_tlb_mem = &io_tlb_default_mem;
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ INIT_LIST_HEAD(&dev->dma_io_tlb_pools);
+ spin_lock_init(&dev->dma_io_tlb_lock);
+ dev->dma_uses_io_tlb = false;
+#endif
+}
+
/*
* Return the offset into a iotlb slot required to keep the device happy.
*/
@@ -500,7 +835,7 @@ static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size,
enum dma_data_direction dir)
{
- struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+ struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr);
int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT;
phys_addr_t orig_addr = mem->slots[index].orig_addr;
size_t alloc_size = mem->slots[index].alloc_size;
@@ -577,12 +912,10 @@ static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
*/
static inline unsigned long get_max_slots(unsigned long boundary_mask)
{
- if (boundary_mask == ~0UL)
- return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
- return nr_slots(boundary_mask + 1);
+ return (boundary_mask >> IO_TLB_SHIFT) + 1;
}
-static unsigned int wrap_area_index(struct io_tlb_mem *mem, unsigned int index)
+static unsigned int wrap_area_index(struct io_tlb_pool *mem, unsigned int index)
{
if (index >= mem->area_nslabs)
return 0;
@@ -623,19 +956,30 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
}
#endif /* CONFIG_DEBUG_FS */
-/*
- * Find a suitable number of IO TLB entries size that will fit this request and
- * allocate a buffer from that IO TLB pool.
+/**
+ * swiotlb_area_find_slots() - search for slots in one IO TLB memory area
+ * @dev: Device which maps the buffer.
+ * @pool: Memory pool to be searched.
+ * @area_index: Index of the IO TLB memory area to be searched.
+ * @orig_addr: Original (non-bounced) IO buffer address.
+ * @alloc_size: Total requested size of the bounce buffer,
+ * including initial alignment padding.
+ * @alloc_align_mask: Required alignment of the allocated buffer.
+ *
+ * Find a suitable sequence of IO TLB entries for the request and allocate
+ * a buffer from the given IO TLB memory area.
+ * This function takes care of locking.
+ *
+ * Return: Index of the first allocated slot, or -1 on error.
*/
-static int swiotlb_do_find_slots(struct device *dev, int area_index,
- phys_addr_t orig_addr, size_t alloc_size,
+static int swiotlb_area_find_slots(struct device *dev, struct io_tlb_pool *pool,
+ int area_index, phys_addr_t orig_addr, size_t alloc_size,
unsigned int alloc_align_mask)
{
- struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
- struct io_tlb_area *area = mem->areas + area_index;
+ struct io_tlb_area *area = pool->areas + area_index;
unsigned long boundary_mask = dma_get_seg_boundary(dev);
dma_addr_t tbl_dma_addr =
- phys_to_dma_unencrypted(dev, mem->start) & boundary_mask;
+ phys_to_dma_unencrypted(dev, pool->start) & boundary_mask;
unsigned long max_slots = get_max_slots(boundary_mask);
unsigned int iotlb_align_mask =
dma_get_min_align_mask(dev) | alloc_align_mask;
@@ -647,7 +991,7 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
unsigned int slot_index;
BUG_ON(!nslots);
- BUG_ON(area_index >= mem->nareas);
+ BUG_ON(area_index >= pool->nareas);
/*
* For allocations of PAGE_SIZE or larger only look for page aligned
@@ -664,35 +1008,30 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
spin_lock_irqsave(&area->lock, flags);
- if (unlikely(nslots > mem->area_nslabs - area->used))
+ if (unlikely(nslots > pool->area_nslabs - area->used))
goto not_found;
- slot_base = area_index * mem->area_nslabs;
+ slot_base = area_index * pool->area_nslabs;
index = area->index;
- for (slots_checked = 0; slots_checked < mem->area_nslabs; ) {
+ for (slots_checked = 0; slots_checked < pool->area_nslabs; ) {
slot_index = slot_base + index;
if (orig_addr &&
(slot_addr(tbl_dma_addr, slot_index) &
iotlb_align_mask) != (orig_addr & iotlb_align_mask)) {
- index = wrap_area_index(mem, index + 1);
+ index = wrap_area_index(pool, index + 1);
slots_checked++;
continue;
}
- /*
- * If we find a slot that indicates we have 'nslots' number of
- * contiguous buffers, we allocate the buffers from that slot
- * and mark the entries as '0' indicating unavailable.
- */
if (!iommu_is_span_boundary(slot_index, nslots,
nr_slots(tbl_dma_addr),
max_slots)) {
- if (mem->slots[slot_index].list >= nslots)
+ if (pool->slots[slot_index].list >= nslots)
goto found;
}
- index = wrap_area_index(mem, index + stride);
+ index = wrap_area_index(pool, index + stride);
slots_checked += stride;
}
@@ -701,48 +1040,176 @@ not_found:
return -1;
found:
+ /*
+ * If we find a slot that indicates we have 'nslots' number of
+ * contiguous buffers, we allocate the buffers from that slot onwards
+ * and set the list of free entries to '0' indicating unavailable.
+ */
for (i = slot_index; i < slot_index + nslots; i++) {
- mem->slots[i].list = 0;
- mem->slots[i].alloc_size = alloc_size - (offset +
+ pool->slots[i].list = 0;
+ pool->slots[i].alloc_size = alloc_size - (offset +
((i - slot_index) << IO_TLB_SHIFT));
}
for (i = slot_index - 1;
io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
- mem->slots[i].list; i--)
- mem->slots[i].list = ++count;
+ pool->slots[i].list; i--)
+ pool->slots[i].list = ++count;
/*
* Update the indices to avoid searching in the next round.
*/
- area->index = wrap_area_index(mem, index + nslots);
+ area->index = wrap_area_index(pool, index + nslots);
area->used += nslots;
spin_unlock_irqrestore(&area->lock, flags);
- inc_used_and_hiwater(mem, nslots);
+ inc_used_and_hiwater(dev->dma_io_tlb_mem, nslots);
return slot_index;
}
-static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
- size_t alloc_size, unsigned int alloc_align_mask)
+/**
+ * swiotlb_pool_find_slots() - search for slots in one memory pool
+ * @dev: Device which maps the buffer.
+ * @pool: Memory pool to be searched.
+ * @orig_addr: Original (non-bounced) IO buffer address.
+ * @alloc_size: Total requested size of the bounce buffer,
+ * including initial alignment padding.
+ * @alloc_align_mask: Required alignment of the allocated buffer.
+ *
+ * Search through one memory pool to find a sequence of slots that match the
+ * allocation constraints.
+ *
+ * Return: Index of the first allocated slot, or -1 on error.
+ */
+static int swiotlb_pool_find_slots(struct device *dev, struct io_tlb_pool *pool,
+ phys_addr_t orig_addr, size_t alloc_size,
+ unsigned int alloc_align_mask)
{
- struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
- int start = raw_smp_processor_id() & (mem->nareas - 1);
+ int start = raw_smp_processor_id() & (pool->nareas - 1);
int i = start, index;
do {
- index = swiotlb_do_find_slots(dev, i, orig_addr, alloc_size,
- alloc_align_mask);
+ index = swiotlb_area_find_slots(dev, pool, i, orig_addr,
+ alloc_size, alloc_align_mask);
if (index >= 0)
return index;
- if (++i >= mem->nareas)
+ if (++i >= pool->nareas)
i = 0;
} while (i != start);
return -1;
}
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+
+/**
+ * swiotlb_find_slots() - search for slots in the whole swiotlb
+ * @dev: Device which maps the buffer.
+ * @orig_addr: Original (non-bounced) IO buffer address.
+ * @alloc_size: Total requested size of the bounce buffer,
+ * including initial alignment padding.
+ * @alloc_align_mask: Required alignment of the allocated buffer.
+ * @retpool: Used memory pool, updated on return.
+ *
+ * Search through the whole software IO TLB to find a sequence of slots that
+ * match the allocation constraints.
+ *
+ * Return: Index of the first allocated slot, or -1 on error.
+ */
+static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
+ size_t alloc_size, unsigned int alloc_align_mask,
+ struct io_tlb_pool **retpool)
+{
+ struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+ struct io_tlb_pool *pool;
+ unsigned long nslabs;
+ unsigned long flags;
+ u64 phys_limit;
+ int index;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(pool, &mem->pools, node) {
+ index = swiotlb_pool_find_slots(dev, pool, orig_addr,
+ alloc_size, alloc_align_mask);
+ if (index >= 0) {
+ rcu_read_unlock();
+ goto found;
+ }
+ }
+ rcu_read_unlock();
+ if (!mem->can_grow)
+ return -1;
+
+ schedule_work(&mem->dyn_alloc);
+
+ nslabs = nr_slots(alloc_size);
+ phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit);
+ pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit,
+ GFP_NOWAIT | __GFP_NOWARN);
+ if (!pool)
+ return -1;
+
+ index = swiotlb_pool_find_slots(dev, pool, orig_addr,
+ alloc_size, alloc_align_mask);
+ if (index < 0) {
+ swiotlb_dyn_free(&pool->rcu);
+ return -1;
+ }
+
+ pool->transient = true;
+ spin_lock_irqsave(&dev->dma_io_tlb_lock, flags);
+ list_add_rcu(&pool->node, &dev->dma_io_tlb_pools);
+ spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
+
+found:
+ WRITE_ONCE(dev->dma_uses_io_tlb, true);
+
+ /*
+ * The general barrier orders reads and writes against a presumed store
+ * of the SWIOTLB buffer address by a device driver (to a driver private
+ * data structure). It serves two purposes.
+ *
+ * First, the store to dev->dma_uses_io_tlb must be ordered before the
+ * presumed store. This guarantees that the returned buffer address
+ * cannot be passed to another CPU before updating dev->dma_uses_io_tlb.
+ *
+ * Second, the load from mem->pools must be ordered before the same
+ * presumed store. This guarantees that the returned buffer address
+ * cannot be observed by another CPU before an update of the RCU list
+ * that was made by swiotlb_dyn_alloc() on a third CPU (cf. multicopy
+ * atomicity).
+ *
+ * See also the comment in is_swiotlb_buffer().
+ */
+ smp_mb();
+
+ *retpool = pool;
+ return index;
+}
+
+#else /* !CONFIG_SWIOTLB_DYNAMIC */
+
+static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
+ size_t alloc_size, unsigned int alloc_align_mask,
+ struct io_tlb_pool **retpool)
+{
+ *retpool = &dev->dma_io_tlb_mem->defpool;
+ return swiotlb_pool_find_slots(dev, *retpool,
+ orig_addr, alloc_size, alloc_align_mask);
+}
+
+#endif /* CONFIG_SWIOTLB_DYNAMIC */
+
#ifdef CONFIG_DEBUG_FS
+/**
+ * mem_used() - get number of used slots in an allocator
+ * @mem: Software IO TLB allocator.
+ *
+ * The result is accurate in this version of the function, because an atomic
+ * counter is available if CONFIG_DEBUG_FS is set.
+ *
+ * Return: Number of used slots.
+ */
static unsigned long mem_used(struct io_tlb_mem *mem)
{
return atomic_long_read(&mem->total_used);
@@ -750,16 +1217,50 @@ static unsigned long mem_used(struct io_tlb_mem *mem)
#else /* !CONFIG_DEBUG_FS */
-static unsigned long mem_used(struct io_tlb_mem *mem)
+/**
+ * mem_pool_used() - get number of used slots in a memory pool
+ * @pool: Software IO TLB memory pool.
+ *
+ * The result is not accurate, see mem_used().
+ *
+ * Return: Approximate number of used slots.
+ */
+static unsigned long mem_pool_used(struct io_tlb_pool *pool)
{
int i;
unsigned long used = 0;
- for (i = 0; i < mem->nareas; i++)
- used += mem->areas[i].used;
+ for (i = 0; i < pool->nareas; i++)
+ used += pool->areas[i].used;
return used;
}
+/**
+ * mem_used() - get number of used slots in an allocator
+ * @mem: Software IO TLB allocator.
+ *
+ * The result is not accurate, because there is no locking of individual
+ * areas.
+ *
+ * Return: Approximate number of used slots.
+ */
+static unsigned long mem_used(struct io_tlb_mem *mem)
+{
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ struct io_tlb_pool *pool;
+ unsigned long used = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(pool, &mem->pools, node)
+ used += mem_pool_used(pool);
+ rcu_read_unlock();
+
+ return used;
+#else
+ return mem_pool_used(&mem->defpool);
+#endif
+}
+
#endif /* CONFIG_DEBUG_FS */
phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
@@ -769,6 +1270,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+ struct io_tlb_pool *pool;
unsigned int i;
int index;
phys_addr_t tlb_addr;
@@ -789,7 +1291,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
}
index = swiotlb_find_slots(dev, orig_addr,
- alloc_size + offset, alloc_align_mask);
+ alloc_size + offset, alloc_align_mask, &pool);
if (index == -1) {
if (!(attrs & DMA_ATTR_NO_WARN))
dev_warn_ratelimited(dev,
@@ -804,14 +1306,16 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
* needed.
*/
for (i = 0; i < nr_slots(alloc_size + offset); i++)
- mem->slots[index + i].orig_addr = slot_addr(orig_addr, i);
- tlb_addr = slot_addr(mem->start, index) + offset;
+ pool->slots[index + i].orig_addr = slot_addr(orig_addr, i);
+ tlb_addr = slot_addr(pool->start, index) + offset;
/*
- * When dir == DMA_FROM_DEVICE we could omit the copy from the orig
- * to the tlb buffer, if we knew for sure the device will
- * overwrite the entire current content. But we don't. Thus
- * unconditional bounce may prevent leaking swiotlb content (i.e.
- * kernel memory) to user-space.
+ * When the device is writing memory, i.e. dir == DMA_FROM_DEVICE, copy
+ * the original buffer to the TLB buffer before initiating DMA in order
+ * to preserve the original's data if the device does a partial write,
+ * i.e. if the device doesn't overwrite the entire buffer. Preserving
+ * the original data, even if it's garbage, is necessary to match
+ * hardware behavior. Use of swiotlb is supposed to be transparent,
+ * i.e. swiotlb must not corrupt memory by clobbering unwritten bytes.
*/
swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
return tlb_addr;
@@ -819,7 +1323,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
{
- struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+ struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr);
unsigned long flags;
unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
@@ -863,9 +1367,44 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
area->used -= nslots;
spin_unlock_irqrestore(&area->lock, flags);
- dec_used(mem, nslots);
+ dec_used(dev->dma_io_tlb_mem, nslots);
+}
+
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+
+/**
+ * swiotlb_del_transient() - delete a transient memory pool
+ * @dev: Device which mapped the buffer.
+ * @tlb_addr: Physical address within a bounce buffer.
+ *
+ * Check whether the address belongs to a transient SWIOTLB memory pool.
+ * If yes, then delete the pool.
+ *
+ * Return: %true if @tlb_addr belonged to a transient pool that was released.
+ */
+static bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr)
+{
+ struct io_tlb_pool *pool;
+
+ pool = swiotlb_find_pool(dev, tlb_addr);
+ if (!pool->transient)
+ return false;
+
+ dec_used(dev->dma_io_tlb_mem, pool->nslabs);
+ swiotlb_del_pool(dev, pool);
+ return true;
+}
+
+#else /* !CONFIG_SWIOTLB_DYNAMIC */
+
+static inline bool swiotlb_del_transient(struct device *dev,
+ phys_addr_t tlb_addr)
+{
+ return false;
}
+#endif /* CONFIG_SWIOTLB_DYNAMIC */
+
/*
* tlb_addr is the physical address of the bounce buffer to unmap.
*/
@@ -880,6 +1419,8 @@ void swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr,
(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_FROM_DEVICE);
+ if (swiotlb_del_transient(dev, tlb_addr))
+ return;
swiotlb_release_slots(dev, tlb_addr);
}
@@ -950,13 +1491,47 @@ size_t swiotlb_max_mapping_size(struct device *dev)
return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align;
}
+/**
+ * is_swiotlb_allocated() - check if the default software IO TLB is initialized
+ */
+bool is_swiotlb_allocated(void)
+{
+ return io_tlb_default_mem.nslabs;
+}
+
bool is_swiotlb_active(struct device *dev)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
return mem && mem->nslabs;
}
-EXPORT_SYMBOL_GPL(is_swiotlb_active);
+
+/**
+ * default_swiotlb_base() - get the base address of the default SWIOTLB
+ *
+ * Get the lowest physical address used by the default software IO TLB pool.
+ */
+phys_addr_t default_swiotlb_base(void)
+{
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ io_tlb_default_mem.can_grow = false;
+#endif
+ return io_tlb_default_mem.defpool.start;
+}
+
+/**
+ * default_swiotlb_limit() - get the address limit of the default SWIOTLB
+ *
+ * Get the highest physical address used by the default software IO TLB pool.
+ */
+phys_addr_t default_swiotlb_limit(void)
+{
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ return io_tlb_default_mem.phys_limit;
+#else
+ return io_tlb_default_mem.defpool.end - 1;
+#endif
+}
#ifdef CONFIG_DEBUG_FS
@@ -1031,17 +1606,18 @@ static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
struct page *swiotlb_alloc(struct device *dev, size_t size)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+ struct io_tlb_pool *pool;
phys_addr_t tlb_addr;
int index;
if (!mem)
return NULL;
- index = swiotlb_find_slots(dev, 0, size, 0);
+ index = swiotlb_find_slots(dev, 0, size, 0, &pool);
if (index == -1)
return NULL;
- tlb_addr = slot_addr(mem->start, index);
+ tlb_addr = slot_addr(pool->start, index);
return pfn_to_page(PFN_DOWN(tlb_addr));
}
@@ -1078,29 +1654,37 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
* to it.
*/
if (!mem) {
+ struct io_tlb_pool *pool;
+
mem = kzalloc(sizeof(*mem), GFP_KERNEL);
if (!mem)
return -ENOMEM;
+ pool = &mem->defpool;
- mem->slots = kcalloc(nslabs, sizeof(*mem->slots), GFP_KERNEL);
- if (!mem->slots) {
+ pool->slots = kcalloc(nslabs, sizeof(*pool->slots), GFP_KERNEL);
+ if (!pool->slots) {
kfree(mem);
return -ENOMEM;
}
- mem->areas = kcalloc(nareas, sizeof(*mem->areas),
+ pool->areas = kcalloc(nareas, sizeof(*pool->areas),
GFP_KERNEL);
- if (!mem->areas) {
- kfree(mem->slots);
+ if (!pool->areas) {
+ kfree(pool->slots);
kfree(mem);
return -ENOMEM;
}
set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
rmem->size >> PAGE_SHIFT);
- swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, SWIOTLB_FORCE,
- false, nareas);
+ swiotlb_init_io_tlb_pool(pool, rmem->base, nslabs,
+ false, nareas);
+ mem->force_bounce = true;
mem->for_alloc = true;
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ spin_lock_init(&mem->lock);
+#endif
+ add_mem_pool(mem, pool);
rmem->priv = mem;
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index be61332c66b5..d7ee4bc3f2ba 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -205,8 +205,7 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
arch_exit_to_user_mode_prepare(regs, ti_work);
- /* Ensure that the address limit is intact and no locks are held */
- addr_limit_user_check();
+ /* Ensure that kernel state is sane for a return to userspace */
kmap_assert_nomap();
lockdep_assert_irqs_disabled();
lockdep_sys_exit();
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 78ae7b6f90fd..9efd0d7775e7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -375,6 +375,7 @@ enum event_type_t {
EVENT_TIME = 0x4,
/* see ctx_resched() for details */
EVENT_CPU = 0x8,
+ EVENT_CGROUP = 0x10,
EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
};
@@ -449,8 +450,8 @@ static void update_perf_cpu_limits(void)
static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc);
-int perf_proc_update_handler(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
+int perf_event_max_sample_rate_handler(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
int perf_cpu = sysctl_perf_cpu_time_max_percent;
@@ -684,20 +685,26 @@ do { \
___p; \
})
-static void perf_ctx_disable(struct perf_event_context *ctx)
+static void perf_ctx_disable(struct perf_event_context *ctx, bool cgroup)
{
struct perf_event_pmu_context *pmu_ctx;
- list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry)
+ list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+ if (cgroup && !pmu_ctx->nr_cgroups)
+ continue;
perf_pmu_disable(pmu_ctx->pmu);
+ }
}
-static void perf_ctx_enable(struct perf_event_context *ctx)
+static void perf_ctx_enable(struct perf_event_context *ctx, bool cgroup)
{
struct perf_event_pmu_context *pmu_ctx;
- list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry)
+ list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+ if (cgroup && !pmu_ctx->nr_cgroups)
+ continue;
perf_pmu_enable(pmu_ctx->pmu);
+ }
}
static void ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type);
@@ -856,9 +863,9 @@ static void perf_cgroup_switch(struct task_struct *task)
return;
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
- perf_ctx_disable(&cpuctx->ctx);
+ perf_ctx_disable(&cpuctx->ctx, true);
- ctx_sched_out(&cpuctx->ctx, EVENT_ALL);
+ ctx_sched_out(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP);
/*
* must not be done before ctxswout due
* to update_cgrp_time_from_cpuctx() in
@@ -870,9 +877,9 @@ static void perf_cgroup_switch(struct task_struct *task)
* perf_cgroup_set_timestamp() in ctx_sched_in()
* to not have to pass task around
*/
- ctx_sched_in(&cpuctx->ctx, EVENT_ALL);
+ ctx_sched_in(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP);
- perf_ctx_enable(&cpuctx->ctx);
+ perf_ctx_enable(&cpuctx->ctx, true);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
@@ -965,6 +972,8 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct
if (!is_cgroup_event(event))
return;
+ event->pmu_ctx->nr_cgroups++;
+
/*
* Because cgroup events are always per-cpu events,
* @ctx == &cpuctx->ctx.
@@ -985,6 +994,8 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c
if (!is_cgroup_event(event))
return;
+ event->pmu_ctx->nr_cgroups--;
+
/*
* Because cgroup events are always per-cpu events,
* @ctx == &cpuctx->ctx.
@@ -1803,31 +1814,34 @@ static inline void perf_event__state_init(struct perf_event *event)
PERF_EVENT_STATE_INACTIVE;
}
-static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
+static int __perf_event_read_size(u64 read_format, int nr_siblings)
{
int entry = sizeof(u64); /* value */
int size = 0;
int nr = 1;
- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+ if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
size += sizeof(u64);
- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+ if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
size += sizeof(u64);
- if (event->attr.read_format & PERF_FORMAT_ID)
+ if (read_format & PERF_FORMAT_ID)
entry += sizeof(u64);
- if (event->attr.read_format & PERF_FORMAT_LOST)
+ if (read_format & PERF_FORMAT_LOST)
entry += sizeof(u64);
- if (event->attr.read_format & PERF_FORMAT_GROUP) {
+ if (read_format & PERF_FORMAT_GROUP) {
nr += nr_siblings;
size += sizeof(u64);
}
- size += entry * nr;
- event->read_size = size;
+ /*
+ * Since perf_event_validate_size() limits this to 16k and inhibits
+ * adding more siblings, this will never overflow.
+ */
+ return size + nr * entry;
}
static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
@@ -1877,8 +1891,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
*/
static void perf_event__header_size(struct perf_event *event)
{
- __perf_event_read_size(event,
- event->group_leader->nr_siblings);
+ event->read_size =
+ __perf_event_read_size(event->attr.read_format,
+ event->group_leader->nr_siblings);
__perf_event_header_size(event, event->attr.sample_type);
}
@@ -1909,23 +1924,44 @@ static void perf_event__id_header_size(struct perf_event *event)
event->id_header_size = size;
}
+/*
+ * Check that adding an event to the group does not result in anybody
+ * overflowing the 64k event limit imposed by the output buffer.
+ *
+ * Specifically, check that the read_size for the event does not exceed 16k,
+ * read_size being the one term that grows with groups size. Since read_size
+ * depends on per-event read_format, also (re)check the existing events.
+ *
+ * This leaves 48k for the constant size fields and things like callchains,
+ * branch stacks and register sets.
+ */
static bool perf_event_validate_size(struct perf_event *event)
{
- /*
- * The values computed here will be over-written when we actually
- * attach the event.
- */
- __perf_event_read_size(event, event->group_leader->nr_siblings + 1);
- __perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
- perf_event__id_header_size(event);
+ struct perf_event *sibling, *group_leader = event->group_leader;
+
+ if (__perf_event_read_size(event->attr.read_format,
+ group_leader->nr_siblings + 1) > 16*1024)
+ return false;
+
+ if (__perf_event_read_size(group_leader->attr.read_format,
+ group_leader->nr_siblings + 1) > 16*1024)
+ return false;
/*
- * Sum the lot; should not exceed the 64k limit we have on records.
- * Conservative limit to allow for callchains and other variable fields.
+ * When creating a new group leader, group_leader->ctx is initialized
+ * after the size has been validated, but we cannot safely use
+ * for_each_sibling_event() until group_leader->ctx is set. A new group
+ * leader cannot have any siblings yet, so we can safely skip checking
+ * the non-existent siblings.
*/
- if (event->read_size + event->header_size +
- event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
- return false;
+ if (event == group_leader)
+ return true;
+
+ for_each_sibling_event(sibling, group_leader) {
+ if (__perf_event_read_size(sibling->attr.read_format,
+ group_leader->nr_siblings + 1) > 16*1024)
+ return false;
+ }
return true;
}
@@ -1954,6 +1990,7 @@ static void perf_group_attach(struct perf_event *event)
list_add_tail(&event->sibling_list, &group_leader->sibling_list);
group_leader->nr_siblings++;
+ group_leader->group_generation++;
perf_event__header_size(group_leader);
@@ -2144,6 +2181,7 @@ static void perf_group_detach(struct perf_event *event)
if (leader != event) {
list_del_init(&event->sibling_list);
event->group_leader->nr_siblings--;
+ event->group_leader->group_generation++;
goto out;
}
@@ -2677,9 +2715,9 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
event_type &= EVENT_ALL;
- perf_ctx_disable(&cpuctx->ctx);
+ perf_ctx_disable(&cpuctx->ctx, false);
if (task_ctx) {
- perf_ctx_disable(task_ctx);
+ perf_ctx_disable(task_ctx, false);
task_ctx_sched_out(task_ctx, event_type);
}
@@ -2697,9 +2735,9 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
perf_event_sched_in(cpuctx, task_ctx);
- perf_ctx_enable(&cpuctx->ctx);
+ perf_ctx_enable(&cpuctx->ctx, false);
if (task_ctx)
- perf_ctx_enable(task_ctx);
+ perf_ctx_enable(task_ctx, false);
}
void perf_pmu_resched(struct pmu *pmu)
@@ -3244,6 +3282,9 @@ ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
struct perf_event_pmu_context *pmu_ctx;
int is_active = ctx->is_active;
+ bool cgroup = event_type & EVENT_CGROUP;
+
+ event_type &= ~EVENT_CGROUP;
lockdep_assert_held(&ctx->lock);
@@ -3290,8 +3331,11 @@ ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
is_active ^= ctx->is_active; /* changed bits */
- list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry)
+ list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+ if (cgroup && !pmu_ctx->nr_cgroups)
+ continue;
__pmu_ctx_sched_out(pmu_ctx, is_active);
+ }
}
/*
@@ -3482,7 +3526,7 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next)
raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
if (context_equiv(ctx, next_ctx)) {
- perf_ctx_disable(ctx);
+ perf_ctx_disable(ctx, false);
/* PMIs are disabled; ctx->nr_pending is stable. */
if (local_read(&ctx->nr_pending) ||
@@ -3502,7 +3546,7 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next)
perf_ctx_sched_task_cb(ctx, false);
perf_event_swap_task_ctx_data(ctx, next_ctx);
- perf_ctx_enable(ctx);
+ perf_ctx_enable(ctx, false);
/*
* RCU_INIT_POINTER here is safe because we've not
@@ -3526,13 +3570,13 @@ unlock:
if (do_switch) {
raw_spin_lock(&ctx->lock);
- perf_ctx_disable(ctx);
+ perf_ctx_disable(ctx, false);
inside_switch:
perf_ctx_sched_task_cb(ctx, false);
task_ctx_sched_out(ctx, EVENT_ALL);
- perf_ctx_enable(ctx);
+ perf_ctx_enable(ctx, false);
raw_spin_unlock(&ctx->lock);
}
}
@@ -3818,47 +3862,32 @@ static int merge_sched_in(struct perf_event *event, void *data)
return 0;
}
-static void ctx_pinned_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void pmu_groups_sched_in(struct perf_event_context *ctx,
+ struct perf_event_groups *groups,
+ struct pmu *pmu)
{
- struct perf_event_pmu_context *pmu_ctx;
int can_add_hw = 1;
-
- if (pmu) {
- visit_groups_merge(ctx, &ctx->pinned_groups,
- smp_processor_id(), pmu,
- merge_sched_in, &can_add_hw);
- } else {
- list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
- can_add_hw = 1;
- visit_groups_merge(ctx, &ctx->pinned_groups,
- smp_processor_id(), pmu_ctx->pmu,
- merge_sched_in, &can_add_hw);
- }
- }
+ visit_groups_merge(ctx, groups, smp_processor_id(), pmu,
+ merge_sched_in, &can_add_hw);
}
-static void ctx_flexible_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void ctx_groups_sched_in(struct perf_event_context *ctx,
+ struct perf_event_groups *groups,
+ bool cgroup)
{
struct perf_event_pmu_context *pmu_ctx;
- int can_add_hw = 1;
- if (pmu) {
- visit_groups_merge(ctx, &ctx->flexible_groups,
- smp_processor_id(), pmu,
- merge_sched_in, &can_add_hw);
- } else {
- list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
- can_add_hw = 1;
- visit_groups_merge(ctx, &ctx->flexible_groups,
- smp_processor_id(), pmu_ctx->pmu,
- merge_sched_in, &can_add_hw);
- }
+ list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+ if (cgroup && !pmu_ctx->nr_cgroups)
+ continue;
+ pmu_groups_sched_in(ctx, groups, pmu_ctx->pmu);
}
}
-static void __pmu_ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void __pmu_ctx_sched_in(struct perf_event_context *ctx,
+ struct pmu *pmu)
{
- ctx_flexible_sched_in(ctx, pmu);
+ pmu_groups_sched_in(ctx, &ctx->flexible_groups, pmu);
}
static void
@@ -3866,6 +3895,9 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
int is_active = ctx->is_active;
+ bool cgroup = event_type & EVENT_CGROUP;
+
+ event_type &= ~EVENT_CGROUP;
lockdep_assert_held(&ctx->lock);
@@ -3898,11 +3930,11 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
* in order to give them the best chance of going on.
*/
if (is_active & EVENT_PINNED)
- ctx_pinned_sched_in(ctx, NULL);
+ ctx_groups_sched_in(ctx, &ctx->pinned_groups, cgroup);
/* Then walk through the lower prio flexible groups */
if (is_active & EVENT_FLEXIBLE)
- ctx_flexible_sched_in(ctx, NULL);
+ ctx_groups_sched_in(ctx, &ctx->flexible_groups, cgroup);
}
static void perf_event_context_sched_in(struct task_struct *task)
@@ -3917,11 +3949,11 @@ static void perf_event_context_sched_in(struct task_struct *task)
if (cpuctx->task_ctx == ctx) {
perf_ctx_lock(cpuctx, ctx);
- perf_ctx_disable(ctx);
+ perf_ctx_disable(ctx, false);
perf_ctx_sched_task_cb(ctx, true);
- perf_ctx_enable(ctx);
+ perf_ctx_enable(ctx, false);
perf_ctx_unlock(cpuctx, ctx);
goto rcu_unlock;
}
@@ -3934,7 +3966,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
if (!ctx->nr_events)
goto unlock;
- perf_ctx_disable(ctx);
+ perf_ctx_disable(ctx, false);
/*
* We want to keep the following priority order:
* cpu pinned (that don't need to move), task pinned,
@@ -3944,7 +3976,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
* events, no need to flip the cpuctx's events around.
*/
if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) {
- perf_ctx_disable(&cpuctx->ctx);
+ perf_ctx_disable(&cpuctx->ctx, false);
ctx_sched_out(&cpuctx->ctx, EVENT_FLEXIBLE);
}
@@ -3953,9 +3985,9 @@ static void perf_event_context_sched_in(struct task_struct *task)
perf_ctx_sched_task_cb(cpuctx->task_ctx, true);
if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree))
- perf_ctx_enable(&cpuctx->ctx);
+ perf_ctx_enable(&cpuctx->ctx, false);
- perf_ctx_enable(ctx);
+ perf_ctx_enable(ctx, false);
unlock:
perf_ctx_unlock(cpuctx, ctx);
@@ -4425,6 +4457,9 @@ static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
{
u16 local_pkg, event_pkg;
+ if ((unsigned)event_cpu >= nr_cpu_ids)
+ return event_cpu;
+
if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
int local_cpu = smp_processor_id();
@@ -4527,6 +4562,8 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
u64 *enabled, u64 *running)
{
unsigned long flags;
+ int event_oncpu;
+ int event_cpu;
int ret = 0;
/*
@@ -4551,15 +4588,22 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
goto out;
}
+ /*
+ * Get the event CPU numbers, and adjust them to local if the event is
+ * a per-package event that can be read locally
+ */
+ event_oncpu = __perf_event_read_cpu(event, event->oncpu);
+ event_cpu = __perf_event_read_cpu(event, event->cpu);
+
/* If this is a per-CPU event, it must be for this CPU */
if (!(event->attach_state & PERF_ATTACH_TASK) &&
- event->cpu != smp_processor_id()) {
+ event_cpu != smp_processor_id()) {
ret = -EINVAL;
goto out;
}
/* If this is a pinned event it must be running on this CPU */
- if (event->attr.pinned && event->oncpu != smp_processor_id()) {
+ if (event->attr.pinned && event_oncpu != smp_processor_id()) {
ret = -EBUSY;
goto out;
}
@@ -4569,7 +4613,7 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
* or local to this CPU. Furthermore it means its ACTIVE (otherwise
* oncpu == -1).
*/
- if (event->oncpu == smp_processor_id())
+ if (event_oncpu == smp_processor_id())
event->pmu->read(event);
*value = local64_read(&event->count);
@@ -4809,6 +4853,11 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
void *task_ctx_data = NULL;
if (!ctx->task) {
+ /*
+ * perf_pmu_migrate_context() / __perf_pmu_install_event()
+ * relies on the fact that find_get_pmu_context() cannot fail
+ * for CPU contexts.
+ */
struct perf_cpu_pmu_context *cpc;
cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
@@ -5440,7 +5489,7 @@ static int __perf_read_group_add(struct perf_event *leader,
u64 read_format, u64 *values)
{
struct perf_event_context *ctx = leader->ctx;
- struct perf_event *sub;
+ struct perf_event *sub, *parent;
unsigned long flags;
int n = 1; /* skip @nr */
int ret;
@@ -5450,6 +5499,33 @@ static int __perf_read_group_add(struct perf_event *leader,
return ret;
raw_spin_lock_irqsave(&ctx->lock, flags);
+ /*
+ * Verify the grouping between the parent and child (inherited)
+ * events is still in tact.
+ *
+ * Specifically:
+ * - leader->ctx->lock pins leader->sibling_list
+ * - parent->child_mutex pins parent->child_list
+ * - parent->ctx->mutex pins parent->sibling_list
+ *
+ * Because parent->ctx != leader->ctx (and child_list nests inside
+ * ctx->mutex), group destruction is not atomic between children, also
+ * see perf_event_release_kernel(). Additionally, parent can grow the
+ * group.
+ *
+ * Therefore it is possible to have parent and child groups in a
+ * different configuration and summing over such a beast makes no sense
+ * what so ever.
+ *
+ * Reject this.
+ */
+ parent = leader->parent;
+ if (parent &&
+ (parent->group_generation != leader->group_generation ||
+ parent->nr_siblings != leader->nr_siblings)) {
+ ret = -ECHILD;
+ goto unlock;
+ }
/*
* Since we co-schedule groups, {enabled,running} times of siblings
@@ -5483,8 +5559,9 @@ static int __perf_read_group_add(struct perf_event *leader,
values[n++] = atomic64_read(&sub->lost_samples);
}
+unlock:
raw_spin_unlock_irqrestore(&ctx->lock, flags);
- return 0;
+ return ret;
}
static int perf_read_group(struct perf_event *event,
@@ -5503,10 +5580,6 @@ static int perf_read_group(struct perf_event *event,
values[0] = 1 + leader->nr_siblings;
- /*
- * By locking the child_mutex of the leader we effectively
- * lock the child list of all siblings.. XXX explain how.
- */
mutex_lock(&leader->child_mutex);
ret = __perf_read_group_add(leader, read_format, values);
@@ -8249,7 +8322,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
unsigned int size;
memset(comm, 0, sizeof(comm));
- strlcpy(comm, comm_event->task->comm, sizeof(comm));
+ strscpy(comm, comm_event->task->comm, sizeof(comm));
size = ALIGN(strlen(comm)+1, sizeof(u64));
comm_event->comm = comm;
@@ -8631,7 +8704,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
unsigned int size;
char tmp[16];
char *buf = NULL;
- char *name;
+ char *name = NULL;
if (vma->vm_flags & VM_READ)
prot |= PROT_READ;
@@ -8678,33 +8751,22 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
goto got_name;
} else {
- if (vma->vm_ops && vma->vm_ops->name) {
+ if (vma->vm_ops && vma->vm_ops->name)
name = (char *) vma->vm_ops->name(vma);
- if (name)
- goto cpy_name;
+ if (!name)
+ name = (char *)arch_vma_name(vma);
+ if (!name) {
+ if (vma_is_initial_heap(vma))
+ name = "[heap]";
+ else if (vma_is_initial_stack(vma))
+ name = "[stack]";
+ else
+ name = "//anon";
}
-
- name = (char *)arch_vma_name(vma);
- if (name)
- goto cpy_name;
-
- if (vma->vm_start <= vma->vm_mm->start_brk &&
- vma->vm_end >= vma->vm_mm->brk) {
- name = "[heap]";
- goto cpy_name;
- }
- if (vma->vm_start <= vma->vm_mm->start_stack &&
- vma->vm_end >= vma->vm_mm->start_stack) {
- name = "[stack]";
- goto cpy_name;
- }
-
- name = "//anon";
- goto cpy_name;
}
cpy_name:
- strlcpy(tmp, name, sizeof(tmp));
+ strscpy(tmp, name, sizeof(tmp));
name = tmp;
got_name:
/*
@@ -9128,7 +9190,7 @@ void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister,
ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN)
goto err;
- strlcpy(name, sym, KSYM_NAME_LEN);
+ strscpy(name, sym, KSYM_NAME_LEN);
name_len = strlen(name) + 1;
while (!IS_ALIGNED(name_len, sizeof(u64)))
name[name_len++] = '\0';
@@ -9595,16 +9657,16 @@ u64 perf_swevent_set_period(struct perf_event *event)
hwc->last_period = hwc->sample_period;
-again:
- old = val = local64_read(&hwc->period_left);
- if (val < 0)
- return 0;
+ old = local64_read(&hwc->period_left);
+ do {
+ val = old;
+ if (val < 0)
+ return 0;
- nr = div64_u64(period + val, period);
- offset = nr * period;
- val -= offset;
- if (local64_cmpxchg(&hwc->period_left, old, val) != old)
- goto again;
+ nr = div64_u64(period + val, period);
+ offset = nr * period;
+ val -= offset;
+ } while (!local64_try_cmpxchg(&hwc->period_left, &old, val));
return nr;
}
@@ -12857,6 +12919,9 @@ static void __perf_pmu_install_event(struct pmu *pmu,
int cpu, struct perf_event *event)
{
struct perf_event_pmu_context *epc;
+ struct perf_event_context *old_ctx = event->ctx;
+
+ get_ctx(ctx); /* normally find_get_context() */
event->cpu = cpu;
epc = find_get_pmu_context(pmu, ctx, event);
@@ -12865,6 +12930,11 @@ static void __perf_pmu_install_event(struct pmu *pmu,
if (event->state >= PERF_EVENT_STATE_OFF)
event->state = PERF_EVENT_STATE_INACTIVE;
perf_install_in_context(ctx, event, cpu);
+
+ /*
+ * Now that event->ctx is updated and visible, put the old ctx.
+ */
+ put_ctx(old_ctx);
}
static void __perf_pmu_install(struct perf_event_context *ctx,
@@ -12903,6 +12973,10 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
struct perf_event_context *src_ctx, *dst_ctx;
LIST_HEAD(events);
+ /*
+ * Since per-cpu context is persistent, no need to grab an extra
+ * reference.
+ */
src_ctx = &per_cpu_ptr(&perf_cpu_context, src_cpu)->ctx;
dst_ctx = &per_cpu_ptr(&perf_cpu_context, dst_cpu)->ctx;
@@ -13357,6 +13431,8 @@ static int inherit_group(struct perf_event *parent_event,
!perf_get_aux_event(child_ctr, leader))
return -EINVAL;
}
+ if (leader)
+ leader->group_generation = parent_event->group_generation;
return 0;
}
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index c3797701339c..6c2cb4e4f48d 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -523,26 +523,6 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, int we
return 0;
}
-__weak int arch_reserve_bp_slot(struct perf_event *bp)
-{
- return 0;
-}
-
-__weak void arch_release_bp_slot(struct perf_event *bp)
-{
-}
-
-/*
- * Function to perform processor-specific cleanup during unregistration
- */
-__weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
-{
- /*
- * A weak stub function here for those archs that don't define
- * it inside arch/.../kernel/hw_breakpoint.c
- */
-}
-
/*
* Constraints to check before allowing this new breakpoint counter.
*
@@ -594,7 +574,6 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
enum bp_type_idx type;
int max_pinned_slots;
int weight;
- int ret;
/* We couldn't initialize breakpoint constraints on boot */
if (!constraints_initialized)
@@ -613,10 +592,6 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
if (max_pinned_slots > hw_breakpoint_slots_cached(type))
return -ENOSPC;
- ret = arch_reserve_bp_slot(bp);
- if (ret)
- return ret;
-
return toggle_bp_slot(bp, true, type, weight);
}
@@ -634,8 +609,6 @@ static void __release_bp_slot(struct perf_event *bp, u64 bp_type)
enum bp_type_idx type;
int weight;
- arch_release_bp_slot(bp);
-
type = find_slot_idx(bp_type);
weight = hw_breakpoint_weight(bp);
WARN_ON(toggle_bp_slot(bp, false, type, weight));
@@ -645,7 +618,6 @@ void release_bp_slot(struct perf_event *bp)
{
struct mutex *mtx = bp_constraints_lock(bp);
- arch_unregister_hw_breakpoint(bp);
__release_bp_slot(bp, bp->attr.bp_type);
bp_constraints_unlock(mtx);
}
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index a0433f37b024..e8d82c2f07d0 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -191,9 +191,10 @@ __perf_output_begin(struct perf_output_handle *handle,
perf_output_get_handle(handle);
+ offset = local_read(&rb->head);
do {
+ head = offset;
tail = READ_ONCE(rb->user_page->data_tail);
- offset = head = local_read(&rb->head);
if (!rb->overwrite) {
if (unlikely(!ring_buffer_has_space(head, tail,
perf_data_size(rb),
@@ -217,7 +218,7 @@ __perf_output_begin(struct perf_output_handle *handle,
head += size;
else
head -= size;
- } while (local_cmpxchg(&rb->head, offset, head) != offset);
+ } while (!local_try_cmpxchg(&rb->head, &offset, head));
if (backward) {
offset = head;
@@ -699,6 +700,12 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
watermark = 0;
}
+ /*
+ * kcalloc_node() is unable to allocate buffer if the size is larger
+ * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case.
+ */
+ if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER)
+ return -ENOMEM;
rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,
node);
if (!rb->aux_pages)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f0ac5b874919..435aac1d8c27 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -193,7 +193,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
}
flush_cache_page(vma, addr, pte_pfn(ptep_get(pvmw.pte)));
- ptep_clear_flush_notify(vma, addr, pvmw.pte);
+ ptep_clear_flush(vma, addr, pvmw.pte);
if (new_page)
set_pte_at_notify(mm, addr, pvmw.pte,
mk_pte(new_page, vma->vm_page_prot));
@@ -474,8 +474,8 @@ retry:
gup_flags |= FOLL_SPLIT_PMD;
/* Read the page with vaddr into memory */
old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
- if (IS_ERR_OR_NULL(old_page))
- return old_page ? PTR_ERR(old_page) : 0;
+ if (IS_ERR(old_page))
+ return PTR_ERR(old_page);
ret = verify_opcode(old_page, vaddr, &opcode);
if (ret <= 0)
diff --git a/kernel/exit.c b/kernel/exit.c
index edb50b4c9972..aedc0832c9f4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,8 @@
#include <asm/unistd.h>
#include <asm/mmu_context.h>
+#include "exit.h"
+
/*
* The default value should be high enough to not crash a system that randomly
* crashes its kernel from time to time, but low enough to at least not permit
@@ -133,7 +135,6 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
list_del_init(&p->sibling);
__this_cpu_dec(process_counts);
}
- list_del_rcu(&p->thread_group);
list_del_rcu(&p->thread_node);
}
@@ -539,7 +540,6 @@ static void exit_mm(void)
exit_mm_release(current, mm);
if (!mm)
return;
- sync_mm_rss(mm);
mmap_read_lock(mm);
mmgrab_lazy_tlb(mm);
BUG_ON(mm != current->active_mm);
@@ -824,14 +824,9 @@ void __noreturn do_exit(long code)
ptrace_event(PTRACE_EVENT_EXIT, code);
user_events_exit(tsk);
- validate_creds_for_do_exit(tsk);
-
io_uring_files_cancel();
exit_signals(tsk); /* sets PF_EXITING */
- /* sync mm's RSS info before statistics gathering */
- if (tsk->mm)
- sync_mm_rss(tsk->mm);
acct_update_integrals(tsk);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
@@ -912,7 +907,6 @@ void __noreturn do_exit(long code)
if (tsk->task_frag.page)
put_page(tsk->task_frag.page);
- validate_creds_for_do_exit(tsk);
exit_task_stack_account(tsk);
check_stack_usage();
@@ -1037,26 +1031,6 @@ SYSCALL_DEFINE1(exit_group, int, error_code)
return 0;
}
-struct waitid_info {
- pid_t pid;
- uid_t uid;
- int status;
- int cause;
-};
-
-struct wait_opts {
- enum pid_type wo_type;
- int wo_flags;
- struct pid *wo_pid;
-
- struct waitid_info *wo_info;
- int wo_stat;
- struct rusage *wo_rusage;
-
- wait_queue_entry_t child_wait;
- int notask_error;
-};
-
static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
{
return wo->wo_type == PIDTYPE_MAX ||
@@ -1520,6 +1494,17 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
return 0;
}
+bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p)
+{
+ if (!eligible_pid(wo, p))
+ return false;
+
+ if ((wo->wo_flags & __WNOTHREAD) && wo->child_wait.private != p->parent)
+ return false;
+
+ return true;
+}
+
static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
int sync, void *key)
{
@@ -1527,13 +1512,10 @@ static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
child_wait);
struct task_struct *p = key;
- if (!eligible_pid(wo, p))
- return 0;
-
- if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
- return 0;
+ if (pid_child_should_wake(wo, p))
+ return default_wake_function(wait, mode, sync, key);
- return default_wake_function(wait, mode, sync, key);
+ return 0;
}
void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
@@ -1582,16 +1564,10 @@ static int do_wait_pid(struct wait_opts *wo)
return 0;
}
-static long do_wait(struct wait_opts *wo)
+long __do_wait(struct wait_opts *wo)
{
- int retval;
+ long retval;
- trace_sched_process_wait(wo->wo_pid);
-
- init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
- wo->child_wait.private = current;
- add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
-repeat:
/*
* If there is nothing that can match our criteria, just get out.
* We will clear ->notask_error to zero if we see any child that
@@ -1603,24 +1579,23 @@ repeat:
(!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type)))
goto notask;
- set_current_state(TASK_INTERRUPTIBLE);
read_lock(&tasklist_lock);
if (wo->wo_type == PIDTYPE_PID) {
retval = do_wait_pid(wo);
if (retval)
- goto end;
+ return retval;
} else {
struct task_struct *tsk = current;
do {
retval = do_wait_thread(wo, tsk);
if (retval)
- goto end;
+ return retval;
retval = ptrace_do_wait(wo, tsk);
if (retval)
- goto end;
+ return retval;
if (wo->wo_flags & __WNOTHREAD)
break;
@@ -1630,27 +1605,44 @@ repeat:
notask:
retval = wo->notask_error;
- if (!retval && !(wo->wo_flags & WNOHANG)) {
- retval = -ERESTARTSYS;
- if (!signal_pending(current)) {
- schedule();
- goto repeat;
- }
- }
-end:
+ if (!retval && !(wo->wo_flags & WNOHANG))
+ return -ERESTARTSYS;
+
+ return retval;
+}
+
+static long do_wait(struct wait_opts *wo)
+{
+ int retval;
+
+ trace_sched_process_wait(wo->wo_pid);
+
+ init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+ wo->child_wait.private = current;
+ add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
+
+ do {
+ set_current_state(TASK_INTERRUPTIBLE);
+ retval = __do_wait(wo);
+ if (retval != -ERESTARTSYS)
+ break;
+ if (signal_pending(current))
+ break;
+ schedule();
+ } while (1);
+
__set_current_state(TASK_RUNNING);
remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
return retval;
}
-static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
- int options, struct rusage *ru)
+int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
+ struct waitid_info *infop, int options,
+ struct rusage *ru)
{
- struct wait_opts wo;
+ unsigned int f_flags = 0;
struct pid *pid = NULL;
enum pid_type type;
- long ret;
- unsigned int f_flags = 0;
if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
__WNOTHREAD|__WCLONE|__WALL))
@@ -1693,19 +1685,32 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
return -EINVAL;
}
- wo.wo_type = type;
- wo.wo_pid = pid;
- wo.wo_flags = options;
- wo.wo_info = infop;
- wo.wo_rusage = ru;
+ wo->wo_type = type;
+ wo->wo_pid = pid;
+ wo->wo_flags = options;
+ wo->wo_info = infop;
+ wo->wo_rusage = ru;
if (f_flags & O_NONBLOCK)
- wo.wo_flags |= WNOHANG;
+ wo->wo_flags |= WNOHANG;
+
+ return 0;
+}
+
+static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
+ int options, struct rusage *ru)
+{
+ struct wait_opts wo;
+ long ret;
+
+ ret = kernel_waitid_prepare(&wo, which, upid, infop, options, ru);
+ if (ret)
+ return ret;
ret = do_wait(&wo);
- if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK))
+ if (!ret && !(options & WNOHANG) && (wo.wo_flags & WNOHANG))
ret = -EAGAIN;
- put_pid(pid);
+ put_pid(wo.wo_pid);
return ret;
}
diff --git a/kernel/exit.h b/kernel/exit.h
new file mode 100644
index 000000000000..278faa26a653
--- /dev/null
+++ b/kernel/exit.h
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef LINUX_WAITID_H
+#define LINUX_WAITID_H
+
+struct waitid_info {
+ pid_t pid;
+ uid_t uid;
+ int status;
+ int cause;
+};
+
+struct wait_opts {
+ enum pid_type wo_type;
+ int wo_flags;
+ struct pid *wo_pid;
+
+ struct waitid_info *wo_info;
+ int wo_stat;
+ struct rusage *wo_rusage;
+
+ wait_queue_entry_t child_wait;
+ int notask_error;
+};
+
+bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p);
+long __do_wait(struct wait_opts *wo);
+int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
+ struct waitid_info *infop, int options,
+ struct rusage *ru);
+#endif
diff --git a/kernel/fork.c b/kernel/fork.c
index d2e12b6d2b18..10917c3e1f03 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -733,7 +733,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
get_file(file);
i_mmap_lock_write(mapping);
- if (tmp->vm_flags & VM_SHARED)
+ if (vma_is_shared_maywrite(tmp))
mapping_allow_writable(mapping);
flush_dcache_mmap_lock(mapping);
/* insert tmp into the share list, just after mpnt */
@@ -909,8 +909,6 @@ static void cleanup_lazy_tlbs(struct mm_struct *mm)
*/
void __mmdrop(struct mm_struct *mm)
{
- int i;
-
BUG_ON(mm == &init_mm);
WARN_ON_ONCE(mm == current->mm);
@@ -925,9 +923,8 @@ void __mmdrop(struct mm_struct *mm)
put_user_ns(mm->user_ns);
mm_pasid_drop(mm);
mm_destroy_cid(mm);
+ percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS);
- for (i = 0; i < NR_MM_COUNTERS; i++)
- percpu_counter_destroy(&mm->rss_stat[i]);
free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);
@@ -985,6 +982,14 @@ void __put_task_struct(struct task_struct *tsk)
}
EXPORT_SYMBOL_GPL(__put_task_struct);
+void __put_task_struct_rcu_cb(struct rcu_head *rhp)
+{
+ struct task_struct *task = container_of(rhp, struct task_struct, rcu);
+
+ __put_task_struct(task);
+}
+EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb);
+
void __init __weak arch_task_cache_init(void) { }
/*
@@ -1252,8 +1257,6 @@ static void mm_init_uprobes_state(struct mm_struct *mm)
static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
struct user_namespace *user_ns)
{
- int i;
-
mt_init_flags(&mm->mm_mt, MM_MT_FLAGS);
mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock);
atomic_set(&mm->mm_users, 1);
@@ -1285,7 +1288,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
hugetlb_count_init(mm);
if (current->mm) {
- mm->flags = current->mm->flags & MMF_INIT_MASK;
+ mm->flags = mmf_init_flags(current->mm->flags);
mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
} else {
mm->flags = default_dump_filter;
@@ -1301,17 +1304,15 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
if (mm_alloc_cid(mm))
goto fail_cid;
- for (i = 0; i < NR_MM_COUNTERS; i++)
- if (percpu_counter_init(&mm->rss_stat[i], 0, GFP_KERNEL_ACCOUNT))
- goto fail_pcpu;
+ if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT,
+ NR_MM_COUNTERS))
+ goto fail_pcpu;
mm->user_ns = get_user_ns(user_ns);
lru_gen_init_mm(mm);
return mm;
fail_pcpu:
- while (i > 0)
- percpu_counter_destroy(&mm->rss_stat[--i]);
mm_destroy_cid(mm);
fail_cid:
destroy_context(mm);
@@ -1392,12 +1393,14 @@ EXPORT_SYMBOL_GPL(mmput_async);
/**
* set_mm_exe_file - change a reference to the mm's executable file
+ * @mm: The mm to change.
+ * @new_exe_file: The new file to use.
*
* This changes mm's executable file (shown as symlink /proc/[pid]/exe).
*
* Main users are mmput() and sys_execve(). Callers prevent concurrent
- * invocations: in mmput() nobody alive left, in execve task is single
- * threaded.
+ * invocations: in mmput() nobody alive left, in execve it happens before
+ * the new mm is made visible to anyone.
*
* Can only fail if new_exe_file != NULL.
*/
@@ -1431,10 +1434,10 @@ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
/**
* replace_mm_exe_file - replace a reference to the mm's executable file
+ * @mm: The mm to change.
+ * @new_exe_file: The new file to use.
*
- * This changes mm's executable file (shown as symlink /proc/[pid]/exe),
- * dealing with concurrent invocation and without grabbing the mmap lock in
- * write mode.
+ * This changes mm's executable file (shown as symlink /proc/[pid]/exe).
*
* Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE).
*/
@@ -1464,28 +1467,27 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
return ret;
}
- /* set the new file, lockless */
ret = deny_write_access(new_exe_file);
if (ret)
return -EACCES;
get_file(new_exe_file);
- old_exe_file = xchg(&mm->exe_file, new_exe_file);
+ /* set the new file */
+ mmap_write_lock(mm);
+ old_exe_file = rcu_dereference_raw(mm->exe_file);
+ rcu_assign_pointer(mm->exe_file, new_exe_file);
+ mmap_write_unlock(mm);
+
if (old_exe_file) {
- /*
- * Don't race with dup_mmap() getting the file and disallowing
- * write access while someone might open the file writable.
- */
- mmap_read_lock(mm);
allow_write_access(old_exe_file);
fput(old_exe_file);
- mmap_read_unlock(mm);
}
return 0;
}
/**
* get_mm_exe_file - acquire a reference to the mm's executable file
+ * @mm: The mm of interest.
*
* Returns %NULL if mm has no associated executable file.
* User must release file via fput().
@@ -1495,15 +1497,14 @@ struct file *get_mm_exe_file(struct mm_struct *mm)
struct file *exe_file;
rcu_read_lock();
- exe_file = rcu_dereference(mm->exe_file);
- if (exe_file && !get_file_rcu(exe_file))
- exe_file = NULL;
+ exe_file = get_file_rcu(&mm->exe_file);
rcu_read_unlock();
return exe_file;
}
/**
* get_task_exe_file - acquire a reference to the task's executable file
+ * @task: The task.
*
* Returns %NULL if task's mm (if any) has no associated executable file or
* this is a kernel thread with borrowed mm (see the comment above get_task_mm).
@@ -1526,6 +1527,7 @@ struct file *get_task_exe_file(struct task_struct *task)
/**
* get_task_mm - acquire a reference to the task's mm
+ * @task: The task.
*
* Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning
* this kernel workthread has transiently adopted a user mm with use_mm,
@@ -2105,11 +2107,11 @@ const struct file_operations pidfd_fops = {
* __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
* @pid: the struct pid for which to create a pidfd
* @flags: flags of the new @pidfd
- * @pidfd: the pidfd to return
+ * @ret: Where to return the file for the pidfd.
*
* Allocate a new file that stashes @pid and reserve a new pidfd number in the
* caller's file descriptor table. The pidfd is reserved but not installed yet.
-
+ *
* The helper doesn't perform checks on @pid which makes it useful for pidfds
* created via CLONE_PIDFD where @pid has no task attached when the pidfd and
* pidfd file are prepared.
@@ -2156,7 +2158,7 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
* pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
* @pid: the struct pid for which to create a pidfd
* @flags: flags of the new @pidfd
- * @pidfd: the pidfd to return
+ * @ret: Where to return the pidfd.
*
* Allocate a new file that stashes @pid and reserve a new pidfd number in the
* caller's file descriptor table. The pidfd is reserved but not installed yet.
@@ -2409,10 +2411,6 @@ __latent_entropy struct task_struct *copy_process(
p->io_uring = NULL;
#endif
-#if defined(SPLIT_RSS_COUNTING)
- memset(&p->rss_stat, 0, sizeof(p->rss_stat));
-#endif
-
p->default_timer_slack_ns = current->timer_slack_ns;
#ifdef CONFIG_PSI
@@ -2579,7 +2577,6 @@ __latent_entropy struct task_struct *copy_process(
p->dirty_paused_when = 0;
p->pdeath_signal = 0;
- INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
clear_posix_cputimers_work(p);
@@ -2707,8 +2704,6 @@ __latent_entropy struct task_struct *copy_process(
atomic_inc(&current->signal->live);
refcount_inc(&current->signal->sigcnt);
task_join_group_stop(p);
- list_add_tail_rcu(&p->thread_group,
- &p->group_leader->thread_group);
list_add_tail_rcu(&p->thread_node,
&p->signal->thread_head);
}
@@ -3147,7 +3142,7 @@ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
if (!access_ok((void __user *)kargs->stack, kargs->stack_size))
return false;
-#if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64)
+#if !defined(CONFIG_STACK_GROWSUP)
kargs->stack += kargs->stack_size;
#endif
}
@@ -3184,7 +3179,7 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs)
}
/**
- * clone3 - create a new process with specific properties
+ * sys_clone3 - create a new process with specific properties
* @uargs: argument structure
* @size: size of @uargs
*
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 4fad0e6fca64..759006a9a910 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -71,7 +71,11 @@ bool __refrigerator(bool check_kthr_stop)
for (;;) {
bool freeze;
+ raw_spin_lock_irq(&current->pi_lock);
set_current_state(TASK_FROZEN);
+ /* unstale saved_state so that __thaw_task() will wake us up */
+ current->saved_state = TASK_RUNNING;
+ raw_spin_unlock_irq(&current->pi_lock);
spin_lock_irq(&freezer_lock);
freeze = freezing(current) && !(check_kthr_stop && kthread_should_stop());
@@ -129,6 +133,7 @@ static int __set_task_frozen(struct task_struct *p, void *arg)
WARN_ON_ONCE(debug_locks && p->lockdep_depth);
#endif
+ p->saved_state = p->__state;
WRITE_ONCE(p->__state, TASK_FROZEN);
return TASK_FROZEN;
}
@@ -170,42 +175,34 @@ bool freeze_task(struct task_struct *p)
}
/*
- * The special task states (TASK_STOPPED, TASK_TRACED) keep their canonical
- * state in p->jobctl. If either of them got a wakeup that was missed because
- * TASK_FROZEN, then their canonical state reflects that and the below will
- * refuse to restore the special state and instead issue the wakeup.
+ * Restore the saved_state before the task entered freezer. For typical task
+ * in the __refrigerator(), saved_state == TASK_RUNNING so nothing happens
+ * here. For tasks which were TASK_NORMAL | TASK_FREEZABLE, their initial state
+ * is restored unless they got an expected wakeup (see ttwu_state_match()).
+ * Returns 1 if the task state was restored.
*/
-static int __set_task_special(struct task_struct *p, void *arg)
+static int __restore_freezer_state(struct task_struct *p, void *arg)
{
- unsigned int state = 0;
+ unsigned int state = p->saved_state;
- if (p->jobctl & JOBCTL_TRACED)
- state = TASK_TRACED;
-
- else if (p->jobctl & JOBCTL_STOPPED)
- state = TASK_STOPPED;
-
- if (state)
+ if (state != TASK_RUNNING) {
WRITE_ONCE(p->__state, state);
+ return 1;
+ }
- return state;
+ return 0;
}
void __thaw_task(struct task_struct *p)
{
- unsigned long flags, flags2;
+ unsigned long flags;
spin_lock_irqsave(&freezer_lock, flags);
if (WARN_ON_ONCE(freezing(p)))
goto unlock;
- if (lock_task_sighand(p, &flags2)) {
- /* TASK_FROZEN -> TASK_{STOPPED,TRACED} */
- bool ret = task_call_func(p, __set_task_special, NULL);
- unlock_task_sighand(p, &flags2);
- if (ret)
- goto unlock;
- }
+ if (!frozen(p) || task_call_func(p, __restore_freezer_state, NULL))
+ goto unlock;
wake_up_state(p, TASK_FROZEN);
unlock:
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 514e4582b863..dad981a865b8 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -193,7 +193,7 @@ static u64 get_inode_sequence_number(struct inode *inode)
/**
* get_futex_key() - Get parameters which are the keys for a futex
* @uaddr: virtual address of the futex
- * @fshared: false for a PROCESS_PRIVATE futex, true for PROCESS_SHARED
+ * @flags: FLAGS_*
* @key: address where result is stored.
* @rw: mapping needs to be read/write (values: FUTEX_READ,
* FUTEX_WRITE)
@@ -217,14 +217,18 @@ static u64 get_inode_sequence_number(struct inode *inode)
*
* lock_page() might sleep, the caller should not hold a spinlock.
*/
-int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key,
+int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
enum futex_access rw)
{
unsigned long address = (unsigned long)uaddr;
struct mm_struct *mm = current->mm;
- struct page *page, *tail;
+ struct page *page;
+ struct folio *folio;
struct address_space *mapping;
int err, ro = 0;
+ bool fshared;
+
+ fshared = flags & FLAGS_SHARED;
/*
* The futex address must be "naturally" aligned.
@@ -248,7 +252,17 @@ int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key,
* but access_ok() should be faster than find_vma()
*/
if (!fshared) {
- key->private.mm = mm;
+ /*
+ * On no-MMU, shared futexes are treated as private, therefore
+ * we must not include the current process in the key. Since
+ * there is only one address space, the address is a unique key
+ * on its own.
+ */
+ if (IS_ENABLED(CONFIG_MMU))
+ key->private.mm = mm;
+ else
+ key->private.mm = NULL;
+
key->private.address = address;
return 0;
}
@@ -273,54 +287,52 @@ again:
err = 0;
/*
- * The treatment of mapping from this point on is critical. The page
- * lock protects many things but in this context the page lock
+ * The treatment of mapping from this point on is critical. The folio
+ * lock protects many things but in this context the folio lock
* stabilizes mapping, prevents inode freeing in the shared
* file-backed region case and guards against movement to swap cache.
*
- * Strictly speaking the page lock is not needed in all cases being
- * considered here and page lock forces unnecessarily serialization
+ * Strictly speaking the folio lock is not needed in all cases being
+ * considered here and folio lock forces unnecessarily serialization.
* From this point on, mapping will be re-verified if necessary and
- * page lock will be acquired only if it is unavoidable
+ * folio lock will be acquired only if it is unavoidable
*
- * Mapping checks require the head page for any compound page so the
- * head page and mapping is looked up now. For anonymous pages, it
- * does not matter if the page splits in the future as the key is
- * based on the address. For filesystem-backed pages, the tail is
- * required as the index of the page determines the key. For
- * base pages, there is no tail page and tail == page.
+ * Mapping checks require the folio so it is looked up now. For
+ * anonymous pages, it does not matter if the folio is split
+ * in the future as the key is based on the address. For
+ * filesystem-backed pages, the precise page is required as the
+ * index of the page determines the key.
*/
- tail = page;
- page = compound_head(page);
- mapping = READ_ONCE(page->mapping);
+ folio = page_folio(page);
+ mapping = READ_ONCE(folio->mapping);
/*
- * If page->mapping is NULL, then it cannot be a PageAnon
+ * If folio->mapping is NULL, then it cannot be an anonymous
* page; but it might be the ZERO_PAGE or in the gate area or
* in a special mapping (all cases which we are happy to fail);
* or it may have been a good file page when get_user_pages_fast
* found it, but truncated or holepunched or subjected to
- * invalidate_complete_page2 before we got the page lock (also
+ * invalidate_complete_page2 before we got the folio lock (also
* cases which we are happy to fail). And we hold a reference,
* so refcount care in invalidate_inode_page's remove_mapping
* prevents drop_caches from setting mapping to NULL beneath us.
*
* The case we do have to guard against is when memory pressure made
* shmem_writepage move it from filecache to swapcache beneath us:
- * an unlikely race, but we do need to retry for page->mapping.
+ * an unlikely race, but we do need to retry for folio->mapping.
*/
if (unlikely(!mapping)) {
int shmem_swizzled;
/*
- * Page lock is required to identify which special case above
- * applies. If this is really a shmem page then the page lock
+ * Folio lock is required to identify which special case above
+ * applies. If this is really a shmem page then the folio lock
* will prevent unexpected transitions.
*/
- lock_page(page);
- shmem_swizzled = PageSwapCache(page) || page->mapping;
- unlock_page(page);
- put_page(page);
+ folio_lock(folio);
+ shmem_swizzled = folio_test_swapcache(folio) || folio->mapping;
+ folio_unlock(folio);
+ folio_put(folio);
if (shmem_swizzled)
goto again;
@@ -331,14 +343,14 @@ again:
/*
* Private mappings are handled in a simple way.
*
- * If the futex key is stored on an anonymous page, then the associated
+ * If the futex key is stored in anonymous memory, then the associated
* object is the mm which is implicitly pinned by the calling process.
*
* NOTE: When userspace waits on a MAP_SHARED mapping, even if
* it's a read-only handle, it's expected that futexes attach to
* the object not the particular process.
*/
- if (PageAnon(page)) {
+ if (folio_test_anon(folio)) {
/*
* A RO anonymous page will never change and thus doesn't make
* sense for futex operations.
@@ -357,10 +369,10 @@ again:
/*
* The associated futex object in this case is the inode and
- * the page->mapping must be traversed. Ordinarily this should
- * be stabilised under page lock but it's not strictly
+ * the folio->mapping must be traversed. Ordinarily this should
+ * be stabilised under folio lock but it's not strictly
* necessary in this case as we just want to pin the inode, not
- * update the radix tree or anything like that.
+ * update i_pages or anything like that.
*
* The RCU read lock is taken as the inode is finally freed
* under RCU. If the mapping still matches expectations then the
@@ -368,9 +380,9 @@ again:
*/
rcu_read_lock();
- if (READ_ONCE(page->mapping) != mapping) {
+ if (READ_ONCE(folio->mapping) != mapping) {
rcu_read_unlock();
- put_page(page);
+ folio_put(folio);
goto again;
}
@@ -378,19 +390,19 @@ again:
inode = READ_ONCE(mapping->host);
if (!inode) {
rcu_read_unlock();
- put_page(page);
+ folio_put(folio);
goto again;
}
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
key->shared.i_seq = get_inode_sequence_number(inode);
- key->shared.pgoff = page_to_pgoff(tail);
+ key->shared.pgoff = folio->index + folio_page_idx(folio, page);
rcu_read_unlock();
}
out:
- put_page(page);
+ folio_put(folio);
return err;
}
@@ -688,7 +700,8 @@ retry:
owner = uval & FUTEX_TID_MASK;
if (pending_op && !pi && !owner) {
- futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+ futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+ FUTEX_BITSET_MATCH_ANY);
return 0;
}
@@ -740,8 +753,10 @@ retry:
* Wake robust non-PI futexes here. The wakeup of
* PI futexes happens in exit_pi_state():
*/
- if (!pi && (uval & FUTEX_WAITERS))
- futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+ if (!pi && (uval & FUTEX_WAITERS)) {
+ futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+ FUTEX_BITSET_MATCH_ANY);
+ }
return 0;
}
@@ -1132,8 +1147,7 @@ static int __init futex_init(void)
#endif
futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
- futex_hashsize, 0,
- futex_hashsize < 256 ? HASH_SMALL : 0,
+ futex_hashsize, 0, 0,
&futex_shift, NULL,
futex_hashsize, futex_hashsize);
futex_hashsize = 1UL << futex_shift;
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index b5379c0e6d6d..8b195d06f4e8 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -5,6 +5,7 @@
#include <linux/futex.h>
#include <linux/rtmutex.h>
#include <linux/sched/wake_q.h>
+#include <linux/compat.h>
#ifdef CONFIG_PREEMPT_RT
#include <linux/rcuwait.h>
@@ -16,17 +17,86 @@
* Futex flags used to encode options to functions and preserve them across
* restarts.
*/
+#define FLAGS_SIZE_8 0x0000
+#define FLAGS_SIZE_16 0x0001
+#define FLAGS_SIZE_32 0x0002
+#define FLAGS_SIZE_64 0x0003
+
+#define FLAGS_SIZE_MASK 0x0003
+
#ifdef CONFIG_MMU
-# define FLAGS_SHARED 0x01
+# define FLAGS_SHARED 0x0010
#else
/*
* NOMMU does not have per process address space. Let the compiler optimize
* code away.
*/
-# define FLAGS_SHARED 0x00
+# define FLAGS_SHARED 0x0000
#endif
-#define FLAGS_CLOCKRT 0x02
-#define FLAGS_HAS_TIMEOUT 0x04
+#define FLAGS_CLOCKRT 0x0020
+#define FLAGS_HAS_TIMEOUT 0x0040
+#define FLAGS_NUMA 0x0080
+#define FLAGS_STRICT 0x0100
+
+/* FUTEX_ to FLAGS_ */
+static inline unsigned int futex_to_flags(unsigned int op)
+{
+ unsigned int flags = FLAGS_SIZE_32;
+
+ if (!(op & FUTEX_PRIVATE_FLAG))
+ flags |= FLAGS_SHARED;
+
+ if (op & FUTEX_CLOCK_REALTIME)
+ flags |= FLAGS_CLOCKRT;
+
+ return flags;
+}
+
+#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE)
+
+/* FUTEX2_ to FLAGS_ */
+static inline unsigned int futex2_to_flags(unsigned int flags2)
+{
+ unsigned int flags = flags2 & FUTEX2_SIZE_MASK;
+
+ if (!(flags2 & FUTEX2_PRIVATE))
+ flags |= FLAGS_SHARED;
+
+ if (flags2 & FUTEX2_NUMA)
+ flags |= FLAGS_NUMA;
+
+ return flags;
+}
+
+static inline unsigned int futex_size(unsigned int flags)
+{
+ return 1 << (flags & FLAGS_SIZE_MASK);
+}
+
+static inline bool futex_flags_valid(unsigned int flags)
+{
+ /* Only 64bit futexes for 64bit code */
+ if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) {
+ if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64)
+ return false;
+ }
+
+ /* Only 32bit futexes are implemented -- for now */
+ if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32)
+ return false;
+
+ return true;
+}
+
+static inline bool futex_validate_input(unsigned int flags, u64 val)
+{
+ int bits = 8 * futex_size(flags);
+
+ if (bits < 64 && (val >> bits))
+ return false;
+
+ return true;
+}
#ifdef CONFIG_FAIL_FUTEX
extern bool should_fail_futex(bool fshared);
@@ -69,11 +139,16 @@ struct futex_pi_state {
union futex_key key;
} __randomize_layout;
+struct futex_q;
+typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q);
+
/**
* struct futex_q - The hashed futex queue entry, one per waiting task
* @list: priority-sorted list of tasks waiting on this futex
* @task: the task waiting on the futex
* @lock_ptr: the hash bucket lock
+ * @wake: the wake handler for this queue
+ * @wake_data: data associated with the wake handler
* @key: the key the futex is hashed on
* @pi_state: optional priority inheritance state
* @rt_waiter: rt_waiter storage for use with requeue_pi
@@ -98,6 +173,8 @@ struct futex_q {
struct task_struct *task;
spinlock_t *lock_ptr;
+ futex_wake_fn *wake;
+ void *wake_data;
union futex_key key;
struct futex_pi_state *pi_state;
struct rt_mutex_waiter *rt_waiter;
@@ -116,7 +193,7 @@ enum futex_access {
FUTEX_WRITE
};
-extern int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key,
+extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
enum futex_access rw);
extern struct hrtimer_sleeper *
@@ -144,6 +221,7 @@ extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
struct futex_q *q, struct futex_hash_bucket **hb);
extern void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
struct hrtimer_sleeper *timeout);
+extern bool __futex_wake_mark(struct futex_q *q);
extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q);
extern int fault_in_user_writeable(u32 __user *uaddr);
@@ -260,10 +338,14 @@ extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32
val, ktime_t *abs_time, u32 bitset, u32 __user
*uaddr2);
-extern int futex_requeue(u32 __user *uaddr1, unsigned int flags,
- u32 __user *uaddr2, int nr_wake, int nr_requeue,
+extern int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
+ u32 __user *uaddr2, unsigned int flags2,
+ int nr_wake, int nr_requeue,
u32 *cmpval, int requeue_pi);
+extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
+ struct hrtimer_sleeper *to, u32 bitset);
+
extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
ktime_t *abs_time, u32 bitset);
@@ -279,6 +361,16 @@ struct futex_vector {
struct futex_q q;
};
+extern int futex_parse_waitv(struct futex_vector *futexv,
+ struct futex_waitv __user *uwaitv,
+ unsigned int nr_futexes, futex_wake_fn *wake,
+ void *wake_data);
+
+extern int futex_wait_multiple_setup(struct futex_vector *vs, int count,
+ int *woken);
+
+extern int futex_unqueue_multiple(struct futex_vector *v, int count);
+
extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
struct hrtimer_sleeper *to);
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index ce2889f12375..90e5197f4e56 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/slab.h>
+#include <linux/sched/rt.h>
#include <linux/sched/task.h>
#include "futex.h"
@@ -610,29 +611,16 @@ int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
/*
* Caller must hold a reference on @pi_state.
*/
-static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
+static int wake_futex_pi(u32 __user *uaddr, u32 uval,
+ struct futex_pi_state *pi_state,
+ struct rt_mutex_waiter *top_waiter)
{
- struct rt_mutex_waiter *top_waiter;
struct task_struct *new_owner;
bool postunlock = false;
DEFINE_RT_WAKE_Q(wqh);
u32 curval, newval;
int ret = 0;
- top_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
- if (WARN_ON_ONCE(!top_waiter)) {
- /*
- * As per the comment in futex_unlock_pi() this should not happen.
- *
- * When this happens, give up our locks and try again, giving
- * the futex_lock_pi() instance time to complete, either by
- * waiting on the rtmutex or removing itself from the futex
- * queue.
- */
- ret = -EAGAIN;
- goto out_unlock;
- }
-
new_owner = top_waiter->task;
/*
@@ -945,7 +933,7 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl
to = futex_setup_timer(time, &timeout, flags, 0);
retry:
- ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, FUTEX_WRITE);
+ ret = get_futex_key(uaddr, flags, &q.key, FUTEX_WRITE);
if (unlikely(ret != 0))
goto out;
@@ -1002,6 +990,12 @@ retry_private:
goto no_block;
}
+ /*
+ * Must be done before we enqueue the waiter, here is unfortunately
+ * under the hb lock, but that *should* work because it does nothing.
+ */
+ rt_mutex_pre_schedule();
+
rt_mutex_init_waiter(&rt_waiter);
/*
@@ -1039,19 +1033,37 @@ retry_private:
ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
cleanup:
- spin_lock(q.lock_ptr);
/*
* If we failed to acquire the lock (deadlock/signal/timeout), we must
- * first acquire the hb->lock before removing the lock from the
- * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait
- * lists consistent.
+ * must unwind the above, however we canont lock hb->lock because
+ * rt_mutex already has a waiter enqueued and hb->lock can itself try
+ * and enqueue an rt_waiter through rtlock.
+ *
+ * Doing the cleanup without holding hb->lock can cause inconsistent
+ * state between hb and pi_state, but only in the direction of not
+ * seeing a waiter that is leaving.
+ *
+ * See futex_unlock_pi(), it deals with this inconsistency.
+ *
+ * There be dragons here, since we must deal with the inconsistency on
+ * the way out (here), it is impossible to detect/warn about the race
+ * the other way around (missing an incoming waiter).
*
- * In particular; it is important that futex_unlock_pi() can not
- * observe this inconsistency.
+ * What could possibly go wrong...
*/
if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
ret = 0;
+ /*
+ * Now that the rt_waiter has been dequeued, it is safe to use
+ * spinlock/rtlock (which might enqueue its own rt_waiter) and fix up
+ * the
+ */
+ spin_lock(q.lock_ptr);
+ /*
+ * Waiter is unqueued.
+ */
+ rt_mutex_post_schedule();
no_block:
/*
* Fixup the pi_state owner and possibly acquire the lock if we
@@ -1117,7 +1129,7 @@ retry:
if ((uval & FUTEX_TID_MASK) != vpid)
return -EPERM;
- ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_WRITE);
+ ret = get_futex_key(uaddr, flags, &key, FUTEX_WRITE);
if (ret)
return ret;
@@ -1132,6 +1144,7 @@ retry:
top_waiter = futex_top_waiter(hb, &key);
if (top_waiter) {
struct futex_pi_state *pi_state = top_waiter->pi_state;
+ struct rt_mutex_waiter *rt_waiter;
ret = -EINVAL;
if (!pi_state)
@@ -1144,22 +1157,39 @@ retry:
if (pi_state->owner != current)
goto out_unlock;
- get_pi_state(pi_state);
/*
* By taking wait_lock while still holding hb->lock, we ensure
- * there is no point where we hold neither; and therefore
- * wake_futex_p() must observe a state consistent with what we
- * observed.
+ * there is no point where we hold neither; and thereby
+ * wake_futex_pi() must observe any new waiters.
+ *
+ * Since the cleanup: case in futex_lock_pi() removes the
+ * rt_waiter without holding hb->lock, it is possible for
+ * wake_futex_pi() to not find a waiter while the above does,
+ * in this case the waiter is on the way out and it can be
+ * ignored.
*
* In particular; this forces __rt_mutex_start_proxy() to
* complete such that we're guaranteed to observe the
- * rt_waiter. Also see the WARN in wake_futex_pi().
+ * rt_waiter.
*/
raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+ /*
+ * Futex vs rt_mutex waiter state -- if there are no rt_mutex
+ * waiters even though futex thinks there are, then the waiter
+ * is leaving and the uncontended path is safe to take.
+ */
+ rt_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
+ if (!rt_waiter) {
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+ goto do_uncontended;
+ }
+
+ get_pi_state(pi_state);
spin_unlock(&hb->lock);
/* drops pi_state->pi_mutex.wait_lock */
- ret = wake_futex_pi(uaddr, uval, pi_state);
+ ret = wake_futex_pi(uaddr, uval, pi_state, rt_waiter);
put_pi_state(pi_state);
@@ -1187,6 +1217,7 @@ retry:
return ret;
}
+do_uncontended:
/*
* We have no kernel internal state, i.e. no waiters in the
* kernel. Waiters which are about to queue themselves are stuck
diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c
index cba8b1a6a4cc..eb21f065816b 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -58,6 +58,7 @@ enum {
const struct futex_q futex_q_init = {
/* list gets initialized in futex_queue()*/
+ .wake = futex_wake_mark,
.key = FUTEX_KEY_INIT,
.bitset = FUTEX_BITSET_MATCH_ANY,
.requeue_state = ATOMIC_INIT(Q_REQUEUE_PI_NONE),
@@ -269,7 +270,7 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1,
union futex_key *key2, struct futex_pi_state **ps,
struct task_struct **exiting, int set_waiters)
{
- struct futex_q *top_waiter = NULL;
+ struct futex_q *top_waiter;
u32 curval;
int ret;
@@ -346,8 +347,9 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1,
/**
* futex_requeue() - Requeue waiters from uaddr1 to uaddr2
* @uaddr1: source futex user address
- * @flags: futex flags (FLAGS_SHARED, etc.)
+ * @flags1: futex flags (FLAGS_SHARED, etc.)
* @uaddr2: target futex user address
+ * @flags2: futex flags (FLAGS_SHARED, etc.)
* @nr_wake: number of waiters to wake (must be 1 for requeue_pi)
* @nr_requeue: number of waiters to requeue (0-INT_MAX)
* @cmpval: @uaddr1 expected value (or %NULL)
@@ -361,7 +363,8 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1,
* - >=0 - on success, the number of tasks requeued or woken;
* - <0 - on error
*/
-int futex_requeue(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
+int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
+ u32 __user *uaddr2, unsigned int flags2,
int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
@@ -424,10 +427,10 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
}
retry:
- ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ);
+ ret = get_futex_key(uaddr1, flags1, &key1, FUTEX_READ);
if (unlikely(ret != 0))
return ret;
- ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2,
+ ret = get_futex_key(uaddr2, flags2, &key2,
requeue_pi ? FUTEX_WRITE : FUTEX_READ);
if (unlikely(ret != 0))
return ret;
@@ -459,7 +462,7 @@ retry_private:
if (ret)
return ret;
- if (!(flags & FLAGS_SHARED))
+ if (!(flags1 & FLAGS_SHARED))
goto retry_private;
goto retry;
@@ -591,7 +594,7 @@ retry_private:
/* Plain futexes just wake or requeue and are done */
if (!requeue_pi) {
if (++task_count <= nr_wake)
- futex_wake_mark(&wake_q, this);
+ this->wake(&wake_q, this);
else
requeue_futex(this, hb1, hb2, &key2);
continue;
@@ -789,7 +792,7 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
*/
rt_mutex_init_waiter(&rt_waiter);
- ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE);
+ ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE);
if (unlikely(ret != 0))
goto out;
@@ -850,11 +853,13 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
pi_mutex = &q.pi_state->pi_mutex;
ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
- /* Current is not longer pi_blocked_on */
- spin_lock(q.lock_ptr);
+ /*
+ * See futex_unlock_pi()'s cleanup: comment.
+ */
if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
ret = 0;
+ spin_lock(q.lock_ptr);
debug_rt_mutex_free_waiter(&rt_waiter);
/*
* Fixup the pi_state owner and possibly acquire the lock if we
diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c
index a8074079b09e..4b6da9116aa6 100644
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -1,6 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/time_namespace.h>
@@ -85,15 +84,12 @@ err_unlock:
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
+ unsigned int flags = futex_to_flags(op);
int cmd = op & FUTEX_CMD_MASK;
- unsigned int flags = 0;
- if (!(op & FUTEX_PRIVATE_FLAG))
- flags |= FLAGS_SHARED;
-
- if (op & FUTEX_CLOCK_REALTIME) {
- flags |= FLAGS_CLOCKRT;
- if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI &&
+ if (flags & FLAGS_CLOCKRT) {
+ if (cmd != FUTEX_WAIT_BITSET &&
+ cmd != FUTEX_WAIT_REQUEUE_PI &&
cmd != FUTEX_LOCK_PI2)
return -ENOSYS;
}
@@ -110,9 +106,9 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
case FUTEX_WAKE_BITSET:
return futex_wake(uaddr, flags, val, val3);
case FUTEX_REQUEUE:
- return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0);
+ return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0);
case FUTEX_CMP_REQUEUE:
- return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0);
+ return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0);
case FUTEX_WAKE_OP:
return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
case FUTEX_LOCK_PI:
@@ -129,7 +125,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
uaddr2);
case FUTEX_CMP_REQUEUE_PI:
- return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
+ return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1);
}
return -ENOSYS;
}
@@ -183,43 +179,91 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
}
-/* Mask of available flags for each futex in futex_waitv list */
-#define FUTEXV_WAITER_MASK (FUTEX_32 | FUTEX_PRIVATE_FLAG)
-
/**
* futex_parse_waitv - Parse a waitv array from userspace
* @futexv: Kernel side list of waiters to be filled
* @uwaitv: Userspace list to be parsed
* @nr_futexes: Length of futexv
+ * @wake: Wake to call when futex is woken
+ * @wake_data: Data for the wake handler
*
* Return: Error code on failure, 0 on success
*/
-static int futex_parse_waitv(struct futex_vector *futexv,
- struct futex_waitv __user *uwaitv,
- unsigned int nr_futexes)
+int futex_parse_waitv(struct futex_vector *futexv,
+ struct futex_waitv __user *uwaitv,
+ unsigned int nr_futexes, futex_wake_fn *wake,
+ void *wake_data)
{
struct futex_waitv aux;
unsigned int i;
for (i = 0; i < nr_futexes; i++) {
+ unsigned int flags;
+
if (copy_from_user(&aux, &uwaitv[i], sizeof(aux)))
return -EFAULT;
- if ((aux.flags & ~FUTEXV_WAITER_MASK) || aux.__reserved)
+ if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved)
+ return -EINVAL;
+
+ flags = futex2_to_flags(aux.flags);
+ if (!futex_flags_valid(flags))
return -EINVAL;
- if (!(aux.flags & FUTEX_32))
+ if (!futex_validate_input(flags, aux.val))
return -EINVAL;
- futexv[i].w.flags = aux.flags;
+ futexv[i].w.flags = flags;
futexv[i].w.val = aux.val;
futexv[i].w.uaddr = aux.uaddr;
futexv[i].q = futex_q_init;
+ futexv[i].q.wake = wake;
+ futexv[i].q.wake_data = wake_data;
}
return 0;
}
+static int futex2_setup_timeout(struct __kernel_timespec __user *timeout,
+ clockid_t clockid, struct hrtimer_sleeper *to)
+{
+ int flag_clkid = 0, flag_init = 0;
+ struct timespec64 ts;
+ ktime_t time;
+ int ret;
+
+ if (!timeout)
+ return 0;
+
+ if (clockid == CLOCK_REALTIME) {
+ flag_clkid = FLAGS_CLOCKRT;
+ flag_init = FUTEX_CLOCK_REALTIME;
+ }
+
+ if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC)
+ return -EINVAL;
+
+ if (get_timespec64(&ts, timeout))
+ return -EFAULT;
+
+ /*
+ * Since there's no opcode for futex_waitv, use
+ * FUTEX_WAIT_BITSET that uses absolute timeout as well
+ */
+ ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time);
+ if (ret)
+ return ret;
+
+ futex_setup_timer(&time, to, flag_clkid, 0);
+ return 0;
+}
+
+static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to)
+{
+ hrtimer_cancel(&to->timer);
+ destroy_hrtimer_on_stack(&to->timer);
+}
+
/**
* sys_futex_waitv - Wait on a list of futexes
* @waiters: List of futexes to wait on
@@ -249,8 +293,6 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters,
{
struct hrtimer_sleeper to;
struct futex_vector *futexv;
- struct timespec64 ts;
- ktime_t time;
int ret;
/* This syscall supports no flags for now */
@@ -260,30 +302,8 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters,
if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters)
return -EINVAL;
- if (timeout) {
- int flag_clkid = 0, flag_init = 0;
-
- if (clockid == CLOCK_REALTIME) {
- flag_clkid = FLAGS_CLOCKRT;
- flag_init = FUTEX_CLOCK_REALTIME;
- }
-
- if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC)
- return -EINVAL;
-
- if (get_timespec64(&ts, timeout))
- return -EFAULT;
-
- /*
- * Since there's no opcode for futex_waitv, use
- * FUTEX_WAIT_BITSET that uses absolute timeout as well
- */
- ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time);
- if (ret)
- return ret;
-
- futex_setup_timer(&time, &to, flag_clkid, 0);
- }
+ if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to)))
+ return ret;
futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL);
if (!futexv) {
@@ -291,20 +311,133 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters,
goto destroy_timer;
}
- ret = futex_parse_waitv(futexv, waiters, nr_futexes);
+ ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark,
+ NULL);
if (!ret)
ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL);
kfree(futexv);
destroy_timer:
- if (timeout) {
- hrtimer_cancel(&to.timer);
- destroy_hrtimer_on_stack(&to.timer);
- }
+ if (timeout)
+ futex2_destroy_timeout(&to);
return ret;
}
+/*
+ * sys_futex_wake - Wake a number of futexes
+ * @uaddr: Address of the futex(es) to wake
+ * @mask: bitmask
+ * @nr: Number of the futexes to wake
+ * @flags: FUTEX2 flags
+ *
+ * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the
+ * futex2 family of calls.
+ */
+
+SYSCALL_DEFINE4(futex_wake,
+ void __user *, uaddr,
+ unsigned long, mask,
+ int, nr,
+ unsigned int, flags)
+{
+ if (flags & ~FUTEX2_VALID_MASK)
+ return -EINVAL;
+
+ flags = futex2_to_flags(flags);
+ if (!futex_flags_valid(flags))
+ return -EINVAL;
+
+ if (!futex_validate_input(flags, mask))
+ return -EINVAL;
+
+ return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask);
+}
+
+/*
+ * sys_futex_wait - Wait on a futex
+ * @uaddr: Address of the futex to wait on
+ * @val: Value of @uaddr
+ * @mask: bitmask
+ * @flags: FUTEX2 flags
+ * @timeout: Optional absolute timeout
+ * @clockid: Clock to be used for the timeout, realtime or monotonic
+ *
+ * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the
+ * futex2 familiy of calls.
+ */
+
+SYSCALL_DEFINE6(futex_wait,
+ void __user *, uaddr,
+ unsigned long, val,
+ unsigned long, mask,
+ unsigned int, flags,
+ struct __kernel_timespec __user *, timeout,
+ clockid_t, clockid)
+{
+ struct hrtimer_sleeper to;
+ int ret;
+
+ if (flags & ~FUTEX2_VALID_MASK)
+ return -EINVAL;
+
+ flags = futex2_to_flags(flags);
+ if (!futex_flags_valid(flags))
+ return -EINVAL;
+
+ if (!futex_validate_input(flags, val) ||
+ !futex_validate_input(flags, mask))
+ return -EINVAL;
+
+ if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to)))
+ return ret;
+
+ ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask);
+
+ if (timeout)
+ futex2_destroy_timeout(&to);
+
+ return ret;
+}
+
+/*
+ * sys_futex_requeue - Requeue a waiter from one futex to another
+ * @waiters: array describing the source and destination futex
+ * @flags: unused
+ * @nr_wake: number of futexes to wake
+ * @nr_requeue: number of futexes to requeue
+ *
+ * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the
+ * futex2 family of calls.
+ */
+
+SYSCALL_DEFINE4(futex_requeue,
+ struct futex_waitv __user *, waiters,
+ unsigned int, flags,
+ int, nr_wake,
+ int, nr_requeue)
+{
+ struct futex_vector futexes[2];
+ u32 cmpval;
+ int ret;
+
+ if (flags)
+ return -EINVAL;
+
+ if (!waiters)
+ return -EINVAL;
+
+ ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL);
+ if (ret)
+ return ret;
+
+ cmpval = futexes[0].w.val;
+
+ return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags,
+ u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags,
+ nr_wake, nr_requeue, &cmpval, 0);
+}
+
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(set_robust_list,
struct compat_robust_list_head __user *, head,
diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c
index ba01b9408203..61b112897a84 100644
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -106,20 +106,11 @@
* double_lock_hb() and double_unlock_hb(), respectively.
*/
-/*
- * The hash bucket lock must be held when this is called.
- * Afterwards, the futex_q must not be accessed. Callers
- * must ensure to later call wake_up_q() for the actual
- * wakeups to occur.
- */
-void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q)
+bool __futex_wake_mark(struct futex_q *q)
{
- struct task_struct *p = q->task;
-
if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
- return;
+ return false;
- get_task_struct(p);
__futex_unqueue(q);
/*
* The waiting task can free the futex_q as soon as q->lock_ptr = NULL
@@ -130,6 +121,26 @@ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q)
*/
smp_store_release(&q->lock_ptr, NULL);
+ return true;
+}
+
+/*
+ * The hash bucket lock must be held when this is called.
+ * Afterwards, the futex_q must not be accessed. Callers
+ * must ensure to later call wake_up_q() for the actual
+ * wakeups to occur.
+ */
+void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q)
+{
+ struct task_struct *p = q->task;
+
+ get_task_struct(p);
+
+ if (!__futex_wake_mark(q)) {
+ put_task_struct(p);
+ return;
+ }
+
/*
* Queue the task for later wakeup for after we've released
* the hb->lock.
@@ -145,16 +156,19 @@ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
union futex_key key = FUTEX_KEY_INIT;
- int ret;
DEFINE_WAKE_Q(wake_q);
+ int ret;
if (!bitset)
return -EINVAL;
- ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_READ);
+ ret = get_futex_key(uaddr, flags, &key, FUTEX_READ);
if (unlikely(ret != 0))
return ret;
+ if ((flags & FLAGS_STRICT) && !nr_wake)
+ return 0;
+
hb = futex_hash(&key);
/* Make sure we really have tasks to wakeup */
@@ -174,7 +188,7 @@ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
if (!(this->bitset & bitset))
continue;
- futex_wake_mark(&wake_q, this);
+ this->wake(&wake_q, this);
if (++ret >= nr_wake)
break;
}
@@ -245,10 +259,10 @@ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
DEFINE_WAKE_Q(wake_q);
retry:
- ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ);
+ ret = get_futex_key(uaddr1, flags, &key1, FUTEX_READ);
if (unlikely(ret != 0))
return ret;
- ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE);
+ ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE);
if (unlikely(ret != 0))
return ret;
@@ -289,7 +303,7 @@ retry_private:
ret = -EINVAL;
goto out_unlock;
}
- futex_wake_mark(&wake_q, this);
+ this->wake(&wake_q, this);
if (++ret >= nr_wake)
break;
}
@@ -303,7 +317,7 @@ retry_private:
ret = -EINVAL;
goto out_unlock;
}
- futex_wake_mark(&wake_q, this);
+ this->wake(&wake_q, this);
if (++op_ret >= nr_wake2)
break;
}
@@ -358,7 +372,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
}
/**
- * unqueue_multiple - Remove various futexes from their hash bucket
+ * futex_unqueue_multiple - Remove various futexes from their hash bucket
* @v: The list of futexes to unqueue
* @count: Number of futexes in the list
*
@@ -368,7 +382,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
* - >=0 - Index of the last futex that was awoken;
* - -1 - No futex was awoken
*/
-static int unqueue_multiple(struct futex_vector *v, int count)
+int futex_unqueue_multiple(struct futex_vector *v, int count)
{
int ret = -1, i;
@@ -396,7 +410,7 @@ static int unqueue_multiple(struct futex_vector *v, int count)
* - 0 - Success
* - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL
*/
-static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken)
+int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken)
{
struct futex_hash_bucket *hb;
bool retry = false;
@@ -419,11 +433,11 @@ static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *wo
*/
retry:
for (i = 0; i < count; i++) {
- if ((vs[i].w.flags & FUTEX_PRIVATE_FLAG) && retry)
+ if (!(vs[i].w.flags & FLAGS_SHARED) && retry)
continue;
ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr),
- !(vs[i].w.flags & FUTEX_PRIVATE_FLAG),
+ vs[i].w.flags,
&vs[i].q.key, FUTEX_READ);
if (unlikely(ret))
@@ -435,7 +449,7 @@ retry:
for (i = 0; i < count; i++) {
u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr;
struct futex_q *q = &vs[i].q;
- u32 val = (u32)vs[i].w.val;
+ u32 val = vs[i].w.val;
hb = futex_q_lock(q);
ret = futex_get_value_locked(&uval, uaddr);
@@ -458,7 +472,7 @@ retry:
* was woken, we don't return error and return this index to
* userspace
*/
- *woken = unqueue_multiple(vs, i);
+ *woken = futex_unqueue_multiple(vs, i);
if (*woken >= 0)
return 1;
@@ -543,7 +557,7 @@ int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
__set_current_state(TASK_RUNNING);
- ret = unqueue_multiple(vs, count);
+ ret = futex_unqueue_multiple(vs, count);
if (ret >= 0)
return ret;
@@ -599,7 +613,7 @@ int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
* while the syscall executes.
*/
retry:
- ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, FUTEX_READ);
+ ret = get_futex_key(uaddr, flags, &q->key, FUTEX_READ);
if (unlikely(ret != 0))
return ret;
@@ -629,20 +643,18 @@ retry_private:
return ret;
}
-int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset)
+int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
+ struct hrtimer_sleeper *to, u32 bitset)
{
- struct hrtimer_sleeper timeout, *to;
- struct restart_block *restart;
- struct futex_hash_bucket *hb;
struct futex_q q = futex_q_init;
+ struct futex_hash_bucket *hb;
int ret;
if (!bitset)
return -EINVAL;
+
q.bitset = bitset;
- to = futex_setup_timer(abs_time, &timeout, flags,
- current->timer_slack_ns);
retry:
/*
* Prepare to wait on uaddr. On success, it holds hb->lock and q
@@ -650,18 +662,17 @@ retry:
*/
ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
if (ret)
- goto out;
+ return ret;
/* futex_queue and wait for wakeup, timeout, or a signal. */
futex_wait_queue(hb, &q, to);
/* If we were woken (and unqueued), we succeeded, whatever. */
- ret = 0;
if (!futex_unqueue(&q))
- goto out;
- ret = -ETIMEDOUT;
+ return 0;
+
if (to && !to->task)
- goto out;
+ return -ETIMEDOUT;
/*
* We expect signal_pending(current), but we might be the
@@ -670,24 +681,38 @@ retry:
if (!signal_pending(current))
goto retry;
- ret = -ERESTARTSYS;
- if (!abs_time)
- goto out;
+ return -ERESTARTSYS;
+}
- restart = &current->restart_block;
- restart->futex.uaddr = uaddr;
- restart->futex.val = val;
- restart->futex.time = *abs_time;
- restart->futex.bitset = bitset;
- restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
+int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset)
+{
+ struct hrtimer_sleeper timeout, *to;
+ struct restart_block *restart;
+ int ret;
- ret = set_restart_fn(restart, futex_wait_restart);
+ to = futex_setup_timer(abs_time, &timeout, flags,
+ current->timer_slack_ns);
-out:
- if (to) {
- hrtimer_cancel(&to->timer);
- destroy_hrtimer_on_stack(&to->timer);
+ ret = __futex_wait(uaddr, flags, val, to, bitset);
+
+ /* No timeout, nothing to clean up. */
+ if (!to)
+ return ret;
+
+ hrtimer_cancel(&to->timer);
+ destroy_hrtimer_on_stack(&to->timer);
+
+ if (ret == -ERESTARTSYS) {
+ restart = &current->restart_block;
+ restart->futex.uaddr = uaddr;
+ restart->futex.val = val;
+ restart->futex.time = *abs_time;
+ restart->futex.bitset = bitset;
+ restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
+
+ return set_restart_fn(restart, futex_wait_restart);
}
+
return ret;
}
diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile
index 16f8ecc7d882..ccd02afaeffb 100644
--- a/kernel/gcov/Makefile
+++ b/kernel/gcov/Makefile
@@ -3,4 +3,6 @@ ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
obj-y := base.o fs.o
obj-$(CONFIG_CC_IS_GCC) += gcc_base.o gcc_4_7.o
+CFLAGS_gcc_base.o += -Wno-missing-prototypes -Wno-missing-declarations
obj-$(CONFIG_CC_IS_CLANG) += clang.o
+CFLAGS_clang.o += -Wno-missing-prototypes -Wno-missing-declarations
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index 5c3086cad8f9..01520689b57c 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -99,7 +99,7 @@ struct gcov_iterator {
struct gcov_info *info;
size_t size;
loff_t pos;
- char buffer[];
+ char buffer[] __counted_by(size);
};
/**
diff --git a/kernel/groups.c b/kernel/groups.c
index 9aaed2a31073..9b43da22647d 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -19,7 +19,7 @@ struct group_info *groups_alloc(int gidsetsize)
if (!gi)
return NULL;
- atomic_set(&gi->usage, 1);
+ refcount_set(&gi->usage, 1);
gi->ngroups = gidsetsize;
return gi;
}
diff --git a/kernel/iomem.c b/kernel/iomem.c
index 62c92e43aa0d..dc2120776e1c 100644
--- a/kernel/iomem.c
+++ b/kernel/iomem.c
@@ -3,19 +3,16 @@
#include <linux/types.h>
#include <linux/io.h>
#include <linux/mm.h>
-
-#ifndef ioremap_cache
-/* temporary while we convert existing ioremap_cache users to memremap */
-__weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size)
-{
- return ioremap(offset, size);
-}
-#endif
+#include <linux/ioremap.h>
#ifndef arch_memremap_wb
static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
{
+#ifdef ioremap_cache
return (__force void *)ioremap_cache(offset, size);
+#else
+ return (__force void *)ioremap(offset, size);
+#endif
}
#endif
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index ee8c0acf39df..dc94e0bf2c94 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -473,11 +473,12 @@ void handle_nested_irq(unsigned int irq)
action = desc->action;
if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
desc->istate |= IRQS_PENDING;
- goto out_unlock;
+ raw_spin_unlock_irq(&desc->lock);
+ return;
}
kstat_incr_irqs_this_cpu(desc);
- irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
+ atomic_inc(&desc->threads_active);
raw_spin_unlock_irq(&desc->lock);
action_ret = IRQ_NONE;
@@ -487,11 +488,7 @@ void handle_nested_irq(unsigned int irq)
if (!irq_settings_no_debug(desc))
note_interrupt(desc, action_ret);
- raw_spin_lock_irq(&desc->lock);
- irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
-
-out_unlock:
- raw_spin_unlock_irq(&desc->lock);
+ wake_threads_waitq(desc);
}
EXPORT_SYMBOL_GPL(handle_nested_irq);
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index 5971a66be034..aae0402507ed 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -121,7 +121,6 @@ static const struct irq_bit_descr irqdata_states[] = {
BIT_MASK_DESCR(IRQD_AFFINITY_ON_ACTIVATE),
BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
BIT_MASK_DESCR(IRQD_CAN_RESERVE),
- BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK),
BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU),
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index c653cd31548d..d39a40bc542b 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -219,11 +219,15 @@ void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name,
int num_ct, unsigned int irq_base,
void __iomem *reg_base, irq_flow_handler_t handler)
{
+ struct irq_chip_type *ct = gc->chip_types;
+ int i;
+
raw_spin_lock_init(&gc->lock);
gc->num_ct = num_ct;
gc->irq_base = irq_base;
gc->reg_base = reg_base;
- gc->chip_types->chip.name = name;
+ for (i = 0; i < num_ct; i++)
+ ct[i].chip.name = name;
gc->chip_types->handler = handler;
}
@@ -544,21 +548,34 @@ EXPORT_SYMBOL_GPL(irq_setup_alt_chip);
void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk,
unsigned int clr, unsigned int set)
{
- unsigned int i = gc->irq_base;
+ unsigned int i, virq;
raw_spin_lock(&gc_lock);
list_del(&gc->list);
raw_spin_unlock(&gc_lock);
- for (; msk; msk >>= 1, i++) {
+ for (i = 0; msk; msk >>= 1, i++) {
if (!(msk & 0x01))
continue;
+ /*
+ * Interrupt domain based chips store the base hardware
+ * interrupt number in gc::irq_base. Otherwise gc::irq_base
+ * contains the base Linux interrupt number.
+ */
+ if (gc->domain) {
+ virq = irq_find_mapping(gc->domain, gc->irq_base + i);
+ if (!virq)
+ continue;
+ } else {
+ virq = gc->irq_base + i;
+ }
+
/* Remove handler first. That will mask the irq line */
- irq_set_handler(i, NULL);
- irq_set_chip(i, &no_irq_chip);
- irq_set_chip_data(i, NULL);
- irq_modify_status(i, clr, set);
+ irq_set_handler(virq, NULL);
+ irq_set_chip(virq, &no_irq_chip);
+ irq_set_chip_data(virq, NULL);
+ irq_modify_status(virq, clr, set);
}
}
EXPORT_SYMBOL_GPL(irq_remove_generic_chip);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index bdd35bb9c735..bcc7f21db9ee 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -108,8 +108,6 @@ extern int __irq_get_irqchip_state(struct irq_data *data,
enum irqchip_irq_state which,
bool *state);
-extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
-
irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc);
irqreturn_t handle_irq_event_percpu(struct irq_desc *desc);
irqreturn_t handle_irq_event(struct irq_desc *desc);
@@ -121,6 +119,8 @@ void irq_resend_init(struct irq_desc *desc);
bool irq_wait_for_poll(struct irq_desc *desc);
void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action);
+void wake_threads_waitq(struct irq_desc *desc);
+
#ifdef CONFIG_PROC_FS
extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d2742af0f0fd..1782f90cd8c6 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -108,6 +108,16 @@ bool synchronize_hardirq(unsigned int irq)
}
EXPORT_SYMBOL(synchronize_hardirq);
+static void __synchronize_irq(struct irq_desc *desc)
+{
+ __synchronize_hardirq(desc, true);
+ /*
+ * We made sure that no hardirq handler is running. Now verify that no
+ * threaded handlers are active.
+ */
+ wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
+}
+
/**
* synchronize_irq - wait for pending IRQ handlers (on other CPUs)
* @irq: interrupt number to wait for
@@ -127,16 +137,8 @@ void synchronize_irq(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
- if (desc) {
- __synchronize_hardirq(desc, true);
- /*
- * We made sure that no hardirq handler is
- * running. Now verify that no threaded handlers are
- * active.
- */
- wait_event(desc->wait_for_threads,
- !atomic_read(&desc->threads_active));
- }
+ if (desc)
+ __synchronize_irq(desc);
}
EXPORT_SYMBOL(synchronize_irq);
@@ -1216,7 +1218,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
return ret;
}
-static void wake_threads_waitq(struct irq_desc *desc)
+void wake_threads_waitq(struct irq_desc *desc)
{
if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
@@ -1850,15 +1852,13 @@ out_thread:
struct task_struct *t = new->thread;
new->thread = NULL;
- kthread_stop(t);
- put_task_struct(t);
+ kthread_stop_put(t);
}
if (new->secondary && new->secondary->thread) {
struct task_struct *t = new->secondary->thread;
new->secondary->thread = NULL;
- kthread_stop(t);
- put_task_struct(t);
+ kthread_stop_put(t);
}
out_mput:
module_put(desc->owner);
@@ -1944,7 +1944,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
* supports it also make sure that there is no (not yet serviced)
* interrupt in flight at the hardware level.
*/
- __synchronize_hardirq(desc, true);
+ __synchronize_irq(desc);
#ifdef CONFIG_DEBUG_SHIRQ
/*
@@ -1969,12 +1969,9 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
* the same bit to a newly requested action.
*/
if (action->thread) {
- kthread_stop(action->thread);
- put_task_struct(action->thread);
- if (action->secondary && action->secondary->thread) {
- kthread_stop(action->secondary->thread);
- put_task_struct(action->secondary->thread);
- }
+ kthread_stop_put(action->thread);
+ if (action->secondary && action->secondary->thread)
+ kthread_stop_put(action->secondary->thread);
}
/* Last action releases resources */
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 1698e77645ac..75d0ae490e29 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -466,16 +466,16 @@ unsigned int irq_matrix_reserved(struct irq_matrix *m)
}
/**
- * irq_matrix_allocated - Get the number of allocated irqs on the local cpu
+ * irq_matrix_allocated - Get the number of allocated non-managed irqs on the local CPU
* @m: Pointer to the matrix to search
*
- * This returns number of allocated irqs
+ * This returns number of allocated non-managed interrupts.
*/
unsigned int irq_matrix_allocated(struct irq_matrix *m)
{
struct cpumap *cm = this_cpu_ptr(m->maps);
- return cm->allocated;
+ return cm->allocated - cm->managed_allocated;
}
#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index b4c31a5c1147..79b4a58ba9c3 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -1204,7 +1204,6 @@ static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc,
#define VIRQ_CAN_RESERVE 0x01
#define VIRQ_ACTIVATE 0x02
-#define VIRQ_NOMASK_QUIRK 0x04
static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflags)
{
@@ -1213,8 +1212,6 @@ static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflag
if (!(vflags & VIRQ_CAN_RESERVE)) {
irqd_clr_can_reserve(irqd);
- if (vflags & VIRQ_NOMASK_QUIRK)
- irqd_set_msi_nomask_quirk(irqd);
/*
* If the interrupt is managed but no CPU is available to
@@ -1275,15 +1272,8 @@ static int __msi_domain_alloc_irqs(struct device *dev, struct irq_domain *domain
* Interrupt can use a reserved vector and will not occupy
* a real device vector until the interrupt is requested.
*/
- if (msi_check_reservation_mode(domain, info, dev)) {
+ if (msi_check_reservation_mode(domain, info, dev))
vflags |= VIRQ_CAN_RESERVE;
- /*
- * MSI affinity setting requires a special quirk (X86) when
- * reservation mode is active.
- */
- if (info->flags & MSI_FLAG_NOMASK_QUIRK)
- vflags |= VIRQ_NOMASK_QUIRK;
- }
xa_for_each_range(xa, idx, desc, ctrl->first, ctrl->last) {
if (!msi_desc_match(desc, MSI_DESC_NOTASSOCIATED))
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 016d997131d4..18edd57b5fe8 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -163,12 +163,12 @@ unsigned long kallsyms_sym_address(int idx)
return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
}
-static bool cleanup_symbol_name(char *s)
+static void cleanup_symbol_name(char *s)
{
char *res;
if (!IS_ENABLED(CONFIG_LTO_CLANG))
- return false;
+ return;
/*
* LLVM appends various suffixes for local functions and variables that
@@ -178,26 +178,21 @@ static bool cleanup_symbol_name(char *s)
* - foo.llvm.[0-9a-f]+
*/
res = strstr(s, ".llvm.");
- if (res) {
+ if (res)
*res = '\0';
- return true;
- }
- return false;
+ return;
}
static int compare_symbol_name(const char *name, char *namebuf)
{
- int ret;
-
- ret = strcmp(name, namebuf);
- if (!ret)
- return ret;
-
- if (cleanup_symbol_name(namebuf) && !strcmp(name, namebuf))
- return 0;
-
- return ret;
+ /* The kallsyms_seqs_of_names is sorted based on names after
+ * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled.
+ * To ensure correct bisection in kallsyms_lookup_names(), do
+ * cleanup_symbol_name(namebuf) before comparing name and namebuf.
+ */
+ cleanup_symbol_name(namebuf);
+ return strcmp(name, namebuf);
}
static unsigned int get_symbol_seq(int index)
diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c
index a2e3745d15c4..b4cac76ea5e9 100644
--- a/kernel/kallsyms_selftest.c
+++ b/kernel/kallsyms_selftest.c
@@ -196,7 +196,7 @@ static bool match_cleanup_name(const char *s, const char *name)
if (!IS_ENABLED(CONFIG_LTO_CLANG))
return false;
- p = strchr(s, '.');
+ p = strstr(s, ".llvm.");
if (!p)
return false;
@@ -341,30 +341,10 @@ static int test_kallsyms_basic_function(void)
ret = lookup_symbol_name(addr, namebuf);
if (unlikely(ret)) {
namebuf[0] = 0;
+ pr_info("%d: lookup_symbol_name(%lx) failed\n", i, addr);
goto failed;
}
- /*
- * The first '.' may be the initial letter, in which case the
- * entire symbol name will be truncated to an empty string in
- * cleanup_symbol_name(). Do not test these symbols.
- *
- * For example:
- * cat /proc/kallsyms | awk '{print $3}' | grep -E "^\." | head
- * .E_read_words
- * .E_leading_bytes
- * .E_trailing_bytes
- * .E_write_words
- * .E_copy
- * .str.292.llvm.12122243386960820698
- * .str.24.llvm.12122243386960820698
- * .str.29.llvm.12122243386960820698
- * .str.75.llvm.12122243386960820698
- * .str.99.llvm.12122243386960820698
- */
- if (IS_ENABLED(CONFIG_LTO_CLANG) && !namebuf[0])
- continue;
-
lookup_addr = kallsyms_lookup_name(namebuf);
memset(stat, 0, sizeof(*stat));
@@ -388,8 +368,11 @@ static int test_kallsyms_basic_function(void)
if (stat->addr != stat2->addr ||
stat->real_cnt != stat2->real_cnt ||
memcmp(stat->addrs, stat2->addrs,
- stat->save_cnt * sizeof(stat->addrs[0])))
+ stat->save_cnt * sizeof(stat->addrs[0]))) {
+ pr_info("%s: mismatch between kallsyms_on_each_symbol() and kallsyms_on_each_match_symbol()\n",
+ namebuf);
goto failed;
+ }
/*
* The average of random increments is 128, that is, one of
@@ -400,15 +383,23 @@ static int test_kallsyms_basic_function(void)
}
/* Need to be found at least once */
- if (!stat->real_cnt)
+ if (!stat->real_cnt) {
+ pr_info("%s: Never found\n", namebuf);
goto failed;
+ }
/*
* kallsyms_lookup_name() returns the address of the first
* symbol found and cannot be NULL.
*/
- if (!lookup_addr || lookup_addr != stat->addrs[0])
+ if (!lookup_addr) {
+ pr_info("%s: NULL lookup_addr?!\n", namebuf);
+ goto failed;
+ }
+ if (lookup_addr != stat->addrs[0]) {
+ pr_info("%s: lookup_addr != stat->addrs[0]\n", namebuf);
goto failed;
+ }
/*
* If the addresses of all matching symbols are recorded, the
@@ -420,8 +411,10 @@ static int test_kallsyms_basic_function(void)
break;
}
- if (j == stat->save_cnt)
+ if (j == stat->save_cnt) {
+ pr_info("%s: j == save_cnt?!\n", namebuf);
goto failed;
+ }
}
}
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 5353edfad8e1..b0639f21041f 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -64,8 +64,10 @@ get_file_raw_ptr(struct task_struct *task, unsigned int idx)
struct file *file;
rcu_read_lock();
- file = task_lookup_fd_rcu(task, idx);
+ file = task_lookup_fdget_rcu(task, idx);
rcu_read_unlock();
+ if (file)
+ fput(file);
return file;
}
diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index 0ddbdab5903d..015586217875 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -699,12 +699,9 @@ static void test_barrier_nothreads(struct kunit *test)
KCSAN_EXPECT_RW_BARRIER(spin_unlock(&test_spinlock), true);
KCSAN_EXPECT_RW_BARRIER(mutex_lock(&test_mutex), false);
KCSAN_EXPECT_RW_BARRIER(mutex_unlock(&test_mutex), true);
-
-#ifdef clear_bit_unlock_is_negative_byte
- KCSAN_EXPECT_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
- KCSAN_EXPECT_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
- KCSAN_EXPECT_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
-#endif
+ KCSAN_EXPECT_READ_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
+ KCSAN_EXPECT_WRITE_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
+ KCSAN_EXPECT_RW_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
kcsan_nestable_atomic_end();
}
diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c
index 8679322450f2..84a1200271af 100644
--- a/kernel/kcsan/selftest.c
+++ b/kernel/kcsan/selftest.c
@@ -227,12 +227,9 @@ static bool __init test_barrier(void)
KCSAN_CHECK_RW_BARRIER(arch_spin_unlock(&arch_spinlock));
spin_lock(&test_spinlock);
KCSAN_CHECK_RW_BARRIER(spin_unlock(&test_spinlock));
-
-#ifdef clear_bit_unlock_is_negative_byte
- KCSAN_CHECK_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
- KCSAN_CHECK_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
- KCSAN_CHECK_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
-#endif
+ KCSAN_CHECK_RW_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+ KCSAN_CHECK_READ_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+ KCSAN_CHECK_WRITE_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
kcsan_nestable_atomic_end();
return ret;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 92d301f98776..8f35a5a42af8 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -129,6 +129,11 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
if (flags & KEXEC_PRESERVE_CONTEXT)
image->preserve_context = 1;
+#ifdef CONFIG_CRASH_HOTPLUG
+ if (flags & KEXEC_UPDATE_ELFCOREHDR)
+ image->update_elfcorehdr = 1;
+#endif
+
ret = machine_kexec_prepare(image);
if (ret)
goto out;
@@ -242,7 +247,7 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT))
return -EINVAL;
- ksegments = memdup_user(segments, nr_segments * sizeof(ksegments[0]));
+ ksegments = memdup_array_user(segments, nr_segments, sizeof(ksegments[0]));
if (IS_ERR(ksegments))
return PTR_ERR(ksegments);
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index e2f2574d8b74..be5642a4ec49 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -49,29 +49,9 @@
atomic_t __kexec_lock = ATOMIC_INIT(0);
-/* Per cpu memory for storing cpu states in case of system crash. */
-note_buf_t __percpu *crash_notes;
-
/* Flag to indicate we are going to kexec a new kernel */
bool kexec_in_progress = false;
-
-/* Location of the reserved area for the crash kernel */
-struct resource crashk_res = {
- .name = "Crash kernel",
- .start = 0,
- .end = 0,
- .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
- .desc = IORES_DESC_CRASH_KERNEL
-};
-struct resource crashk_low_res = {
- .name = "Crash kernel",
- .start = 0,
- .end = 0,
- .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
- .desc = IORES_DESC_CRASH_KERNEL
-};
-
int kexec_should_crash(struct task_struct *p)
{
/*
@@ -277,6 +257,12 @@ struct kimage *do_kimage_alloc_init(void)
/* Initialize the list of unusable pages */
INIT_LIST_HEAD(&image->unusable_pages);
+#ifdef CONFIG_CRASH_HOTPLUG
+ image->hp_action = KEXEC_CRASH_HP_NONE;
+ image->elfcorehdr_index = -1;
+ image->elfcorehdr_updated = false;
+#endif
+
return image;
}
@@ -1218,40 +1204,6 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
final_note(buf);
}
-static int __init crash_notes_memory_init(void)
-{
- /* Allocate memory for saving cpu registers. */
- size_t size, align;
-
- /*
- * crash_notes could be allocated across 2 vmalloc pages when percpu
- * is vmalloc based . vmalloc doesn't guarantee 2 continuous vmalloc
- * pages are also on 2 continuous physical pages. In this case the
- * 2nd part of crash_notes in 2nd page could be lost since only the
- * starting address and size of crash_notes are exported through sysfs.
- * Here round up the size of crash_notes to the nearest power of two
- * and pass it to __alloc_percpu as align value. This can make sure
- * crash_notes is allocated inside one physical page.
- */
- size = sizeof(note_buf_t);
- align = min(roundup_pow_of_two(sizeof(note_buf_t)), PAGE_SIZE);
-
- /*
- * Break compile if size is bigger than PAGE_SIZE since crash_notes
- * definitely will be in 2 pages with that.
- */
- BUILD_BUG_ON(size > PAGE_SIZE);
-
- crash_notes = __alloc_percpu(size, align);
- if (!crash_notes) {
- pr_warn("Memory allocation for saving cpu register states failed\n");
- return -ENOMEM;
- }
- return 0;
-}
-subsys_initcall(crash_notes_memory_init);
-
-
/*
* Move into place and start executing a preloaded standalone
* executable. If nothing was preloaded return an error.
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 881ba0d1714c..f9a419cd22d4 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -624,7 +624,7 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
* kexec_add_buffer - place a buffer in a kexec segment
* @kbuf: Buffer contents and memory parameters.
*
- * This function assumes that kexec_mutex is held.
+ * This function assumes that kexec_lock is held.
* On successful return, @kbuf->mem will have the physical address of
* the buffer in memory.
*
@@ -685,7 +685,7 @@ static int kexec_calculate_store_digests(struct kimage *image)
struct kexec_sha_region *sha_regions;
struct purgatory_info *pi = &image->purgatory_info;
- if (!IS_ENABLED(CONFIG_ARCH_HAS_KEXEC_PURGATORY))
+ if (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY))
return 0;
zero_buf = __va(page_to_pfn(ZERO_PAGE(0)) << PAGE_SHIFT);
@@ -726,6 +726,12 @@ static int kexec_calculate_store_digests(struct kimage *image)
for (j = i = 0; i < image->nr_segments; i++) {
struct kexec_segment *ksegment;
+#ifdef CONFIG_CRASH_HOTPLUG
+ /* Exclude elfcorehdr segment to allow future changes via hotplug */
+ if (j == image->elfcorehdr_index)
+ continue;
+#endif
+
ksegment = &image->segment[i];
/*
* Skip purgatory as it will be modified once we put digest
@@ -790,7 +796,7 @@ out:
return ret;
}
-#ifdef CONFIG_ARCH_HAS_KEXEC_PURGATORY
+#ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY
/*
* kexec_purgatory_setup_kbuf - prepare buffer to load purgatory.
* @pi: Purgatory to be loaded.
@@ -1150,185 +1156,4 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
return 0;
}
-#endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */
-
-int crash_exclude_mem_range(struct crash_mem *mem,
- unsigned long long mstart, unsigned long long mend)
-{
- int i, j;
- unsigned long long start, end, p_start, p_end;
- struct range temp_range = {0, 0};
-
- for (i = 0; i < mem->nr_ranges; i++) {
- start = mem->ranges[i].start;
- end = mem->ranges[i].end;
- p_start = mstart;
- p_end = mend;
-
- if (mstart > end || mend < start)
- continue;
-
- /* Truncate any area outside of range */
- if (mstart < start)
- p_start = start;
- if (mend > end)
- p_end = end;
-
- /* Found completely overlapping range */
- if (p_start == start && p_end == end) {
- mem->ranges[i].start = 0;
- mem->ranges[i].end = 0;
- if (i < mem->nr_ranges - 1) {
- /* Shift rest of the ranges to left */
- for (j = i; j < mem->nr_ranges - 1; j++) {
- mem->ranges[j].start =
- mem->ranges[j+1].start;
- mem->ranges[j].end =
- mem->ranges[j+1].end;
- }
-
- /*
- * Continue to check if there are another overlapping ranges
- * from the current position because of shifting the above
- * mem ranges.
- */
- i--;
- mem->nr_ranges--;
- continue;
- }
- mem->nr_ranges--;
- return 0;
- }
-
- if (p_start > start && p_end < end) {
- /* Split original range */
- mem->ranges[i].end = p_start - 1;
- temp_range.start = p_end + 1;
- temp_range.end = end;
- } else if (p_start != start)
- mem->ranges[i].end = p_start - 1;
- else
- mem->ranges[i].start = p_end + 1;
- break;
- }
-
- /* If a split happened, add the split to array */
- if (!temp_range.end)
- return 0;
-
- /* Split happened */
- if (i == mem->max_nr_ranges - 1)
- return -ENOMEM;
-
- /* Location where new range should go */
- j = i + 1;
- if (j < mem->nr_ranges) {
- /* Move over all ranges one slot towards the end */
- for (i = mem->nr_ranges - 1; i >= j; i--)
- mem->ranges[i + 1] = mem->ranges[i];
- }
-
- mem->ranges[j].start = temp_range.start;
- mem->ranges[j].end = temp_range.end;
- mem->nr_ranges++;
- return 0;
-}
-
-int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
- void **addr, unsigned long *sz)
-{
- Elf64_Ehdr *ehdr;
- Elf64_Phdr *phdr;
- unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
- unsigned char *buf;
- unsigned int cpu, i;
- unsigned long long notes_addr;
- unsigned long mstart, mend;
-
- /* extra phdr for vmcoreinfo ELF note */
- nr_phdr = nr_cpus + 1;
- nr_phdr += mem->nr_ranges;
-
- /*
- * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
- * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64).
- * I think this is required by tools like gdb. So same physical
- * memory will be mapped in two ELF headers. One will contain kernel
- * text virtual addresses and other will have __va(physical) addresses.
- */
-
- nr_phdr++;
- elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
- elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
-
- buf = vzalloc(elf_sz);
- if (!buf)
- return -ENOMEM;
-
- ehdr = (Elf64_Ehdr *)buf;
- phdr = (Elf64_Phdr *)(ehdr + 1);
- memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
- ehdr->e_ident[EI_CLASS] = ELFCLASS64;
- ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
- ehdr->e_ident[EI_VERSION] = EV_CURRENT;
- ehdr->e_ident[EI_OSABI] = ELF_OSABI;
- memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
- ehdr->e_type = ET_CORE;
- ehdr->e_machine = ELF_ARCH;
- ehdr->e_version = EV_CURRENT;
- ehdr->e_phoff = sizeof(Elf64_Ehdr);
- ehdr->e_ehsize = sizeof(Elf64_Ehdr);
- ehdr->e_phentsize = sizeof(Elf64_Phdr);
-
- /* Prepare one phdr of type PT_NOTE for each present CPU */
- for_each_present_cpu(cpu) {
- phdr->p_type = PT_NOTE;
- notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
- phdr->p_offset = phdr->p_paddr = notes_addr;
- phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
- (ehdr->e_phnum)++;
- phdr++;
- }
-
- /* Prepare one PT_NOTE header for vmcoreinfo */
- phdr->p_type = PT_NOTE;
- phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
- phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
- (ehdr->e_phnum)++;
- phdr++;
-
- /* Prepare PT_LOAD type program header for kernel text region */
- if (need_kernel_map) {
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R|PF_W|PF_X;
- phdr->p_vaddr = (unsigned long) _text;
- phdr->p_filesz = phdr->p_memsz = _end - _text;
- phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
- ehdr->e_phnum++;
- phdr++;
- }
-
- /* Go through all the ranges in mem->ranges[] and prepare phdr */
- for (i = 0; i < mem->nr_ranges; i++) {
- mstart = mem->ranges[i].start;
- mend = mem->ranges[i].end;
-
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R|PF_W|PF_X;
- phdr->p_offset = mstart;
-
- phdr->p_paddr = mstart;
- phdr->p_vaddr = (unsigned long) __va(mstart);
- phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
- phdr->p_align = 0;
- ehdr->e_phnum++;
- pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
- phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
- ehdr->e_phnum, phdr->p_offset);
- phdr++;
- }
-
- *addr = buf;
- *sz = elf_sz;
- return 0;
-}
+#endif /* CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ca385b61d546..d5a0ee40bf66 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1877,13 +1877,27 @@ static struct notifier_block kprobe_exceptions_nb = {
#ifdef CONFIG_KRETPROBES
#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
+
+/* callbacks for objpool of kretprobe instances */
+static int kretprobe_init_inst(void *nod, void *context)
+{
+ struct kretprobe_instance *ri = nod;
+
+ ri->rph = context;
+ return 0;
+}
+static int kretprobe_fini_pool(struct objpool_head *head, void *context)
+{
+ kfree(context);
+ return 0;
+}
+
static void free_rp_inst_rcu(struct rcu_head *head)
{
struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
+ struct kretprobe_holder *rph = ri->rph;
- if (refcount_dec_and_test(&ri->rph->ref))
- kfree(ri->rph);
- kfree(ri);
+ objpool_drop(ri, &rph->pool);
}
NOKPROBE_SYMBOL(free_rp_inst_rcu);
@@ -1892,7 +1906,7 @@ static void recycle_rp_inst(struct kretprobe_instance *ri)
struct kretprobe *rp = get_kretprobe(ri);
if (likely(rp))
- freelist_add(&ri->freelist, &rp->freelist);
+ objpool_push(ri, &rp->rph->pool);
else
call_rcu(&ri->rcu, free_rp_inst_rcu);
}
@@ -1929,23 +1943,12 @@ NOKPROBE_SYMBOL(kprobe_flush_task);
static inline void free_rp_inst(struct kretprobe *rp)
{
- struct kretprobe_instance *ri;
- struct freelist_node *node;
- int count = 0;
-
- node = rp->freelist.head;
- while (node) {
- ri = container_of(node, struct kretprobe_instance, freelist);
- node = node->next;
-
- kfree(ri);
- count++;
- }
+ struct kretprobe_holder *rph = rp->rph;
- if (refcount_sub_and_test(count, &rp->rph->ref)) {
- kfree(rp->rph);
- rp->rph = NULL;
- }
+ if (!rph)
+ return;
+ rp->rph = NULL;
+ objpool_fini(&rph->pool);
}
/* This assumes the 'tsk' is the current task or the is not running. */
@@ -2087,19 +2090,17 @@ NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
{
struct kretprobe *rp = container_of(p, struct kretprobe, kp);
+ struct kretprobe_holder *rph = rp->rph;
struct kretprobe_instance *ri;
- struct freelist_node *fn;
- fn = freelist_try_get(&rp->freelist);
- if (!fn) {
+ ri = objpool_pop(&rph->pool);
+ if (!ri) {
rp->nmissed++;
return 0;
}
- ri = container_of(fn, struct kretprobe_instance, freelist);
-
if (rp->entry_handler && rp->entry_handler(ri, regs)) {
- freelist_add(&ri->freelist, &rp->freelist);
+ objpool_push(ri, &rph->pool);
return 0;
}
@@ -2193,7 +2194,6 @@ int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long o
int register_kretprobe(struct kretprobe *rp)
{
int ret;
- struct kretprobe_instance *inst;
int i;
void *addr;
@@ -2227,20 +2227,12 @@ int register_kretprobe(struct kretprobe *rp)
rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus());
#ifdef CONFIG_KRETPROBE_ON_RETHOOK
- rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler);
- if (!rp->rh)
- return -ENOMEM;
+ rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler,
+ sizeof(struct kretprobe_instance) +
+ rp->data_size, rp->maxactive);
+ if (IS_ERR(rp->rh))
+ return PTR_ERR(rp->rh);
- for (i = 0; i < rp->maxactive; i++) {
- inst = kzalloc(sizeof(struct kretprobe_instance) +
- rp->data_size, GFP_KERNEL);
- if (inst == NULL) {
- rethook_free(rp->rh);
- rp->rh = NULL;
- return -ENOMEM;
- }
- rethook_add_node(rp->rh, &inst->node);
- }
rp->nmissed = 0;
/* Establish function entry probe point */
ret = register_kprobe(&rp->kp);
@@ -2249,25 +2241,18 @@ int register_kretprobe(struct kretprobe *rp)
rp->rh = NULL;
}
#else /* !CONFIG_KRETPROBE_ON_RETHOOK */
- rp->freelist.head = NULL;
rp->rph = kzalloc(sizeof(struct kretprobe_holder), GFP_KERNEL);
if (!rp->rph)
return -ENOMEM;
- rp->rph->rp = rp;
- for (i = 0; i < rp->maxactive; i++) {
- inst = kzalloc(sizeof(struct kretprobe_instance) +
- rp->data_size, GFP_KERNEL);
- if (inst == NULL) {
- refcount_set(&rp->rph->ref, i);
- free_rp_inst(rp);
- return -ENOMEM;
- }
- inst->rph = rp->rph;
- freelist_add(&inst->freelist, &rp->freelist);
+ if (objpool_init(&rp->rph->pool, rp->maxactive, rp->data_size +
+ sizeof(struct kretprobe_instance), GFP_KERNEL,
+ rp->rph, kretprobe_init_inst, kretprobe_fini_pool)) {
+ kfree(rp->rph);
+ rp->rph = NULL;
+ return -ENOMEM;
}
- refcount_set(&rp->rph->ref, i);
-
+ rcu_assign_pointer(rp->rph->rp, rp);
rp->nmissed = 0;
/* Establish function entry probe point */
ret = register_kprobe(&rp->kp);
@@ -2315,7 +2300,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
#ifdef CONFIG_KRETPROBE_ON_RETHOOK
rethook_free(rps[i]->rh);
#else
- rps[i]->rph->rp = NULL;
+ rcu_assign_pointer(rps[i]->rph->rp, NULL);
#endif
}
mutex_unlock(&kprobe_mutex);
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index aad7a3bfd846..1d4bc493b2f4 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -165,6 +165,18 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
}
KERNEL_ATTR_RO(vmcoreinfo);
+#ifdef CONFIG_CRASH_HOTPLUG
+static ssize_t crash_elfcorehdr_size_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ unsigned int sz = crash_get_elfcorehdr_size();
+
+ return sysfs_emit(buf, "%u\n", sz);
+}
+KERNEL_ATTR_RO(crash_elfcorehdr_size);
+
+#endif
+
#endif /* CONFIG_CRASH_CORE */
/* whether file capabilities are enabled */
@@ -255,6 +267,9 @@ static struct attribute * kernel_attrs[] = {
#endif
#ifdef CONFIG_CRASH_CORE
&vmcoreinfo_attr.attr,
+#ifdef CONFIG_CRASH_HOTPLUG
+ &crash_elfcorehdr_size_attr.attr,
+#endif
#endif
#ifndef CONFIG_TINY_RCU
&rcu_expedited_attr.attr,
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4fff7df17a68..c5e40830c1f2 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -159,11 +159,10 @@ bool kthread_should_stop(void)
}
EXPORT_SYMBOL(kthread_should_stop);
-bool __kthread_should_park(struct task_struct *k)
+static bool __kthread_should_park(struct task_struct *k)
{
return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags);
}
-EXPORT_SYMBOL_GPL(__kthread_should_park);
/**
* kthread_should_park - should this kthread park now?
@@ -716,6 +715,24 @@ int kthread_stop(struct task_struct *k)
}
EXPORT_SYMBOL(kthread_stop);
+/**
+ * kthread_stop_put - stop a thread and put its task struct
+ * @k: thread created by kthread_create().
+ *
+ * Stops a thread created by kthread_create() and put its task_struct.
+ * Only use when holding an extra task struct reference obtained by
+ * calling get_task_struct().
+ */
+int kthread_stop_put(struct task_struct *k)
+{
+ int ret;
+
+ ret = kthread_stop(k);
+ put_task_struct(k);
+ return ret;
+}
+EXPORT_SYMBOL(kthread_stop_put);
+
int kthreadd(void *unused)
{
struct task_struct *tsk = current;
@@ -1470,7 +1487,6 @@ void kthread_unuse_mm(struct mm_struct *mm)
* clearing tsk->mm.
*/
smp_mb__after_spinlock();
- sync_mm_rss(mm);
local_irq_disable();
tsk->mm = NULL;
membarrier_update_current_mm(NULL);
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 61328328c474..ecbc9b6aba3a 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -243,7 +243,7 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab,
* symbols are exported and normal relas can be used instead.
*/
if (!sec_vmlinux && sym_vmlinux) {
- pr_err("invalid access to vmlinux symbol '%s' from module-specific livepatch relocation section",
+ pr_err("invalid access to vmlinux symbol '%s' from module-specific livepatch relocation section\n",
sym_name);
return -EINVAL;
}
diff --git a/kernel/locking/lock_events.c b/kernel/locking/lock_events.c
index fa2c2f951c6b..e68d82099558 100644
--- a/kernel/locking/lock_events.c
+++ b/kernel/locking/lock_events.c
@@ -146,7 +146,7 @@ static int __init init_lockevent_counts(void)
struct dentry *d_counts = debugfs_create_dir(LOCK_EVENTS_DIR, NULL);
int i;
- if (!d_counts)
+ if (IS_ERR(d_counts))
goto out;
/*
@@ -159,14 +159,14 @@ static int __init init_lockevent_counts(void)
for (i = 0; i < lockevent_num; i++) {
if (skip_lockevent(lockevent_names[i]))
continue;
- if (!debugfs_create_file(lockevent_names[i], 0400, d_counts,
- (void *)(long)i, &fops_lockevent))
+ if (IS_ERR(debugfs_create_file(lockevent_names[i], 0400, d_counts,
+ (void *)(long)i, &fops_lockevent)))
goto fail_undo;
}
- if (!debugfs_create_file(lockevent_names[LOCKEVENT_reset_cnts], 0200,
+ if (IS_ERR(debugfs_create_file(lockevent_names[LOCKEVENT_reset_cnts], 0200,
d_counts, (void *)(long)LOCKEVENT_reset_cnts,
- &fops_lockevent))
+ &fops_lockevent)))
goto fail_undo;
return 0;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 111607d91489..151bd3de5936 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -819,34 +819,26 @@ static int very_verbose(struct lock_class *class)
* Is this the address of a static object:
*/
#ifdef __KERNEL__
-/*
- * Check if an address is part of freed initmem. After initmem is freed,
- * memory can be allocated from it, and such allocations would then have
- * addresses within the range [_stext, _end].
- */
-#ifndef arch_is_kernel_initmem_freed
-static int arch_is_kernel_initmem_freed(unsigned long addr)
-{
- if (system_state < SYSTEM_FREEING_INITMEM)
- return 0;
-
- return init_section_contains((void *)addr, 1);
-}
-#endif
-
static int static_obj(const void *obj)
{
- unsigned long start = (unsigned long) &_stext,
- end = (unsigned long) &_end,
- addr = (unsigned long) obj;
+ unsigned long addr = (unsigned long) obj;
- if (arch_is_kernel_initmem_freed(addr))
- return 0;
+ if (is_kernel_core_data(addr))
+ return 1;
+
+ /*
+ * keys are allowed in the __ro_after_init section.
+ */
+ if (is_kernel_rodata(addr))
+ return 1;
/*
- * static variable?
+ * in initdata section and used during bootup only?
+ * NOTE: On some platforms the initdata section is
+ * outside of the _stext ... _end range.
*/
- if ((addr >= start) && (addr < end))
+ if (system_state < SYSTEM_FREEING_INITMEM &&
+ init_section_contains((void *)addr, 1))
return 1;
/*
@@ -3505,7 +3497,8 @@ static int alloc_chain_hlocks(int req)
size = chain_block_size(curr);
if (likely(size >= req)) {
del_chain_block(0, size, chain_block_next(curr));
- add_chain_block(curr + req, size - req);
+ if (size > req)
+ add_chain_block(curr + req, size - req);
return curr;
}
}
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 15fdc7fa5c68..e2bfb1db589d 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -440,7 +440,7 @@ static void snprint_time(char *buf, size_t bufsiz, s64 nr)
static void seq_time(struct seq_file *m, s64 time)
{
- char num[15];
+ char num[22];
snprint_time(num, sizeof(num), time);
seq_printf(m, " %14s", num);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 949d3deae506..69d3cd2cfc3b 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -33,20 +33,23 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
-torture_param(int, nwriters_stress, -1, "Number of write-locking stress-test threads");
-torture_param(int, nreaders_stress, -1, "Number of read-locking stress-test threads");
+torture_param(int, acq_writer_lim, 0, "Write_acquisition time limit (jiffies).");
+torture_param(int, call_rcu_chains, 0, "Self-propagate call_rcu() chains during test (0=disable).");
torture_param(int, long_hold, 100, "Do occasional long hold of lock (ms), 0=disable");
+torture_param(int, nested_locks, 0, "Number of nested locks (max = 8)");
+torture_param(int, nreaders_stress, -1, "Number of read-locking stress-test threads");
+torture_param(int, nwriters_stress, -1, "Number of write-locking stress-test threads");
torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, rt_boost, 2,
+ "Do periodic rt-boost. 0=Disable, 1=Only for rt_mutex, 2=For all lock types.");
+torture_param(int, rt_boost_factor, 50, "A factor determining how often rt-boost happens.");
torture_param(int, shuffle_interval, 3, "Number of jiffies between shuffles, 0=disable");
torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s");
torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
-torture_param(int, rt_boost, 2,
- "Do periodic rt-boost. 0=Disable, 1=Only for rt_mutex, 2=For all lock types.");
-torture_param(int, rt_boost_factor, 50, "A factor determining how often rt-boost happens.");
torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
-torture_param(int, nested_locks, 0, "Number of nested locks (max = 8)");
+torture_param(int, writer_fifo, 0, "Run writers at sched_set_fifo() priority");
/* Going much higher trips "BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!" errors */
#define MAX_NESTED_LOCKS 8
@@ -55,6 +58,55 @@ module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type,
"Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)");
+static cpumask_var_t bind_readers; // Bind the readers to the specified set of CPUs.
+static cpumask_var_t bind_writers; // Bind the writers to the specified set of CPUs.
+
+// Parse a cpumask kernel parameter. If there are more users later on,
+// this might need to got to a more central location.
+static int param_set_cpumask(const char *val, const struct kernel_param *kp)
+{
+ cpumask_var_t *cm_bind = kp->arg;
+ int ret;
+ char *s;
+
+ if (!alloc_cpumask_var(cm_bind, GFP_KERNEL)) {
+ s = "Out of memory";
+ ret = -ENOMEM;
+ goto out_err;
+ }
+ ret = cpulist_parse(val, *cm_bind);
+ if (!ret)
+ return ret;
+ s = "Bad CPU range";
+out_err:
+ pr_warn("%s: %s, all CPUs set\n", kp->name, s);
+ cpumask_setall(*cm_bind);
+ return ret;
+}
+
+// Output a cpumask kernel parameter.
+static int param_get_cpumask(char *buffer, const struct kernel_param *kp)
+{
+ cpumask_var_t *cm_bind = kp->arg;
+
+ return sprintf(buffer, "%*pbl", cpumask_pr_args(*cm_bind));
+}
+
+static bool cpumask_nonempty(cpumask_var_t mask)
+{
+ return cpumask_available(mask) && !cpumask_empty(mask);
+}
+
+static const struct kernel_param_ops lt_bind_ops = {
+ .set = param_set_cpumask,
+ .get = param_get_cpumask,
+};
+
+module_param_cb(bind_readers, &lt_bind_ops, &bind_readers, 0644);
+module_param_cb(bind_writers, &lt_bind_ops, &bind_writers, 0644);
+
+long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask);
+
static struct task_struct *stats_task;
static struct task_struct **writer_tasks;
static struct task_struct **reader_tasks;
@@ -68,6 +120,12 @@ struct lock_stress_stats {
long n_lock_acquired;
};
+struct call_rcu_chain {
+ struct rcu_head crc_rh;
+ bool crc_stop;
+};
+struct call_rcu_chain *call_rcu_chain;
+
/* Forward reference. */
static void lock_torture_cleanup(void);
@@ -115,12 +173,9 @@ static int torture_lock_busted_write_lock(int tid __maybe_unused)
static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
-
/* We want a long delay occasionally to force massive contention. */
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold);
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
torture_preempt_schedule(); /* Allow test to be preempted. */
}
@@ -193,15 +248,14 @@ __acquires(torture_spinlock)
static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
unsigned long j;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
- if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * longdelay_ms))) {
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold))) {
j = jiffies;
- mdelay(longdelay_ms);
+ mdelay(long_hold);
pr_alert("%s: delay = %lu jiffies.\n", __func__, jiffies - j);
}
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 200 * shortdelay_us)))
@@ -319,14 +373,12 @@ __acquires(torture_rwlock)
static void torture_rwlock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold);
else
udelay(shortdelay_us);
}
@@ -347,14 +399,12 @@ __acquires(torture_rwlock)
static void torture_rwlock_read_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 10;
- const unsigned long longdelay_ms = 100;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
- if (!(torture_random(trsp) %
- (cxt.nrealreaders_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealreaders_stress * 2000 * long_hold)))
+ mdelay(long_hold);
else
udelay(shortdelay_us);
}
@@ -452,12 +502,9 @@ __acquires(torture_mutex)
static void torture_mutex_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
-
/* We want a long delay occasionally to force massive contention. */
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms * 5);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold * 5);
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
torture_preempt_schedule(); /* Allow test to be preempted. */
}
@@ -625,15 +672,13 @@ __acquires(torture_rtmutex)
static void torture_rtmutex_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
/*
* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold);
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 200 * shortdelay_us)))
udelay(shortdelay_us);
@@ -690,12 +735,9 @@ __acquires(torture_rwsem)
static void torture_rwsem_write_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
-
/* We want a long delay occasionally to force massive contention. */
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms * 10);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold * 10);
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
torture_preempt_schedule(); /* Allow test to be preempted. */
}
@@ -715,14 +757,11 @@ __acquires(torture_rwsem)
static void torture_rwsem_read_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_ms = 100;
-
/* We want a long delay occasionally to force massive contention. */
- if (!(torture_random(trsp) %
- (cxt.nrealreaders_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms * 2);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealreaders_stress * 2000 * long_hold)))
+ mdelay(long_hold * 2);
else
- mdelay(longdelay_ms / 2);
+ mdelay(long_hold / 2);
if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000)))
torture_preempt_schedule(); /* Allow test to be preempted. */
}
@@ -802,14 +841,17 @@ static struct lock_torture_ops percpu_rwsem_lock_ops = {
*/
static int lock_torture_writer(void *arg)
{
+ unsigned long j;
+ unsigned long j1;
+ u32 lockset_mask;
struct lock_stress_stats *lwsp = arg;
- int tid = lwsp - cxt.lwsa;
DEFINE_TORTURE_RANDOM(rand);
- u32 lockset_mask;
bool skip_main_lock;
+ int tid = lwsp - cxt.lwsa;
VERBOSE_TOROUT_STRING("lock_torture_writer task started");
- set_user_nice(current, MAX_NICE);
+ if (!rt_task(current))
+ set_user_nice(current, MAX_NICE);
do {
if ((torture_random(&rand) & 0xfffff) == 0)
@@ -832,17 +874,24 @@ static int lock_torture_writer(void *arg)
cxt.cur_ops->nested_lock(tid, lockset_mask);
if (!skip_main_lock) {
+ if (acq_writer_lim > 0)
+ j = jiffies;
cxt.cur_ops->writelock(tid);
if (WARN_ON_ONCE(lock_is_write_held))
lwsp->n_lock_fail++;
lock_is_write_held = true;
if (WARN_ON_ONCE(atomic_read(&lock_is_read_held)))
lwsp->n_lock_fail++; /* rare, but... */
-
+ if (acq_writer_lim > 0) {
+ j1 = jiffies;
+ WARN_ONCE(time_after(j1, j + acq_writer_lim),
+ "%s: Lock acquisition took %lu jiffies.\n",
+ __func__, j1 - j);
+ }
lwsp->n_lock_acquired++;
- }
- if (!skip_main_lock) {
+
cxt.cur_ops->write_delay(&rand);
+
lock_is_write_held = false;
WRITE_ONCE(last_lock_release, jiffies);
cxt.cur_ops->writeunlock(tid);
@@ -984,16 +1033,69 @@ static int lock_torture_stats(void *arg)
return 0;
}
+
static inline void
lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
const char *tag)
{
+ static cpumask_t cpumask_all;
+ cpumask_t *rcmp = cpumask_nonempty(bind_readers) ? bind_readers : &cpumask_all;
+ cpumask_t *wcmp = cpumask_nonempty(bind_writers) ? bind_writers : &cpumask_all;
+
+ cpumask_setall(&cpumask_all);
pr_alert("%s" TORTURE_FLAG
- "--- %s%s: nwriters_stress=%d nreaders_stress=%d nested_locks=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
+ "--- %s%s: acq_writer_lim=%d bind_readers=%*pbl bind_writers=%*pbl call_rcu_chains=%d long_hold=%d nested_locks=%d nreaders_stress=%d nwriters_stress=%d onoff_holdoff=%d onoff_interval=%d rt_boost=%d rt_boost_factor=%d shuffle_interval=%d shutdown_secs=%d stat_interval=%d stutter=%d verbose=%d writer_fifo=%d\n",
torture_type, tag, cxt.debug_lock ? " [debug]": "",
- cxt.nrealwriters_stress, cxt.nrealreaders_stress,
- nested_locks, stat_interval, verbose, shuffle_interval,
- stutter, shutdown_secs, onoff_interval, onoff_holdoff);
+ acq_writer_lim, cpumask_pr_args(rcmp), cpumask_pr_args(wcmp),
+ call_rcu_chains, long_hold, nested_locks, cxt.nrealreaders_stress,
+ cxt.nrealwriters_stress, onoff_holdoff, onoff_interval, rt_boost,
+ rt_boost_factor, shuffle_interval, shutdown_secs, stat_interval, stutter,
+ verbose, writer_fifo);
+}
+
+// If requested, maintain call_rcu() chains to keep a grace period always
+// in flight. These increase the probability of getting an RCU CPU stall
+// warning and associated diagnostics when a locking primitive stalls.
+
+static void call_rcu_chain_cb(struct rcu_head *rhp)
+{
+ struct call_rcu_chain *crcp = container_of(rhp, struct call_rcu_chain, crc_rh);
+
+ if (!smp_load_acquire(&crcp->crc_stop)) {
+ (void)start_poll_synchronize_rcu(); // Start one grace period...
+ call_rcu(&crcp->crc_rh, call_rcu_chain_cb); // ... and later start another.
+ }
+}
+
+// Start the requested number of call_rcu() chains.
+static int call_rcu_chain_init(void)
+{
+ int i;
+
+ if (call_rcu_chains <= 0)
+ return 0;
+ call_rcu_chain = kcalloc(call_rcu_chains, sizeof(*call_rcu_chain), GFP_KERNEL);
+ if (!call_rcu_chain)
+ return -ENOMEM;
+ for (i = 0; i < call_rcu_chains; i++) {
+ call_rcu_chain[i].crc_stop = false;
+ call_rcu(&call_rcu_chain[i].crc_rh, call_rcu_chain_cb);
+ }
+ return 0;
+}
+
+// Stop all of the call_rcu() chains.
+static void call_rcu_chain_cleanup(void)
+{
+ int i;
+
+ if (!call_rcu_chain)
+ return;
+ for (i = 0; i < call_rcu_chains; i++)
+ smp_store_release(&call_rcu_chain[i].crc_stop, true);
+ rcu_barrier();
+ kfree(call_rcu_chain);
+ call_rcu_chain = NULL;
}
static void lock_torture_cleanup(void)
@@ -1015,8 +1117,7 @@ static void lock_torture_cleanup(void)
if (writer_tasks) {
for (i = 0; i < cxt.nrealwriters_stress; i++)
- torture_stop_kthread(lock_torture_writer,
- writer_tasks[i]);
+ torture_stop_kthread(lock_torture_writer, writer_tasks[i]);
kfree(writer_tasks);
writer_tasks = NULL;
}
@@ -1047,6 +1148,8 @@ static void lock_torture_cleanup(void)
kfree(cxt.lrsa);
cxt.lrsa = NULL;
+ call_rcu_chain_cleanup();
+
end:
if (cxt.init_called) {
if (cxt.cur_ops->exit)
@@ -1176,6 +1279,10 @@ static int __init lock_torture_init(void)
}
}
+ firsterr = call_rcu_chain_init();
+ if (torture_init_error(firsterr))
+ goto unwind;
+
lock_torture_print_module_parms(cxt.cur_ops, "Start of test");
/* Prepare torture context. */
@@ -1244,10 +1351,13 @@ static int __init lock_torture_init(void)
goto create_reader;
/* Create writer. */
- firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i],
- writer_tasks[i]);
+ firsterr = torture_create_kthread_cb(lock_torture_writer, &cxt.lwsa[i],
+ writer_tasks[i],
+ writer_fifo ? sched_set_fifo : NULL);
if (torture_init_error(firsterr))
goto unwind;
+ if (cpumask_nonempty(bind_writers))
+ torture_sched_setaffinity(writer_tasks[i]->pid, bind_writers);
create_reader:
if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress))
@@ -1257,6 +1367,8 @@ static int __init lock_torture_init(void)
reader_tasks[j]);
if (torture_init_error(firsterr))
goto unwind;
+ if (cpumask_nonempty(bind_readers))
+ torture_sched_setaffinity(reader_tasks[j]->pid, bind_readers);
}
if (stat_interval > 0) {
firsterr = torture_create_kthread(lock_torture_stats, NULL,
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index d973fe6041bf..2deeeca3e71b 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -1126,6 +1126,9 @@ EXPORT_SYMBOL(ww_mutex_lock_interruptible);
#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
#endif /* !CONFIG_PREEMPT_RT */
+EXPORT_TRACEPOINT_SYMBOL_GPL(contention_begin);
+EXPORT_TRACEPOINT_SYMBOL_GPL(contention_end);
+
/**
* atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
* @cnt: the atomic which we are to dec
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 6afc249ce697..6a0184e9c234 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -486,6 +486,16 @@ gotlock:
}
/*
+ * Include the architecture specific callee-save thunk of the
+ * __pv_queued_spin_unlock(). This thunk is put together with
+ * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock
+ * function close to each other sharing consecutive instruction cachelines.
+ * Alternatively, architecture specific version of __pv_queued_spin_unlock()
+ * can be defined.
+ */
+#include <asm/qspinlock_paravirt.h>
+
+/*
* PV versions of the unlock fastpath and slowpath functions to be used
* instead of queued_spin_unlock().
*/
@@ -533,16 +543,6 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
pv_kick(node->cpu);
}
-/*
- * Include the architecture specific callee-save thunk of the
- * __pv_queued_spin_unlock(). This thunk is put together with
- * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock
- * function close to each other sharing consecutive instruction cachelines.
- * Alternatively, architecture specific version of __pv_queued_spin_unlock()
- * can be defined.
- */
-#include <asm/qspinlock_paravirt.h>
-
#ifndef __pv_queued_spin_unlock
__visible __lockfunc void __pv_queued_spin_unlock(struct qspinlock *lock)
{
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 21db0df0eb00..4a10e8c16fd2 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -218,6 +218,11 @@ static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex_base *lock,
return try_cmpxchg_acquire(&lock->owner, &old, new);
}
+static __always_inline bool rt_mutex_try_acquire(struct rt_mutex_base *lock)
+{
+ return rt_mutex_cmpxchg_acquire(lock, NULL, current);
+}
+
static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock,
struct task_struct *old,
struct task_struct *new)
@@ -297,6 +302,20 @@ static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex_base *lock,
}
+static int __sched rt_mutex_slowtrylock(struct rt_mutex_base *lock);
+
+static __always_inline bool rt_mutex_try_acquire(struct rt_mutex_base *lock)
+{
+ /*
+ * With debug enabled rt_mutex_cmpxchg trylock() will always fail.
+ *
+ * Avoid unconditionally taking the slow path by using
+ * rt_mutex_slow_trylock() which is covered by the debug code and can
+ * acquire a non-contended rtmutex.
+ */
+ return rt_mutex_slowtrylock(lock);
+}
+
static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock,
struct task_struct *old,
struct task_struct *new)
@@ -1613,7 +1632,7 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
raw_spin_unlock_irq(&lock->wait_lock);
if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner))
- schedule();
+ rt_mutex_schedule();
raw_spin_lock_irq(&lock->wait_lock);
set_current_state(state);
@@ -1642,7 +1661,7 @@ static void __sched rt_mutex_handle_deadlock(int res, int detect_deadlock,
WARN(1, "rtmutex deadlock detected\n");
while (1) {
set_current_state(TASK_INTERRUPTIBLE);
- schedule();
+ rt_mutex_schedule();
}
}
@@ -1738,6 +1757,15 @@ static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock,
int ret;
/*
+ * Do all pre-schedule work here, before we queue a waiter and invoke
+ * PI -- any such work that trips on rtlock (PREEMPT_RT spinlock) would
+ * otherwise recurse back into task_blocks_on_rt_mutex() through
+ * rtlock_slowlock() and will then enqueue a second waiter for this
+ * same task and things get really confusing real fast.
+ */
+ rt_mutex_pre_schedule();
+
+ /*
* Technically we could use raw_spin_[un]lock_irq() here, but this can
* be called in early boot if the cmpxchg() fast path is disabled
* (debug, no architecture support). In this case we will acquire the
@@ -1748,6 +1776,7 @@ static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock,
raw_spin_lock_irqsave(&lock->wait_lock, flags);
ret = __rt_mutex_slowlock_locked(lock, ww_ctx, state);
raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+ rt_mutex_post_schedule();
return ret;
}
@@ -1755,7 +1784,9 @@ static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock,
static __always_inline int __rt_mutex_lock(struct rt_mutex_base *lock,
unsigned int state)
{
- if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
+ lockdep_assert(!current->pi_blocked_on);
+
+ if (likely(rt_mutex_try_acquire(lock)))
return 0;
return rt_mutex_slowlock(lock, NULL, state);
diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c
index 25ec0239477c..34a59569db6b 100644
--- a/kernel/locking/rwbase_rt.c
+++ b/kernel/locking/rwbase_rt.c
@@ -71,6 +71,7 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb,
struct rt_mutex_base *rtm = &rwb->rtmutex;
int ret;
+ rwbase_pre_schedule();
raw_spin_lock_irq(&rtm->wait_lock);
/*
@@ -125,12 +126,15 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb,
rwbase_rtmutex_unlock(rtm);
trace_contention_end(rwb, ret);
+ rwbase_post_schedule();
return ret;
}
static __always_inline int rwbase_read_lock(struct rwbase_rt *rwb,
unsigned int state)
{
+ lockdep_assert(!current->pi_blocked_on);
+
if (rwbase_read_trylock(rwb))
return 0;
@@ -237,6 +241,8 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb,
/* Force readers into slow path */
atomic_sub(READER_BIAS, &rwb->readers);
+ rwbase_pre_schedule();
+
raw_spin_lock_irqsave(&rtm->wait_lock, flags);
if (__rwbase_write_trylock(rwb))
goto out_unlock;
@@ -248,6 +254,7 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb,
if (rwbase_signal_pending_state(state, current)) {
rwbase_restore_current_state();
__rwbase_write_unlock(rwb, 0, flags);
+ rwbase_post_schedule();
trace_contention_end(rwb, -EINTR);
return -EINTR;
}
@@ -266,6 +273,7 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb,
out_unlock:
raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
+ rwbase_post_schedule();
return 0;
}
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 9eabd585ce7a..2340b6d90ec6 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1427,8 +1427,14 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
#define rwbase_signal_pending_state(state, current) \
signal_pending_state(state, current)
+#define rwbase_pre_schedule() \
+ rt_mutex_pre_schedule()
+
#define rwbase_schedule() \
- schedule()
+ rt_mutex_schedule()
+
+#define rwbase_post_schedule() \
+ rt_mutex_post_schedule()
#include "rwbase_rt.c"
diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c
index 48a19ed8486d..38e292454fcc 100644
--- a/kernel/locking/spinlock_rt.c
+++ b/kernel/locking/spinlock_rt.c
@@ -37,6 +37,8 @@
static __always_inline void rtlock_lock(struct rt_mutex_base *rtm)
{
+ lockdep_assert(!current->pi_blocked_on);
+
if (unlikely(!rt_mutex_cmpxchg_acquire(rtm, NULL, current)))
rtlock_slowlock(rtm);
}
@@ -184,9 +186,13 @@ static __always_inline int rwbase_rtmutex_trylock(struct rt_mutex_base *rtm)
#define rwbase_signal_pending_state(state, current) (0)
+#define rwbase_pre_schedule()
+
#define rwbase_schedule() \
schedule_rtlock()
+#define rwbase_post_schedule()
+
#include "rwbase_rt.c"
/*
* The common functions which get wrapped into the rwlock API.
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 93cca6e69860..78719e1ef1b1 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -9,7 +9,7 @@
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/module.h>
-#include <linux/random.h>
+#include <linux/prandom.h>
#include <linux/slab.h>
#include <linux/ww_mutex.h>
@@ -386,6 +386,19 @@ struct stress {
int nlocks;
};
+struct rnd_state rng;
+DEFINE_SPINLOCK(rng_lock);
+
+static inline u32 prandom_u32_below(u32 ceil)
+{
+ u32 ret;
+
+ spin_lock(&rng_lock);
+ ret = prandom_u32_state(&rng) % ceil;
+ spin_unlock(&rng_lock);
+ return ret;
+}
+
static int *get_random_order(int count)
{
int *order;
@@ -399,7 +412,7 @@ static int *get_random_order(int count)
order[n] = n;
for (n = count - 1; n > 1; n--) {
- r = get_random_u32_below(n + 1);
+ r = prandom_u32_below(n + 1);
if (r != n) {
tmp = order[n];
order[n] = order[r];
@@ -452,21 +465,21 @@ retry:
ww_mutex_unlock(&locks[order[n]]);
if (err == -EDEADLK) {
- ww_mutex_lock_slow(&locks[order[contended]], &ctx);
- goto retry;
+ if (!time_after(jiffies, stress->timeout)) {
+ ww_mutex_lock_slow(&locks[order[contended]], &ctx);
+ goto retry;
+ }
}
+ ww_acquire_fini(&ctx);
if (err) {
pr_err_once("stress (%s) failed with %d\n",
__func__, err);
break;
}
-
- ww_acquire_fini(&ctx);
} while (!time_after(jiffies, stress->timeout));
kfree(order);
- kfree(stress);
}
struct reorder_lock {
@@ -531,7 +544,6 @@ out:
list_for_each_entry_safe(ll, ln, &locks, link)
kfree(ll);
kfree(order);
- kfree(stress);
}
static void stress_one_work(struct work_struct *work)
@@ -552,8 +564,6 @@ static void stress_one_work(struct work_struct *work)
break;
}
} while (!time_after(jiffies, stress->timeout));
-
- kfree(stress);
}
#define STRESS_INORDER BIT(0)
@@ -564,15 +574,24 @@ static void stress_one_work(struct work_struct *work)
static int stress(int nlocks, int nthreads, unsigned int flags)
{
struct ww_mutex *locks;
- int n;
+ struct stress *stress_array;
+ int n, count;
locks = kmalloc_array(nlocks, sizeof(*locks), GFP_KERNEL);
if (!locks)
return -ENOMEM;
+ stress_array = kmalloc_array(nthreads, sizeof(*stress_array),
+ GFP_KERNEL);
+ if (!stress_array) {
+ kfree(locks);
+ return -ENOMEM;
+ }
+
for (n = 0; n < nlocks; n++)
ww_mutex_init(&locks[n], &ww_class);
+ count = 0;
for (n = 0; nthreads; n++) {
struct stress *stress;
void (*fn)(struct work_struct *work);
@@ -596,9 +615,7 @@ static int stress(int nlocks, int nthreads, unsigned int flags)
if (!fn)
continue;
- stress = kmalloc(sizeof(*stress), GFP_KERNEL);
- if (!stress)
- break;
+ stress = &stress_array[count++];
INIT_WORK(&stress->work, fn);
stress->locks = locks;
@@ -613,6 +630,7 @@ static int stress(int nlocks, int nthreads, unsigned int flags)
for (n = 0; n < nlocks; n++)
ww_mutex_destroy(&locks[n]);
+ kfree(stress_array);
kfree(locks);
return 0;
@@ -625,6 +643,8 @@ static int __init test_ww_mutex_init(void)
printk(KERN_INFO "Beginning ww mutex selftests\n");
+ prandom_seed_state(&rng, get_random_u64());
+
wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0);
if (!wq)
return -ENOMEM;
diff --git a/kernel/locking/ww_rt_mutex.c b/kernel/locking/ww_rt_mutex.c
index d1473c624105..c7196de838ed 100644
--- a/kernel/locking/ww_rt_mutex.c
+++ b/kernel/locking/ww_rt_mutex.c
@@ -62,7 +62,7 @@ __ww_rt_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx,
}
mutex_acquire_nest(&rtm->dep_map, 0, 0, nest_lock, ip);
- if (likely(rt_mutex_cmpxchg_acquire(&rtm->rtmutex, NULL, current))) {
+ if (likely(rt_mutex_try_acquire(&rtm->rtmutex))) {
if (ww_ctx)
ww_mutex_set_context_fastpath(lock, ww_ctx);
return 0;
diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index 33a2e991f608..0ea1b2970a23 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -236,14 +236,6 @@ choice
possible to load a signed module containing the algorithm to check
the signature on that module.
-config MODULE_SIG_SHA1
- bool "Sign modules with SHA-1"
- select CRYPTO_SHA1
-
-config MODULE_SIG_SHA224
- bool "Sign modules with SHA-224"
- select CRYPTO_SHA256
-
config MODULE_SIG_SHA256
bool "Sign modules with SHA-256"
select CRYPTO_SHA256
@@ -256,16 +248,29 @@ config MODULE_SIG_SHA512
bool "Sign modules with SHA-512"
select CRYPTO_SHA512
+config MODULE_SIG_SHA3_256
+ bool "Sign modules with SHA3-256"
+ select CRYPTO_SHA3
+
+config MODULE_SIG_SHA3_384
+ bool "Sign modules with SHA3-384"
+ select CRYPTO_SHA3
+
+config MODULE_SIG_SHA3_512
+ bool "Sign modules with SHA3-512"
+ select CRYPTO_SHA3
+
endchoice
config MODULE_SIG_HASH
string
depends on MODULE_SIG || IMA_APPRAISE_MODSIG
- default "sha1" if MODULE_SIG_SHA1
- default "sha224" if MODULE_SIG_SHA224
default "sha256" if MODULE_SIG_SHA256
default "sha384" if MODULE_SIG_SHA384
default "sha512" if MODULE_SIG_SHA512
+ default "sha3-256" if MODULE_SIG_SHA3_256
+ default "sha3-384" if MODULE_SIG_SHA3_384
+ default "sha3-512" if MODULE_SIG_SHA3_512
choice
prompt "Module compression mode"
diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c
index 8a5d6d63b06c..474e68f0f063 100644
--- a/kernel/module/decompress.c
+++ b/kernel/module/decompress.c
@@ -100,7 +100,7 @@ static ssize_t module_gzip_decompress(struct load_info *info,
s.next_in = buf + gzip_hdr_len;
s.avail_in = size - gzip_hdr_len;
- s.workspace = kmalloc(zlib_inflate_workspacesize(), GFP_KERNEL);
+ s.workspace = kvmalloc(zlib_inflate_workspacesize(), GFP_KERNEL);
if (!s.workspace)
return -ENOMEM;
@@ -138,7 +138,7 @@ static ssize_t module_gzip_decompress(struct load_info *info,
out_inflate_end:
zlib_inflateEnd(&s);
out:
- kfree(s.workspace);
+ kvfree(s.workspace);
return retval;
}
#elif defined(CONFIG_MODULE_COMPRESS_XZ)
@@ -241,7 +241,7 @@ static ssize_t module_zstd_decompress(struct load_info *info,
}
wksp_size = zstd_dstream_workspace_bound(header.windowSize);
- wksp = kmalloc(wksp_size, GFP_KERNEL);
+ wksp = kvmalloc(wksp_size, GFP_KERNEL);
if (!wksp) {
retval = -ENOMEM;
goto out;
@@ -284,7 +284,7 @@ static ssize_t module_zstd_decompress(struct load_info *info,
retval = new_size;
out:
- kfree(wksp);
+ kvfree(wksp);
return retval;
}
#else
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 59b1d067e528..98fedfdb8db5 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1295,12 +1295,20 @@ void *__symbol_get(const char *symbol)
};
preempt_disable();
- if (!find_symbol(&fsa) || strong_try_module_get(fsa.owner)) {
- preempt_enable();
- return NULL;
+ if (!find_symbol(&fsa))
+ goto fail;
+ if (fsa.license != GPL_ONLY) {
+ pr_warn("failing symbol_get of non-GPLONLY symbol %s.\n",
+ symbol);
+ goto fail;
}
+ if (strong_try_module_get(fsa.owner))
+ goto fail;
preempt_enable();
return (void *)kernel_symbol_value(fsa.sym);
+fail:
+ preempt_enable();
+ return NULL;
}
EXPORT_SYMBOL_GPL(__symbol_get);
@@ -1484,7 +1492,7 @@ long module_get_offset_and_type(struct module *mod, enum mod_mem_type type,
return offset | mask;
}
-static bool module_init_layout_section(const char *sname)
+bool module_init_layout_section(const char *sname)
{
#ifndef CONFIG_MODULE_UNLOAD
if (module_exit_section(sname))
diff --git a/kernel/module/stats.c b/kernel/module/stats.c
index 6ab2c94d6bc3..3ba0e98b3c91 100644
--- a/kernel/module/stats.c
+++ b/kernel/module/stats.c
@@ -126,7 +126,7 @@ static LIST_HEAD(dup_failed_modules);
* These typically should not happen unless your system is under memory
* pressure.
* * invalid_becoming_bytes: total number of bytes allocated and freed used
- * used to read the kernel module userspace wants us to read before we
+ * to read the kernel module userspace wants us to read before we
* promote it to be processed to be added to our @modules linked list. These
* failures can happen if we had a check in between a successful kernel_read_file_from_fd()
* call and right before we allocate the our private memory for the module
diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c
index c921bf044050..d964167c6658 100644
--- a/kernel/module/sysfs.c
+++ b/kernel/module/sysfs.c
@@ -143,7 +143,7 @@ static void remove_sect_attrs(struct module *mod)
struct module_notes_attrs {
struct kobject *dir;
unsigned int notes;
- struct bin_attribute attrs[];
+ struct bin_attribute attrs[] __counted_by(notes);
};
static ssize_t module_notes_read(struct file *filp, struct kobject *kobj,
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 80d9c6d77a45..15781acaac1c 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -30,7 +30,7 @@
static struct kmem_cache *nsproxy_cachep;
struct nsproxy init_nsproxy = {
- .count = ATOMIC_INIT(1),
+ .count = REFCOUNT_INIT(1),
.uts_ns = &init_uts_ns,
#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
.ipc_ns = &init_ipc_ns,
@@ -55,7 +55,7 @@ static inline struct nsproxy *create_nsproxy(void)
nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
if (nsproxy)
- atomic_set(&nsproxy->count, 1);
+ refcount_set(&nsproxy->count, 1);
return nsproxy;
}
diff --git a/kernel/padata.c b/kernel/padata.c
index 222d60195de6..179fb1518070 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -202,7 +202,7 @@ int padata_do_parallel(struct padata_shell *ps,
*cb_cpu = cpu;
}
- err = -EBUSY;
+ err = -EBUSY;
if ((pinst->flags & PADATA_RESET))
goto out;
@@ -1102,12 +1102,16 @@ EXPORT_SYMBOL(padata_alloc_shell);
*/
void padata_free_shell(struct padata_shell *ps)
{
+ struct parallel_data *pd;
+
if (!ps)
return;
mutex_lock(&ps->pinst->lock);
list_del(&ps->list);
- padata_free_pd(rcu_dereference_protected(ps->pd, 1));
+ pd = rcu_dereference_protected(ps->pd, 1);
+ if (refcount_dec_and_test(&pd->refcnt))
+ padata_free_pd(pd);
mutex_unlock(&ps->pinst->lock);
kfree(ps);
diff --git a/kernel/panic.c b/kernel/panic.c
index 10effe40a3fa..2807639aab51 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -192,14 +192,15 @@ atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID);
*/
void nmi_panic(struct pt_regs *regs, const char *msg)
{
- int old_cpu, cpu;
+ int old_cpu, this_cpu;
- cpu = raw_smp_processor_id();
- old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu);
+ old_cpu = PANIC_CPU_INVALID;
+ this_cpu = raw_smp_processor_id();
- if (old_cpu == PANIC_CPU_INVALID)
+ /* atomic_try_cmpxchg updates old_cpu on failure */
+ if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu))
panic("%s", msg);
- else if (old_cpu != cpu)
+ else if (old_cpu != this_cpu)
nmi_panic_self_stop(regs);
}
EXPORT_SYMBOL(nmi_panic);
@@ -216,7 +217,7 @@ static void panic_print_sys_info(bool console_flush)
show_state();
if (panic_print & PANIC_PRINT_MEM_INFO)
- show_mem(0, NULL);
+ show_mem();
if (panic_print & PANIC_PRINT_TIMER_INFO)
sysrq_timer_list_show();
@@ -311,15 +312,18 @@ void panic(const char *fmt, ...)
* stop themself or will wait until they are stopped by the 1st CPU
* with smp_send_stop().
*
- * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which
- * comes here, so go ahead.
+ * cmpxchg success means this is the 1st CPU which comes here,
+ * so go ahead.
* `old_cpu == this_cpu' means we came from nmi_panic() which sets
* panic_cpu to this CPU. In this case, this is also the 1st CPU.
*/
+ old_cpu = PANIC_CPU_INVALID;
this_cpu = raw_smp_processor_id();
- old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
- if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu)
+ /* atomic_try_cmpxchg updates old_cpu on failure */
+ if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) {
+ /* go ahead */
+ } else if (old_cpu != this_cpu)
panic_smp_self_stop();
console_verbose();
@@ -697,6 +701,7 @@ void warn_slowpath_fmt(const char *file, int line, unsigned taint,
if (!fmt) {
__warn(file, line, __builtin_return_address(0), taint,
NULL, NULL);
+ warn_rcu_exit(rcu);
return;
}
diff --git a/kernel/params.c b/kernel/params.c
index 07d01f6ce9a2..2d4a0564697e 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -331,7 +331,7 @@ EXPORT_SYMBOL(param_ops_bool);
int param_set_bool_enable_only(const char *val, const struct kernel_param *kp)
{
- int err = 0;
+ int err;
bool new_value;
bool orig_value = *(bool *)kp->arg;
struct kernel_param dummy_kp = *kp;
diff --git a/kernel/pid.c b/kernel/pid.c
index 6a1d23a11026..6500ef956f2f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -83,6 +83,9 @@ struct pid_namespace init_pid_ns = {
#ifdef CONFIG_PID_NS
.ns.ops = &pidns_operations,
#endif
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+ .memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC,
+#endif
};
EXPORT_SYMBOL_GPL(init_pid_ns);
@@ -606,7 +609,7 @@ int pidfd_create(struct pid *pid, unsigned int flags)
}
/**
- * pidfd_open() - Open new pid file descriptor.
+ * sys_pidfd_open() - Open new pid file descriptor.
*
* @pid: pid for which to retrieve a pidfd
* @flags: flags to pass
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 0bf44afe04dd..3028b2218aa4 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -110,9 +110,9 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
ns->user_ns = get_user_ns(user_ns);
ns->ucounts = ucounts;
ns->pid_allocated = PIDNS_ADDING;
-
- initialize_memfd_noexec_scope(ns);
-
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+ ns->memfd_noexec_scope = pidns_memfd_noexec_scope(parent_pid_ns);
+#endif
return ns;
out_free_idr:
@@ -286,12 +286,6 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
if (write && !checkpoint_restore_ns_capable(pid_ns->user_ns))
return -EPERM;
- /*
- * Writing directly to ns' last_pid field is OK, since this field
- * is volatile in a living namespace anyway and a code writing to
- * it should synchronize its usage with external means.
- */
-
next = idr_get_cursor(&pid_ns->idr) - 1;
tmp.data = &next;
diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h
index b26e027fc9cd..2ee41a3a1dfd 100644
--- a/kernel/pid_sysctl.h
+++ b/kernel/pid_sysctl.h
@@ -5,33 +5,30 @@
#include <linux/pid_namespace.h>
#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
-static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns)
-{
- ns->memfd_noexec_scope =
- task_active_pid_ns(current)->memfd_noexec_scope;
-}
-
static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table,
int write, void *buf, size_t *lenp, loff_t *ppos)
{
struct pid_namespace *ns = task_active_pid_ns(current);
struct ctl_table table_copy;
+ int err, scope, parent_scope;
if (write && !ns_capable(ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
table_copy = *table;
- if (ns != &init_pid_ns)
- table_copy.data = &ns->memfd_noexec_scope;
- /*
- * set minimum to current value, the effect is only bigger
- * value is accepted.
- */
- if (*(int *)table_copy.data > *(int *)table_copy.extra1)
- table_copy.extra1 = table_copy.data;
+ /* You cannot set a lower enforcement value than your parent. */
+ parent_scope = pidns_memfd_noexec_scope(ns->parent);
+ /* Equivalent to pidns_memfd_noexec_scope(ns). */
+ scope = max(READ_ONCE(ns->memfd_noexec_scope), parent_scope);
+
+ table_copy.data = &scope;
+ table_copy.extra1 = &parent_scope;
- return proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos);
+ err = proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos);
+ if (!err && write)
+ WRITE_ONCE(ns->memfd_noexec_scope, scope);
+ return err;
}
static struct ctl_table pid_ns_ctl_table_vm[] = {
@@ -51,7 +48,6 @@ static inline void register_pid_ns_sysctl_table_vm(void)
register_sysctl("vm", pid_ns_ctl_table_vm);
}
#else
-static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {}
static inline void register_pid_ns_sysctl_table_vm(void) {}
#endif
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 2b4a946a6ff5..dee341ae4ace 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -684,7 +684,7 @@ static void power_down(void)
cpu_relax();
}
-static int load_image_and_restore(bool snapshot_test)
+static int load_image_and_restore(void)
{
int error;
unsigned int flags;
@@ -694,12 +694,12 @@ static int load_image_and_restore(bool snapshot_test)
lock_device_hotplug();
error = create_basic_memory_bitmaps();
if (error) {
- swsusp_close(snapshot_test);
+ swsusp_close();
goto Unlock;
}
error = swsusp_read(&flags);
- swsusp_close(snapshot_test);
+ swsusp_close();
if (!error)
error = hibernation_restore(flags & SF_PLATFORM_MODE);
@@ -786,9 +786,9 @@ int hibernate(void)
unlock_device_hotplug();
if (snapshot_test) {
pm_pr_dbg("Checking hibernation image\n");
- error = swsusp_check(snapshot_test);
+ error = swsusp_check(false);
if (!error)
- error = load_image_and_restore(snapshot_test);
+ error = load_image_and_restore();
}
thaw_processes();
@@ -945,14 +945,14 @@ static int software_resume(void)
pm_pr_dbg("Looking for hibernation image.\n");
mutex_lock(&system_transition_mutex);
- error = swsusp_check(false);
+ error = swsusp_check(true);
if (error)
goto Unlock;
/* The snapshot device should not be opened while we're running */
if (!hibernate_acquire()) {
error = -EBUSY;
- swsusp_close(false);
+ swsusp_close();
goto Unlock;
}
@@ -973,7 +973,7 @@ static int software_resume(void)
goto Close_Finish;
}
- error = load_image_and_restore(false);
+ error = load_image_and_restore();
thaw_processes();
Finish:
pm_notifier_call_chain(PM_POST_RESTORE);
@@ -987,7 +987,7 @@ static int software_resume(void)
pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
return error;
Close_Finish:
- swsusp_close(false);
+ swsusp_close();
goto Finish;
}
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 46eb14dc50c3..17fd9aaaf084 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -168,11 +168,11 @@ extern int swsusp_swap_in_use(void);
#define SF_HW_SIG 8
/* kernel/power/hibernate.c */
-int swsusp_check(bool snapshot_test);
+int swsusp_check(bool exclusive);
extern void swsusp_free(void);
extern int swsusp_read(unsigned int *flags_p);
extern int swsusp_write(unsigned int flags);
-void swsusp_close(bool snapshot_test);
+void swsusp_close(void);
#ifdef CONFIG_SUSPEND
extern int swsusp_unmark(void);
#endif
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 562aa0e450ed..1f306f158696 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -23,7 +23,7 @@ static void do_poweroff(struct work_struct *dummy)
static DECLARE_WORK(poweroff_work, do_poweroff);
-static void handle_poweroff(int key)
+static void handle_poweroff(u8 key)
{
/* run sysrq poweroff on boot cpu */
schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work);
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 782d3b41c1f3..4244b069442e 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -220,6 +220,11 @@ static struct pm_qos_constraints cpu_latency_constraints = {
.type = PM_QOS_MIN,
};
+static inline bool cpu_latency_qos_value_invalid(s32 value)
+{
+ return value < 0 && value != PM_QOS_DEFAULT_VALUE;
+}
+
/**
* cpu_latency_qos_limit - Return current system-wide CPU latency QoS limit.
*/
@@ -263,7 +268,7 @@ static void cpu_latency_qos_apply(struct pm_qos_request *req,
*/
void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value)
{
- if (!req)
+ if (!req || cpu_latency_qos_value_invalid(value))
return;
if (cpu_latency_qos_request_active(req)) {
@@ -289,7 +294,7 @@ EXPORT_SYMBOL_GPL(cpu_latency_qos_add_request);
*/
void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value)
{
- if (!req)
+ if (!req || cpu_latency_qos_value_invalid(new_value))
return;
if (!cpu_latency_qos_request_active(req)) {
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0415d5ecb977..50a15408c3fc 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -404,6 +404,7 @@ struct bm_position {
struct mem_zone_bm_rtree *zone;
struct rtree_node *node;
unsigned long node_pfn;
+ unsigned long cur_pfn;
int node_bit;
};
@@ -589,6 +590,7 @@ static void memory_bm_position_reset(struct memory_bitmap *bm)
bm->cur.node = list_entry(bm->cur.zone->leaves.next,
struct rtree_node, list);
bm->cur.node_pfn = 0;
+ bm->cur.cur_pfn = BM_END_OF_MAP;
bm->cur.node_bit = 0;
}
@@ -799,6 +801,7 @@ node_found:
bm->cur.zone = zone;
bm->cur.node = node;
bm->cur.node_pfn = (pfn - zone->start_pfn) & ~BM_BLOCK_MASK;
+ bm->cur.cur_pfn = pfn;
/* Set return values */
*addr = node->data;
@@ -850,6 +853,11 @@ static void memory_bm_clear_current(struct memory_bitmap *bm)
clear_bit(bit, bm->cur.node->data);
}
+static unsigned long memory_bm_get_current(struct memory_bitmap *bm)
+{
+ return bm->cur.cur_pfn;
+}
+
static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
{
void *addr;
@@ -929,10 +937,12 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
if (bit < bits) {
pfn = bm->cur.zone->start_pfn + bm->cur.node_pfn + bit;
bm->cur.node_bit = bit + 1;
+ bm->cur.cur_pfn = pfn;
return pfn;
}
} while (rtree_next_node(bm));
+ bm->cur.cur_pfn = BM_END_OF_MAP;
return BM_END_OF_MAP;
}
@@ -1423,14 +1433,19 @@ static unsigned int count_data_pages(void)
/*
* This is needed, because copy_page and memcpy are not usable for copying
- * task structs.
+ * task structs. Returns true if the page was filled with only zeros,
+ * otherwise false.
*/
-static inline void do_copy_page(long *dst, long *src)
+static inline bool do_copy_page(long *dst, long *src)
{
+ long z = 0;
int n;
- for (n = PAGE_SIZE / sizeof(long); n; n--)
+ for (n = PAGE_SIZE / sizeof(long); n; n--) {
+ z |= *src;
*dst++ = *src++;
+ }
+ return !z;
}
/**
@@ -1439,17 +1454,21 @@ static inline void do_copy_page(long *dst, long *src)
* Check if the page we are going to copy is marked as present in the kernel
* page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or
* CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present()
- * always returns 'true'.
+ * always returns 'true'. Returns true if the page was entirely composed of
+ * zeros, otherwise it will return false.
*/
-static void safe_copy_page(void *dst, struct page *s_page)
+static bool safe_copy_page(void *dst, struct page *s_page)
{
+ bool zeros_only;
+
if (kernel_page_present(s_page)) {
- do_copy_page(dst, page_address(s_page));
+ zeros_only = do_copy_page(dst, page_address(s_page));
} else {
hibernate_map_page(s_page);
- do_copy_page(dst, page_address(s_page));
+ zeros_only = do_copy_page(dst, page_address(s_page));
hibernate_unmap_page(s_page);
}
+ return zeros_only;
}
#ifdef CONFIG_HIGHMEM
@@ -1459,17 +1478,18 @@ static inline struct page *page_is_saveable(struct zone *zone, unsigned long pfn
saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn);
}
-static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
+static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
{
struct page *s_page, *d_page;
void *src, *dst;
+ bool zeros_only;
s_page = pfn_to_page(src_pfn);
d_page = pfn_to_page(dst_pfn);
if (PageHighMem(s_page)) {
src = kmap_atomic(s_page);
dst = kmap_atomic(d_page);
- do_copy_page(dst, src);
+ zeros_only = do_copy_page(dst, src);
kunmap_atomic(dst);
kunmap_atomic(src);
} else {
@@ -1478,30 +1498,39 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
* The page pointed to by src may contain some kernel
* data modified by kmap_atomic()
*/
- safe_copy_page(buffer, s_page);
+ zeros_only = safe_copy_page(buffer, s_page);
dst = kmap_atomic(d_page);
copy_page(dst, buffer);
kunmap_atomic(dst);
} else {
- safe_copy_page(page_address(d_page), s_page);
+ zeros_only = safe_copy_page(page_address(d_page), s_page);
}
}
+ return zeros_only;
}
#else
#define page_is_saveable(zone, pfn) saveable_page(zone, pfn)
-static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
+static inline int copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
{
- safe_copy_page(page_address(pfn_to_page(dst_pfn)),
+ return safe_copy_page(page_address(pfn_to_page(dst_pfn)),
pfn_to_page(src_pfn));
}
#endif /* CONFIG_HIGHMEM */
-static void copy_data_pages(struct memory_bitmap *copy_bm,
- struct memory_bitmap *orig_bm)
+/*
+ * Copy data pages will copy all pages into pages pulled from the copy_bm.
+ * If a page was entirely filled with zeros it will be marked in the zero_bm.
+ *
+ * Returns the number of pages copied.
+ */
+static unsigned long copy_data_pages(struct memory_bitmap *copy_bm,
+ struct memory_bitmap *orig_bm,
+ struct memory_bitmap *zero_bm)
{
+ unsigned long copied_pages = 0;
struct zone *zone;
- unsigned long pfn;
+ unsigned long pfn, copy_pfn;
for_each_populated_zone(zone) {
unsigned long max_zone_pfn;
@@ -1514,18 +1543,29 @@ static void copy_data_pages(struct memory_bitmap *copy_bm,
}
memory_bm_position_reset(orig_bm);
memory_bm_position_reset(copy_bm);
+ copy_pfn = memory_bm_next_pfn(copy_bm);
for(;;) {
pfn = memory_bm_next_pfn(orig_bm);
if (unlikely(pfn == BM_END_OF_MAP))
break;
- copy_data_page(memory_bm_next_pfn(copy_bm), pfn);
+ if (copy_data_page(copy_pfn, pfn)) {
+ memory_bm_set_bit(zero_bm, pfn);
+ /* Use this copy_pfn for a page that is not full of zeros */
+ continue;
+ }
+ copied_pages++;
+ copy_pfn = memory_bm_next_pfn(copy_bm);
}
+ return copied_pages;
}
/* Total number of image pages */
static unsigned int nr_copy_pages;
/* Number of pages needed for saving the original pfns of the image pages */
static unsigned int nr_meta_pages;
+/* Number of zero pages */
+static unsigned int nr_zero_pages;
+
/*
* Numbers of normal and highmem page frames allocated for hibernation image
* before suspending devices.
@@ -1546,6 +1586,9 @@ static struct memory_bitmap orig_bm;
*/
static struct memory_bitmap copy_bm;
+/* Memory bitmap which tracks which saveable pages were zero filled. */
+static struct memory_bitmap zero_bm;
+
/**
* swsusp_free - Free pages allocated for hibernation image.
*
@@ -1590,6 +1633,7 @@ loop:
out:
nr_copy_pages = 0;
nr_meta_pages = 0;
+ nr_zero_pages = 0;
restore_pblist = NULL;
buffer = NULL;
alloc_normal = 0;
@@ -1808,8 +1852,15 @@ int hibernate_preallocate_memory(void)
goto err_out;
}
+ error = memory_bm_create(&zero_bm, GFP_IMAGE, PG_ANY);
+ if (error) {
+ pr_err("Cannot allocate zero bitmap\n");
+ goto err_out;
+ }
+
alloc_normal = 0;
alloc_highmem = 0;
+ nr_zero_pages = 0;
/* Count the number of saveable data pages. */
save_highmem = count_highmem_pages();
@@ -2089,19 +2140,19 @@ asmlinkage __visible int swsusp_save(void)
* Kill them.
*/
drain_local_pages(NULL);
- copy_data_pages(&copy_bm, &orig_bm);
+ nr_copy_pages = copy_data_pages(&copy_bm, &orig_bm, &zero_bm);
/*
* End of critical section. From now on, we can write to memory,
* but we should not touch disk. This specially means we must _not_
* touch swap space! Except we must write out our image of course.
*/
-
nr_pages += nr_highmem;
- nr_copy_pages = nr_pages;
+ /* We don't actually copy the zero pages */
+ nr_zero_pages = nr_pages - nr_copy_pages;
nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE);
- pr_info("Image created (%d pages copied)\n", nr_pages);
+ pr_info("Image created (%d pages copied, %d zero pages)\n", nr_copy_pages, nr_zero_pages);
return 0;
}
@@ -2146,15 +2197,22 @@ static int init_header(struct swsusp_info *info)
return init_header_complete(info);
}
+#define ENCODED_PFN_ZERO_FLAG ((unsigned long)1 << (BITS_PER_LONG - 1))
+#define ENCODED_PFN_MASK (~ENCODED_PFN_ZERO_FLAG)
+
/**
* pack_pfns - Prepare PFNs for saving.
* @bm: Memory bitmap.
* @buf: Memory buffer to store the PFNs in.
+ * @zero_bm: Memory bitmap containing PFNs of zero pages.
*
* PFNs corresponding to set bits in @bm are stored in the area of memory
- * pointed to by @buf (1 page at a time).
+ * pointed to by @buf (1 page at a time). Pages which were filled with only
+ * zeros will have the highest bit set in the packed format to distinguish
+ * them from PFNs which will be contained in the image file.
*/
-static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
+static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm,
+ struct memory_bitmap *zero_bm)
{
int j;
@@ -2162,6 +2220,8 @@ static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
buf[j] = memory_bm_next_pfn(bm);
if (unlikely(buf[j] == BM_END_OF_MAP))
break;
+ if (memory_bm_test_bit(zero_bm, buf[j]))
+ buf[j] |= ENCODED_PFN_ZERO_FLAG;
}
}
@@ -2203,7 +2263,7 @@ int snapshot_read_next(struct snapshot_handle *handle)
memory_bm_position_reset(&copy_bm);
} else if (handle->cur <= nr_meta_pages) {
clear_page(buffer);
- pack_pfns(buffer, &orig_bm);
+ pack_pfns(buffer, &orig_bm, &zero_bm);
} else {
struct page *page;
@@ -2299,24 +2359,35 @@ static int load_header(struct swsusp_info *info)
* unpack_orig_pfns - Set bits corresponding to given PFNs in a memory bitmap.
* @bm: Memory bitmap.
* @buf: Area of memory containing the PFNs.
+ * @zero_bm: Memory bitmap with the zero PFNs marked.
*
* For each element of the array pointed to by @buf (1 page at a time), set the
- * corresponding bit in @bm.
+ * corresponding bit in @bm. If the page was originally populated with only
+ * zeros then a corresponding bit will also be set in @zero_bm.
*/
-static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
+static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm,
+ struct memory_bitmap *zero_bm)
{
+ unsigned long decoded_pfn;
+ bool zero;
int j;
for (j = 0; j < PAGE_SIZE / sizeof(long); j++) {
if (unlikely(buf[j] == BM_END_OF_MAP))
break;
- if (pfn_valid(buf[j]) && memory_bm_pfn_present(bm, buf[j])) {
- memory_bm_set_bit(bm, buf[j]);
+ zero = !!(buf[j] & ENCODED_PFN_ZERO_FLAG);
+ decoded_pfn = buf[j] & ENCODED_PFN_MASK;
+ if (pfn_valid(decoded_pfn) && memory_bm_pfn_present(bm, decoded_pfn)) {
+ memory_bm_set_bit(bm, decoded_pfn);
+ if (zero) {
+ memory_bm_set_bit(zero_bm, decoded_pfn);
+ nr_zero_pages++;
+ }
} else {
- if (!pfn_valid(buf[j]))
+ if (!pfn_valid(decoded_pfn))
pr_err(FW_BUG "Memory map mismatch at 0x%llx after hibernation\n",
- (unsigned long long)PFN_PHYS(buf[j]));
+ (unsigned long long)PFN_PHYS(decoded_pfn));
return -EFAULT;
}
}
@@ -2474,8 +2545,9 @@ static void *get_highmem_page_buffer(struct page *page,
pbe->copy_page = tmp;
} else {
/* Copy of the page will be stored in normal memory */
- kaddr = safe_pages_list;
- safe_pages_list = safe_pages_list->next;
+ kaddr = __get_safe_page(ca->gfp_mask);
+ if (!kaddr)
+ return ERR_PTR(-ENOMEM);
pbe->copy_page = virt_to_page(kaddr);
}
pbe->next = highmem_pblist;
@@ -2538,6 +2610,7 @@ static inline void free_highmem_data(void) {}
* prepare_image - Make room for loading hibernation image.
* @new_bm: Uninitialized memory bitmap structure.
* @bm: Memory bitmap with unsafe pages marked.
+ * @zero_bm: Memory bitmap containing the zero pages.
*
* Use @bm to mark the pages that will be overwritten in the process of
* restoring the system memory state from the suspend image ("unsafe" pages)
@@ -2548,10 +2621,15 @@ static inline void free_highmem_data(void) {}
* pages will be used for just yet. Instead, we mark them all as allocated and
* create a lists of "safe" pages to be used later. On systems with high
* memory a list of "safe" highmem pages is created too.
+ *
+ * Because it was not known which pages were unsafe when @zero_bm was created,
+ * make a copy of it and recreate it within safe pages.
*/
-static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
+static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm,
+ struct memory_bitmap *zero_bm)
{
unsigned int nr_pages, nr_highmem;
+ struct memory_bitmap tmp;
struct linked_page *lp;
int error;
@@ -2568,6 +2646,24 @@ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
duplicate_memory_bitmap(new_bm, bm);
memory_bm_free(bm, PG_UNSAFE_KEEP);
+
+ /* Make a copy of zero_bm so it can be created in safe pages */
+ error = memory_bm_create(&tmp, GFP_ATOMIC, PG_SAFE);
+ if (error)
+ goto Free;
+
+ duplicate_memory_bitmap(&tmp, zero_bm);
+ memory_bm_free(zero_bm, PG_UNSAFE_KEEP);
+
+ /* Recreate zero_bm in safe pages */
+ error = memory_bm_create(zero_bm, GFP_ATOMIC, PG_SAFE);
+ if (error)
+ goto Free;
+
+ duplicate_memory_bitmap(zero_bm, &tmp);
+ memory_bm_free(&tmp, PG_UNSAFE_CLEAR);
+ /* At this point zero_bm is in safe pages and it can be used for restoring. */
+
if (nr_highmem > 0) {
error = prepare_highmem_image(bm, &nr_highmem);
if (error)
@@ -2582,7 +2678,7 @@ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
*
* nr_copy_pages cannot be less than allocated_unsafe_pages too.
*/
- nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
+ nr_pages = (nr_zero_pages + nr_copy_pages) - nr_highmem - allocated_unsafe_pages;
nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE);
while (nr_pages > 0) {
lp = get_image_page(GFP_ATOMIC, PG_SAFE);
@@ -2595,7 +2691,7 @@ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
nr_pages--;
}
/* Preallocate memory for the image */
- nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
+ nr_pages = (nr_zero_pages + nr_copy_pages) - nr_highmem - allocated_unsafe_pages;
while (nr_pages > 0) {
lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC);
if (!lp) {
@@ -2655,8 +2751,9 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
return ERR_PTR(-ENOMEM);
}
pbe->orig_address = page_address(page);
- pbe->address = safe_pages_list;
- safe_pages_list = safe_pages_list->next;
+ pbe->address = __get_safe_page(ca->gfp_mask);
+ if (!pbe->address)
+ return ERR_PTR(-ENOMEM);
pbe->next = restore_pblist;
restore_pblist = pbe;
return pbe->address;
@@ -2683,12 +2780,11 @@ int snapshot_write_next(struct snapshot_handle *handle)
static struct chain_allocator ca;
int error = 0;
+next:
/* Check if we have already loaded the entire image */
- if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages)
+ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages + nr_zero_pages)
return 0;
- handle->sync_read = 1;
-
if (!handle->cur) {
if (!buffer)
/* This makes the buffer be freed by swsusp_free() */
@@ -2709,22 +2805,28 @@ int snapshot_write_next(struct snapshot_handle *handle)
if (error)
return error;
+ error = memory_bm_create(&zero_bm, GFP_ATOMIC, PG_ANY);
+ if (error)
+ return error;
+
+ nr_zero_pages = 0;
+
hibernate_restore_protection_begin();
} else if (handle->cur <= nr_meta_pages + 1) {
- error = unpack_orig_pfns(buffer, &copy_bm);
+ error = unpack_orig_pfns(buffer, &copy_bm, &zero_bm);
if (error)
return error;
if (handle->cur == nr_meta_pages + 1) {
- error = prepare_image(&orig_bm, &copy_bm);
+ error = prepare_image(&orig_bm, &copy_bm, &zero_bm);
if (error)
return error;
chain_init(&ca, GFP_ATOMIC, PG_SAFE);
memory_bm_position_reset(&orig_bm);
+ memory_bm_position_reset(&zero_bm);
restore_pblist = NULL;
handle->buffer = get_buffer(&orig_bm, &ca);
- handle->sync_read = 0;
if (IS_ERR(handle->buffer))
return PTR_ERR(handle->buffer);
}
@@ -2734,10 +2836,17 @@ int snapshot_write_next(struct snapshot_handle *handle)
handle->buffer = get_buffer(&orig_bm, &ca);
if (IS_ERR(handle->buffer))
return PTR_ERR(handle->buffer);
- if (handle->buffer != buffer)
- handle->sync_read = 0;
}
+ handle->sync_read = (handle->buffer == buffer);
handle->cur++;
+
+ /* Zero pages were not included in the image, memset it and move on. */
+ if (handle->cur > nr_meta_pages + 1 &&
+ memory_bm_test_bit(&zero_bm, memory_bm_get_current(&orig_bm))) {
+ memset(handle->buffer, 0, PAGE_SIZE);
+ goto next;
+ }
+
return PAGE_SIZE;
}
@@ -2754,7 +2863,7 @@ void snapshot_write_finalize(struct snapshot_handle *handle)
copy_last_highmem_page();
hibernate_restore_protect_page(handle->buffer);
/* Do that only if we have loaded the image entirely */
- if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) {
+ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages + nr_zero_pages) {
memory_bm_recycle(&orig_bm);
free_highmem_data();
}
@@ -2763,7 +2872,7 @@ void snapshot_write_finalize(struct snapshot_handle *handle)
int snapshot_image_loaded(struct snapshot_handle *handle)
{
return !(!nr_copy_pages || !last_highmem_page_copied() ||
- handle->cur <= nr_meta_pages + nr_copy_pages);
+ handle->cur <= nr_meta_pages + nr_copy_pages + nr_zero_pages);
}
#ifdef CONFIG_HIGHMEM
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index f6ebcd00c410..a2cb0babb5ec 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -222,7 +222,7 @@ int swsusp_swap_in_use(void)
*/
static unsigned short root_swap = 0xffff;
-static struct block_device *hib_resume_bdev;
+static struct bdev_handle *hib_resume_bdev_handle;
struct hib_bio_batch {
atomic_t count;
@@ -276,7 +276,8 @@ static int hib_submit_io(blk_opf_t opf, pgoff_t page_off, void *addr,
struct bio *bio;
int error = 0;
- bio = bio_alloc(hib_resume_bdev, 1, opf, GFP_NOIO | __GFP_HIGH);
+ bio = bio_alloc(hib_resume_bdev_handle->bdev, 1, opf,
+ GFP_NOIO | __GFP_HIGH);
bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
@@ -356,14 +357,14 @@ static int swsusp_swap_check(void)
return res;
root_swap = res;
- hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device,
+ hib_resume_bdev_handle = bdev_open_by_dev(swsusp_resume_device,
BLK_OPEN_WRITE, NULL, NULL);
- if (IS_ERR(hib_resume_bdev))
- return PTR_ERR(hib_resume_bdev);
+ if (IS_ERR(hib_resume_bdev_handle))
+ return PTR_ERR(hib_resume_bdev_handle);
- res = set_blocksize(hib_resume_bdev, PAGE_SIZE);
+ res = set_blocksize(hib_resume_bdev_handle->bdev, PAGE_SIZE);
if (res < 0)
- blkdev_put(hib_resume_bdev, NULL);
+ bdev_release(hib_resume_bdev_handle);
return res;
}
@@ -443,7 +444,7 @@ static int get_swap_writer(struct swap_map_handle *handle)
err_rel:
release_swap_writer(handle);
err_close:
- swsusp_close(false);
+ swsusp_close();
return ret;
}
@@ -508,7 +509,7 @@ static int swap_writer_finish(struct swap_map_handle *handle,
if (error)
free_all_swap_pages(root_swap);
release_swap_writer(handle);
- swsusp_close(false);
+ swsusp_close();
return error;
}
@@ -1513,18 +1514,19 @@ end:
static void *swsusp_holder;
/**
- * swsusp_check - Check for swsusp signature in the resume device
+ * swsusp_check - Open the resume device and check for the swsusp signature.
+ * @exclusive: Open the resume device exclusively.
*/
-int swsusp_check(bool snapshot_test)
+int swsusp_check(bool exclusive)
{
- void *holder = snapshot_test ? &swsusp_holder : NULL;
+ void *holder = exclusive ? &swsusp_holder : NULL;
int error;
- hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, BLK_OPEN_READ,
- holder, NULL);
- if (!IS_ERR(hib_resume_bdev)) {
- set_blocksize(hib_resume_bdev, PAGE_SIZE);
+ hib_resume_bdev_handle = bdev_open_by_dev(swsusp_resume_device,
+ BLK_OPEN_READ, holder, NULL);
+ if (!IS_ERR(hib_resume_bdev_handle)) {
+ set_blocksize(hib_resume_bdev_handle->bdev, PAGE_SIZE);
clear_page(swsusp_header);
error = hib_submit_io(REQ_OP_READ, swsusp_resume_block,
swsusp_header, NULL);
@@ -1549,11 +1551,11 @@ int swsusp_check(bool snapshot_test)
put:
if (error)
- blkdev_put(hib_resume_bdev, holder);
+ bdev_release(hib_resume_bdev_handle);
else
pr_debug("Image signature found, resuming\n");
} else {
- error = PTR_ERR(hib_resume_bdev);
+ error = PTR_ERR(hib_resume_bdev_handle);
}
if (error)
@@ -1563,17 +1565,18 @@ put:
}
/**
- * swsusp_close - close swap device.
+ * swsusp_close - close resume device.
+ * @exclusive: Close the resume device which is exclusively opened.
*/
-void swsusp_close(bool snapshot_test)
+void swsusp_close(void)
{
- if (IS_ERR(hib_resume_bdev)) {
+ if (IS_ERR(hib_resume_bdev_handle)) {
pr_debug("Image device not initialised\n");
return;
}
- blkdev_put(hib_resume_bdev, snapshot_test ? &swsusp_holder : NULL);
+ bdev_release(hib_resume_bdev_handle);
}
/**
diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile
index f5b388e810b9..39a2b61c7232 100644
--- a/kernel/printk/Makefile
+++ b/kernel/printk/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-y = printk.o
-obj-$(CONFIG_PRINTK) += printk_safe.o
+obj-$(CONFIG_PRINTK) += printk_safe.o nbcon.o
obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o
obj-$(CONFIG_PRINTK_INDEX) += index.o
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 2a17704136f1..6c2afee5ef62 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -3,6 +3,8 @@
* internal.h - printk internal definitions
*/
#include <linux/percpu.h>
+#include <linux/console.h>
+#include "printk_ringbuffer.h"
#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
void __init printk_sysctl_init(void);
@@ -12,6 +14,12 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
#define printk_sysctl_init() do { } while (0)
#endif
+#define con_printk(lvl, con, fmt, ...) \
+ printk(lvl pr_fmt("%s%sconsole [%s%d] " fmt), \
+ (con->flags & CON_NBCON) ? "" : "legacy ", \
+ (con->flags & CON_BOOT) ? "boot" : "", \
+ con->name, con->index, ##__VA_ARGS__)
+
#ifdef CONFIG_PRINTK
#ifdef CONFIG_PRINTK_CALLER
@@ -35,6 +43,8 @@ enum printk_info_flags {
LOG_CONT = 8, /* text is a fragment of a continuation line */
};
+extern struct printk_ringbuffer *prb;
+
__printf(4, 0)
int vprintk_store(int facility, int level,
const struct dev_printk_info *dev_info,
@@ -61,6 +71,13 @@ void defer_console_output(void);
u16 printk_parse_prefix(const char *text, int *level,
enum printk_info_flags *flags);
+
+u64 nbcon_seq_read(struct console *con);
+void nbcon_seq_force(struct console *con, u64 seq);
+bool nbcon_alloc(struct console *con);
+void nbcon_init(struct console *con);
+void nbcon_free(struct console *con);
+
#else
#define PRINTK_PREFIX_MAX 0
@@ -76,8 +93,16 @@ u16 printk_parse_prefix(const char *text, int *level,
#define printk_safe_exit_irqrestore(flags) local_irq_restore(flags)
static inline bool printk_percpu_data_ready(void) { return false; }
+static inline u64 nbcon_seq_read(struct console *con) { return 0; }
+static inline void nbcon_seq_force(struct console *con, u64 seq) { }
+static inline bool nbcon_alloc(struct console *con) { return false; }
+static inline void nbcon_init(struct console *con) { }
+static inline void nbcon_free(struct console *con) { }
+
#endif /* CONFIG_PRINTK */
+extern struct printk_buffers printk_shared_pbufs;
+
/**
* struct printk_buffers - Buffers to read/format/output printk messages.
* @outbuf: After formatting, contains text to output.
@@ -103,3 +128,11 @@ struct printk_message {
u64 seq;
unsigned long dropped;
};
+
+bool other_cpu_in_panic(void);
+bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
+ bool is_extended, bool may_supress);
+
+#ifdef CONFIG_PRINTK
+void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped);
+#endif
diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c
new file mode 100644
index 000000000000..b96077152f49
--- /dev/null
+++ b/kernel/printk/nbcon.c
@@ -0,0 +1,1029 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2022 Linutronix GmbH, John Ogness
+// Copyright (C) 2022 Intel, Thomas Gleixner
+
+#include <linux/kernel.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include "internal.h"
+/*
+ * Printk console printing implementation for consoles which does not depend
+ * on the legacy style console_lock mechanism.
+ *
+ * The state of the console is maintained in the "nbcon_state" atomic
+ * variable.
+ *
+ * The console is locked when:
+ *
+ * - The 'prio' field contains the priority of the context that owns the
+ * console. Only higher priority contexts are allowed to take over the
+ * lock. A value of 0 (NBCON_PRIO_NONE) means the console is not locked.
+ *
+ * - The 'cpu' field denotes on which CPU the console is locked. It is used
+ * to prevent busy waiting on the same CPU. Also it informs the lock owner
+ * that it has lost the lock in a more complex scenario when the lock was
+ * taken over by a higher priority context, released, and taken on another
+ * CPU with the same priority as the interrupted owner.
+ *
+ * The acquire mechanism uses a few more fields:
+ *
+ * - The 'req_prio' field is used by the handover approach to make the
+ * current owner aware that there is a context with a higher priority
+ * waiting for the friendly handover.
+ *
+ * - The 'unsafe' field allows to take over the console in a safe way in the
+ * middle of emitting a message. The field is set only when accessing some
+ * shared resources or when the console device is manipulated. It can be
+ * cleared, for example, after emitting one character when the console
+ * device is in a consistent state.
+ *
+ * - The 'unsafe_takeover' field is set when a hostile takeover took the
+ * console in an unsafe state. The console will stay in the unsafe state
+ * until re-initialized.
+ *
+ * The acquire mechanism uses three approaches:
+ *
+ * 1) Direct acquire when the console is not owned or is owned by a lower
+ * priority context and is in a safe state.
+ *
+ * 2) Friendly handover mechanism uses a request/grant handshake. It is used
+ * when the current owner has lower priority and the console is in an
+ * unsafe state.
+ *
+ * The requesting context:
+ *
+ * a) Sets its priority into the 'req_prio' field.
+ *
+ * b) Waits (with a timeout) for the owning context to unlock the
+ * console.
+ *
+ * c) Takes the lock and clears the 'req_prio' field.
+ *
+ * The owning context:
+ *
+ * a) Observes the 'req_prio' field set on exit from the unsafe
+ * console state.
+ *
+ * b) Gives up console ownership by clearing the 'prio' field.
+ *
+ * 3) Unsafe hostile takeover allows to take over the lock even when the
+ * console is an unsafe state. It is used only in panic() by the final
+ * attempt to flush consoles in a try and hope mode.
+ *
+ * Note that separate record buffers are used in panic(). As a result,
+ * the messages can be read and formatted without any risk even after
+ * using the hostile takeover in unsafe state.
+ *
+ * The release function simply clears the 'prio' field.
+ *
+ * All operations on @console::nbcon_state are atomic cmpxchg based to
+ * handle concurrency.
+ *
+ * The acquire/release functions implement only minimal policies:
+ *
+ * - Preference for higher priority contexts.
+ * - Protection of the panic CPU.
+ *
+ * All other policy decisions must be made at the call sites:
+ *
+ * - What is marked as an unsafe section.
+ * - Whether to spin-wait if there is already an owner and the console is
+ * in an unsafe state.
+ * - Whether to attempt an unsafe hostile takeover.
+ *
+ * The design allows to implement the well known:
+ *
+ * acquire()
+ * output_one_printk_record()
+ * release()
+ *
+ * The output of one printk record might be interrupted with a higher priority
+ * context. The new owner is supposed to reprint the entire interrupted record
+ * from scratch.
+ */
+
+/**
+ * nbcon_state_set - Helper function to set the console state
+ * @con: Console to update
+ * @new: The new state to write
+ *
+ * Only to be used when the console is not yet or no longer visible in the
+ * system. Otherwise use nbcon_state_try_cmpxchg().
+ */
+static inline void nbcon_state_set(struct console *con, struct nbcon_state *new)
+{
+ atomic_set(&ACCESS_PRIVATE(con, nbcon_state), new->atom);
+}
+
+/**
+ * nbcon_state_read - Helper function to read the console state
+ * @con: Console to read
+ * @state: The state to store the result
+ */
+static inline void nbcon_state_read(struct console *con, struct nbcon_state *state)
+{
+ state->atom = atomic_read(&ACCESS_PRIVATE(con, nbcon_state));
+}
+
+/**
+ * nbcon_state_try_cmpxchg() - Helper function for atomic_try_cmpxchg() on console state
+ * @con: Console to update
+ * @cur: Old/expected state
+ * @new: New state
+ *
+ * Return: True on success. False on fail and @cur is updated.
+ */
+static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_state *cur,
+ struct nbcon_state *new)
+{
+ return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom);
+}
+
+#ifdef CONFIG_64BIT
+
+#define __seq_to_nbcon_seq(seq) (seq)
+#define __nbcon_seq_to_seq(seq) (seq)
+
+#else /* CONFIG_64BIT */
+
+#define __seq_to_nbcon_seq(seq) ((u32)seq)
+
+static inline u64 __nbcon_seq_to_seq(u32 nbcon_seq)
+{
+ u64 seq;
+ u64 rb_next_seq;
+
+ /*
+ * The provided sequence is only the lower 32 bits of the ringbuffer
+ * sequence. It needs to be expanded to 64bit. Get the next sequence
+ * number from the ringbuffer and fold it.
+ *
+ * Having a 32bit representation in the console is sufficient.
+ * If a console ever gets more than 2^31 records behind
+ * the ringbuffer then this is the least of the problems.
+ *
+ * Also the access to the ring buffer is always safe.
+ */
+ rb_next_seq = prb_next_seq(prb);
+ seq = rb_next_seq - ((u32)rb_next_seq - nbcon_seq);
+
+ return seq;
+}
+
+#endif /* CONFIG_64BIT */
+
+/**
+ * nbcon_seq_read - Read the current console sequence
+ * @con: Console to read the sequence of
+ *
+ * Return: Sequence number of the next record to print on @con.
+ */
+u64 nbcon_seq_read(struct console *con)
+{
+ unsigned long nbcon_seq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_seq));
+
+ return __nbcon_seq_to_seq(nbcon_seq);
+}
+
+/**
+ * nbcon_seq_force - Force console sequence to a specific value
+ * @con: Console to work on
+ * @seq: Sequence number value to set
+ *
+ * Only to be used during init (before registration) or in extreme situations
+ * (such as panic with CONSOLE_REPLAY_ALL).
+ */
+void nbcon_seq_force(struct console *con, u64 seq)
+{
+ /*
+ * If the specified record no longer exists, the oldest available record
+ * is chosen. This is especially important on 32bit systems because only
+ * the lower 32 bits of the sequence number are stored. The upper 32 bits
+ * are derived from the sequence numbers available in the ringbuffer.
+ */
+ u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb));
+
+ atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __seq_to_nbcon_seq(valid_seq));
+
+ /* Clear con->seq since nbcon consoles use con->nbcon_seq instead. */
+ con->seq = 0;
+}
+
+/**
+ * nbcon_seq_try_update - Try to update the console sequence number
+ * @ctxt: Pointer to an acquire context that contains
+ * all information about the acquire mode
+ * @new_seq: The new sequence number to set
+ *
+ * @ctxt->seq is updated to the new value of @con::nbcon_seq (expanded to
+ * the 64bit value). This could be a different value than @new_seq if
+ * nbcon_seq_force() was used or the current context no longer owns the
+ * console. In the later case, it will stop printing anyway.
+ */
+static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq)
+{
+ unsigned long nbcon_seq = __seq_to_nbcon_seq(ctxt->seq);
+ struct console *con = ctxt->console;
+
+ if (atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_seq), &nbcon_seq,
+ __seq_to_nbcon_seq(new_seq))) {
+ ctxt->seq = new_seq;
+ } else {
+ ctxt->seq = nbcon_seq_read(con);
+ }
+}
+
+/**
+ * nbcon_context_try_acquire_direct - Try to acquire directly
+ * @ctxt: The context of the caller
+ * @cur: The current console state
+ *
+ * Acquire the console when it is released. Also acquire the console when
+ * the current owner has a lower priority and the console is in a safe state.
+ *
+ * Return: 0 on success. Otherwise, an error code on failure. Also @cur
+ * is updated to the latest state when failed to modify it.
+ *
+ * Errors:
+ *
+ * -EPERM: A panic is in progress and this is not the panic CPU.
+ * Or the current owner or waiter has the same or higher
+ * priority. No acquire method can be successful in
+ * this case.
+ *
+ * -EBUSY: The current owner has a lower priority but the console
+ * in an unsafe state. The caller should try using
+ * the handover acquire method.
+ */
+static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt,
+ struct nbcon_state *cur)
+{
+ unsigned int cpu = smp_processor_id();
+ struct console *con = ctxt->console;
+ struct nbcon_state new;
+
+ do {
+ if (other_cpu_in_panic())
+ return -EPERM;
+
+ if (ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio)
+ return -EPERM;
+
+ if (cur->unsafe)
+ return -EBUSY;
+
+ /*
+ * The console should never be safe for a direct acquire
+ * if an unsafe hostile takeover has ever happened.
+ */
+ WARN_ON_ONCE(cur->unsafe_takeover);
+
+ new.atom = cur->atom;
+ new.prio = ctxt->prio;
+ new.req_prio = NBCON_PRIO_NONE;
+ new.unsafe = cur->unsafe_takeover;
+ new.cpu = cpu;
+
+ } while (!nbcon_state_try_cmpxchg(con, cur, &new));
+
+ return 0;
+}
+
+static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio)
+{
+ /*
+ * The request context is well defined by the @req_prio because:
+ *
+ * - Only a context with a higher priority can take over the request.
+ * - There are only three priorities.
+ * - Only one CPU is allowed to request PANIC priority.
+ * - Lower priorities are ignored during panic() until reboot.
+ *
+ * As a result, the following scenario is *not* possible:
+ *
+ * 1. Another context with a higher priority directly takes ownership.
+ * 2. The higher priority context releases the ownership.
+ * 3. A lower priority context takes the ownership.
+ * 4. Another context with the same priority as this context
+ * creates a request and starts waiting.
+ */
+
+ return (cur->req_prio == expected_prio);
+}
+
+/**
+ * nbcon_context_try_acquire_requested - Try to acquire after having
+ * requested a handover
+ * @ctxt: The context of the caller
+ * @cur: The current console state
+ *
+ * This is a helper function for nbcon_context_try_acquire_handover().
+ * It is called when the console is in an unsafe state. The current
+ * owner will release the console on exit from the unsafe region.
+ *
+ * Return: 0 on success and @cur is updated to the new console state.
+ * Otherwise an error code on failure.
+ *
+ * Errors:
+ *
+ * -EPERM: A panic is in progress and this is not the panic CPU
+ * or this context is no longer the waiter.
+ *
+ * -EBUSY: The console is still locked. The caller should
+ * continue waiting.
+ *
+ * Note: The caller must still remove the request when an error has occurred
+ * except when this context is no longer the waiter.
+ */
+static int nbcon_context_try_acquire_requested(struct nbcon_context *ctxt,
+ struct nbcon_state *cur)
+{
+ unsigned int cpu = smp_processor_id();
+ struct console *con = ctxt->console;
+ struct nbcon_state new;
+
+ /* Note that the caller must still remove the request! */
+ if (other_cpu_in_panic())
+ return -EPERM;
+
+ /*
+ * Note that the waiter will also change if there was an unsafe
+ * hostile takeover.
+ */
+ if (!nbcon_waiter_matches(cur, ctxt->prio))
+ return -EPERM;
+
+ /* If still locked, caller should continue waiting. */
+ if (cur->prio != NBCON_PRIO_NONE)
+ return -EBUSY;
+
+ /*
+ * The previous owner should have never released ownership
+ * in an unsafe region.
+ */
+ WARN_ON_ONCE(cur->unsafe);
+
+ new.atom = cur->atom;
+ new.prio = ctxt->prio;
+ new.req_prio = NBCON_PRIO_NONE;
+ new.unsafe = cur->unsafe_takeover;
+ new.cpu = cpu;
+
+ if (!nbcon_state_try_cmpxchg(con, cur, &new)) {
+ /*
+ * The acquire could fail only when it has been taken
+ * over by a higher priority context.
+ */
+ WARN_ON_ONCE(nbcon_waiter_matches(cur, ctxt->prio));
+ return -EPERM;
+ }
+
+ /* Handover success. This context now owns the console. */
+ return 0;
+}
+
+/**
+ * nbcon_context_try_acquire_handover - Try to acquire via handover
+ * @ctxt: The context of the caller
+ * @cur: The current console state
+ *
+ * The function must be called only when the context has higher priority
+ * than the current owner and the console is in an unsafe state.
+ * It is the case when nbcon_context_try_acquire_direct() returns -EBUSY.
+ *
+ * The function sets "req_prio" field to make the current owner aware of
+ * the request. Then it waits until the current owner releases the console,
+ * or an even higher context takes over the request, or timeout expires.
+ *
+ * The current owner checks the "req_prio" field on exit from the unsafe
+ * region and releases the console. It does not touch the "req_prio" field
+ * so that the console stays reserved for the waiter.
+ *
+ * Return: 0 on success. Otherwise, an error code on failure. Also @cur
+ * is updated to the latest state when failed to modify it.
+ *
+ * Errors:
+ *
+ * -EPERM: A panic is in progress and this is not the panic CPU.
+ * Or a higher priority context has taken over the
+ * console or the handover request.
+ *
+ * -EBUSY: The current owner is on the same CPU so that the hand
+ * shake could not work. Or the current owner is not
+ * willing to wait (zero timeout). Or the console does
+ * not enter the safe state before timeout passed. The
+ * caller might still use the unsafe hostile takeover
+ * when allowed.
+ *
+ * -EAGAIN: @cur has changed when creating the handover request.
+ * The caller should retry with direct acquire.
+ */
+static int nbcon_context_try_acquire_handover(struct nbcon_context *ctxt,
+ struct nbcon_state *cur)
+{
+ unsigned int cpu = smp_processor_id();
+ struct console *con = ctxt->console;
+ struct nbcon_state new;
+ int timeout;
+ int request_err = -EBUSY;
+
+ /*
+ * Check that the handover is called when the direct acquire failed
+ * with -EBUSY.
+ */
+ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio);
+ WARN_ON_ONCE(!cur->unsafe);
+
+ /* Handover is not possible on the same CPU. */
+ if (cur->cpu == cpu)
+ return -EBUSY;
+
+ /*
+ * Console stays unsafe after an unsafe takeover until re-initialized.
+ * Waiting is not going to help in this case.
+ */
+ if (cur->unsafe_takeover)
+ return -EBUSY;
+
+ /* Is the caller willing to wait? */
+ if (ctxt->spinwait_max_us == 0)
+ return -EBUSY;
+
+ /*
+ * Setup a request for the handover. The caller should try to acquire
+ * the console directly when the current state has been modified.
+ */
+ new.atom = cur->atom;
+ new.req_prio = ctxt->prio;
+ if (!nbcon_state_try_cmpxchg(con, cur, &new))
+ return -EAGAIN;
+
+ cur->atom = new.atom;
+
+ /* Wait until there is no owner and then acquire the console. */
+ for (timeout = ctxt->spinwait_max_us; timeout >= 0; timeout--) {
+ /* On successful acquire, this request is cleared. */
+ request_err = nbcon_context_try_acquire_requested(ctxt, cur);
+ if (!request_err)
+ return 0;
+
+ /*
+ * If the acquire should be aborted, it must be ensured
+ * that the request is removed before returning to caller.
+ */
+ if (request_err == -EPERM)
+ break;
+
+ udelay(1);
+
+ /* Re-read the state because some time has passed. */
+ nbcon_state_read(con, cur);
+ }
+
+ /* Timed out or aborted. Carefully remove handover request. */
+ do {
+ /*
+ * No need to remove request if there is a new waiter. This
+ * can only happen if a higher priority context has taken over
+ * the console or the handover request.
+ */
+ if (!nbcon_waiter_matches(cur, ctxt->prio))
+ return -EPERM;
+
+ /* Unset request for handover. */
+ new.atom = cur->atom;
+ new.req_prio = NBCON_PRIO_NONE;
+ if (nbcon_state_try_cmpxchg(con, cur, &new)) {
+ /*
+ * Request successfully unset. Report failure of
+ * acquiring via handover.
+ */
+ cur->atom = new.atom;
+ return request_err;
+ }
+
+ /*
+ * Unable to remove request. Try to acquire in case
+ * the owner has released the lock.
+ */
+ } while (nbcon_context_try_acquire_requested(ctxt, cur));
+
+ /* Lucky timing. The acquire succeeded while removing the request. */
+ return 0;
+}
+
+/**
+ * nbcon_context_try_acquire_hostile - Acquire via unsafe hostile takeover
+ * @ctxt: The context of the caller
+ * @cur: The current console state
+ *
+ * Acquire the console even in the unsafe state.
+ *
+ * It can be permitted by setting the 'allow_unsafe_takeover' field only
+ * by the final attempt to flush messages in panic().
+ *
+ * Return: 0 on success. -EPERM when not allowed by the context.
+ */
+static int nbcon_context_try_acquire_hostile(struct nbcon_context *ctxt,
+ struct nbcon_state *cur)
+{
+ unsigned int cpu = smp_processor_id();
+ struct console *con = ctxt->console;
+ struct nbcon_state new;
+
+ if (!ctxt->allow_unsafe_takeover)
+ return -EPERM;
+
+ /* Ensure caller is allowed to perform unsafe hostile takeovers. */
+ if (WARN_ON_ONCE(ctxt->prio != NBCON_PRIO_PANIC))
+ return -EPERM;
+
+ /*
+ * Check that try_acquire_direct() and try_acquire_handover() returned
+ * -EBUSY in the right situation.
+ */
+ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio);
+ WARN_ON_ONCE(cur->unsafe != true);
+
+ do {
+ new.atom = cur->atom;
+ new.cpu = cpu;
+ new.prio = ctxt->prio;
+ new.unsafe |= cur->unsafe_takeover;
+ new.unsafe_takeover |= cur->unsafe;
+
+ } while (!nbcon_state_try_cmpxchg(con, cur, &new));
+
+ return 0;
+}
+
+static struct printk_buffers panic_nbcon_pbufs;
+
+/**
+ * nbcon_context_try_acquire - Try to acquire nbcon console
+ * @ctxt: The context of the caller
+ *
+ * Return: True if the console was acquired. False otherwise.
+ *
+ * If the caller allowed an unsafe hostile takeover, on success the
+ * caller should check the current console state to see if it is
+ * in an unsafe state. Otherwise, on success the caller may assume
+ * the console is not in an unsafe state.
+ */
+__maybe_unused
+static bool nbcon_context_try_acquire(struct nbcon_context *ctxt)
+{
+ unsigned int cpu = smp_processor_id();
+ struct console *con = ctxt->console;
+ struct nbcon_state cur;
+ int err;
+
+ nbcon_state_read(con, &cur);
+try_again:
+ err = nbcon_context_try_acquire_direct(ctxt, &cur);
+ if (err != -EBUSY)
+ goto out;
+
+ err = nbcon_context_try_acquire_handover(ctxt, &cur);
+ if (err == -EAGAIN)
+ goto try_again;
+ if (err != -EBUSY)
+ goto out;
+
+ err = nbcon_context_try_acquire_hostile(ctxt, &cur);
+out:
+ if (err)
+ return false;
+
+ /* Acquire succeeded. */
+
+ /* Assign the appropriate buffer for this context. */
+ if (atomic_read(&panic_cpu) == cpu)
+ ctxt->pbufs = &panic_nbcon_pbufs;
+ else
+ ctxt->pbufs = con->pbufs;
+
+ /* Set the record sequence for this context to print. */
+ ctxt->seq = nbcon_seq_read(ctxt->console);
+
+ return true;
+}
+
+static bool nbcon_owner_matches(struct nbcon_state *cur, int expected_cpu,
+ int expected_prio)
+{
+ /*
+ * Since consoles can only be acquired by higher priorities,
+ * owning contexts are uniquely identified by @prio. However,
+ * since contexts can unexpectedly lose ownership, it is
+ * possible that later another owner appears with the same
+ * priority. For this reason @cpu is also needed.
+ */
+
+ if (cur->prio != expected_prio)
+ return false;
+
+ if (cur->cpu != expected_cpu)
+ return false;
+
+ return true;
+}
+
+/**
+ * nbcon_context_release - Release the console
+ * @ctxt: The nbcon context from nbcon_context_try_acquire()
+ */
+static void nbcon_context_release(struct nbcon_context *ctxt)
+{
+ unsigned int cpu = smp_processor_id();
+ struct console *con = ctxt->console;
+ struct nbcon_state cur;
+ struct nbcon_state new;
+
+ nbcon_state_read(con, &cur);
+
+ do {
+ if (!nbcon_owner_matches(&cur, cpu, ctxt->prio))
+ break;
+
+ new.atom = cur.atom;
+ new.prio = NBCON_PRIO_NONE;
+
+ /*
+ * If @unsafe_takeover is set, it is kept set so that
+ * the state remains permanently unsafe.
+ */
+ new.unsafe |= cur.unsafe_takeover;
+
+ } while (!nbcon_state_try_cmpxchg(con, &cur, &new));
+
+ ctxt->pbufs = NULL;
+}
+
+/**
+ * nbcon_context_can_proceed - Check whether ownership can proceed
+ * @ctxt: The nbcon context from nbcon_context_try_acquire()
+ * @cur: The current console state
+ *
+ * Return: True if this context still owns the console. False if
+ * ownership was handed over or taken.
+ *
+ * Must be invoked when entering the unsafe state to make sure that it still
+ * owns the lock. Also must be invoked when exiting the unsafe context
+ * to eventually free the lock for a higher priority context which asked
+ * for the friendly handover.
+ *
+ * It can be called inside an unsafe section when the console is just
+ * temporary in safe state instead of exiting and entering the unsafe
+ * state.
+ *
+ * Also it can be called in the safe context before doing an expensive
+ * safe operation. It does not make sense to do the operation when
+ * a higher priority context took the lock.
+ *
+ * When this function returns false then the calling context no longer owns
+ * the console and is no longer allowed to go forward. In this case it must
+ * back out immediately and carefully. The buffer content is also no longer
+ * trusted since it no longer belongs to the calling context.
+ */
+static bool nbcon_context_can_proceed(struct nbcon_context *ctxt, struct nbcon_state *cur)
+{
+ unsigned int cpu = smp_processor_id();
+
+ /* Make sure this context still owns the console. */
+ if (!nbcon_owner_matches(cur, cpu, ctxt->prio))
+ return false;
+
+ /* The console owner can proceed if there is no waiter. */
+ if (cur->req_prio == NBCON_PRIO_NONE)
+ return true;
+
+ /*
+ * A console owner within an unsafe region is always allowed to
+ * proceed, even if there are waiters. It can perform a handover
+ * when exiting the unsafe region. Otherwise the waiter will
+ * need to perform an unsafe hostile takeover.
+ */
+ if (cur->unsafe)
+ return true;
+
+ /* Waiters always have higher priorities than owners. */
+ WARN_ON_ONCE(cur->req_prio <= cur->prio);
+
+ /*
+ * Having a safe point for take over and eventually a few
+ * duplicated characters or a full line is way better than a
+ * hostile takeover. Post processing can take care of the garbage.
+ * Release and hand over.
+ */
+ nbcon_context_release(ctxt);
+
+ /*
+ * It is not clear whether the waiter really took over ownership. The
+ * outermost callsite must make the final decision whether console
+ * ownership is needed for it to proceed. If yes, it must reacquire
+ * ownership (possibly hostile) before carefully proceeding.
+ *
+ * The calling context no longer owns the console so go back all the
+ * way instead of trying to implement reacquire heuristics in tons of
+ * places.
+ */
+ return false;
+}
+
+/**
+ * nbcon_can_proceed - Check whether ownership can proceed
+ * @wctxt: The write context that was handed to the write function
+ *
+ * Return: True if this context still owns the console. False if
+ * ownership was handed over or taken.
+ *
+ * It is used in nbcon_enter_unsafe() to make sure that it still owns the
+ * lock. Also it is used in nbcon_exit_unsafe() to eventually free the lock
+ * for a higher priority context which asked for the friendly handover.
+ *
+ * It can be called inside an unsafe section when the console is just
+ * temporary in safe state instead of exiting and entering the unsafe state.
+ *
+ * Also it can be called in the safe context before doing an expensive safe
+ * operation. It does not make sense to do the operation when a higher
+ * priority context took the lock.
+ *
+ * When this function returns false then the calling context no longer owns
+ * the console and is no longer allowed to go forward. In this case it must
+ * back out immediately and carefully. The buffer content is also no longer
+ * trusted since it no longer belongs to the calling context.
+ */
+bool nbcon_can_proceed(struct nbcon_write_context *wctxt)
+{
+ struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
+ struct console *con = ctxt->console;
+ struct nbcon_state cur;
+
+ nbcon_state_read(con, &cur);
+
+ return nbcon_context_can_proceed(ctxt, &cur);
+}
+EXPORT_SYMBOL_GPL(nbcon_can_proceed);
+
+#define nbcon_context_enter_unsafe(c) __nbcon_context_update_unsafe(c, true)
+#define nbcon_context_exit_unsafe(c) __nbcon_context_update_unsafe(c, false)
+
+/**
+ * __nbcon_context_update_unsafe - Update the unsafe bit in @con->nbcon_state
+ * @ctxt: The nbcon context from nbcon_context_try_acquire()
+ * @unsafe: The new value for the unsafe bit
+ *
+ * Return: True if the unsafe state was updated and this context still
+ * owns the console. Otherwise false if ownership was handed
+ * over or taken.
+ *
+ * This function allows console owners to modify the unsafe status of the
+ * console.
+ *
+ * When this function returns false then the calling context no longer owns
+ * the console and is no longer allowed to go forward. In this case it must
+ * back out immediately and carefully. The buffer content is also no longer
+ * trusted since it no longer belongs to the calling context.
+ *
+ * Internal helper to avoid duplicated code.
+ */
+static bool __nbcon_context_update_unsafe(struct nbcon_context *ctxt, bool unsafe)
+{
+ struct console *con = ctxt->console;
+ struct nbcon_state cur;
+ struct nbcon_state new;
+
+ nbcon_state_read(con, &cur);
+
+ do {
+ /*
+ * The unsafe bit must not be cleared if an
+ * unsafe hostile takeover has occurred.
+ */
+ if (!unsafe && cur.unsafe_takeover)
+ goto out;
+
+ if (!nbcon_context_can_proceed(ctxt, &cur))
+ return false;
+
+ new.atom = cur.atom;
+ new.unsafe = unsafe;
+ } while (!nbcon_state_try_cmpxchg(con, &cur, &new));
+
+ cur.atom = new.atom;
+out:
+ return nbcon_context_can_proceed(ctxt, &cur);
+}
+
+/**
+ * nbcon_enter_unsafe - Enter an unsafe region in the driver
+ * @wctxt: The write context that was handed to the write function
+ *
+ * Return: True if this context still owns the console. False if
+ * ownership was handed over or taken.
+ *
+ * When this function returns false then the calling context no longer owns
+ * the console and is no longer allowed to go forward. In this case it must
+ * back out immediately and carefully. The buffer content is also no longer
+ * trusted since it no longer belongs to the calling context.
+ */
+bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt)
+{
+ struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
+
+ return nbcon_context_enter_unsafe(ctxt);
+}
+EXPORT_SYMBOL_GPL(nbcon_enter_unsafe);
+
+/**
+ * nbcon_exit_unsafe - Exit an unsafe region in the driver
+ * @wctxt: The write context that was handed to the write function
+ *
+ * Return: True if this context still owns the console. False if
+ * ownership was handed over or taken.
+ *
+ * When this function returns false then the calling context no longer owns
+ * the console and is no longer allowed to go forward. In this case it must
+ * back out immediately and carefully. The buffer content is also no longer
+ * trusted since it no longer belongs to the calling context.
+ */
+bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt)
+{
+ struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
+
+ return nbcon_context_exit_unsafe(ctxt);
+}
+EXPORT_SYMBOL_GPL(nbcon_exit_unsafe);
+
+/**
+ * nbcon_emit_next_record - Emit a record in the acquired context
+ * @wctxt: The write context that will be handed to the write function
+ *
+ * Return: True if this context still owns the console. False if
+ * ownership was handed over or taken.
+ *
+ * When this function returns false then the calling context no longer owns
+ * the console and is no longer allowed to go forward. In this case it must
+ * back out immediately and carefully. The buffer content is also no longer
+ * trusted since it no longer belongs to the calling context. If the caller
+ * wants to do more it must reacquire the console first.
+ *
+ * When true is returned, @wctxt->ctxt.backlog indicates whether there are
+ * still records pending in the ringbuffer,
+ */
+__maybe_unused
+static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt)
+{
+ struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
+ struct console *con = ctxt->console;
+ bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED;
+ struct printk_message pmsg = {
+ .pbufs = ctxt->pbufs,
+ };
+ unsigned long con_dropped;
+ struct nbcon_state cur;
+ unsigned long dropped;
+ bool done;
+
+ /*
+ * The printk buffers are filled within an unsafe section. This
+ * prevents NBCON_PRIO_NORMAL and NBCON_PRIO_EMERGENCY from
+ * clobbering each other.
+ */
+
+ if (!nbcon_context_enter_unsafe(ctxt))
+ return false;
+
+ ctxt->backlog = printk_get_next_message(&pmsg, ctxt->seq, is_extended, true);
+ if (!ctxt->backlog)
+ return nbcon_context_exit_unsafe(ctxt);
+
+ /*
+ * @con->dropped is not protected in case of an unsafe hostile
+ * takeover. In that situation the update can be racy so
+ * annotate it accordingly.
+ */
+ con_dropped = data_race(READ_ONCE(con->dropped));
+
+ dropped = con_dropped + pmsg.dropped;
+ if (dropped && !is_extended)
+ console_prepend_dropped(&pmsg, dropped);
+
+ if (!nbcon_context_exit_unsafe(ctxt))
+ return false;
+
+ /* For skipped records just update seq/dropped in @con. */
+ if (pmsg.outbuf_len == 0)
+ goto update_con;
+
+ /* Initialize the write context for driver callbacks. */
+ wctxt->outbuf = &pmsg.pbufs->outbuf[0];
+ wctxt->len = pmsg.outbuf_len;
+ nbcon_state_read(con, &cur);
+ wctxt->unsafe_takeover = cur.unsafe_takeover;
+
+ if (con->write_atomic) {
+ done = con->write_atomic(con, wctxt);
+ } else {
+ nbcon_context_release(ctxt);
+ WARN_ON_ONCE(1);
+ done = false;
+ }
+
+ /* If not done, the emit was aborted. */
+ if (!done)
+ return false;
+
+ /*
+ * Since any dropped message was successfully output, reset the
+ * dropped count for the console.
+ */
+ dropped = 0;
+update_con:
+ /*
+ * The dropped count and the sequence number are updated within an
+ * unsafe section. This limits update races to the panic context and
+ * allows the panic context to win.
+ */
+
+ if (!nbcon_context_enter_unsafe(ctxt))
+ return false;
+
+ if (dropped != con_dropped) {
+ /* Counterpart to the READ_ONCE() above. */
+ WRITE_ONCE(con->dropped, dropped);
+ }
+
+ nbcon_seq_try_update(ctxt, pmsg.seq + 1);
+
+ return nbcon_context_exit_unsafe(ctxt);
+}
+
+/**
+ * nbcon_alloc - Allocate buffers needed by the nbcon console
+ * @con: Console to allocate buffers for
+ *
+ * Return: True on success. False otherwise and the console cannot
+ * be used.
+ *
+ * This is not part of nbcon_init() because buffer allocation must
+ * be performed earlier in the console registration process.
+ */
+bool nbcon_alloc(struct console *con)
+{
+ if (con->flags & CON_BOOT) {
+ /*
+ * Boot console printing is synchronized with legacy console
+ * printing, so boot consoles can share the same global printk
+ * buffers.
+ */
+ con->pbufs = &printk_shared_pbufs;
+ } else {
+ con->pbufs = kmalloc(sizeof(*con->pbufs), GFP_KERNEL);
+ if (!con->pbufs) {
+ con_printk(KERN_ERR, con, "failed to allocate printing buffer\n");
+ return false;
+ }
+ }
+
+ return true;
+}
+
+/**
+ * nbcon_init - Initialize the nbcon console specific data
+ * @con: Console to initialize
+ *
+ * nbcon_alloc() *must* be called and succeed before this function
+ * is called.
+ *
+ * This function expects that the legacy @con->seq has been set.
+ */
+void nbcon_init(struct console *con)
+{
+ struct nbcon_state state = { };
+
+ /* nbcon_alloc() must have been called and successful! */
+ BUG_ON(!con->pbufs);
+
+ nbcon_seq_force(con, con->seq);
+ nbcon_state_set(con, &state);
+}
+
+/**
+ * nbcon_free - Free and cleanup the nbcon console specific data
+ * @con: Console to free/cleanup nbcon data
+ */
+void nbcon_free(struct console *con)
+{
+ struct nbcon_state state = { };
+
+ nbcon_state_set(con, &state);
+
+ /* Boot consoles share global printk buffers. */
+ if (!(con->flags & CON_BOOT))
+ kfree(con->pbufs);
+
+ con->pbufs = NULL;
+}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 357a4d18f638..f2444b581e16 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -88,7 +88,7 @@ EXPORT_SYMBOL(oops_in_progress);
static DEFINE_MUTEX(console_mutex);
/*
- * console_sem protects updates to console->seq and console_suspended,
+ * console_sem protects updates to console->seq
* and also provides serialization for console printing.
*/
static DEFINE_SEMAPHORE(console_sem, 1);
@@ -102,12 +102,6 @@ DEFINE_STATIC_SRCU(console_srcu);
*/
int __read_mostly suppress_printk;
-/*
- * During panic, heavy printk by other CPUs can delay the
- * panic and risk deadlock on console resources.
- */
-static int __read_mostly suppress_panic_printk;
-
#ifdef CONFIG_LOCKDEP
static struct lockdep_map console_lock_dep_map = {
.name = "console_lock"
@@ -361,7 +355,7 @@ static bool panic_in_progress(void)
* paths in the console code where we end up in places I want
* locked without the console semaphore held).
*/
-static int console_locked, console_suspended;
+static int console_locked;
/*
* Array of consoles built from command line options (console=)
@@ -445,6 +439,12 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
static DEFINE_MUTEX(syslog_lock);
#ifdef CONFIG_PRINTK
+/*
+ * During panic, heavy printk by other CPUs can delay the
+ * panic and risk deadlock on console resources.
+ */
+static int __read_mostly suppress_panic_printk;
+
DECLARE_WAIT_QUEUE_HEAD(log_wait);
/* All 3 protected by @syslog_lock. */
/* the next printk record to read by syslog(READ) or /proc/kmsg */
@@ -494,7 +494,7 @@ _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS,
static struct printk_ringbuffer printk_rb_dynamic;
-static struct printk_ringbuffer *prb = &printk_rb_static;
+struct printk_ringbuffer *prb = &printk_rb_static;
/*
* We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
@@ -698,9 +698,6 @@ out:
return len;
}
-static bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
- bool is_extended, bool may_supress);
-
/* /dev/kmsg - userspace message inject/listen interface */
struct devkmsg_user {
atomic64_t seq;
@@ -1669,7 +1666,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX);
- len = 0;
prb_for_each_record(seq, prb, seq, &r) {
int textlen;
@@ -2308,7 +2304,11 @@ asmlinkage int vprintk_emit(int facility, int level,
preempt_enable();
}
- wake_up_klogd();
+ if (in_sched)
+ defer_console_output();
+ else
+ wake_up_klogd();
+
return printed_len;
}
EXPORT_SYMBOL(vprintk_emit);
@@ -2345,22 +2345,6 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
static u64 syslog_seq;
-static size_t record_print_text(const struct printk_record *r,
- bool syslog, bool time)
-{
- return 0;
-}
-static ssize_t info_print_ext_header(char *buf, size_t size,
- struct printk_info *info)
-{
- return 0;
-}
-static ssize_t msg_print_ext_body(char *buf, size_t size,
- char *text, size_t text_len,
- struct dev_printk_info *dev_info) { return 0; }
-static void console_lock_spinning_enable(void) { }
-static int console_lock_spinning_disable_and_check(int cookie) { return 0; }
-static bool suppress_message_printing(int level) { return false; }
static bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; }
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }
@@ -2400,13 +2384,21 @@ static void set_user_specified(struct console_cmdline *c, bool user_specified)
console_set_on_cmdline = 1;
}
-static int __add_preferred_console(char *name, int idx, char *options,
+static int __add_preferred_console(const char *name, const short idx, char *options,
char *brl_options, bool user_specified)
{
struct console_cmdline *c;
int i;
/*
+ * We use a signed short index for struct console for device drivers to
+ * indicate a not yet assigned index or port. However, a negative index
+ * value is not valid for preferred console.
+ */
+ if (idx < 0)
+ return -EINVAL;
+
+ /*
* See if this tty is not yet registered, and
* if we have a slot free.
*/
@@ -2509,7 +2501,7 @@ __setup("console=", console_setup);
* commonly to provide a default console (ie from PROM variables) when
* the user has not supplied one.
*/
-int add_preferred_console(char *name, int idx, char *options)
+int add_preferred_console(const char *name, const short idx, char *options)
{
return __add_preferred_console(name, idx, options, NULL, false);
}
@@ -2547,22 +2539,46 @@ MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to hig
*/
void suspend_console(void)
{
+ struct console *con;
+
if (!console_suspend_enabled)
return;
pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
pr_flush(1000, true);
- console_lock();
- console_suspended = 1;
- up_console_sem();
+
+ console_list_lock();
+ for_each_console(con)
+ console_srcu_write_flags(con, con->flags | CON_SUSPENDED);
+ console_list_unlock();
+
+ /*
+ * Ensure that all SRCU list walks have completed. All printing
+ * contexts must be able to see that they are suspended so that it
+ * is guaranteed that all printing has stopped when this function
+ * completes.
+ */
+ synchronize_srcu(&console_srcu);
}
void resume_console(void)
{
+ struct console *con;
+
if (!console_suspend_enabled)
return;
- down_console_sem();
- console_suspended = 0;
- console_unlock();
+
+ console_list_lock();
+ for_each_console(con)
+ console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED);
+ console_list_unlock();
+
+ /*
+ * Ensure that all SRCU list walks have completed. All printing
+ * contexts must be able to see they are no longer suspended so
+ * that they are guaranteed to wake up and resume printing.
+ */
+ synchronize_srcu(&console_srcu);
+
pr_flush(1000, true);
}
@@ -2585,6 +2601,26 @@ static int console_cpu_notify(unsigned int cpu)
return 0;
}
+/*
+ * Return true if a panic is in progress on a remote CPU.
+ *
+ * On true, the local CPU should immediately release any printing resources
+ * that may be needed by the panic CPU.
+ */
+bool other_cpu_in_panic(void)
+{
+ if (!panic_in_progress())
+ return false;
+
+ /*
+ * We can use raw_smp_processor_id() here because it is impossible for
+ * the task to be migrated to the panic_cpu, or away from it. If
+ * panic_cpu has already been set, and we're not currently executing on
+ * that CPU, then we never will be.
+ */
+ return atomic_read(&panic_cpu) != raw_smp_processor_id();
+}
+
/**
* console_lock - block the console subsystem from printing
*
@@ -2597,9 +2633,11 @@ void console_lock(void)
{
might_sleep();
+ /* On panic, the console_lock must be left to the panic cpu. */
+ while (other_cpu_in_panic())
+ msleep(1000);
+
down_console_sem();
- if (console_suspended)
- return;
console_locked = 1;
console_may_schedule = 1;
}
@@ -2615,12 +2653,11 @@ EXPORT_SYMBOL(console_lock);
*/
int console_trylock(void)
{
- if (down_trylock_console_sem())
+ /* On panic, the console_lock must be left to the panic cpu. */
+ if (other_cpu_in_panic())
return 0;
- if (console_suspended) {
- up_console_sem();
+ if (down_trylock_console_sem())
return 0;
- }
console_locked = 1;
console_may_schedule = 0;
return 1;
@@ -2634,25 +2671,6 @@ int is_console_locked(void)
EXPORT_SYMBOL(is_console_locked);
/*
- * Return true when this CPU should unlock console_sem without pushing all
- * messages to the console. This reduces the chance that the console is
- * locked when the panic CPU tries to use it.
- */
-static bool abandon_console_lock_in_panic(void)
-{
- if (!panic_in_progress())
- return false;
-
- /*
- * We can use raw_smp_processor_id() here because it is impossible for
- * the task to be migrated to the panic_cpu, or away from it. If
- * panic_cpu has already been set, and we're not currently executing on
- * that CPU, then we never will be.
- */
- return atomic_read(&panic_cpu) != raw_smp_processor_id();
-}
-
-/*
* Check if the given console is currently capable and allowed to print
* records.
*
@@ -2665,6 +2683,9 @@ static inline bool console_is_usable(struct console *con)
if (!(flags & CON_ENABLED))
return false;
+ if ((flags & CON_SUSPENDED))
+ return false;
+
if (!con->write)
return false;
@@ -2685,6 +2706,8 @@ static void __console_unlock(void)
up_console_sem();
}
+#ifdef CONFIG_PRINTK
+
/*
* Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". This
* is achieved by shifting the existing message over and inserting the dropped
@@ -2699,8 +2722,7 @@ static void __console_unlock(void)
*
* If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated.
*/
-#ifdef CONFIG_PRINTK
-static void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped)
+void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped)
{
struct printk_buffers *pbufs = pmsg->pbufs;
const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf);
@@ -2731,9 +2753,6 @@ static void console_prepend_dropped(struct printk_message *pmsg, unsigned long d
memcpy(outbuf, scratchbuf, len);
pmsg->outbuf_len += len;
}
-#else
-#define console_prepend_dropped(pmsg, dropped)
-#endif /* CONFIG_PRINTK */
/*
* Read and format the specified record (or a later record if the specified
@@ -2754,8 +2773,8 @@ static void console_prepend_dropped(struct printk_message *pmsg, unsigned long d
* of @pmsg are valid. (See the documentation of struct printk_message
* for information about the @pmsg fields.)
*/
-static bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
- bool is_extended, bool may_suppress)
+bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
+ bool is_extended, bool may_suppress)
{
static int panic_console_dropped;
@@ -2814,6 +2833,13 @@ out:
}
/*
+ * Used as the printk buffers for non-panic, serialized console printing.
+ * This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles.
+ * Its usage requires the console_lock held.
+ */
+struct printk_buffers printk_shared_pbufs;
+
+/*
* Print one record for the given console. The record printed is whatever
* record is the next available record for the given console.
*
@@ -2830,12 +2856,10 @@ out:
*/
static bool console_emit_next_record(struct console *con, bool *handover, int cookie)
{
- static struct printk_buffers pbufs;
-
bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED;
- char *outbuf = &pbufs.outbuf[0];
+ char *outbuf = &printk_shared_pbufs.outbuf[0];
struct printk_message pmsg = {
- .pbufs = &pbufs,
+ .pbufs = &printk_shared_pbufs,
};
unsigned long flags;
@@ -2886,6 +2910,16 @@ skip:
return true;
}
+#else
+
+static bool console_emit_next_record(struct console *con, bool *handover, int cookie)
+{
+ *handover = false;
+ return false;
+}
+
+#endif /* CONFIG_PRINTK */
+
/*
* Print out all remaining records to all consoles.
*
@@ -2948,7 +2982,7 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove
any_progress = true;
/* Allow panic_cpu to take over the consoles safely. */
- if (abandon_console_lock_in_panic())
+ if (other_cpu_in_panic())
goto abandon;
if (do_cond_resched)
@@ -2983,11 +3017,6 @@ void console_unlock(void)
bool flushed;
u64 next_seq;
- if (console_suspended) {
- up_console_sem();
- return;
- }
-
/*
* Console drivers are called with interrupts disabled, so
* @console_may_schedule should be cleared before; however, we may
@@ -3045,10 +3074,28 @@ EXPORT_SYMBOL(console_conditional_schedule);
void console_unblank(void)
{
+ bool found_unblank = false;
struct console *c;
int cookie;
/*
+ * First check if there are any consoles implementing the unblank()
+ * callback. If not, there is no reason to continue and take the
+ * console lock, which in particular can be dangerous if
+ * @oops_in_progress is set.
+ */
+ cookie = console_srcu_read_lock();
+ for_each_console_srcu(c) {
+ if ((console_srcu_read_flags(c) & CON_ENABLED) && c->unblank) {
+ found_unblank = true;
+ break;
+ }
+ }
+ console_srcu_read_unlock(cookie);
+ if (!found_unblank)
+ return;
+
+ /*
* Stop console printing because the unblank() callback may
* assume the console is not within its write() callback.
*
@@ -3056,6 +3103,16 @@ void console_unblank(void)
* In that case, attempt a trylock as best-effort.
*/
if (oops_in_progress) {
+ /* Semaphores are not NMI-safe. */
+ if (in_nmi())
+ return;
+
+ /*
+ * Attempting to trylock the console lock can deadlock
+ * if another CPU was stopped while modifying the
+ * semaphore. "Hope and pray" that this is not the
+ * current situation.
+ */
if (down_trylock_console_sem() != 0)
return;
} else
@@ -3085,18 +3142,29 @@ void console_unblank(void)
*/
void console_flush_on_panic(enum con_flush_mode mode)
{
+ bool handover;
+ u64 next_seq;
+
+ /*
+ * Ignore the console lock and flush out the messages. Attempting a
+ * trylock would not be useful because:
+ *
+ * - if it is contended, it must be ignored anyway
+ * - console_lock() and console_trylock() block and fail
+ * respectively in panic for non-panic CPUs
+ * - semaphores are not NMI-safe
+ */
+
/*
- * If someone else is holding the console lock, trylock will fail
- * and may_schedule may be set. Ignore and proceed to unlock so
- * that messages are flushed out. As this can be called from any
- * context and we don't want to get preempted while flushing,
- * ensure may_schedule is cleared.
+ * If another context is holding the console lock,
+ * @console_may_schedule might be set. Clear it so that
+ * this context does not call cond_resched() while flushing.
*/
- console_trylock();
console_may_schedule = 0;
if (mode == CONSOLE_REPLAY_ALL) {
struct console *c;
+ short flags;
int cookie;
u64 seq;
@@ -3104,16 +3172,22 @@ void console_flush_on_panic(enum con_flush_mode mode)
cookie = console_srcu_read_lock();
for_each_console_srcu(c) {
- /*
- * If the above console_trylock() failed, this is an
- * unsynchronized assignment. But in that case, the
- * kernel is in "hope and pray" mode anyway.
- */
- c->seq = seq;
+ flags = console_srcu_read_flags(c);
+
+ if (flags & CON_NBCON) {
+ nbcon_seq_force(c, seq);
+ } else {
+ /*
+ * This is an unsynchronized assignment. On
+ * panic legacy consoles are only best effort.
+ */
+ c->seq = seq;
+ }
}
console_srcu_read_unlock(cookie);
}
- console_unlock();
+
+ console_flush_all(false, &next_seq, &handover);
}
/*
@@ -3260,11 +3334,6 @@ static void try_enable_default_console(struct console *newcon)
newcon->flags |= CON_CONSDEV;
}
-#define con_printk(lvl, con, fmt, ...) \
- printk(lvl pr_fmt("%sconsole [%s%d] " fmt), \
- (con->flags & CON_BOOT) ? "boot" : "", \
- con->name, con->index, ##__VA_ARGS__)
-
static void console_init_seq(struct console *newcon, bool bootcon_registered)
{
struct console *con;
@@ -3378,6 +3447,15 @@ void register_console(struct console *newcon)
goto unlock;
}
+ if (newcon->flags & CON_NBCON) {
+ /*
+ * Ensure the nbcon console buffers can be allocated
+ * before modifying any global data.
+ */
+ if (!nbcon_alloc(newcon))
+ goto unlock;
+ }
+
/*
* See if we want to enable this console driver by default.
*
@@ -3405,8 +3483,11 @@ void register_console(struct console *newcon)
err = try_enable_preferred_console(newcon, false);
/* printk() messages are not printed to the Braille console. */
- if (err || newcon->flags & CON_BRL)
+ if (err || newcon->flags & CON_BRL) {
+ if (newcon->flags & CON_NBCON)
+ nbcon_free(newcon);
goto unlock;
+ }
/*
* If we have a bootconsole, and are switching to a real console,
@@ -3422,6 +3503,9 @@ void register_console(struct console *newcon)
newcon->dropped = 0;
console_init_seq(newcon, bootcon_registered);
+ if (newcon->flags & CON_NBCON)
+ nbcon_init(newcon);
+
/*
* Put this console in the list - keep the
* preferred driver at the head of the list.
@@ -3513,6 +3597,9 @@ static int unregister_console_locked(struct console *console)
*/
synchronize_srcu(&console_srcu);
+ if (console->flags & CON_NBCON)
+ nbcon_free(console);
+
console_sysfs_notify();
if (console->exit)
@@ -3662,10 +3749,12 @@ late_initcall(printk_late_init);
/* If @con is specified, only wait for that console. Otherwise wait for all. */
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress)
{
- int remaining = timeout_ms;
+ unsigned long timeout_jiffies = msecs_to_jiffies(timeout_ms);
+ unsigned long remaining_jiffies = timeout_jiffies;
struct console *c;
u64 last_diff = 0;
u64 printk_seq;
+ short flags;
int cookie;
u64 diff;
u64 seq;
@@ -3674,13 +3763,21 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
seq = prb_next_seq(prb);
+ /* Flush the consoles so that records up to @seq are printed. */
+ console_lock();
+ console_unlock();
+
for (;;) {
+ unsigned long begin_jiffies;
+ unsigned long slept_jiffies;
+
diff = 0;
/*
* Hold the console_lock to guarantee safe access to
- * console->seq and to prevent changes to @console_suspended
- * until all consoles have been processed.
+ * console->seq. Releasing console_lock flushes more
+ * records in case @seq is still not printed on all
+ * usable consoles.
*/
console_lock();
@@ -3688,39 +3785,43 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
for_each_console_srcu(c) {
if (con && con != c)
continue;
+
+ flags = console_srcu_read_flags(c);
+
+ /*
+ * If consoles are not usable, it cannot be expected
+ * that they make forward progress, so only increment
+ * @diff for usable consoles.
+ */
if (!console_is_usable(c))
continue;
- printk_seq = c->seq;
+
+ if (flags & CON_NBCON) {
+ printk_seq = nbcon_seq_read(c);
+ } else {
+ printk_seq = c->seq;
+ }
+
if (printk_seq < seq)
diff += seq - printk_seq;
}
console_srcu_read_unlock(cookie);
- /*
- * If consoles are suspended, it cannot be expected that they
- * make forward progress, so timeout immediately. @diff is
- * still used to return a valid flush status.
- */
- if (console_suspended)
- remaining = 0;
- else if (diff != last_diff && reset_on_progress)
- remaining = timeout_ms;
+ if (diff != last_diff && reset_on_progress)
+ remaining_jiffies = timeout_jiffies;
console_unlock();
- if (diff == 0 || remaining == 0)
+ /* Note: @diff is 0 if there are no usable consoles. */
+ if (diff == 0 || remaining_jiffies == 0)
break;
- if (remaining < 0) {
- /* no timeout limit */
- msleep(100);
- } else if (remaining < 100) {
- msleep(remaining);
- remaining = 0;
- } else {
- msleep(100);
- remaining -= 100;
- }
+ /* msleep(1) might sleep much longer. Check time by jiffies. */
+ begin_jiffies = jiffies;
+ msleep(1);
+ slept_jiffies = jiffies - begin_jiffies;
+
+ remaining_jiffies -= min(slept_jiffies, remaining_jiffies);
last_diff = diff;
}
@@ -3741,7 +3842,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
* printer has been seen to make some forward progress.
*
* Context: Process context. May sleep while acquiring console lock.
- * Return: true if all enabled printers are caught up.
+ * Return: true if all usable printers are caught up.
*/
static bool pr_flush(int timeout_ms, bool reset_on_progress)
{
@@ -3798,11 +3899,33 @@ static void __wake_up_klogd(int val)
preempt_enable();
}
+/**
+ * wake_up_klogd - Wake kernel logging daemon
+ *
+ * Use this function when new records have been added to the ringbuffer
+ * and the console printing of those records has already occurred or is
+ * known to be handled by some other context. This function will only
+ * wake the logging daemon.
+ *
+ * Context: Any context.
+ */
void wake_up_klogd(void)
{
__wake_up_klogd(PRINTK_PENDING_WAKEUP);
}
+/**
+ * defer_console_output - Wake kernel logging daemon and trigger
+ * console printing in a deferred context
+ *
+ * Use this function when new records have been added to the ringbuffer,
+ * this context is responsible for console printing those records, but
+ * the current context is not allowed to perform the console printing.
+ * Trigger an irq_work context to perform the console printing. This
+ * function also wakes the logging daemon.
+ *
+ * Context: Any context.
+ */
void defer_console_output(void)
{
/*
@@ -3819,12 +3942,7 @@ void printk_trigger_flush(void)
int vprintk_deferred(const char *fmt, va_list args)
{
- int r;
-
- r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
- defer_console_output();
-
- return r;
+ return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
}
int _printk_deferred(const char *fmt, ...)
@@ -4107,7 +4225,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
prb_rec_init_rd(&r, &info, buf, size);
- len = 0;
prb_for_each_record(seq, prb, seq, &r) {
if (r.info->seq >= iter->next_seq)
break;
diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c
index 2dc4d5a1f1ff..fde338606ce8 100644
--- a/kernel/printk/printk_ringbuffer.c
+++ b/kernel/printk/printk_ringbuffer.c
@@ -1735,7 +1735,7 @@ static bool copy_data(struct prb_data_ring *data_ring,
if (!buf || !buf_size)
return true;
- data_size = min_t(u16, buf_size, len);
+ data_size = min_t(unsigned int, buf_size, len);
memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */
return true;
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index ef0f9a2044da..6d10927a07d8 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -38,13 +38,8 @@ asmlinkage int vprintk(const char *fmt, va_list args)
* Use the main logbuf even in NMI. But avoid calling console
* drivers that might have their own locks.
*/
- if (this_cpu_read(printk_context) || in_nmi()) {
- int len;
-
- len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
- defer_console_output();
- return len;
- }
+ if (this_cpu_read(printk_context) || in_nmi())
+ return vprintk_deferred(fmt, args);
/* No obstacles. */
return vprintk_default(fmt, args);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 443057bee87c..d8b5e13a2229 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -59,7 +59,7 @@ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
return 0;
}
- ret = __access_remote_vm(mm, addr, buf, len, gup_flags);
+ ret = access_remote_vm(mm, addr, buf, len, gup_flags);
mmput(mm);
return ret;
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 98c1544cf572..b531c33e9545 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -10,6 +10,7 @@
#ifndef __LINUX_RCU_H
#define __LINUX_RCU_H
+#include <linux/slab.h>
#include <trace/events/rcu.h>
/*
@@ -248,6 +249,12 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void debug_rcu_head_callback(struct rcu_head *rhp)
+{
+ if (unlikely(!rhp->func))
+ kmem_dump_obj(rhp);
+}
+
extern int rcu_cpu_stall_suppress_at_boot;
static inline bool rcu_stall_is_suppressed_at_boot(void)
@@ -493,7 +500,7 @@ static inline void rcu_expedite_gp(void) { }
static inline void rcu_unexpedite_gp(void) { }
static inline void rcu_async_hurry(void) { }
static inline void rcu_async_relax(void) { }
-static inline void rcu_request_urgent_qs_task(struct task_struct *t) { }
+static inline bool rcu_cpu_online(int cpu) { return true; }
#else /* #ifdef CONFIG_TINY_RCU */
bool rcu_gp_is_normal(void); /* Internal RCU use. */
bool rcu_gp_is_expedited(void); /* Internal RCU use. */
@@ -503,14 +510,22 @@ void rcu_unexpedite_gp(void);
void rcu_async_hurry(void);
void rcu_async_relax(void);
void rcupdate_announce_bootup_oddness(void);
+bool rcu_cpu_online(int cpu);
#ifdef CONFIG_TASKS_RCU_GENERIC
void show_rcu_tasks_gp_kthreads(void);
#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
static inline void show_rcu_tasks_gp_kthreads(void) {}
#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
-void rcu_request_urgent_qs_task(struct task_struct *t);
#endif /* #else #ifdef CONFIG_TINY_RCU */
+#ifdef CONFIG_TASKS_RCU
+struct task_struct *get_rcu_tasks_gp_kthread(void);
+#endif // # ifdef CONFIG_TASKS_RCU
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+struct task_struct *get_rcu_tasks_rude_gp_kthread(void);
+#endif // # ifdef CONFIG_TASKS_RUDE_RCU
+
#define RCU_SCHEDULER_INACTIVE 0
#define RCU_SCHEDULER_INIT 1
#define RCU_SCHEDULER_RUNNING 2
@@ -562,10 +577,6 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
static inline void rcu_gp_set_torture_wait(int duration) { }
#endif
-#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
-long rcutorture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask);
-#endif
-
#ifdef CONFIG_TINY_SRCU
static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
@@ -648,4 +659,10 @@ static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
bool rcu_cpu_beenfullyonline(int cpu);
#endif
+#ifdef CONFIG_RCU_STALL_COMMON
+int rcu_stall_notifier_call_chain(unsigned long val, void *v);
+#else // #ifdef CONFIG_RCU_STALL_COMMON
+static inline int rcu_stall_notifier_call_chain(unsigned long val, void *v) { return NOTIFY_DONE; }
+#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+
#endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index f71fac422c8f..1693ea22ef1b 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -368,7 +368,7 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
smp_mb(); /* Ensure counts are updated before callback is entrained. */
rhp->next = NULL;
for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
- if (rsclp->tails[i] != rsclp->tails[i - 1])
+ if (!rcu_segcblist_segempty(rsclp, i))
break;
rcu_segcblist_inc_seglen(rsclp, i);
WRITE_ONCE(*rsclp->tails[i], rhp);
@@ -551,7 +551,7 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
* as their ->gp_seq[] grace-period completion sequence number.
*/
for (i = RCU_NEXT_READY_TAIL; i > RCU_DONE_TAIL; i--)
- if (rsclp->tails[i] != rsclp->tails[i - 1] &&
+ if (!rcu_segcblist_segempty(rsclp, i) &&
ULONG_CMP_LT(rsclp->gp_seq[i], seq))
break;
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index d1221731c7cf..ffdb30495e3c 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -84,15 +84,17 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
#endif
torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
-torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
+torture_param(int, gp_async_max, 1000, "Max # outstanding waits per writer");
torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
+torture_param(int, minruntime, 0, "Minimum run time (s)");
torture_param(int, nreaders, -1, "Number of RCU reader threads");
torture_param(int, nwriters, -1, "Number of RCU updater threads");
torture_param(bool, shutdown, RCUSCALE_SHUTDOWN,
"Shutdown at end of scalability tests.");
torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
+torture_param(int, writer_holdoff_jiffies, 0, "Holdoff (jiffies) between GPs, zero to disable");
torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() scale test?");
torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
torture_param(int, kfree_by_call_rcu, 0, "Use call_rcu() to emulate kfree_rcu()?");
@@ -139,6 +141,7 @@ struct rcu_scale_ops {
void (*gp_barrier)(void);
void (*sync)(void);
void (*exp_sync)(void);
+ struct task_struct *(*rso_gp_kthread)(void);
const char *name;
};
@@ -295,6 +298,7 @@ static struct rcu_scale_ops tasks_ops = {
.gp_barrier = rcu_barrier_tasks,
.sync = synchronize_rcu_tasks,
.exp_sync = synchronize_rcu_tasks,
+ .rso_gp_kthread = get_rcu_tasks_gp_kthread,
.name = "tasks"
};
@@ -306,6 +310,44 @@ static struct rcu_scale_ops tasks_ops = {
#endif // #else // #ifdef CONFIG_TASKS_RCU
+#ifdef CONFIG_TASKS_RUDE_RCU
+
+/*
+ * Definitions for RCU-tasks-rude scalability testing.
+ */
+
+static int tasks_rude_scale_read_lock(void)
+{
+ return 0;
+}
+
+static void tasks_rude_scale_read_unlock(int idx)
+{
+}
+
+static struct rcu_scale_ops tasks_rude_ops = {
+ .ptype = RCU_TASKS_RUDE_FLAVOR,
+ .init = rcu_sync_scale_init,
+ .readlock = tasks_rude_scale_read_lock,
+ .readunlock = tasks_rude_scale_read_unlock,
+ .get_gp_seq = rcu_no_completed,
+ .gp_diff = rcu_seq_diff,
+ .async = call_rcu_tasks_rude,
+ .gp_barrier = rcu_barrier_tasks_rude,
+ .sync = synchronize_rcu_tasks_rude,
+ .exp_sync = synchronize_rcu_tasks_rude,
+ .rso_gp_kthread = get_rcu_tasks_rude_gp_kthread,
+ .name = "tasks-rude"
+};
+
+#define TASKS_RUDE_OPS &tasks_rude_ops,
+
+#else // #ifdef CONFIG_TASKS_RUDE_RCU
+
+#define TASKS_RUDE_OPS
+
+#endif // #else // #ifdef CONFIG_TASKS_RUDE_RCU
+
#ifdef CONFIG_TASKS_TRACE_RCU
/*
@@ -334,6 +376,7 @@ static struct rcu_scale_ops tasks_tracing_ops = {
.gp_barrier = rcu_barrier_tasks_trace,
.sync = synchronize_rcu_tasks_trace,
.exp_sync = synchronize_rcu_tasks_trace,
+ .rso_gp_kthread = get_rcu_tasks_trace_gp_kthread,
.name = "tasks-tracing"
};
@@ -410,10 +453,12 @@ rcu_scale_writer(void *arg)
{
int i = 0;
int i_max;
+ unsigned long jdone;
long me = (long)arg;
struct rcu_head *rhp = NULL;
bool started = false, done = false, alldone = false;
u64 t;
+ DEFINE_TORTURE_RANDOM(tr);
u64 *wdp;
u64 *wdpp = writer_durations[me];
@@ -424,7 +469,7 @@ rcu_scale_writer(void *arg)
sched_set_fifo_low(current);
if (holdoff)
- schedule_timeout_uninterruptible(holdoff * HZ);
+ schedule_timeout_idle(holdoff * HZ);
/*
* Wait until rcu_end_inkernel_boot() is called for normal GP tests
@@ -445,9 +490,12 @@ rcu_scale_writer(void *arg)
}
}
+ jdone = jiffies + minruntime * HZ;
do {
if (writer_holdoff)
udelay(writer_holdoff);
+ if (writer_holdoff_jiffies)
+ schedule_timeout_idle(torture_random(&tr) % writer_holdoff_jiffies + 1);
wdp = &wdpp[i];
*wdp = ktime_get_mono_fast_ns();
if (gp_async) {
@@ -475,7 +523,7 @@ retry:
if (!started &&
atomic_read(&n_rcu_scale_writer_started) >= nrealwriters)
started = true;
- if (!done && i >= MIN_MEAS) {
+ if (!done && i >= MIN_MEAS && time_after(jiffies, jdone)) {
done = true;
sched_set_normal(current, 0);
pr_alert("%s%s rcu_scale_writer %ld has %d measurements\n",
@@ -518,8 +566,8 @@ static void
rcu_scale_print_module_parms(struct rcu_scale_ops *cur_ops, const char *tag)
{
pr_alert("%s" SCALE_FLAG
- "--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n",
- scale_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
+ "--- %s: gp_async=%d gp_async_max=%d gp_exp=%d holdoff=%d minruntime=%d nreaders=%d nwriters=%d writer_holdoff=%d writer_holdoff_jiffies=%d verbose=%d shutdown=%d\n",
+ scale_type, tag, gp_async, gp_async_max, gp_exp, holdoff, minruntime, nrealreaders, nrealwriters, writer_holdoff, writer_holdoff_jiffies, verbose, shutdown);
}
/*
@@ -556,6 +604,8 @@ static struct task_struct **kfree_reader_tasks;
static int kfree_nrealthreads;
static atomic_t n_kfree_scale_thread_started;
static atomic_t n_kfree_scale_thread_ended;
+static struct task_struct *kthread_tp;
+static u64 kthread_stime;
struct kfree_obj {
char kfree_obj[8];
@@ -701,6 +751,10 @@ kfree_scale_init(void)
unsigned long jif_start;
unsigned long orig_jif;
+ pr_alert("%s" SCALE_FLAG
+ "--- kfree_rcu_test: kfree_mult=%d kfree_by_call_rcu=%d kfree_nthreads=%d kfree_alloc_num=%d kfree_loops=%d kfree_rcu_test_double=%d kfree_rcu_test_single=%d\n",
+ scale_type, kfree_mult, kfree_by_call_rcu, kfree_nthreads, kfree_alloc_num, kfree_loops, kfree_rcu_test_double, kfree_rcu_test_single);
+
// Also, do a quick self-test to ensure laziness is as much as
// expected.
if (kfree_by_call_rcu && !IS_ENABLED(CONFIG_RCU_LAZY)) {
@@ -797,6 +851,18 @@ rcu_scale_cleanup(void)
if (gp_exp && gp_async)
SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
+ // If built-in, just report all of the GP kthread's CPU time.
+ if (IS_BUILTIN(CONFIG_RCU_SCALE_TEST) && !kthread_tp && cur_ops->rso_gp_kthread)
+ kthread_tp = cur_ops->rso_gp_kthread();
+ if (kthread_tp) {
+ u32 ns;
+ u64 us;
+
+ kthread_stime = kthread_tp->stime - kthread_stime;
+ us = div_u64_rem(kthread_stime, 1000, &ns);
+ pr_info("rcu_scale: Grace-period kthread CPU time: %llu.%03u us\n", us, ns);
+ show_rcu_gp_kthreads();
+ }
if (kfree_rcu_test) {
kfree_scale_cleanup();
return;
@@ -885,7 +951,7 @@ rcu_scale_init(void)
long i;
int firsterr = 0;
static struct rcu_scale_ops *scale_ops[] = {
- &rcu_ops, &srcu_ops, &srcud_ops, TASKS_OPS TASKS_TRACING_OPS
+ &rcu_ops, &srcu_ops, &srcud_ops, TASKS_OPS TASKS_RUDE_OPS TASKS_TRACING_OPS
};
if (!torture_init_begin(scale_type, verbose))
@@ -910,6 +976,11 @@ rcu_scale_init(void)
if (cur_ops->init)
cur_ops->init();
+ if (cur_ops->rso_gp_kthread) {
+ kthread_tp = cur_ops->rso_gp_kthread();
+ if (kthread_tp)
+ kthread_stime = kthread_tp->stime;
+ }
if (kfree_rcu_test)
return kfree_scale_init();
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 147551c23baf..30fc9d34e329 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -21,6 +21,7 @@
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate_wait.h>
+#include <linux/rcu_notifier.h>
#include <linux/interrupt.h>
#include <linux/sched/signal.h>
#include <uapi/linux/sched/types.h>
@@ -810,7 +811,7 @@ static void synchronize_rcu_trivial(void)
int cpu;
for_each_online_cpu(cpu) {
- rcutorture_sched_setaffinity(current->pid, cpumask_of(cpu));
+ torture_sched_setaffinity(current->pid, cpumask_of(cpu));
WARN_ON_ONCE(raw_smp_processor_id() != cpu);
}
}
@@ -1149,7 +1150,7 @@ static int rcu_torture_boost(void *arg)
mutex_unlock(&boost_mutex);
break;
}
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ / 20);
}
/* Go do the stutter. */
@@ -1160,7 +1161,7 @@ checkwait: if (stutter_wait("rcu_torture_boost"))
/* Clean up and exit. */
while (!kthread_should_stop()) {
torture_shutdown_absorb("rcu_torture_boost");
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ / 20);
}
torture_kthread_stopping("rcu_torture_boost");
return 0;
@@ -1183,7 +1184,7 @@ rcu_torture_fqs(void *arg)
fqs_resume_time = jiffies + fqs_stutter * HZ;
while (time_before(jiffies, fqs_resume_time) &&
!kthread_should_stop()) {
- schedule_timeout_interruptible(1);
+ schedule_timeout_interruptible(HZ / 20);
}
fqs_burst_remaining = fqs_duration;
while (fqs_burst_remaining > 0 &&
@@ -1581,6 +1582,7 @@ rcu_torture_writer(void *arg)
rcu_access_pointer(rcu_torture_current) !=
&rcu_tortures[i]) {
tracing_off();
+ show_rcu_gp_kthreads();
WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
rcu_ftrace_dump(DUMP_ALL);
}
@@ -1876,7 +1878,7 @@ static int
rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
{
int mask = rcutorture_extend_mask_max();
- unsigned long randmask1 = torture_random(trsp) >> 8;
+ unsigned long randmask1 = torture_random(trsp);
unsigned long randmask2 = randmask1 >> 3;
unsigned long preempts = RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED;
unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ;
@@ -1935,7 +1937,7 @@ rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp,
if (!((mask - 1) & mask))
return rtrsp; /* Current RCU reader not extendable. */
/* Bias towards larger numbers of loops. */
- i = (torture_random(trsp) >> 3);
+ i = torture_random(trsp);
i = ((i | (i >> 3)) & RCUTORTURE_RDR_MAX_LOOPS) + 1;
for (j = 0; j < i; j++) {
mask = rcutorture_extend_mask(*readstate, trsp);
@@ -2125,7 +2127,7 @@ static int rcu_nocb_toggle(void *arg)
VERBOSE_TOROUT_STRING("rcu_nocb_toggle task started");
while (!rcu_inkernel_boot_has_ended())
schedule_timeout_interruptible(HZ / 10);
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu)
maxcpu = cpu;
WARN_ON(maxcpu < 0);
if (toggle_interval > ULONG_MAX)
@@ -2136,7 +2138,7 @@ static int rcu_nocb_toggle(void *arg)
toggle_fuzz = NSEC_PER_USEC;
do {
r = torture_random(&rand);
- cpu = (r >> 4) % (maxcpu + 1);
+ cpu = (r >> 1) % (maxcpu + 1);
if (r & 0x1) {
rcu_nocb_cpu_offload(cpu);
atomic_long_inc(&n_nocb_offload);
@@ -2427,6 +2429,16 @@ static int rcutorture_booster_init(unsigned int cpu)
return 0;
}
+static int rcu_torture_stall_nf(struct notifier_block *nb, unsigned long v, void *ptr)
+{
+ pr_info("%s: v=%lu, duration=%lu.\n", __func__, v, (unsigned long)ptr);
+ return NOTIFY_OK;
+}
+
+static struct notifier_block rcu_torture_stall_block = {
+ .notifier_call = rcu_torture_stall_nf,
+};
+
/*
* CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then
* induces a CPU stall for the time specified by stall_cpu.
@@ -2434,9 +2446,14 @@ static int rcutorture_booster_init(unsigned int cpu)
static int rcu_torture_stall(void *args)
{
int idx;
+ int ret;
unsigned long stop_at;
VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
+ ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);
+ if (ret)
+ pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",
+ __func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");
if (stall_cpu_holdoff > 0) {
VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
@@ -2480,6 +2497,11 @@ static int rcu_torture_stall(void *args)
cur_ops->readunlock(idx);
}
pr_alert("%s end.\n", __func__);
+ if (!ret) {
+ ret = rcu_stall_chain_notifier_unregister(&rcu_torture_stall_block);
+ if (ret)
+ pr_info("%s: rcu_stall_chain_notifier_unregister() returned %d.\n", __func__, ret);
+ }
torture_shutdown_absorb("rcu_torture_stall");
while (!kthread_should_stop())
schedule_timeout_interruptible(10 * HZ);
@@ -2898,7 +2920,7 @@ static int rcu_torture_fwd_prog(void *args)
WRITE_ONCE(rcu_fwd_seq, rcu_fwd_seq + 1);
} else {
while (READ_ONCE(rcu_fwd_seq) == oldseq && !torture_must_stop())
- schedule_timeout_interruptible(1);
+ schedule_timeout_interruptible(HZ / 20);
oldseq = READ_ONCE(rcu_fwd_seq);
}
pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id);
@@ -3199,7 +3221,7 @@ static int rcu_torture_read_exit_child(void *trsp_in)
set_user_nice(current, MAX_NICE);
// Minimize time between reading and exiting.
while (!kthread_should_stop())
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ / 20);
(void)rcu_torture_one_read(trsp, -1);
return 0;
}
@@ -3247,7 +3269,7 @@ static int rcu_torture_read_exit(void *unused)
smp_mb(); // Store before wakeup.
wake_up(&read_exit_wq);
while (!torture_must_stop())
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ / 20);
torture_kthread_stopping("rcu_torture_read_exit");
return 0;
}
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 1970ce5f22d4..2c2648a3ad30 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -528,6 +528,38 @@ static struct ref_scale_ops clock_ops = {
.name = "clock"
};
+static void ref_jiffies_section(const int nloops)
+{
+ u64 x = 0;
+ int i;
+
+ preempt_disable();
+ for (i = nloops; i >= 0; i--)
+ x += jiffies;
+ preempt_enable();
+ stopopts = x;
+}
+
+static void ref_jiffies_delay_section(const int nloops, const int udl, const int ndl)
+{
+ u64 x = 0;
+ int i;
+
+ preempt_disable();
+ for (i = nloops; i >= 0; i--) {
+ x += jiffies;
+ un_delay(udl, ndl);
+ }
+ preempt_enable();
+ stopopts = x;
+}
+
+static struct ref_scale_ops jiffies_ops = {
+ .readsection = ref_jiffies_section,
+ .delaysection = ref_jiffies_delay_section,
+ .name = "jiffies"
+};
+
////////////////////////////////////////////////////////////////////////
//
// Methods leveraging SLAB_TYPESAFE_BY_RCU.
@@ -623,12 +655,12 @@ retry:
goto retry;
}
un_delay(udl, ndl);
+ b = READ_ONCE(rtsp->a);
// Remember, seqlock read-side release can fail.
if (!rts_release(rtsp, start)) {
rcu_read_unlock();
goto retry;
}
- b = READ_ONCE(rtsp->a);
WARN_ONCE(a != b, "Re-read of ->a changed from %u to %u.\n", a, b);
b = rtsp->b;
rcu_read_unlock();
@@ -993,8 +1025,8 @@ static void
ref_scale_print_module_parms(struct ref_scale_ops *cur_ops, const char *tag)
{
pr_alert("%s" SCALE_FLAG
- "--- %s: verbose=%d shutdown=%d holdoff=%d loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
- verbose, shutdown, holdoff, loops, nreaders, nruns, readdelay);
+ "--- %s: verbose=%d verbose_batched=%d shutdown=%d holdoff=%d lookup_instances=%ld loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
+ verbose, verbose_batched, shutdown, holdoff, lookup_instances, loops, nreaders, nruns, readdelay);
}
static void
@@ -1047,7 +1079,7 @@ ref_scale_init(void)
int firsterr = 0;
static struct ref_scale_ops *scale_ops[] = {
&rcu_ops, &srcu_ops, RCU_TRACE_OPS RCU_TASKS_OPS &refcnt_ops, &rwlock_ops,
- &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops,
+ &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops, &jiffies_ops,
&typesafe_ref_ops, &typesafe_lock_ops, &typesafe_seqlock_ops,
};
@@ -1107,12 +1139,11 @@ ref_scale_init(void)
VERBOSE_SCALEOUT("Starting %d reader threads", nreaders);
for (i = 0; i < nreaders; i++) {
+ init_waitqueue_head(&reader_tasks[i].wq);
firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
reader_tasks[i].task);
if (torture_init_error(firsterr))
goto unwind;
-
- init_waitqueue_head(&(reader_tasks[i].wq));
}
// Main Task
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 336af24e0fe3..c38e5933a5d6 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -138,6 +138,7 @@ void srcu_drive_gp(struct work_struct *wp)
while (lh) {
rhp = lh;
lh = lh->next;
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 20d7a238d675..560e99ec5333 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -223,7 +223,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
snp->grplo = cpu;
snp->grphi = cpu;
}
- sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
+ sdp->grpmask = 1UL << (cpu - sdp->mynode->grplo);
}
smp_store_release(&ssp->srcu_sup->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
return true;
@@ -255,29 +255,31 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
ssp->srcu_sup->sda_is_static = is_static;
if (!is_static)
ssp->sda = alloc_percpu(struct srcu_data);
- if (!ssp->sda) {
- if (!is_static)
- kfree(ssp->srcu_sup);
- return -ENOMEM;
- }
+ if (!ssp->sda)
+ goto err_free_sup;
init_srcu_struct_data(ssp);
ssp->srcu_sup->srcu_gp_seq_needed_exp = 0;
ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns();
if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
- if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) {
- if (!ssp->srcu_sup->sda_is_static) {
- free_percpu(ssp->sda);
- ssp->sda = NULL;
- kfree(ssp->srcu_sup);
- return -ENOMEM;
- }
- } else {
- WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
- }
+ if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC))
+ goto err_free_sda;
+ WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
}
ssp->srcu_sup->srcu_ssp = ssp;
smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, 0); /* Init done. */
return 0;
+
+err_free_sda:
+ if (!is_static) {
+ free_percpu(ssp->sda);
+ ssp->sda = NULL;
+ }
+err_free_sup:
+ if (!is_static) {
+ kfree(ssp->srcu_sup);
+ ssp->srcu_sup = NULL;
+ }
+ return -ENOMEM;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -782,8 +784,7 @@ static void srcu_gp_start(struct srcu_struct *ssp)
spin_lock_rcu_node(sdp); /* Interrupts already disabled. */
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
- (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
- rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
+ WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */
WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies);
WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0);
@@ -833,7 +834,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp
int cpu;
for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
- if (!(mask & (1 << (cpu - snp->grplo))))
+ if (!(mask & (1UL << (cpu - snp->grplo))))
continue;
srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay);
}
@@ -1242,10 +1243,37 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
spin_lock_irqsave_sdp_contention(sdp, &flags);
if (rhp)
rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
+ /*
+ * The snapshot for acceleration must be taken _before_ the read of the
+ * current gp sequence used for advancing, otherwise advancing may fail
+ * and acceleration may then fail too.
+ *
+ * This could happen if:
+ *
+ * 1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the
+ * RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8).
+ *
+ * 2) The grace period for RCU_WAIT_TAIL is seen as started but not
+ * completed so rcu_seq_current() returns X + SRCU_STATE_SCAN1.
+ *
+ * 3) This value is passed to rcu_segcblist_advance() which can't move
+ * any segment forward and fails.
+ *
+ * 4) srcu_gp_start_if_needed() still proceeds with callback acceleration.
+ * But then the call to rcu_seq_snap() observes the grace period for the
+ * RCU_WAIT_TAIL segment as completed and the subsequent one for the
+ * RCU_NEXT_READY_TAIL segment as started (ie: X + 4 + SRCU_STATE_SCAN1)
+ * so it returns a snapshot of the next grace period, which is X + 12.
+ *
+ * 5) The value of X + 12 is passed to rcu_segcblist_accelerate() but the
+ * freshly enqueued callback in RCU_NEXT_TAIL can't move to
+ * RCU_NEXT_READY_TAIL which already has callbacks for a previous grace
+ * period (gp_num = X + 8). So acceleration fails.
+ */
+ s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
- s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
- (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
+ WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp);
if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
sdp->srcu_gp_seq_needed = s;
needgp = true;
@@ -1692,6 +1720,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
ssp = sdp->ssp;
rcu_cblist_init(&ready_cbs);
spin_lock_irq_rcu_node(sdp);
+ WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
if (sdp->srcu_cblist_invoking ||
@@ -1708,6 +1737,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
rhp = rcu_cblist_dequeue(&ready_cbs);
for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
debug_rcu_head_unqueue(rhp);
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
@@ -1720,8 +1750,6 @@ static void srcu_invoke_callbacks(struct work_struct *work)
*/
spin_lock_irq_rcu_node(sdp);
rcu_segcblist_add_len(&sdp->srcu_cblist, -len);
- (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
- rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
sdp->srcu_cblist_invoking = false;
more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
spin_unlock_irq_rcu_node(sdp);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index b770add3f843..f54d5782eca0 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -25,6 +25,8 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
* @cblist: Callback list.
* @lock: Lock protecting per-CPU callback list.
* @rtp_jiffies: Jiffies counter value for statistics.
+ * @lazy_timer: Timer to unlazify callbacks.
+ * @urgent_gp: Number of additional non-lazy grace periods.
* @rtp_n_lock_retries: Rough lock-contention statistic.
* @rtp_work: Work queue for invoking callbacks.
* @rtp_irq_work: IRQ work queue for deferred wakeups.
@@ -38,6 +40,8 @@ struct rcu_tasks_percpu {
raw_spinlock_t __private lock;
unsigned long rtp_jiffies;
unsigned long rtp_n_lock_retries;
+ struct timer_list lazy_timer;
+ unsigned int urgent_gp;
struct work_struct rtp_work;
struct irq_work rtp_irq_work;
struct rcu_head barrier_q_head;
@@ -51,7 +55,6 @@ struct rcu_tasks_percpu {
* @cbs_wait: RCU wait allowing a new callback to get kthread's attention.
* @cbs_gbl_lock: Lock protecting callback list.
* @tasks_gp_mutex: Mutex protecting grace period, needed during mid-boot dead zone.
- * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
* @gp_func: This flavor's grace-period-wait function.
* @gp_state: Grace period's most recent state transition (debugging).
* @gp_sleep: Per-grace-period sleep to prevent CPU-bound looping.
@@ -61,6 +64,8 @@ struct rcu_tasks_percpu {
* @tasks_gp_seq: Number of grace periods completed since boot.
* @n_ipis: Number of IPIs sent to encourage grace periods to end.
* @n_ipis_fails: Number of IPI-send failures.
+ * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
+ * @lazy_jiffies: Number of jiffies to allow callbacks to be lazy.
* @pregp_func: This flavor's pre-grace-period function (optional).
* @pertask_func: This flavor's per-task scan function (optional).
* @postscan_func: This flavor's post-task scan function (optional).
@@ -92,6 +97,7 @@ struct rcu_tasks {
unsigned long n_ipis;
unsigned long n_ipis_fails;
struct task_struct *kthread_ptr;
+ unsigned long lazy_jiffies;
rcu_tasks_gp_func_t gp_func;
pregp_func_t pregp_func;
pertask_func_t pertask_func;
@@ -127,6 +133,7 @@ static struct rcu_tasks rt_name = \
.gp_func = gp, \
.call_func = call, \
.rtpcpu = &rt_name ## __percpu, \
+ .lazy_jiffies = DIV_ROUND_UP(HZ, 4), \
.name = n, \
.percpu_enqueue_shift = order_base_2(CONFIG_NR_CPUS), \
.percpu_enqueue_lim = 1, \
@@ -139,9 +146,7 @@ static struct rcu_tasks rt_name = \
#ifdef CONFIG_TASKS_RCU
/* Track exiting tasks in order to allow them to be waited for. */
DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
-#endif
-#ifdef CONFIG_TASKS_RCU
/* Report delay in synchronize_srcu() completion in rcu_tasks_postscan(). */
static void tasks_rcu_exit_srcu_stall(struct timer_list *unused);
static DEFINE_TIMER(tasks_rcu_exit_srcu_stall_timer, tasks_rcu_exit_srcu_stall);
@@ -171,6 +176,8 @@ static int rcu_task_contend_lim __read_mostly = 100;
module_param(rcu_task_contend_lim, int, 0444);
static int rcu_task_collapse_lim __read_mostly = 10;
module_param(rcu_task_collapse_lim, int, 0444);
+static int rcu_task_lazy_lim __read_mostly = 32;
+module_param(rcu_task_lazy_lim, int, 0444);
/* RCU tasks grace-period state for debugging. */
#define RTGS_INIT 0
@@ -229,7 +236,7 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
#endif /* #ifndef CONFIG_TINY_RCU */
// Initialize per-CPU callback lists for the specified flavor of
-// Tasks RCU.
+// Tasks RCU. Do not enqueue callbacks before this function is invoked.
static void cblist_init_generic(struct rcu_tasks *rtp)
{
int cpu;
@@ -237,7 +244,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
int lim;
int shift;
- raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
if (rcu_task_enqueue_lim < 0) {
rcu_task_enqueue_lim = 1;
rcu_task_cb_adjust = true;
@@ -260,22 +266,48 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
WARN_ON_ONCE(!rtpcp);
if (cpu)
raw_spin_lock_init(&ACCESS_PRIVATE(rtpcp, lock));
- raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
+ local_irq_save(flags); // serialize initialization
if (rcu_segcblist_empty(&rtpcp->cblist))
rcu_segcblist_init(&rtpcp->cblist);
+ local_irq_restore(flags);
INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq);
rtpcp->cpu = cpu;
rtpcp->rtpp = rtp;
if (!rtpcp->rtp_blkd_tasks.next)
INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
- raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
}
- raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name,
data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim), rcu_task_cb_adjust);
}
+// Compute wakeup time for lazy callback timer.
+static unsigned long rcu_tasks_lazy_time(struct rcu_tasks *rtp)
+{
+ return jiffies + rtp->lazy_jiffies;
+}
+
+// Timer handler that unlazifies lazy callbacks.
+static void call_rcu_tasks_generic_timer(struct timer_list *tlp)
+{
+ unsigned long flags;
+ bool needwake = false;
+ struct rcu_tasks *rtp;
+ struct rcu_tasks_percpu *rtpcp = from_timer(rtpcp, tlp, lazy_timer);
+
+ rtp = rtpcp->rtpp;
+ raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+ if (!rcu_segcblist_empty(&rtpcp->cblist) && rtp->lazy_jiffies) {
+ if (!rtpcp->urgent_gp)
+ rtpcp->urgent_gp = 1;
+ needwake = true;
+ mod_timer(&rtpcp->lazy_timer, rcu_tasks_lazy_time(rtp));
+ }
+ raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+ if (needwake)
+ rcuwait_wake_up(&rtp->cbs_wait);
+}
+
// IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic().
static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp)
{
@@ -292,6 +324,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
{
int chosen_cpu;
unsigned long flags;
+ bool havekthread = smp_load_acquire(&rtp->kthread_ptr);
int ideal_cpu;
unsigned long j;
bool needadjust = false;
@@ -316,12 +349,19 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
READ_ONCE(rtp->percpu_enqueue_lim) != nr_cpu_ids)
needadjust = true; // Defer adjustment to avoid deadlock.
}
- if (!rcu_segcblist_is_enabled(&rtpcp->cblist)) {
- raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
- cblist_init_generic(rtp);
- raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
+ // Queuing callbacks before initialization not yet supported.
+ if (WARN_ON_ONCE(!rcu_segcblist_is_enabled(&rtpcp->cblist)))
+ rcu_segcblist_init(&rtpcp->cblist);
+ needwake = (func == wakeme_after_rcu) ||
+ (rcu_segcblist_n_cbs(&rtpcp->cblist) == rcu_task_lazy_lim);
+ if (havekthread && !needwake && !timer_pending(&rtpcp->lazy_timer)) {
+ if (rtp->lazy_jiffies)
+ mod_timer(&rtpcp->lazy_timer, rcu_tasks_lazy_time(rtp));
+ else
+ needwake = rcu_segcblist_empty(&rtpcp->cblist);
}
- needwake = rcu_segcblist_empty(&rtpcp->cblist);
+ if (needwake)
+ rtpcp->urgent_gp = 3;
rcu_segcblist_enqueue(&rtpcp->cblist, rhp);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
if (unlikely(needadjust)) {
@@ -392,6 +432,7 @@ static void rcu_barrier_tasks_generic(struct rcu_tasks *rtp)
static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
{
int cpu;
+ int dequeue_limit;
unsigned long flags;
bool gpdone = poll_state_synchronize_rcu(rtp->percpu_dequeue_gpseq);
long n;
@@ -399,7 +440,8 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
long ncbsnz = 0;
int needgpcb = 0;
- for (cpu = 0; cpu < smp_load_acquire(&rtp->percpu_dequeue_lim); cpu++) {
+ dequeue_limit = smp_load_acquire(&rtp->percpu_dequeue_lim);
+ for (cpu = 0; cpu < dequeue_limit; cpu++) {
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
/* Advance and accelerate any new callbacks. */
@@ -415,9 +457,14 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
}
rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq));
(void)rcu_segcblist_accelerate(&rtpcp->cblist, rcu_seq_snap(&rtp->tasks_gp_seq));
- if (rcu_segcblist_pend_cbs(&rtpcp->cblist))
+ if (rtpcp->urgent_gp > 0 && rcu_segcblist_pend_cbs(&rtpcp->cblist)) {
+ if (rtp->lazy_jiffies)
+ rtpcp->urgent_gp--;
needgpcb |= 0x3;
- if (!rcu_segcblist_empty(&rtpcp->cblist))
+ } else if (rcu_segcblist_empty(&rtpcp->cblist)) {
+ rtpcp->urgent_gp = 0;
+ }
+ if (rcu_segcblist_ready_cbs(&rtpcp->cblist))
needgpcb |= 0x1;
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
}
@@ -493,6 +540,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
len = rcl.len;
for (rhp = rcu_cblist_dequeue(&rcl); rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
@@ -525,10 +573,12 @@ static void rcu_tasks_one_gp(struct rcu_tasks *rtp, bool midboot)
if (unlikely(midboot)) {
needgpcb = 0x2;
} else {
+ mutex_unlock(&rtp->tasks_gp_mutex);
set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
rcuwait_wait_event(&rtp->cbs_wait,
(needgpcb = rcu_tasks_need_gpcb(rtp)),
TASK_IDLE);
+ mutex_lock(&rtp->tasks_gp_mutex);
}
if (needgpcb & 0x2) {
@@ -549,11 +599,19 @@ static void rcu_tasks_one_gp(struct rcu_tasks *rtp, bool midboot)
// RCU-tasks kthread that detects grace periods and invokes callbacks.
static int __noreturn rcu_tasks_kthread(void *arg)
{
+ int cpu;
struct rcu_tasks *rtp = arg;
+ for_each_possible_cpu(cpu) {
+ struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
+
+ timer_setup(&rtpcp->lazy_timer, call_rcu_tasks_generic_timer, 0);
+ rtpcp->urgent_gp = 1;
+ }
+
/* Run on housekeeping CPUs by default. Sysadm can move if desired. */
housekeeping_affine(current, HK_TYPE_RCU);
- WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start!
+ smp_store_release(&rtp->kthread_ptr, current); // Let GPs start!
/*
* Each pass through the following loop makes one check for
@@ -635,16 +693,22 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
{
int cpu;
bool havecbs = false;
+ bool haveurgent = false;
+ bool haveurgentcbs = false;
for_each_possible_cpu(cpu) {
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
- if (!data_race(rcu_segcblist_empty(&rtpcp->cblist))) {
+ if (!data_race(rcu_segcblist_empty(&rtpcp->cblist)))
havecbs = true;
+ if (data_race(rtpcp->urgent_gp))
+ haveurgent = true;
+ if (!data_race(rcu_segcblist_empty(&rtpcp->cblist)) && data_race(rtpcp->urgent_gp))
+ haveurgentcbs = true;
+ if (havecbs && haveurgent && haveurgentcbs)
break;
- }
}
- pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c %s\n",
+ pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c%c%c l:%lu %s\n",
rtp->kname,
tasks_gp_state_getname(rtp), data_race(rtp->gp_state),
jiffies - data_race(rtp->gp_jiffies),
@@ -652,6 +716,9 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis),
".k"[!!data_race(rtp->kthread_ptr)],
".C"[havecbs],
+ ".u"[haveurgent],
+ ".U"[haveurgentcbs],
+ rtp->lazy_jiffies,
s);
}
#endif // #ifndef CONFIG_TINY_RCU
@@ -828,10 +895,36 @@ static void rcu_tasks_pregp_step(struct list_head *hop)
synchronize_rcu();
}
+/* Check for quiescent states since the pregp's synchronize_rcu() */
+static bool rcu_tasks_is_holdout(struct task_struct *t)
+{
+ int cpu;
+
+ /* Has the task been seen voluntarily sleeping? */
+ if (!READ_ONCE(t->on_rq))
+ return false;
+
+ /*
+ * Idle tasks (or idle injection) within the idle loop are RCU-tasks
+ * quiescent states. But CPU boot code performed by the idle task
+ * isn't a quiescent state.
+ */
+ if (is_idle_task(t))
+ return false;
+
+ cpu = task_cpu(t);
+
+ /* Idle tasks on offline CPUs are RCU-tasks quiescent states. */
+ if (t == idle_task(cpu) && !rcu_cpu_online(cpu))
+ return false;
+
+ return true;
+}
+
/* Per-task initial processing. */
static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
{
- if (t != current && READ_ONCE(t->on_rq) && !is_idle_task(t)) {
+ if (t != current && rcu_tasks_is_holdout(t)) {
get_task_struct(t);
t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
WRITE_ONCE(t->rcu_tasks_holdout, true);
@@ -880,7 +973,7 @@ static void check_holdout_task(struct task_struct *t,
if (!READ_ONCE(t->rcu_tasks_holdout) ||
t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
- !READ_ONCE(t->on_rq) ||
+ !rcu_tasks_is_holdout(t) ||
(IS_ENABLED(CONFIG_NO_HZ_FULL) &&
!is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
WRITE_ONCE(t->rcu_tasks_holdout, false);
@@ -1020,11 +1113,16 @@ void rcu_barrier_tasks(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
+static int rcu_tasks_lazy_ms = -1;
+module_param(rcu_tasks_lazy_ms, int, 0444);
+
static int __init rcu_spawn_tasks_kthread(void)
{
cblist_init_generic(&rcu_tasks);
rcu_tasks.gp_sleep = HZ / 10;
rcu_tasks.init_fract = HZ / 10;
+ if (rcu_tasks_lazy_ms >= 0)
+ rcu_tasks.lazy_jiffies = msecs_to_jiffies(rcu_tasks_lazy_ms);
rcu_tasks.pregp_func = rcu_tasks_pregp_step;
rcu_tasks.pertask_func = rcu_tasks_pertask;
rcu_tasks.postscan_func = rcu_tasks_postscan;
@@ -1042,6 +1140,12 @@ void show_rcu_tasks_classic_gp_kthread(void)
EXPORT_SYMBOL_GPL(show_rcu_tasks_classic_gp_kthread);
#endif // !defined(CONFIG_TINY_RCU)
+struct task_struct *get_rcu_tasks_gp_kthread(void)
+{
+ return rcu_tasks.kthread_ptr;
+}
+EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread);
+
/*
* Contribute to protect against tasklist scan blind spot while the
* task is exiting and may be removed from the tasklist. See
@@ -1173,10 +1277,15 @@ void rcu_barrier_tasks_rude(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude);
+int rcu_tasks_rude_lazy_ms = -1;
+module_param(rcu_tasks_rude_lazy_ms, int, 0444);
+
static int __init rcu_spawn_tasks_rude_kthread(void)
{
cblist_init_generic(&rcu_tasks_rude);
rcu_tasks_rude.gp_sleep = HZ / 10;
+ if (rcu_tasks_rude_lazy_ms >= 0)
+ rcu_tasks_rude.lazy_jiffies = msecs_to_jiffies(rcu_tasks_rude_lazy_ms);
rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
return 0;
}
@@ -1188,6 +1297,13 @@ void show_rcu_tasks_rude_gp_kthread(void)
}
EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
#endif // !defined(CONFIG_TINY_RCU)
+
+struct task_struct *get_rcu_tasks_rude_gp_kthread(void)
+{
+ return rcu_tasks_rude.kthread_ptr;
+}
+EXPORT_SYMBOL_GPL(get_rcu_tasks_rude_gp_kthread);
+
#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
////////////////////////////////////////////////////////////////////////
@@ -1435,7 +1551,7 @@ static int trc_inspect_reader(struct task_struct *t, void *bhp_in)
} else {
// The task is not running, so C-language access is safe.
nesting = t->trc_reader_nesting;
- WARN_ON_ONCE(ofl && task_curr(t) && !is_idle_task(t));
+ WARN_ON_ONCE(ofl && task_curr(t) && (t != idle_task(task_cpu(t))));
if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && ofl)
n_heavy_reader_ofl_updates++;
}
@@ -1793,6 +1909,9 @@ void rcu_barrier_tasks_trace(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
+int rcu_tasks_trace_lazy_ms = -1;
+module_param(rcu_tasks_trace_lazy_ms, int, 0444);
+
static int __init rcu_spawn_tasks_trace_kthread(void)
{
cblist_init_generic(&rcu_tasks_trace);
@@ -1807,6 +1926,8 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
if (rcu_tasks_trace.init_fract <= 0)
rcu_tasks_trace.init_fract = 1;
}
+ if (rcu_tasks_trace_lazy_ms >= 0)
+ rcu_tasks_trace.lazy_jiffies = msecs_to_jiffies(rcu_tasks_trace_lazy_ms);
rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace;
@@ -1830,6 +1951,12 @@ void show_rcu_tasks_trace_gp_kthread(void)
EXPORT_SYMBOL_GPL(show_rcu_tasks_trace_gp_kthread);
#endif // !defined(CONFIG_TINY_RCU)
+struct task_struct *get_rcu_tasks_trace_gp_kthread(void)
+{
+ return rcu_tasks_trace.kthread_ptr;
+}
+EXPORT_SYMBOL_GPL(get_rcu_tasks_trace_gp_kthread);
+
#else /* #ifdef CONFIG_TASKS_TRACE_RCU */
static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
@@ -1881,20 +2008,22 @@ static void test_rcu_tasks_callback(struct rcu_head *rhp)
static void rcu_tasks_initiate_self_tests(void)
{
- pr_info("Running RCU-tasks wait API self tests\n");
#ifdef CONFIG_TASKS_RCU
+ pr_info("Running RCU Tasks wait API self tests\n");
tests[0].runstart = jiffies;
synchronize_rcu_tasks();
call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback);
#endif
#ifdef CONFIG_TASKS_RUDE_RCU
+ pr_info("Running RCU Tasks Rude wait API self tests\n");
tests[1].runstart = jiffies;
synchronize_rcu_tasks_rude();
call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback);
#endif
#ifdef CONFIG_TASKS_TRACE_RCU
+ pr_info("Running RCU Tasks Trace wait API self tests\n");
tests[2].runstart = jiffies;
synchronize_rcu_tasks_trace();
call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback);
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 42f7589e51e0..fec804b79080 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -97,6 +97,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)
trace_rcu_invoke_callback("", head);
f = head->func;
+ debug_rcu_head_callback(head);
WRITE_ONCE(head->func, (rcu_callback_t)0L);
f(head);
rcu_lock_release(&rcu_callback_map);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1449cb69a0e0..3ac3c846105f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -31,6 +31,7 @@
#include <linux/bitops.h>
#include <linux/export.h>
#include <linux/completion.h>
+#include <linux/kmemleak.h>
#include <linux/moduleparam.h>
#include <linux/panic.h>
#include <linux/panic_notifier.h>
@@ -632,7 +633,7 @@ void __rcu_irq_enter_check_tick(void)
// prevents self-deadlock. So we can safely recheck under the lock.
// Note that the nohz_full state currently cannot change.
raw_spin_lock_rcu_node(rdp->mynode);
- if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+ if (READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) {
// A nohz_full CPU is in the kernel and RCU needs a
// quiescent state. Turn on the tick!
WRITE_ONCE(rdp->rcu_forced_tick, true);
@@ -677,12 +678,16 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
}
/**
- * rcu_is_watching - see if RCU thinks that the current CPU is not idle
+ * rcu_is_watching - RCU read-side critical sections permitted on current CPU?
*
- * Return true if RCU is watching the running CPU, which means that this
- * CPU can safely enter RCU read-side critical sections. In other words,
- * if the current CPU is not in its idle loop or is in an interrupt or
- * NMI handler, return true.
+ * Return @true if RCU is watching the running CPU and @false otherwise.
+ * An @true return means that this CPU can safely enter RCU read-side
+ * critical sections.
+ *
+ * Although calls to rcu_is_watching() from most parts of the kernel
+ * will return @true, there are important exceptions. For example, if the
+ * current CPU is deep within its idle loop, in kernel entry/exit code,
+ * or offline, rcu_is_watching() will return @false.
*
* Make notrace because it can be called by the internal functions of
* ftrace, and making this notrace removes unnecessary recursion calls.
@@ -750,14 +755,19 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
}
/*
- * Return true if the specified CPU has passed through a quiescent
- * state by virtue of being in or having passed through an dynticks
- * idle state since the last call to dyntick_save_progress_counter()
- * for this same CPU, or by virtue of having been offline.
+ * Returns positive if the specified CPU has passed through a quiescent state
+ * by virtue of being in or having passed through an dynticks idle state since
+ * the last call to dyntick_save_progress_counter() for this same CPU, or by
+ * virtue of having been offline.
+ *
+ * Returns negative if the specified CPU needs a force resched.
+ *
+ * Returns zero otherwise.
*/
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
{
unsigned long jtsq;
+ int ret = 0;
struct rcu_node *rnp = rdp->mynode;
/*
@@ -843,8 +853,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
(time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
rcu_state.cbovld)) {
WRITE_ONCE(rdp->rcu_urgent_qs, true);
- resched_cpu(rdp->cpu);
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
+ ret = -1;
}
/*
@@ -857,8 +867,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
if (time_after(jiffies, rcu_state.jiffies_resched)) {
if (time_after(jiffies,
READ_ONCE(rdp->last_fqs_resched) + jtsq)) {
- resched_cpu(rdp->cpu);
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
+ ret = -1;
}
if (IS_ENABLED(CONFIG_IRQ_WORK) &&
!rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
@@ -887,7 +897,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
}
}
- return 0;
+ return ret;
}
/* Trace-event wrapper function for trace_rcu_future_grace_period. */
@@ -1256,7 +1266,7 @@ EXPORT_SYMBOL_GPL(rcu_gp_slow_register);
/* Unregister a counter, with NULL for not caring which. */
void rcu_gp_slow_unregister(atomic_t *rgssp)
{
- WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress);
+ WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress && rcu_gp_slow_suppress != NULL);
WRITE_ONCE(rcu_gp_slow_suppress, NULL);
}
@@ -1552,10 +1562,22 @@ static bool rcu_gp_fqs_check_wake(int *gfp)
*/
static void rcu_gp_fqs(bool first_time)
{
+ int nr_fqs = READ_ONCE(rcu_state.nr_fqs_jiffies_stall);
struct rcu_node *rnp = rcu_get_root();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
+
+ WARN_ON_ONCE(nr_fqs > 3);
+ /* Only countdown nr_fqs for stall purposes if jiffies moves. */
+ if (nr_fqs) {
+ if (nr_fqs == 1) {
+ WRITE_ONCE(rcu_state.jiffies_stall,
+ jiffies + rcu_jiffies_till_stall_check());
+ }
+ WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, --nr_fqs);
+ }
+
if (first_time) {
/* Collect dyntick-idle snapshots. */
force_qs_rnp(dyntick_save_progress_counter);
@@ -2131,6 +2153,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
trace_rcu_invoke_callback(rcu_state.name, rhp);
f = rhp->func;
+ debug_rcu_head_callback(rhp);
WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
f(rhp);
@@ -2253,15 +2276,15 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
{
int cpu;
unsigned long flags;
- unsigned long mask;
- struct rcu_data *rdp;
struct rcu_node *rnp;
rcu_state.cbovld = rcu_state.cbovldnext;
rcu_state.cbovldnext = false;
rcu_for_each_leaf_node(rnp) {
+ unsigned long mask = 0;
+ unsigned long rsmask = 0;
+
cond_resched_tasks_rcu_qs();
- mask = 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rcu_state.cbovldnext |= !!rnp->cbovldmask;
if (rnp->qsmask == 0) {
@@ -2279,11 +2302,17 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
continue;
}
for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) {
+ struct rcu_data *rdp;
+ int ret;
+
rdp = per_cpu_ptr(&rcu_data, cpu);
- if (f(rdp)) {
+ ret = f(rdp);
+ if (ret > 0) {
mask |= rdp->grpmask;
rcu_disable_urgency_upon_qs(rdp);
}
+ if (ret < 0)
+ rsmask |= rdp->grpmask;
}
if (mask != 0) {
/* Idle/offline CPUs, report (releases rnp->lock). */
@@ -2292,6 +2321,9 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
/* Nothing to do here, so just drop the lock. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
+
+ for_each_leaf_node_cpu_mask(rnp, cpu, rsmask)
+ resched_cpu(cpu);
}
}
@@ -2709,7 +2741,7 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
*/
void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
{
- return __call_rcu_common(head, func, false);
+ __call_rcu_common(head, func, false);
}
EXPORT_SYMBOL_GPL(call_rcu_hurry);
#endif
@@ -2760,7 +2792,7 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry);
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
- return __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+ __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
}
EXPORT_SYMBOL_GPL(call_rcu);
@@ -3384,6 +3416,14 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr)
success = true;
}
+ /*
+ * The kvfree_rcu() caller considers the pointer freed at this point
+ * and likely removes any references to it. Since the actual slab
+ * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore
+ * this object (no scanning or false positives reporting).
+ */
+ kmemleak_ignore(ptr);
+
// Set timer to drain after KFREE_DRAIN_JIFFIES.
if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
schedule_delayed_monitor_work(krcp);
@@ -3445,13 +3485,6 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
return freed == 0 ? SHRINK_STOP : freed;
}
-static struct shrinker kfree_rcu_shrinker = {
- .count_objects = kfree_rcu_shrink_count,
- .scan_objects = kfree_rcu_shrink_scan,
- .batch = 0,
- .seeks = DEFAULT_SEEKS,
-};
-
void __init kfree_rcu_scheduler_running(void)
{
int cpu;
@@ -4079,6 +4112,82 @@ retry:
}
EXPORT_SYMBOL_GPL(rcu_barrier);
+static unsigned long rcu_barrier_last_throttle;
+
+/**
+ * rcu_barrier_throttled - Do rcu_barrier(), but limit to one per second
+ *
+ * This can be thought of as guard rails around rcu_barrier() that
+ * permits unrestricted userspace use, at least assuming the hardware's
+ * try_cmpxchg() is robust. There will be at most one call per second to
+ * rcu_barrier() system-wide from use of this function, which means that
+ * callers might needlessly wait a second or three.
+ *
+ * This is intended for use by test suites to avoid OOM by flushing RCU
+ * callbacks from the previous test before starting the next. See the
+ * rcutree.do_rcu_barrier module parameter for more information.
+ *
+ * Why not simply make rcu_barrier() more scalable? That might be
+ * the eventual endpoint, but let's keep it simple for the time being.
+ * Note that the module parameter infrastructure serializes calls to a
+ * given .set() function, but should concurrent .set() invocation ever be
+ * possible, we are ready!
+ */
+static void rcu_barrier_throttled(void)
+{
+ unsigned long j = jiffies;
+ unsigned long old = READ_ONCE(rcu_barrier_last_throttle);
+ unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
+
+ while (time_in_range(j, old, old + HZ / 16) ||
+ !try_cmpxchg(&rcu_barrier_last_throttle, &old, j)) {
+ schedule_timeout_idle(HZ / 16);
+ if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
+ smp_mb(); /* caller's subsequent code after above check. */
+ return;
+ }
+ j = jiffies;
+ old = READ_ONCE(rcu_barrier_last_throttle);
+ }
+ rcu_barrier();
+}
+
+/*
+ * Invoke rcu_barrier_throttled() when a rcutree.do_rcu_barrier
+ * request arrives. We insist on a true value to allow for possible
+ * future expansion.
+ */
+static int param_set_do_rcu_barrier(const char *val, const struct kernel_param *kp)
+{
+ bool b;
+ int ret;
+
+ if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING)
+ return -EAGAIN;
+ ret = kstrtobool(val, &b);
+ if (!ret && b) {
+ atomic_inc((atomic_t *)kp->arg);
+ rcu_barrier_throttled();
+ atomic_dec((atomic_t *)kp->arg);
+ }
+ return ret;
+}
+
+/*
+ * Output the number of outstanding rcutree.do_rcu_barrier requests.
+ */
+static int param_get_do_rcu_barrier(char *buffer, const struct kernel_param *kp)
+{
+ return sprintf(buffer, "%d\n", atomic_read((atomic_t *)kp->arg));
+}
+
+static const struct kernel_param_ops do_rcu_barrier_ops = {
+ .set = param_set_do_rcu_barrier,
+ .get = param_get_do_rcu_barrier,
+};
+static atomic_t do_rcu_barrier;
+module_param_cb(do_rcu_barrier, &do_rcu_barrier_ops, &do_rcu_barrier, 0644);
+
/*
* Compute the mask of online CPUs for the specified rcu_node structure.
* This will not be stable unless the rcu_node structure's ->lock is
@@ -4100,6 +4209,13 @@ static bool rcu_rdp_cpu_online(struct rcu_data *rdp)
return !!(rdp->grpmask & rcu_rnp_online_cpus(rdp->mynode));
}
+bool rcu_cpu_online(int cpu)
+{
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+ return rcu_rdp_cpu_online(rdp);
+}
+
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
@@ -4126,7 +4242,7 @@ bool rcu_lockdep_current_cpu_online(void)
rdp = this_cpu_ptr(&rcu_data);
/*
* Strictly, we care here about the case where the current CPU is
- * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask
+ * in rcutree_report_cpu_starting() and thus has an excuse for rdp->grpmask
* not being up to date. So arch_spin_is_locked() might have a
* false positive if it's held by some *other* CPU, but that's
* OK because that just means a false *negative* on the warning.
@@ -4148,25 +4264,6 @@ static bool rcu_init_invoked(void)
}
/*
- * Near the end of the offline process. Trace the fact that this CPU
- * is going offline.
- */
-int rcutree_dying_cpu(unsigned int cpu)
-{
- bool blkd;
- struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
- struct rcu_node *rnp = rdp->mynode;
-
- if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
- return 0;
-
- blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
- trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
- blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
- return 0;
-}
-
-/*
* All CPUs for the specified rcu_node structure have gone offline,
* and all tasks that were preempted within an RCU read-side critical
* section while running on one of those CPUs have since exited their RCU
@@ -4212,23 +4309,6 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
}
/*
- * The CPU has been completely removed, and some other CPU is reporting
- * this fact from process context. Do the remainder of the cleanup.
- * There can only be one CPU hotplug operation at a time, so no need for
- * explicit locking.
- */
-int rcutree_dead_cpu(unsigned int cpu)
-{
- if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
- return 0;
-
- WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
- // Stop-machine done, so allow nohz_full to disable tick.
- tick_dep_clear(TICK_DEP_BIT_RCU);
- return 0;
-}
-
-/*
* Propagate ->qsinitmask bits up the rcu_node tree to account for the
* first CPU in a given leaf rcu_node structure coming online. The caller
* must hold the corresponding leaf rcu_node ->lock with interrupts
@@ -4381,29 +4461,6 @@ int rcutree_online_cpu(unsigned int cpu)
}
/*
- * Near the beginning of the process. The CPU is still very much alive
- * with pretty much all services enabled.
- */
-int rcutree_offline_cpu(unsigned int cpu)
-{
- unsigned long flags;
- struct rcu_data *rdp;
- struct rcu_node *rnp;
-
- rdp = per_cpu_ptr(&rcu_data, cpu);
- rnp = rdp->mynode;
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rnp->ffmask &= ~rdp->grpmask;
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
- rcutree_affinity_setting(cpu, cpu);
-
- // nohz_full CPUs need the tick for stop-machine to work quickly
- tick_dep_set(TICK_DEP_BIT_RCU);
- return 0;
-}
-
-/*
* Mark the specified CPU as being online so that subsequent grace periods
* (both expedited and normal) will wait on it. Note that this means that
* incoming CPUs are not allowed to use RCU read-side critical sections
@@ -4414,8 +4471,10 @@ int rcutree_offline_cpu(unsigned int cpu)
* from the incoming CPU rather than from the cpuhp_step mechanism.
* This is because this function must be invoked at a precise location.
* This incoming CPU must not have enabled interrupts yet.
+ *
+ * This mirrors the effects of rcutree_report_cpu_dead().
*/
-void rcu_cpu_starting(unsigned int cpu)
+void rcutree_report_cpu_starting(unsigned int cpu)
{
unsigned long mask;
struct rcu_data *rdp;
@@ -4469,14 +4528,21 @@ void rcu_cpu_starting(unsigned int cpu)
* Note that this function is special in that it is invoked directly
* from the outgoing CPU rather than from the cpuhp_step mechanism.
* This is because this function must be invoked at a precise location.
+ *
+ * This mirrors the effect of rcutree_report_cpu_starting().
*/
-void rcu_report_dead(unsigned int cpu)
+void rcutree_report_cpu_dead(void)
{
- unsigned long flags, seq_flags;
+ unsigned long flags;
unsigned long mask;
- struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
+ /*
+ * IRQS must be disabled from now on and until the CPU dies, or an interrupt
+ * may introduce a new READ-side while it is actually off the QS masks.
+ */
+ lockdep_assert_irqs_disabled();
// Do any dangling deferred wakeups.
do_nocb_deferred_wakeup(rdp);
@@ -4484,7 +4550,6 @@ void rcu_report_dead(unsigned int cpu)
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
- local_irq_save(seq_flags);
arch_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
@@ -4498,8 +4563,6 @@ void rcu_report_dead(unsigned int cpu)
WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
arch_spin_unlock(&rcu_state.ofl_lock);
- local_irq_restore(seq_flags);
-
rdp->cpu_started = false;
}
@@ -4554,7 +4617,60 @@ void rcutree_migrate_callbacks(int cpu)
cpu, rcu_segcblist_n_cbs(&rdp->cblist),
rcu_segcblist_first_cb(&rdp->cblist));
}
-#endif
+
+/*
+ * The CPU has been completely removed, and some other CPU is reporting
+ * this fact from process context. Do the remainder of the cleanup.
+ * There can only be one CPU hotplug operation at a time, so no need for
+ * explicit locking.
+ */
+int rcutree_dead_cpu(unsigned int cpu)
+{
+ WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
+ // Stop-machine done, so allow nohz_full to disable tick.
+ tick_dep_clear(TICK_DEP_BIT_RCU);
+ return 0;
+}
+
+/*
+ * Near the end of the offline process. Trace the fact that this CPU
+ * is going offline.
+ */
+int rcutree_dying_cpu(unsigned int cpu)
+{
+ bool blkd;
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ struct rcu_node *rnp = rdp->mynode;
+
+ blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
+ trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
+ blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
+ return 0;
+}
+
+/*
+ * Near the beginning of the process. The CPU is still very much alive
+ * with pretty much all services enabled.
+ */
+int rcutree_offline_cpu(unsigned int cpu)
+{
+ unsigned long flags;
+ struct rcu_data *rdp;
+ struct rcu_node *rnp;
+
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ rnp = rdp->mynode;
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ rnp->ffmask &= ~rdp->grpmask;
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+ rcutree_affinity_setting(cpu, cpu);
+
+ // nohz_full CPUs need the tick for stop-machine to work quickly
+ tick_dep_set(TICK_DEP_BIT_RCU);
+ return 0;
+}
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
/*
* On non-huge systems, use expedited RCU grace periods to make suspend
@@ -4927,6 +5043,7 @@ static void __init kfree_rcu_batch_init(void)
{
int cpu;
int i, j;
+ struct shrinker *kfree_rcu_shrinker;
/* Clamp it to [0:100] seconds interval. */
if (rcu_delay_page_cache_fill_msec < 0 ||
@@ -4958,8 +5075,17 @@ static void __init kfree_rcu_batch_init(void)
INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func);
krcp->initialized = true;
}
- if (register_shrinker(&kfree_rcu_shrinker, "rcu-kfree"))
- pr_err("Failed to register kfree_rcu() shrinker!\n");
+
+ kfree_rcu_shrinker = shrinker_alloc(0, "rcu-kfree");
+ if (!kfree_rcu_shrinker) {
+ pr_err("Failed to allocate kfree_rcu() shrinker!\n");
+ return;
+ }
+
+ kfree_rcu_shrinker->count_objects = kfree_rcu_shrink_count;
+ kfree_rcu_shrinker->scan_objects = kfree_rcu_shrink_scan;
+
+ shrinker_register(kfree_rcu_shrinker);
}
void __init rcu_init(void)
@@ -4986,7 +5112,7 @@ void __init rcu_init(void)
pm_notifier(rcu_pm_notify, 0);
WARN_ON(num_online_cpus() > 1); // Only one CPU this early in boot.
rcutree_prepare_cpu(cpu);
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
rcutree_online_cpu(cpu);
/* Create workqueue for Tree SRCU and for expedited GPs. */
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 192536916f9a..e9821a8422db 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -386,6 +386,10 @@ struct rcu_state {
/* in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
+ int nr_fqs_jiffies_stall; /* Number of fqs loops after
+ * which read jiffies and set
+ * jiffies_stall. Stall
+ * warnings disabled if !0. */
unsigned long jiffies_resched; /* Time at which to resched */
/* a reluctant CPU. */
unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 8239b39d945b..6d7cea5d591f 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -621,10 +621,14 @@ static void synchronize_rcu_expedited_wait(void)
}
for (;;) {
+ unsigned long j;
+
if (synchronize_rcu_expedited_wait_once(jiffies_stall))
return;
if (rcu_stall_is_suppressed())
continue;
+ j = jiffies;
+ rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_EXP, (void *)(j - jiffies_start));
trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
rcu_state.name);
@@ -647,7 +651,7 @@ static void synchronize_rcu_expedited_wait(void)
}
}
pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
- jiffies - jiffies_start, rcu_state.expedited_sequence,
+ j - jiffies_start, rcu_state.expedited_sequence,
data_race(rnp_root->expmask),
".T"[!!data_race(rnp_root->exp_tasks)]);
if (ndetected) {
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 43229d2b0c44..4efbf7333d4e 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -77,9 +77,9 @@ __setup("rcu_nocbs", rcu_nocb_setup);
static int __init parse_rcu_nocb_poll(char *arg)
{
rcu_nocb_poll = true;
- return 0;
+ return 1;
}
-early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
+__setup("rcu_nocb_poll", parse_rcu_nocb_poll);
/*
* Don't bother bypassing ->cblist if the call_rcu() rate is low.
@@ -1396,13 +1396,6 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
return count ? count : SHRINK_STOP;
}
-
-static struct shrinker lazy_rcu_shrinker = {
- .count_objects = lazy_rcu_shrink_count,
- .scan_objects = lazy_rcu_shrink_scan,
- .batch = 0,
- .seeks = DEFAULT_SEEKS,
-};
#endif // #ifdef CONFIG_RCU_LAZY
void __init rcu_init_nohz(void)
@@ -1410,6 +1403,7 @@ void __init rcu_init_nohz(void)
int cpu;
struct rcu_data *rdp;
const struct cpumask *cpumask = NULL;
+ struct shrinker * __maybe_unused lazy_rcu_shrinker;
#if defined(CONFIG_NO_HZ_FULL)
if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask))
@@ -1436,8 +1430,15 @@ void __init rcu_init_nohz(void)
return;
#ifdef CONFIG_RCU_LAZY
- if (register_shrinker(&lazy_rcu_shrinker, "rcu-lazy"))
- pr_err("Failed to register lazy_rcu shrinker!\n");
+ lazy_rcu_shrinker = shrinker_alloc(0, "rcu-lazy");
+ if (!lazy_rcu_shrinker) {
+ pr_err("Failed to allocate lazy_rcu shrinker!\n");
+ } else {
+ lazy_rcu_shrinker->count_objects = lazy_rcu_shrink_count;
+ lazy_rcu_shrinker->scan_objects = lazy_rcu_shrink_scan;
+
+ shrinker_register(lazy_rcu_shrinker);
+ }
#endif // #ifdef CONFIG_RCU_LAZY
if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index b10b8349bb2a..ac8e86babe44 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -8,6 +8,7 @@
*/
#include <linux/kvm_para.h>
+#include <linux/rcu_notifier.h>
//////////////////////////////////////////////////////////////////////////////
//
@@ -149,12 +150,17 @@ static void panic_on_rcu_stall(void)
/**
* rcu_cpu_stall_reset - restart stall-warning timeout for current grace period
*
+ * To perform the reset request from the caller, disable stall detection until
+ * 3 fqs loops have passed. This is required to ensure a fresh jiffies is
+ * loaded. It should be safe to do from the fqs loop as enough timer
+ * interrupts and context switches should have passed.
+ *
* The caller must disable hard irqs.
*/
void rcu_cpu_stall_reset(void)
{
- WRITE_ONCE(rcu_state.jiffies_stall,
- jiffies + rcu_jiffies_till_stall_check());
+ WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 3);
+ WRITE_ONCE(rcu_state.jiffies_stall, ULONG_MAX);
}
//////////////////////////////////////////////////////////////////////////////
@@ -170,6 +176,7 @@ static void record_gp_stall_check_time(void)
WRITE_ONCE(rcu_state.gp_start, j);
j1 = rcu_jiffies_till_stall_check();
smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq.
+ WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 0);
WRITE_ONCE(rcu_state.jiffies_stall, j + j1);
rcu_state.jiffies_resched = j + j1 / 2;
rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
@@ -534,16 +541,16 @@ static void rcu_check_gp_kthread_starvation(void)
data_race(READ_ONCE(rcu_state.gp_state)),
gpk ? data_race(READ_ONCE(gpk->__state)) : ~0, cpu);
if (gpk) {
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
pr_err("RCU grace-period kthread stack dump:\n");
sched_show_task(gpk);
- if (cpu >= 0) {
- if (cpu_is_offline(cpu)) {
- pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
- } else {
- pr_err("Stack dump where RCU GP kthread last ran:\n");
- dump_cpu_task(cpu);
- }
+ if (cpu_is_offline(cpu)) {
+ pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
+ } else if (!(data_race(READ_ONCE(rdp->mynode->qsmask)) & rdp->grpmask)) {
+ pr_err("Stack dump where RCU GP kthread last ran:\n");
+ dump_cpu_task(cpu);
}
wake_up_process(gpk);
}
@@ -711,7 +718,7 @@ static void print_cpu_stall(unsigned long gps)
static void check_cpu_stall(struct rcu_data *rdp)
{
- bool didstall = false;
+ bool self_detected;
unsigned long gs1;
unsigned long gs2;
unsigned long gps;
@@ -725,6 +732,16 @@ static void check_cpu_stall(struct rcu_data *rdp)
!rcu_gp_in_progress())
return;
rcu_stall_kick_kthreads();
+
+ /*
+ * Check if it was requested (via rcu_cpu_stall_reset()) that the FQS
+ * loop has to set jiffies to ensure a non-stale jiffies value. This
+ * is required to have good jiffies value after coming out of long
+ * breaks of jiffies updates. Not doing so can cause false positives.
+ */
+ if (READ_ONCE(rcu_state.nr_fqs_jiffies_stall) > 0)
+ return;
+
j = jiffies;
/*
@@ -758,10 +775,10 @@ static void check_cpu_stall(struct rcu_data *rdp)
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
jn = jiffies + ULONG_MAX / 2;
+ self_detected = READ_ONCE(rnp->qsmask) & rdp->grpmask;
if (rcu_gp_in_progress() &&
- (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+ (self_detected || ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) &&
cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
/*
* If a virtual machine is stopped by the host it can look to
* the watchdog like an RCU stall. Check to see if the host
@@ -770,39 +787,28 @@ static void check_cpu_stall(struct rcu_data *rdp)
if (kvm_check_and_clear_guest_paused())
return;
- /* We haven't checked in, so go dump stack. */
- print_cpu_stall(gps);
- if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
- rcu_ftrace_dump(DUMP_ALL);
- didstall = true;
-
- } else if (rcu_gp_in_progress() &&
- ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
- cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
- /*
- * If a virtual machine is stopped by the host it can look to
- * the watchdog like an RCU stall. Check to see if the host
- * stopped the vm.
- */
- if (kvm_check_and_clear_guest_paused())
- return;
+ rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_NORM, (void *)j - gps);
+ if (self_detected) {
+ /* We haven't checked in, so go dump stack. */
+ print_cpu_stall(gps);
+ } else {
+ /* They had a few time units to dump stack, so complain. */
+ print_other_cpu_stall(gs2, gps);
+ }
- /* They had a few time units to dump stack, so complain. */
- print_other_cpu_stall(gs2, gps);
if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
rcu_ftrace_dump(DUMP_ALL);
- didstall = true;
- }
- if (didstall && READ_ONCE(rcu_state.jiffies_stall) == jn) {
- jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
- WRITE_ONCE(rcu_state.jiffies_stall, jn);
+
+ if (READ_ONCE(rcu_state.jiffies_stall) == jn) {
+ jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+ WRITE_ONCE(rcu_state.jiffies_stall, jn);
+ }
}
}
//////////////////////////////////////////////////////////////////////////////
//
-// RCU forward-progress mechanisms, including of callback invocation.
+// RCU forward-progress mechanisms, including for callback invocation.
/*
@@ -1035,7 +1041,7 @@ static bool sysrq_rcu;
module_param(sysrq_rcu, bool, 0444);
/* Dump grace-period-request information due to commandeered sysrq. */
-static void sysrq_show_rcu(int key)
+static void sysrq_show_rcu(u8 key)
{
show_rcu_gp_kthreads();
}
@@ -1054,3 +1060,58 @@ static int __init rcu_sysrq_init(void)
return 0;
}
early_initcall(rcu_sysrq_init);
+
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// RCU CPU stall-warning notifiers
+
+static ATOMIC_NOTIFIER_HEAD(rcu_cpu_stall_notifier_list);
+
+/**
+ * rcu_stall_chain_notifier_register - Add an RCU CPU stall notifier
+ * @n: Entry to add.
+ *
+ * Adds an RCU CPU stall notifier to an atomic notifier chain.
+ * The @action passed to a notifier will be @RCU_STALL_NOTIFY_NORM or
+ * friends. The @data will be the duration of the stalled grace period,
+ * in jiffies, coerced to a void* pointer.
+ *
+ * Returns 0 on success, %-EEXIST on error.
+ */
+int rcu_stall_chain_notifier_register(struct notifier_block *n)
+{
+ return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+}
+EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_register);
+
+/**
+ * rcu_stall_chain_notifier_unregister - Remove an RCU CPU stall notifier
+ * @n: Entry to add.
+ *
+ * Removes an RCU CPU stall notifier from an atomic notifier chain.
+ *
+ * Returns zero on success, %-ENOENT on failure.
+ */
+int rcu_stall_chain_notifier_unregister(struct notifier_block *n)
+{
+ return atomic_notifier_chain_unregister(&rcu_cpu_stall_notifier_list, n);
+}
+EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_unregister);
+
+/*
+ * rcu_stall_notifier_call_chain - Call functions in an RCU CPU stall notifier chain
+ * @val: Value passed unmodified to notifier function
+ * @v: Pointer passed unmodified to notifier function
+ *
+ * Calls each function in the RCU CPU stall notifier chain in turn, which
+ * is an atomic call chain. See atomic_notifier_call_chain() for more
+ * information.
+ *
+ * This is for use within RCU, hence the omission of the extra asterisk
+ * to indicate a non-kerneldoc format header comment.
+ */
+int rcu_stall_notifier_call_chain(unsigned long val, void *v)
+{
+ return atomic_notifier_call_chain(&rcu_cpu_stall_notifier_list, val, v);
+}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 19bf6fa3ee6a..c534d6806d3d 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -25,6 +25,7 @@
#include <linux/interrupt.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
+#include <linux/torture.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/percpu.h>
@@ -524,17 +525,17 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
do { } while (0)
#endif
-#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
+#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST)
/* Get rcutorture access to sched_setaffinity(). */
-long rcutorture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
int ret;
ret = sched_setaffinity(pid, in_mask);
- WARN_ONCE(ret, "%s: sched_setaffinity() returned %d\n", __func__, ret);
+ WARN_ONCE(ret, "%s: sched_setaffinity(%d) returned %d\n", __func__, pid, ret);
return ret;
}
-EXPORT_SYMBOL_GPL(rcutorture_sched_setaffinity);
+EXPORT_SYMBOL_GPL(torture_sched_setaffinity);
#endif
#ifdef CONFIG_RCU_STALL_COMMON
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 3bba88c7ffc6..395a0ea3c7a8 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -55,6 +55,7 @@ struct sys_off_handler {
enum sys_off_mode mode;
bool blocking;
void *list;
+ struct device *dev;
};
/*
@@ -74,6 +75,7 @@ void __weak (*pm_power_off)(void);
void emergency_restart(void)
{
kmsg_dump(KMSG_DUMP_EMERG);
+ system_state = SYSTEM_RESTART;
machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);
@@ -323,6 +325,7 @@ static int sys_off_notify(struct notifier_block *nb,
data.cb_data = handler->cb_data;
data.mode = mode;
data.cmd = cmd;
+ data.dev = handler->dev;
return handler->sys_off_cb(&data);
}
@@ -510,6 +513,7 @@ int devm_register_sys_off_handler(struct device *dev,
handler = register_sys_off_handler(mode, priority, callback, cb_data);
if (IS_ERR(handler))
return PTR_ERR(handler);
+ handler->dev = dev;
return devm_add_action_or_reset(dev, devm_unregister_sys_off_handler,
handler);
diff --git a/kernel/relay.c b/kernel/relay.c
index a80fa01042e9..83fe0325cde1 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -375,7 +375,7 @@ static struct dentry *relay_create_buf_file(struct rchan *chan,
*/
static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
{
- struct rchan_buf *buf = NULL;
+ struct rchan_buf *buf;
struct dentry *dentry;
if (chan->is_global)
diff --git a/kernel/resource.c b/kernel/resource.c
index b1763b2fd7ef..91be1bc50b60 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -56,33 +56,17 @@ struct resource_constraint {
static DEFINE_RWLOCK(resource_lock);
-static struct resource *next_resource(struct resource *p)
+static struct resource *next_resource(struct resource *p, bool skip_children)
{
- if (p->child)
+ if (!skip_children && p->child)
return p->child;
while (!p->sibling && p->parent)
p = p->parent;
return p->sibling;
}
-static struct resource *next_resource_skip_children(struct resource *p)
-{
- while (!p->sibling && p->parent)
- p = p->parent;
- return p->sibling;
-}
-
#define for_each_resource(_root, _p, _skip_children) \
- for ((_p) = (_root)->child; (_p); \
- (_p) = (_skip_children) ? next_resource_skip_children(_p) : \
- next_resource(_p))
-
-static void *r_next(struct seq_file *m, void *v, loff_t *pos)
-{
- struct resource *p = v;
- (*pos)++;
- return (void *)next_resource(p);
-}
+ for ((_p) = (_root)->child; (_p); (_p) = next_resource(_p, _skip_children))
#ifdef CONFIG_PROC_FS
@@ -91,14 +75,28 @@ enum { MAX_IORES_LEVEL = 5 };
static void *r_start(struct seq_file *m, loff_t *pos)
__acquires(resource_lock)
{
- struct resource *p = pde_data(file_inode(m->file));
- loff_t l = 0;
+ struct resource *root = pde_data(file_inode(m->file));
+ struct resource *p;
+ loff_t l = *pos;
+
read_lock(&resource_lock);
- for (p = p->child; p && l < *pos; p = r_next(m, p, &l))
- ;
+ for_each_resource(root, p, false) {
+ if (l-- == 0)
+ break;
+ }
+
return p;
}
+static void *r_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct resource *p = v;
+
+ (*pos)++;
+
+ return (void *)next_resource(p, false);
+}
+
static void r_stop(struct seq_file *m, void *v)
__releases(resource_lock)
{
@@ -336,7 +334,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
read_lock(&resource_lock);
- for (p = iomem_resource.child; p; p = next_resource(p)) {
+ for_each_resource(&iomem_resource, p, false) {
/* If we passed the resource we are looking for, stop */
if (p->start > end) {
p = NULL;
@@ -1641,13 +1639,12 @@ __setup("reserve=", reserve_setup);
*/
int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
{
- struct resource *p = &iomem_resource;
resource_size_t end = addr + size - 1;
+ struct resource *p;
int err = 0;
- loff_t l;
read_lock(&resource_lock);
- for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+ for_each_resource(&iomem_resource, p, false) {
/*
* We can probably skip the resources without
* IORESOURCE_IO attribute?
@@ -1847,8 +1844,8 @@ get_free_mem_region(struct device *dev, struct resource *base,
write_lock(&resource_lock);
for (addr = gfr_start(base, size, align, flags);
- gfr_continue(base, addr, size, flags);
- addr = gfr_next(addr, size, flags)) {
+ gfr_continue(base, addr, align, flags);
+ addr = gfr_next(addr, align, flags)) {
if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) !=
REGION_DISJOINT)
continue;
diff --git a/kernel/scftorture.c b/kernel/scftorture.c
index 5d113aa59e77..59032aaccd18 100644
--- a/kernel/scftorture.c
+++ b/kernel/scftorture.c
@@ -171,7 +171,8 @@ static void scf_torture_stats_print(void)
scfs.n_all_wait += scf_stats_p[i].n_all_wait;
}
if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) ||
- atomic_read(&n_mb_out_errs) || atomic_read(&n_alloc_errs))
+ atomic_read(&n_mb_out_errs) ||
+ (!IS_ENABLED(CONFIG_KASAN) && atomic_read(&n_alloc_errs)))
bangstr = "!!! ";
pr_alert("%s %sscf_invoked_count %s: %lld resched: %lld single: %lld/%lld single_ofl: %lld/%lld single_rpc: %lld single_rpc_ofl: %lld many: %lld/%lld all: %lld/%lld ",
SCFTORT_FLAG, bangstr, isdone ? "VER" : "ver", invoked_count, scfs.n_resched,
@@ -312,6 +313,7 @@ static void scf_handler_1(void *scfc_in)
// Randomly do an smp_call_function*() invocation.
static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_random_state *trsp)
{
+ bool allocfail = false;
uintptr_t cpu;
int ret = 0;
struct scf_check *scfcp = NULL;
@@ -323,8 +325,10 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
preempt_disable();
if (scfsp->scfs_prim == SCF_PRIM_SINGLE || scfsp->scfs_wait) {
scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC);
- if (WARN_ON_ONCE(!scfcp)) {
+ if (!scfcp) {
+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_KASAN));
atomic_inc(&n_alloc_errs);
+ allocfail = true;
} else {
scfcp->scfc_cpu = -1;
scfcp->scfc_wait = scfsp->scfs_wait;
@@ -431,7 +435,9 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
cpus_read_unlock();
else
preempt_enable();
- if (!(torture_random(trsp) & 0xfff))
+ if (allocfail)
+ schedule_timeout_idle((1 + longwait) * HZ); // Let no-wait handlers complete.
+ else if (!(torture_random(trsp) & 0xfff))
schedule_timeout_uninterruptible(1);
}
diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
index 99bdd96f454f..80a3df49ab47 100644
--- a/kernel/sched/build_utility.c
+++ b/kernel/sched/build_utility.c
@@ -34,7 +34,6 @@
#include <linux/nospec.h>
#include <linux/proc_fs.h>
#include <linux/psi.h>
-#include <linux/psi.h>
#include <linux/ptrace_api.h>
#include <linux/sched_clock.h>
#include <linux/security.h>
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index d57a5c1c1cd9..3561ab533dd4 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -13,6 +13,23 @@
* Waiting for completion is a typically sync point, but not an exclusion point.
*/
+static void complete_with_flags(struct completion *x, int wake_flags)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
+
+ if (x->done != UINT_MAX)
+ x->done++;
+ swake_up_locked(&x->wait, wake_flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+
+void complete_on_current_cpu(struct completion *x)
+{
+ return complete_with_flags(x, WF_CURRENT_CPU);
+}
+
/**
* complete: - signals a single thread waiting on this completion
* @x: holds the state of this particular completion
@@ -27,14 +44,7 @@
*/
void complete(struct completion *x)
{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&x->wait.lock, flags);
-
- if (x->done != UINT_MAX)
- x->done++;
- swake_up_locked(&x->wait);
- raw_spin_unlock_irqrestore(&x->wait.lock, flags);
+ complete_with_flags(x, 0);
}
EXPORT_SYMBOL(complete);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c52c2eba7c73..a708d225c28e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -85,7 +85,6 @@
#include "sched.h"
#include "stats.h"
-#include "autogroup.h"
#include "autogroup.h"
#include "pelt.h"
@@ -114,6 +113,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -919,14 +919,13 @@ static bool set_nr_if_polling(struct task_struct *p)
struct thread_info *ti = task_thread_info(p);
typeof(ti->flags) val = READ_ONCE(ti->flags);
- for (;;) {
+ do {
if (!(val & _TIF_POLLING_NRFLAG))
return false;
if (val & _TIF_NEED_RESCHED)
return true;
- if (try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED))
- break;
- }
+ } while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
+
return true;
}
@@ -1097,25 +1096,22 @@ int get_nohz_timer_target(void)
hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
- rcu_read_lock();
+ guard(rcu)();
+
for_each_domain(cpu, sd) {
for_each_cpu_and(i, sched_domain_span(sd), hk_mask) {
if (cpu == i)
continue;
- if (!idle_cpu(i)) {
- cpu = i;
- goto unlock;
- }
+ if (!idle_cpu(i))
+ return i;
}
}
if (default_cpu == -1)
default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
- cpu = default_cpu;
-unlock:
- rcu_read_unlock();
- return cpu;
+
+ return default_cpu;
}
/*
@@ -1194,6 +1190,20 @@ static void nohz_csd_func(void *info)
#endif /* CONFIG_NO_HZ_COMMON */
#ifdef CONFIG_NO_HZ_FULL
+static inline bool __need_bw_check(struct rq *rq, struct task_struct *p)
+{
+ if (rq->nr_running != 1)
+ return false;
+
+ if (p->sched_class != &fair_sched_class)
+ return false;
+
+ if (!task_on_rq_queued(p))
+ return false;
+
+ return true;
+}
+
bool sched_can_stop_tick(struct rq *rq)
{
int fifo_nr_running;
@@ -1229,6 +1239,18 @@ bool sched_can_stop_tick(struct rq *rq)
if (rq->nr_running > 1)
return false;
+ /*
+ * If there is one task and it has CFS runtime bandwidth constraints
+ * and it's on the cpu now we don't want to stop the tick.
+ * This check prevents clearing the bit if a newly enqueued task here is
+ * dequeued by migrating while the constrained task continues to run.
+ * E.g. going from 2->1 without going through pick_next_task().
+ */
+ if (sched_feat(HZ_BW) && __need_bw_check(rq, rq->curr)) {
+ if (cfs_task_bw_constrained(rq->curr))
+ return false;
+ }
+
return true;
}
#endif /* CONFIG_NO_HZ_FULL */
@@ -1457,16 +1479,12 @@ static void __uclamp_update_util_min_rt_default(struct task_struct *p)
static void uclamp_update_util_min_rt_default(struct task_struct *p)
{
- struct rq_flags rf;
- struct rq *rq;
-
if (!rt_task(p))
return;
/* Protect updates to p->uclamp_* */
- rq = task_rq_lock(p, &rf);
+ guard(task_rq_lock)(p);
__uclamp_update_util_min_rt_default(p);
- task_rq_unlock(rq, p, &rf);
}
static inline struct uclamp_se
@@ -1762,9 +1780,8 @@ static void uclamp_update_root_tg(void)
uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX],
sysctl_sched_uclamp_util_max, false);
- rcu_read_lock();
+ guard(rcu)();
cpu_util_update_eff(&root_task_group.css);
- rcu_read_unlock();
}
#else
static void uclamp_update_root_tg(void) { }
@@ -1791,10 +1808,9 @@ static void uclamp_sync_util_min_rt_default(void)
smp_mb__after_spinlock();
read_unlock(&tasklist_lock);
- rcu_read_lock();
+ guard(rcu)();
for_each_process_thread(g, p)
uclamp_update_util_min_rt_default(p);
- rcu_read_unlock();
}
static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
@@ -1804,7 +1820,8 @@ static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
int old_min, old_max, old_min_rt;
int result;
- mutex_lock(&uclamp_mutex);
+ guard(mutex)(&uclamp_mutex);
+
old_min = sysctl_sched_uclamp_util_min;
old_max = sysctl_sched_uclamp_util_max;
old_min_rt = sysctl_sched_uclamp_util_min_rt_default;
@@ -1813,7 +1830,7 @@ static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
if (result)
goto undo;
if (!write)
- goto done;
+ return 0;
if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE ||
@@ -1849,16 +1866,12 @@ static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
* Otherwise, keep it simple and do just a lazy update at each next
* task enqueue time.
*/
-
- goto done;
+ return 0;
undo:
sysctl_sched_uclamp_util_min = old_min;
sysctl_sched_uclamp_util_max = old_max;
sysctl_sched_uclamp_util_min_rt_default = old_min_rt;
-done:
- mutex_unlock(&uclamp_mutex);
-
return result;
}
#endif
@@ -2198,10 +2211,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
p->sched_class->prio_changed(rq, p, oldprio);
}
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
{
if (p->sched_class == rq->curr->sched_class)
- rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+ rq->curr->sched_class->wakeup_preempt(rq, p, flags);
else if (sched_class_above(p->sched_class, rq->curr->sched_class))
resched_curr(rq);
@@ -2219,31 +2232,21 @@ int __task_state_match(struct task_struct *p, unsigned int state)
if (READ_ONCE(p->__state) & state)
return 1;
-#ifdef CONFIG_PREEMPT_RT
if (READ_ONCE(p->saved_state) & state)
return -1;
-#endif
+
return 0;
}
static __always_inline
int task_state_match(struct task_struct *p, unsigned int state)
{
-#ifdef CONFIG_PREEMPT_RT
- int match;
-
/*
- * Serialize against current_save_and_set_rtlock_wait_state() and
- * current_restore_rtlock_saved_state().
+ * Serialize against current_save_and_set_rtlock_wait_state(),
+ * current_restore_rtlock_saved_state(), and __refrigerator().
*/
- raw_spin_lock_irq(&p->pi_lock);
- match = __task_state_match(p, state);
- raw_spin_unlock_irq(&p->pi_lock);
-
- return match;
-#else
+ guard(raw_spinlock_irq)(&p->pi_lock);
return __task_state_match(p, state);
-#endif
}
/*
@@ -2397,10 +2400,9 @@ void migrate_disable(void)
return;
}
- preempt_disable();
+ guard(preempt)();
this_rq()->nr_pinned++;
p->migration_disabled = 1;
- preempt_enable();
}
EXPORT_SYMBOL_GPL(migrate_disable);
@@ -2424,7 +2426,7 @@ void migrate_enable(void)
* Ensure stop_task runs either before or after this, and that
* __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
*/
- preempt_disable();
+ guard(preempt)();
if (p->cpus_ptr != &p->cpus_mask)
__set_cpus_allowed_ptr(p, &ac);
/*
@@ -2435,7 +2437,6 @@ void migrate_enable(void)
barrier();
p->migration_disabled = 0;
this_rq()->nr_pinned--;
- preempt_enable();
}
EXPORT_SYMBOL_GPL(migrate_enable);
@@ -2507,7 +2508,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
rq_lock(rq, rf);
WARN_ON_ONCE(task_cpu(p) != new_cpu);
activate_task(rq, p, 0);
- check_preempt_curr(rq, p, 0);
+ wakeup_preempt(rq, p, 0);
return rq;
}
@@ -2644,9 +2645,11 @@ static int migration_cpu_stop(void *data)
* it.
*/
WARN_ON_ONCE(!pending->stop_pending);
+ preempt_disable();
task_rq_unlock(rq, p, &rf);
stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
&pending->arg, &pending->stop_work);
+ preempt_enable();
return 0;
}
out:
@@ -2966,12 +2969,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
complete = true;
}
+ preempt_disable();
task_rq_unlock(rq, p, rf);
-
if (push_task) {
stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
p, &rq->push_work);
}
+ preempt_enable();
if (complete)
complete_all(&pending->done);
@@ -3037,12 +3041,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
if (flags & SCA_MIGRATE_ENABLE)
p->migration_flags &= ~MDF_PUSH;
+ preempt_disable();
task_rq_unlock(rq, p, rf);
-
if (!stop_pending) {
stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
&pending->arg, &pending->stop_work);
}
+ preempt_enable();
if (flags & SCA_MIGRATE_ENABLE)
return 0;
@@ -3389,7 +3394,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
deactivate_task(src_rq, p, 0);
set_task_cpu(p, cpu);
activate_task(dst_rq, p, 0);
- check_preempt_curr(dst_rq, p, 0);
+ wakeup_preempt(dst_rq, p, 0);
rq_unpin_lock(dst_rq, &drf);
rq_unpin_lock(src_rq, &srf);
@@ -3413,7 +3418,6 @@ static int migrate_swap_stop(void *data)
{
struct migration_swap_arg *arg = data;
struct rq *src_rq, *dst_rq;
- int ret = -EAGAIN;
if (!cpu_active(arg->src_cpu) || !cpu_active(arg->dst_cpu))
return -EAGAIN;
@@ -3421,33 +3425,25 @@ static int migrate_swap_stop(void *data)
src_rq = cpu_rq(arg->src_cpu);
dst_rq = cpu_rq(arg->dst_cpu);
- double_raw_lock(&arg->src_task->pi_lock,
- &arg->dst_task->pi_lock);
- double_rq_lock(src_rq, dst_rq);
+ guard(double_raw_spinlock)(&arg->src_task->pi_lock, &arg->dst_task->pi_lock);
+ guard(double_rq_lock)(src_rq, dst_rq);
if (task_cpu(arg->dst_task) != arg->dst_cpu)
- goto unlock;
+ return -EAGAIN;
if (task_cpu(arg->src_task) != arg->src_cpu)
- goto unlock;
+ return -EAGAIN;
if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr))
- goto unlock;
+ return -EAGAIN;
if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr))
- goto unlock;
+ return -EAGAIN;
__migrate_swap_task(arg->src_task, arg->dst_cpu);
__migrate_swap_task(arg->dst_task, arg->src_cpu);
- ret = 0;
-
-unlock:
- double_rq_unlock(src_rq, dst_rq);
- raw_spin_unlock(&arg->dst_task->pi_lock);
- raw_spin_unlock(&arg->src_task->pi_lock);
-
- return ret;
+ return 0;
}
/*
@@ -3505,13 +3501,11 @@ out:
*/
void kick_process(struct task_struct *p)
{
- int cpu;
+ guard(preempt)();
+ int cpu = task_cpu(p);
- preempt_disable();
- cpu = task_cpu(p);
if ((cpu != smp_processor_id()) && task_curr(p))
smp_send_reschedule(cpu);
- preempt_enable();
}
EXPORT_SYMBOL_GPL(kick_process);
@@ -3722,14 +3716,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
struct sched_domain *sd;
__schedstat_inc(p->stats.nr_wakeups_remote);
- rcu_read_lock();
+
+ guard(rcu)();
for_each_domain(rq->cpu, sd) {
if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
__schedstat_inc(sd->ttwu_wake_remote);
break;
}
}
- rcu_read_unlock();
}
if (wake_flags & WF_MIGRATED)
@@ -3774,7 +3768,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
}
activate_task(rq, p, en_flags);
- check_preempt_curr(rq, p, wake_flags);
+ wakeup_preempt(rq, p, wake_flags);
ttwu_do_wakeup(p);
@@ -3798,9 +3792,6 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
if (rq->avg_idle > max)
rq->avg_idle = max;
- rq->wake_stamp = jiffies;
- rq->wake_avg_idle = rq->avg_idle / 2;
-
rq->idle_stamp = 0;
}
#endif
@@ -3845,7 +3836,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
* it should preempt the task that is current now.
*/
update_rq_clock(rq);
- check_preempt_curr(rq, p, wake_flags);
+ wakeup_preempt(rq, p, wake_flags);
}
ttwu_do_wakeup(p);
ret = 1;
@@ -3928,21 +3919,13 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags
void wake_up_if_idle(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- struct rq_flags rf;
-
- rcu_read_lock();
-
- if (!is_idle_task(rcu_dereference(rq->curr)))
- goto out;
- rq_lock_irqsave(rq, &rf);
- if (is_idle_task(rq->curr))
- resched_curr(rq);
- /* Else CPU is not idle, do nothing here: */
- rq_unlock_irqrestore(rq, &rf);
-
-out:
- rcu_read_unlock();
+ guard(rcu)();
+ if (is_idle_task(rcu_dereference(rq->curr))) {
+ guard(rq_lock_irqsave)(rq);
+ if (is_idle_task(rq->curr))
+ resched_curr(rq);
+ }
}
bool cpus_share_cache(int this_cpu, int that_cpu)
@@ -3953,6 +3936,18 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
+/*
+ * Whether CPUs are share cache resources, which means LLC on non-cluster
+ * machines and LLC tag or L2 on machines with clusters.
+ */
+bool cpus_share_resources(int this_cpu, int that_cpu)
+{
+ if (this_cpu == that_cpu)
+ return true;
+
+ return per_cpu(sd_share_id, this_cpu) == per_cpu(sd_share_id, that_cpu);
+}
+
static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
{
/*
@@ -4033,13 +4028,17 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
* The caller holds p::pi_lock if p != current or has preemption
* disabled when p == current.
*
- * The rules of PREEMPT_RT saved_state:
+ * The rules of saved_state:
*
* The related locking code always holds p::pi_lock when updating
* p::saved_state, which means the code is fully serialized in both cases.
*
- * The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other
- * bits set. This allows to distinguish all wakeup scenarios.
+ * For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
+ * No other bits set. This allows to distinguish all wakeup scenarios.
+ *
+ * For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
+ * allows us to prevent early wakeup of tasks before they can be run on
+ * asymmetric ISA architectures (eg ARMv9).
*/
static __always_inline
bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
@@ -4053,13 +4052,13 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
*success = !!(match = __task_state_match(p, state));
-#ifdef CONFIG_PREEMPT_RT
/*
* Saved state preserves the task state across blocking on
- * an RT lock. If the state matches, set p::saved_state to
- * TASK_RUNNING, but do not wake the task because it waits
- * for a lock wakeup. Also indicate success because from
- * the regular waker's point of view this has succeeded.
+ * an RT lock or TASK_FREEZABLE tasks. If the state matches,
+ * set p::saved_state to TASK_RUNNING, but do not wake the task
+ * because it waits for a lock wakeup or __thaw_task(). Also
+ * indicate success because from the regular waker's point of
+ * view this has succeeded.
*
* After acquiring the lock the task will restore p::__state
* from p::saved_state which ensures that the regular
@@ -4069,7 +4068,7 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
*/
if (match < 0)
p->saved_state = TASK_RUNNING;
-#endif
+
return match > 0;
}
@@ -4193,13 +4192,11 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
* Return: %true if @p->state changes (an actual wakeup was done),
* %false otherwise.
*/
-static int
-try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
+int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
- unsigned long flags;
+ guard(preempt)();
int cpu, success = 0;
- preempt_disable();
if (p == current) {
/*
* We're waking current, this means 'p->on_rq' and 'task_cpu(p)
@@ -4226,129 +4223,127 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* reordered with p->state check below. This pairs with smp_store_mb()
* in set_current_state() that the waiting thread does.
*/
- raw_spin_lock_irqsave(&p->pi_lock, flags);
- smp_mb__after_spinlock();
- if (!ttwu_state_match(p, state, &success))
- goto unlock;
+ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
+ smp_mb__after_spinlock();
+ if (!ttwu_state_match(p, state, &success))
+ break;
- trace_sched_waking(p);
+ trace_sched_waking(p);
- /*
- * Ensure we load p->on_rq _after_ p->state, otherwise it would
- * be possible to, falsely, observe p->on_rq == 0 and get stuck
- * in smp_cond_load_acquire() below.
- *
- * sched_ttwu_pending() try_to_wake_up()
- * STORE p->on_rq = 1 LOAD p->state
- * UNLOCK rq->lock
- *
- * __schedule() (switch to task 'p')
- * LOCK rq->lock smp_rmb();
- * smp_mb__after_spinlock();
- * UNLOCK rq->lock
- *
- * [task p]
- * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
- *
- * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
- * __schedule(). See the comment for smp_mb__after_spinlock().
- *
- * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
- */
- smp_rmb();
- if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
- goto unlock;
+ /*
+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
+ * in smp_cond_load_acquire() below.
+ *
+ * sched_ttwu_pending() try_to_wake_up()
+ * STORE p->on_rq = 1 LOAD p->state
+ * UNLOCK rq->lock
+ *
+ * __schedule() (switch to task 'p')
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * UNLOCK rq->lock
+ *
+ * [task p]
+ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
+ *
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
+ *
+ * A similar smp_rmb() lives in __task_needs_rq_lock().
+ */
+ smp_rmb();
+ if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
+ break;
#ifdef CONFIG_SMP
- /*
- * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
- * possible to, falsely, observe p->on_cpu == 0.
- *
- * One must be running (->on_cpu == 1) in order to remove oneself
- * from the runqueue.
- *
- * __schedule() (switch to task 'p') try_to_wake_up()
- * STORE p->on_cpu = 1 LOAD p->on_rq
- * UNLOCK rq->lock
- *
- * __schedule() (put 'p' to sleep)
- * LOCK rq->lock smp_rmb();
- * smp_mb__after_spinlock();
- * STORE p->on_rq = 0 LOAD p->on_cpu
- *
- * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
- * __schedule(). See the comment for smp_mb__after_spinlock().
- *
- * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
- * schedule()'s deactivate_task() has 'happened' and p will no longer
- * care about it's own p->state. See the comment in __schedule().
- */
- smp_acquire__after_ctrl_dep();
+ /*
+ * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
+ * possible to, falsely, observe p->on_cpu == 0.
+ *
+ * One must be running (->on_cpu == 1) in order to remove oneself
+ * from the runqueue.
+ *
+ * __schedule() (switch to task 'p') try_to_wake_up()
+ * STORE p->on_cpu = 1 LOAD p->on_rq
+ * UNLOCK rq->lock
+ *
+ * __schedule() (put 'p' to sleep)
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * STORE p->on_rq = 0 LOAD p->on_cpu
+ *
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
+ *
+ * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
+ * schedule()'s deactivate_task() has 'happened' and p will no longer
+ * care about it's own p->state. See the comment in __schedule().
+ */
+ smp_acquire__after_ctrl_dep();
- /*
- * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
- * == 0), which means we need to do an enqueue, change p->state to
- * TASK_WAKING such that we can unlock p->pi_lock before doing the
- * enqueue, such as ttwu_queue_wakelist().
- */
- WRITE_ONCE(p->__state, TASK_WAKING);
+ /*
+ * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
+ * == 0), which means we need to do an enqueue, change p->state to
+ * TASK_WAKING such that we can unlock p->pi_lock before doing the
+ * enqueue, such as ttwu_queue_wakelist().
+ */
+ WRITE_ONCE(p->__state, TASK_WAKING);
- /*
- * If the owning (remote) CPU is still in the middle of schedule() with
- * this task as prev, considering queueing p on the remote CPUs wake_list
- * which potentially sends an IPI instead of spinning on p->on_cpu to
- * let the waker make forward progress. This is safe because IRQs are
- * disabled and the IPI will deliver after on_cpu is cleared.
- *
- * Ensure we load task_cpu(p) after p->on_cpu:
- *
- * set_task_cpu(p, cpu);
- * STORE p->cpu = @cpu
- * __schedule() (switch to task 'p')
- * LOCK rq->lock
- * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu)
- * STORE p->on_cpu = 1 LOAD p->cpu
- *
- * to ensure we observe the correct CPU on which the task is currently
- * scheduling.
- */
- if (smp_load_acquire(&p->on_cpu) &&
- ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
- goto unlock;
+ /*
+ * If the owning (remote) CPU is still in the middle of schedule() with
+ * this task as prev, considering queueing p on the remote CPUs wake_list
+ * which potentially sends an IPI instead of spinning on p->on_cpu to
+ * let the waker make forward progress. This is safe because IRQs are
+ * disabled and the IPI will deliver after on_cpu is cleared.
+ *
+ * Ensure we load task_cpu(p) after p->on_cpu:
+ *
+ * set_task_cpu(p, cpu);
+ * STORE p->cpu = @cpu
+ * __schedule() (switch to task 'p')
+ * LOCK rq->lock
+ * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu)
+ * STORE p->on_cpu = 1 LOAD p->cpu
+ *
+ * to ensure we observe the correct CPU on which the task is currently
+ * scheduling.
+ */
+ if (smp_load_acquire(&p->on_cpu) &&
+ ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
+ break;
- /*
- * If the owning (remote) CPU is still in the middle of schedule() with
- * this task as prev, wait until it's done referencing the task.
- *
- * Pairs with the smp_store_release() in finish_task().
- *
- * This ensures that tasks getting woken will be fully ordered against
- * their previous state and preserve Program Order.
- */
- smp_cond_load_acquire(&p->on_cpu, !VAL);
+ /*
+ * If the owning (remote) CPU is still in the middle of schedule() with
+ * this task as prev, wait until it's done referencing the task.
+ *
+ * Pairs with the smp_store_release() in finish_task().
+ *
+ * This ensures that tasks getting woken will be fully ordered against
+ * their previous state and preserve Program Order.
+ */
+ smp_cond_load_acquire(&p->on_cpu, !VAL);
- cpu = select_task_rq(p, p->wake_cpu, wake_flags | WF_TTWU);
- if (task_cpu(p) != cpu) {
- if (p->in_iowait) {
- delayacct_blkio_end(p);
- atomic_dec(&task_rq(p)->nr_iowait);
- }
+ cpu = select_task_rq(p, p->wake_cpu, wake_flags | WF_TTWU);
+ if (task_cpu(p) != cpu) {
+ if (p->in_iowait) {
+ delayacct_blkio_end(p);
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
- wake_flags |= WF_MIGRATED;
- psi_ttwu_dequeue(p);
- set_task_cpu(p, cpu);
- }
+ wake_flags |= WF_MIGRATED;
+ psi_ttwu_dequeue(p);
+ set_task_cpu(p, cpu);
+ }
#else
- cpu = task_cpu(p);
+ cpu = task_cpu(p);
#endif /* CONFIG_SMP */
- ttwu_queue(p, cpu, wake_flags);
-unlock:
- raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ ttwu_queue(p, cpu, wake_flags);
+ }
out:
if (success)
ttwu_stat(p, task_cpu(p), wake_flags);
- preempt_enable();
return success;
}
@@ -4501,6 +4496,8 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
p->se.vruntime = 0;
+ p->se.vlag = 0;
+ p->se.slice = sysctl_sched_base_slice;
INIT_LIST_HEAD(&p->se.group_node);
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -4870,7 +4867,7 @@ void wake_up_new_task(struct task_struct *p)
activate_task(rq, p, ENQUEUE_NOCLOCK);
trace_sched_wakeup_new(p);
- check_preempt_curr(rq, p, WF_FORK);
+ wakeup_preempt(rq, p, WF_FORK);
#ifdef CONFIG_SMP
if (p->sched_class->task_woken) {
/*
@@ -5373,8 +5370,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
/* switch_mm_cid() requires the memory barriers above. */
switch_mm_cid(rq, prev, next);
- rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
-
prepare_lock_switch(rq, next, rf);
/* Here we just switch the register state and the stack. */
@@ -5496,23 +5491,20 @@ unsigned int nr_iowait(void)
void sched_exec(void)
{
struct task_struct *p = current;
- unsigned long flags;
+ struct migration_arg arg;
int dest_cpu;
- raw_spin_lock_irqsave(&p->pi_lock, flags);
- dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), WF_EXEC);
- if (dest_cpu == smp_processor_id())
- goto unlock;
+ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
+ dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), WF_EXEC);
+ if (dest_cpu == smp_processor_id())
+ return;
- if (likely(cpu_active(dest_cpu))) {
- struct migration_arg arg = { p, dest_cpu };
+ if (unlikely(!cpu_active(dest_cpu)))
+ return;
- raw_spin_unlock_irqrestore(&p->pi_lock, flags);
- stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
- return;
+ arg = (struct migration_arg){ p, dest_cpu };
}
-unlock:
- raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
}
#endif
@@ -5722,9 +5714,6 @@ static void sched_tick_remote(struct work_struct *work)
struct tick_work *twork = container_of(dwork, struct tick_work, work);
int cpu = twork->cpu;
struct rq *rq = cpu_rq(cpu);
- struct task_struct *curr;
- struct rq_flags rf;
- u64 delta;
int os;
/*
@@ -5734,30 +5723,26 @@ static void sched_tick_remote(struct work_struct *work)
* statistics and checks timeslices in a time-independent way, regardless
* of when exactly it is running.
*/
- if (!tick_nohz_tick_stopped_cpu(cpu))
- goto out_requeue;
+ if (tick_nohz_tick_stopped_cpu(cpu)) {
+ guard(rq_lock_irq)(rq);
+ struct task_struct *curr = rq->curr;
- rq_lock_irq(rq, &rf);
- curr = rq->curr;
- if (cpu_is_offline(cpu))
- goto out_unlock;
+ if (cpu_online(cpu)) {
+ update_rq_clock(rq);
- update_rq_clock(rq);
+ if (!is_idle_task(curr)) {
+ /*
+ * Make sure the next tick runs within a
+ * reasonable amount of time.
+ */
+ u64 delta = rq_clock_task(rq) - curr->se.exec_start;
+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ }
+ curr->sched_class->task_tick(rq, curr, 0);
- if (!is_idle_task(curr)) {
- /*
- * Make sure the next tick runs within a reasonable
- * amount of time.
- */
- delta = rq_clock_task(rq) - curr->se.exec_start;
- WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ calc_load_nohz_remote(rq);
+ }
}
- curr->sched_class->task_tick(rq, curr, 0);
-
- calc_load_nohz_remote(rq);
-out_unlock:
- rq_unlock_irq(rq, &rf);
-out_requeue:
/*
* Run the remote tick once per second (1Hz). This arbitrary
@@ -5925,8 +5910,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
print_modules();
if (irqs_disabled())
print_irqtrace_events(prev);
- if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
- && in_atomic_preempt_off()) {
+ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
pr_err("Preemption disabled at:");
print_ip_sym(KERN_ERR, preempt_disable_ip);
}
@@ -6306,19 +6290,19 @@ static bool try_steal_cookie(int this, int that)
unsigned long cookie;
bool success = false;
- local_irq_disable();
- double_rq_lock(dst, src);
+ guard(irq)();
+ guard(double_rq_lock)(dst, src);
cookie = dst->core->core_cookie;
if (!cookie)
- goto unlock;
+ return false;
if (dst->curr != dst->idle)
- goto unlock;
+ return false;
p = sched_core_find(src, cookie);
if (!p)
- goto unlock;
+ return false;
do {
if (p == src->core_pick || p == src->curr)
@@ -6330,9 +6314,10 @@ static bool try_steal_cookie(int this, int that)
if (p->core_occupation > dst->idle->core_occupation)
goto next;
/*
- * sched_core_find() and sched_core_next() will ensure that task @p
- * is not throttled now, we also need to check whether the runqueue
- * of the destination CPU is being throttled.
+ * sched_core_find() and sched_core_next() will ensure
+ * that task @p is not throttled now, we also need to
+ * check whether the runqueue of the destination CPU is
+ * being throttled.
*/
if (sched_task_is_throttled(p, this))
goto next;
@@ -6350,10 +6335,6 @@ next:
p = sched_core_next(p, cookie);
} while (p);
-unlock:
- double_rq_unlock(dst, src);
- local_irq_enable();
-
return success;
}
@@ -6380,8 +6361,9 @@ static void sched_core_balance(struct rq *rq)
struct sched_domain *sd;
int cpu = cpu_of(rq);
- preempt_disable();
- rcu_read_lock();
+ guard(preempt)();
+ guard(rcu)();
+
raw_spin_rq_unlock_irq(rq);
for_each_domain(cpu, sd) {
if (need_resched())
@@ -6391,8 +6373,6 @@ static void sched_core_balance(struct rq *rq)
break;
}
raw_spin_rq_lock_irq(rq);
- rcu_read_unlock();
- preempt_enable();
}
static DEFINE_PER_CPU(struct balance_callback, core_balance_head);
@@ -6411,20 +6391,24 @@ static void queue_core_balance(struct rq *rq)
queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance);
}
+DEFINE_LOCK_GUARD_1(core_lock, int,
+ sched_core_lock(*_T->lock, &_T->flags),
+ sched_core_unlock(*_T->lock, &_T->flags),
+ unsigned long flags)
+
static void sched_core_cpu_starting(unsigned int cpu)
{
const struct cpumask *smt_mask = cpu_smt_mask(cpu);
struct rq *rq = cpu_rq(cpu), *core_rq = NULL;
- unsigned long flags;
int t;
- sched_core_lock(cpu, &flags);
+ guard(core_lock)(&cpu);
WARN_ON_ONCE(rq->core != rq);
/* if we're the first, we'll be our own leader */
if (cpumask_weight(smt_mask) == 1)
- goto unlock;
+ return;
/* find the leader */
for_each_cpu(t, smt_mask) {
@@ -6438,7 +6422,7 @@ static void sched_core_cpu_starting(unsigned int cpu)
}
if (WARN_ON_ONCE(!core_rq)) /* whoopsie */
- goto unlock;
+ return;
/* install and validate core_rq */
for_each_cpu(t, smt_mask) {
@@ -6449,29 +6433,25 @@ static void sched_core_cpu_starting(unsigned int cpu)
WARN_ON_ONCE(rq->core != core_rq);
}
-
-unlock:
- sched_core_unlock(cpu, &flags);
}
static void sched_core_cpu_deactivate(unsigned int cpu)
{
const struct cpumask *smt_mask = cpu_smt_mask(cpu);
struct rq *rq = cpu_rq(cpu), *core_rq = NULL;
- unsigned long flags;
int t;
- sched_core_lock(cpu, &flags);
+ guard(core_lock)(&cpu);
/* if we're the last man standing, nothing to do */
if (cpumask_weight(smt_mask) == 1) {
WARN_ON_ONCE(rq->core != rq);
- goto unlock;
+ return;
}
/* if we're not the leader, nothing to do */
if (rq->core != rq)
- goto unlock;
+ return;
/* find a new leader */
for_each_cpu(t, smt_mask) {
@@ -6482,7 +6462,7 @@ static void sched_core_cpu_deactivate(unsigned int cpu)
}
if (WARN_ON_ONCE(!core_rq)) /* impossible */
- goto unlock;
+ return;
/* copy the shared state to the new leader */
core_rq->core_task_seq = rq->core_task_seq;
@@ -6504,9 +6484,6 @@ static void sched_core_cpu_deactivate(unsigned int cpu)
rq = cpu_rq(t);
rq->core = core_rq;
}
-
-unlock:
- sched_core_unlock(cpu, &flags);
}
static inline void sched_core_cpu_dying(unsigned int cpu)
@@ -6630,6 +6607,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
/* Promote REQ to ACT */
rq->clock_update_flags <<= 1;
update_rq_clock(rq);
+ rq->clock_update_flags = RQCF_UPDATED;
switch_count = &prev->nivcsw;
@@ -6709,8 +6687,6 @@ static void __sched notrace __schedule(unsigned int sched_mode)
/* Also unlocks the rq: */
rq = context_switch(rq, prev, next, &rf);
} else {
- rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
-
rq_unpin_lock(rq, &rf);
__balance_callbacks(rq);
raw_spin_rq_unlock_irq(rq);
@@ -6735,22 +6711,24 @@ void __noreturn do_task_dead(void)
static inline void sched_submit_work(struct task_struct *tsk)
{
+ static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG);
unsigned int task_flags;
- if (task_is_running(tsk))
- return;
+ /*
+ * Establish LD_WAIT_CONFIG context to ensure none of the code called
+ * will use a blocking primitive -- which would lead to recursion.
+ */
+ lock_map_acquire_try(&sched_map);
task_flags = tsk->flags;
/*
* If a worker goes to sleep, notify and ask workqueue whether it
* wants to wake up a task to maintain concurrency.
*/
- if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
- if (task_flags & PF_WQ_WORKER)
- wq_worker_sleeping(tsk);
- else
- io_wq_worker_sleeping(tsk);
- }
+ if (task_flags & PF_WQ_WORKER)
+ wq_worker_sleeping(tsk);
+ else if (task_flags & PF_IO_WORKER)
+ io_wq_worker_sleeping(tsk);
/*
* spinlock and rwlock must not flush block requests. This will
@@ -6764,6 +6742,8 @@ static inline void sched_submit_work(struct task_struct *tsk)
* make sure to submit it to avoid deadlocks.
*/
blk_flush_plug(tsk->plug, true);
+
+ lock_map_release(&sched_map);
}
static void sched_update_worker(struct task_struct *tsk)
@@ -6776,16 +6756,26 @@ static void sched_update_worker(struct task_struct *tsk)
}
}
-asmlinkage __visible void __sched schedule(void)
+static __always_inline void __schedule_loop(unsigned int sched_mode)
{
- struct task_struct *tsk = current;
-
- sched_submit_work(tsk);
do {
preempt_disable();
- __schedule(SM_NONE);
+ __schedule(sched_mode);
sched_preempt_enable_no_resched();
} while (need_resched());
+}
+
+asmlinkage __visible void __sched schedule(void)
+{
+ struct task_struct *tsk = current;
+
+#ifdef CONFIG_RT_MUTEXES
+ lockdep_assert(!tsk->sched_rt_mutex);
+#endif
+
+ if (!task_is_running(tsk))
+ sched_submit_work(tsk);
+ __schedule_loop(SM_NONE);
sched_update_worker(tsk);
}
EXPORT_SYMBOL(schedule);
@@ -6849,11 +6839,7 @@ void __sched schedule_preempt_disabled(void)
#ifdef CONFIG_PREEMPT_RT
void __sched notrace schedule_rtlock(void)
{
- do {
- preempt_disable();
- __schedule(SM_RTLOCK_WAIT);
- sched_preempt_enable_no_resched();
- } while (need_resched());
+ __schedule_loop(SM_RTLOCK_WAIT);
}
NOKPROBE_SYMBOL(schedule_rtlock);
#endif
@@ -7030,7 +7016,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
void *key)
{
- WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
return try_to_wake_up(curr->private, mode, wake_flags);
}
EXPORT_SYMBOL(default_wake_function);
@@ -7049,6 +7035,32 @@ static void __setscheduler_prio(struct task_struct *p, int prio)
#ifdef CONFIG_RT_MUTEXES
+/*
+ * Would be more useful with typeof()/auto_type but they don't mix with
+ * bit-fields. Since it's a local thing, use int. Keep the generic sounding
+ * name such that if someone were to implement this function we get to compare
+ * notes.
+ */
+#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; })
+
+void rt_mutex_pre_schedule(void)
+{
+ lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1));
+ sched_submit_work(current);
+}
+
+void rt_mutex_schedule(void)
+{
+ lockdep_assert(current->sched_rt_mutex);
+ __schedule_loop(SM_NONE);
+}
+
+void rt_mutex_post_schedule(void)
+{
+ sched_update_worker(current);
+ lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0));
+}
+
static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
{
if (pi_task)
@@ -7202,9 +7214,8 @@ static inline int rt_effective_prio(struct task_struct *p, int prio)
void set_user_nice(struct task_struct *p, long nice)
{
bool queued, running;
- int old_prio;
- struct rq_flags rf;
struct rq *rq;
+ int old_prio;
if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
return;
@@ -7212,7 +7223,9 @@ void set_user_nice(struct task_struct *p, long nice)
* We have to be careful, if called from sys_setpriority(),
* the task might be in the middle of scheduling on another CPU.
*/
- rq = task_rq_lock(p, &rf);
+ CLASS(task_rq_lock, rq_guard)(p);
+ rq = rq_guard.rq;
+
update_rq_clock(rq);
/*
@@ -7223,8 +7236,9 @@ void set_user_nice(struct task_struct *p, long nice)
*/
if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->static_prio = NICE_TO_PRIO(nice);
- goto out_unlock;
+ return;
}
+
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
@@ -7247,9 +7261,6 @@ void set_user_nice(struct task_struct *p, long nice)
* lowered its priority, then reschedule its CPU:
*/
p->sched_class->prio_changed(rq, p, old_prio);
-
-out_unlock:
- task_rq_unlock(rq, p, &rf);
}
EXPORT_SYMBOL(set_user_nice);
@@ -7383,6 +7394,19 @@ struct task_struct *idle_task(int cpu)
return cpu_rq(cpu)->idle;
}
+#ifdef CONFIG_SCHED_CORE
+int sched_core_idle_cpu(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ if (sched_core_enabled(rq) && rq->curr == rq->idle)
+ return 1;
+
+ return idle_cpu(cpu);
+}
+
+#endif
+
#ifdef CONFIG_SMP
/*
* This function computes an effective utilization for the given CPU, to be
@@ -7509,6 +7533,21 @@ static struct task_struct *find_process_by_pid(pid_t pid)
return pid ? find_task_by_vpid(pid) : current;
}
+static struct task_struct *find_get_task(pid_t pid)
+{
+ struct task_struct *p;
+ guard(rcu)();
+
+ p = find_process_by_pid(pid);
+ if (likely(p))
+ get_task_struct(p);
+
+ return p;
+}
+
+DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
+ find_get_task(pid), pid_t pid)
+
/*
* sched_setparam() passes in -1 for its policy, to let the functions
* it calls know not to change it.
@@ -7546,14 +7585,11 @@ static void __setscheduler_params(struct task_struct *p,
static bool check_same_owner(struct task_struct *p)
{
const struct cred *cred = current_cred(), *pcred;
- bool match;
+ guard(rcu)();
- rcu_read_lock();
pcred = __task_cred(p);
- match = (uid_eq(cred->euid, pcred->euid) ||
- uid_eq(cred->euid, pcred->uid));
- rcu_read_unlock();
- return match;
+ return (uid_eq(cred->euid, pcred->euid) ||
+ uid_eq(cred->euid, pcred->uid));
}
/*
@@ -7965,27 +8001,17 @@ static int
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
struct sched_param lparam;
- struct task_struct *p;
- int retval;
if (!param || pid < 0)
return -EINVAL;
if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
return -EFAULT;
- rcu_read_lock();
- retval = -ESRCH;
- p = find_process_by_pid(pid);
- if (likely(p))
- get_task_struct(p);
- rcu_read_unlock();
-
- if (likely(p)) {
- retval = sched_setscheduler(p, policy, &lparam);
- put_task_struct(p);
- }
+ CLASS(find_get_task, p)(pid);
+ if (!p)
+ return -ESRCH;
- return retval;
+ return sched_setscheduler(p, policy, &lparam);
}
/*
@@ -8081,7 +8107,6 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
unsigned int, flags)
{
struct sched_attr attr;
- struct task_struct *p;
int retval;
if (!uattr || pid < 0 || flags)
@@ -8096,21 +8121,14 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY)
attr.sched_policy = SETPARAM_POLICY;
- rcu_read_lock();
- retval = -ESRCH;
- p = find_process_by_pid(pid);
- if (likely(p))
- get_task_struct(p);
- rcu_read_unlock();
+ CLASS(find_get_task, p)(pid);
+ if (!p)
+ return -ESRCH;
- if (likely(p)) {
- if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
- get_params(p, &attr);
- retval = sched_setattr(p, &attr);
- put_task_struct(p);
- }
+ if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
+ get_params(p, &attr);
- return retval;
+ return sched_setattr(p, &attr);
}
/**
@@ -8128,16 +8146,17 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
if (pid < 0)
return -EINVAL;
- retval = -ESRCH;
- rcu_read_lock();
+ guard(rcu)();
p = find_process_by_pid(pid);
- if (p) {
- retval = security_task_getscheduler(p);
- if (!retval)
- retval = p->policy
- | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
+ if (!p)
+ return -ESRCH;
+
+ retval = security_task_getscheduler(p);
+ if (!retval) {
+ retval = p->policy;
+ if (p->sched_reset_on_fork)
+ retval |= SCHED_RESET_ON_FORK;
}
- rcu_read_unlock();
return retval;
}
@@ -8158,30 +8177,23 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
if (!param || pid < 0)
return -EINVAL;
- rcu_read_lock();
- p = find_process_by_pid(pid);
- retval = -ESRCH;
- if (!p)
- goto out_unlock;
+ scoped_guard (rcu) {
+ p = find_process_by_pid(pid);
+ if (!p)
+ return -ESRCH;
- retval = security_task_getscheduler(p);
- if (retval)
- goto out_unlock;
+ retval = security_task_getscheduler(p);
+ if (retval)
+ return retval;
- if (task_has_rt_policy(p))
- lp.sched_priority = p->rt_priority;
- rcu_read_unlock();
+ if (task_has_rt_policy(p))
+ lp.sched_priority = p->rt_priority;
+ }
/*
* This one might sleep, we cannot do it with a spinlock held ...
*/
- retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
-
- return retval;
-
-out_unlock:
- rcu_read_unlock();
- return retval;
+ return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
}
/*
@@ -8241,46 +8253,38 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
usize < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;
- rcu_read_lock();
- p = find_process_by_pid(pid);
- retval = -ESRCH;
- if (!p)
- goto out_unlock;
+ scoped_guard (rcu) {
+ p = find_process_by_pid(pid);
+ if (!p)
+ return -ESRCH;
- retval = security_task_getscheduler(p);
- if (retval)
- goto out_unlock;
+ retval = security_task_getscheduler(p);
+ if (retval)
+ return retval;
- kattr.sched_policy = p->policy;
- if (p->sched_reset_on_fork)
- kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
- get_params(p, &kattr);
- kattr.sched_flags &= SCHED_FLAG_ALL;
+ kattr.sched_policy = p->policy;
+ if (p->sched_reset_on_fork)
+ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ get_params(p, &kattr);
+ kattr.sched_flags &= SCHED_FLAG_ALL;
#ifdef CONFIG_UCLAMP_TASK
- /*
- * This could race with another potential updater, but this is fine
- * because it'll correctly read the old or the new value. We don't need
- * to guarantee who wins the race as long as it doesn't return garbage.
- */
- kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
- kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+ /*
+ * This could race with another potential updater, but this is fine
+ * because it'll correctly read the old or the new value. We don't need
+ * to guarantee who wins the race as long as it doesn't return garbage.
+ */
+ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
#endif
-
- rcu_read_unlock();
+ }
return sched_attr_copy_to_user(uattr, &kattr, usize);
-
-out_unlock:
- rcu_read_unlock();
- return retval;
}
#ifdef CONFIG_SMP
int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
{
- int ret = 0;
-
/*
* If the task isn't a deadline task or admission control is
* disabled then we don't care about affinity changes.
@@ -8294,11 +8298,11 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
* tasks allowed to run on all the CPUs in the task's
* root_domain.
*/
- rcu_read_lock();
+ guard(rcu)();
if (!cpumask_subset(task_rq(p)->rd->span, mask))
- ret = -EBUSY;
- rcu_read_unlock();
- return ret;
+ return -EBUSY;
+
+ return 0;
}
#endif
@@ -8368,39 +8372,24 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
struct affinity_context ac;
struct cpumask *user_mask;
- struct task_struct *p;
int retval;
- rcu_read_lock();
-
- p = find_process_by_pid(pid);
- if (!p) {
- rcu_read_unlock();
+ CLASS(find_get_task, p)(pid);
+ if (!p)
return -ESRCH;
- }
- /* Prevent p going away */
- get_task_struct(p);
- rcu_read_unlock();
-
- if (p->flags & PF_NO_SETAFFINITY) {
- retval = -EINVAL;
- goto out_put_task;
- }
+ if (p->flags & PF_NO_SETAFFINITY)
+ return -EINVAL;
if (!check_same_owner(p)) {
- rcu_read_lock();
- if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
- rcu_read_unlock();
- retval = -EPERM;
- goto out_put_task;
- }
- rcu_read_unlock();
+ guard(rcu)();
+ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
+ return -EPERM;
}
retval = security_task_setscheduler(p);
if (retval)
- goto out_put_task;
+ return retval;
/*
* With non-SMP configs, user_cpus_ptr/user_mask isn't used and
@@ -8410,8 +8399,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
if (user_mask) {
cpumask_copy(user_mask, in_mask);
} else if (IS_ENABLED(CONFIG_SMP)) {
- retval = -ENOMEM;
- goto out_put_task;
+ return -ENOMEM;
}
ac = (struct affinity_context){
@@ -8423,8 +8411,6 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
retval = __sched_setaffinity(p, &ac);
kfree(ac.user_mask);
-out_put_task:
- put_task_struct(p);
return retval;
}
@@ -8466,28 +8452,21 @@ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
struct task_struct *p;
- unsigned long flags;
int retval;
- rcu_read_lock();
-
- retval = -ESRCH;
+ guard(rcu)();
p = find_process_by_pid(pid);
if (!p)
- goto out_unlock;
+ return -ESRCH;
retval = security_task_getscheduler(p);
if (retval)
- goto out_unlock;
+ return retval;
- raw_spin_lock_irqsave(&p->pi_lock, flags);
+ guard(raw_spinlock_irqsave)(&p->pi_lock);
cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
- raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-out_unlock:
- rcu_read_unlock();
-
- return retval;
+ return 0;
}
/**
@@ -8934,55 +8913,46 @@ int __sched yield_to(struct task_struct *p, bool preempt)
{
struct task_struct *curr = current;
struct rq *rq, *p_rq;
- unsigned long flags;
int yielded = 0;
- local_irq_save(flags);
- rq = this_rq();
+ scoped_guard (irqsave) {
+ rq = this_rq();
again:
- p_rq = task_rq(p);
- /*
- * If we're the only runnable task on the rq and target rq also
- * has only one task, there's absolutely no point in yielding.
- */
- if (rq->nr_running == 1 && p_rq->nr_running == 1) {
- yielded = -ESRCH;
- goto out_irq;
- }
+ p_rq = task_rq(p);
+ /*
+ * If we're the only runnable task on the rq and target rq also
+ * has only one task, there's absolutely no point in yielding.
+ */
+ if (rq->nr_running == 1 && p_rq->nr_running == 1)
+ return -ESRCH;
- double_rq_lock(rq, p_rq);
- if (task_rq(p) != p_rq) {
- double_rq_unlock(rq, p_rq);
- goto again;
- }
+ guard(double_rq_lock)(rq, p_rq);
+ if (task_rq(p) != p_rq)
+ goto again;
- if (!curr->sched_class->yield_to_task)
- goto out_unlock;
+ if (!curr->sched_class->yield_to_task)
+ return 0;
- if (curr->sched_class != p->sched_class)
- goto out_unlock;
+ if (curr->sched_class != p->sched_class)
+ return 0;
- if (task_on_cpu(p_rq, p) || !task_is_running(p))
- goto out_unlock;
+ if (task_on_cpu(p_rq, p) || !task_is_running(p))
+ return 0;
- yielded = curr->sched_class->yield_to_task(rq, p);
- if (yielded) {
- schedstat_inc(rq->yld_count);
- /*
- * Make p's CPU reschedule; pick_next_entity takes care of
- * fairness.
- */
- if (preempt && rq != p_rq)
- resched_curr(p_rq);
+ yielded = curr->sched_class->yield_to_task(rq, p);
+ if (yielded) {
+ schedstat_inc(rq->yld_count);
+ /*
+ * Make p's CPU reschedule; pick_next_entity
+ * takes care of fairness.
+ */
+ if (preempt && rq != p_rq)
+ resched_curr(p_rq);
+ }
}
-out_unlock:
- double_rq_unlock(rq, p_rq);
-out_irq:
- local_irq_restore(flags);
-
- if (yielded > 0)
+ if (yielded)
schedule();
return yielded;
@@ -9085,38 +9055,30 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
{
- struct task_struct *p;
- unsigned int time_slice;
- struct rq_flags rf;
- struct rq *rq;
+ unsigned int time_slice = 0;
int retval;
if (pid < 0)
return -EINVAL;
- retval = -ESRCH;
- rcu_read_lock();
- p = find_process_by_pid(pid);
- if (!p)
- goto out_unlock;
+ scoped_guard (rcu) {
+ struct task_struct *p = find_process_by_pid(pid);
+ if (!p)
+ return -ESRCH;
- retval = security_task_getscheduler(p);
- if (retval)
- goto out_unlock;
+ retval = security_task_getscheduler(p);
+ if (retval)
+ return retval;
- rq = task_rq_lock(p, &rf);
- time_slice = 0;
- if (p->sched_class->get_rr_interval)
- time_slice = p->sched_class->get_rr_interval(rq, p);
- task_rq_unlock(rq, p, &rf);
+ scoped_guard (task_rq_lock, p) {
+ struct rq *rq = scope.rq;
+ if (p->sched_class->get_rr_interval)
+ time_slice = p->sched_class->get_rr_interval(rq, p);
+ }
+ }
- rcu_read_unlock();
jiffies_to_timespec64(time_slice, t);
return 0;
-
-out_unlock:
- rcu_read_unlock();
- return retval;
}
/**
@@ -9175,9 +9137,9 @@ void sched_show_task(struct task_struct *p)
if (pid_alive(p))
ppid = task_pid_nr(rcu_dereference(p->real_parent));
rcu_read_unlock();
- pr_cont(" stack:%-5lu pid:%-5d ppid:%-6d flags:0x%08lx\n",
- free, task_pid_nr(p), ppid,
- read_task_thread_flags(p));
+ pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
+ free, task_pid_nr(p), task_tgid_nr(p),
+ ppid, read_task_thread_flags(p));
print_worker_info(KERN_INFO, p);
print_stop_info(KERN_INFO, p);
@@ -9271,7 +9233,7 @@ void __init init_idle(struct task_struct *idle, int cpu)
* PF_KTHREAD should already be set at this point; regardless, make it
* look like a proper per-CPU kthread.
*/
- idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY;
+ idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY;
kthread_set_per_cpu(idle, cpu);
#ifdef CONFIG_SMP
@@ -9507,9 +9469,11 @@ static void balance_push(struct rq *rq)
* Temporarily drop rq->lock such that we can wake-up the stop task.
* Both preemption and IRQs are still disabled.
*/
+ preempt_disable();
raw_spin_rq_unlock(rq);
stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
this_cpu_ptr(&push_work));
+ preempt_enable();
/*
* At this point need_resched() is true and we'll take the loop in
* schedule(). The next pick is obviously going to be the stop task
@@ -9905,7 +9869,7 @@ struct task_group root_task_group;
LIST_HEAD(task_groups);
/* Cacheline aligned slab cache for task_group */
-static struct kmem_cache *task_group_cache __read_mostly;
+static struct kmem_cache *task_group_cache __ro_after_init;
#endif
void __init sched_init(void)
@@ -9940,7 +9904,7 @@ void __init sched_init(void)
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
- init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
+ init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -10015,7 +9979,7 @@ void __init sched_init(void)
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
- rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
+ rq->cpu_capacity = SCHED_CAPACITY_SCALE;
rq->balance_callback = &balance_push_callback;
rq->active_balance = 0;
rq->next_balance = jiffies;
@@ -10024,8 +9988,6 @@ void __init sched_init(void)
rq->online = 0;
rq->idle_stamp = 0;
rq->avg_idle = 2*sysctl_sched_migration_cost;
- rq->wake_stamp = jiffies;
- rq->wake_avg_idle = rq->avg_idle;
rq->max_idle_balance_cost = sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->cfs_tasks);
@@ -10291,9 +10253,9 @@ void normalize_rt_tasks(void)
#endif /* CONFIG_MAGIC_SYSRQ */
-#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
+#if defined(CONFIG_KGDB_KDB)
/*
- * These functions are only useful for the IA64 MCA handling, or kdb.
+ * These functions are only useful for kdb.
*
* They can only be called when the whole system has been
* stopped - every CPU needs to be quiescent, and no scheduling
@@ -10315,30 +10277,7 @@ struct task_struct *curr_task(int cpu)
return cpu_curr(cpu);
}
-#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */
-
-#ifdef CONFIG_IA64
-/**
- * ia64_set_curr_task - set the current task for a given CPU.
- * @cpu: the processor in question.
- * @p: the task pointer to set.
- *
- * Description: This function must only be used when non-maskable interrupts
- * are serviced on a separate stack. It allows the architecture to switch the
- * notion of the current task on a CPU in a non-blocking manner. This function
- * must be called with all CPU's synchronized, and interrupts disabled, the
- * and caller must save the original value of the current task (see
- * curr_task() above) and restore that value before reenabling interrupts and
- * re-starting the system.
- *
- * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
- */
-void ia64_set_curr_task(int cpu, struct task_struct *p)
-{
- cpu_curr(cpu) = p;
-}
-
-#endif
+#endif /* defined(CONFIG_KGDB_KDB) */
#ifdef CONFIG_CGROUP_SCHED
/* task_group_lock serializes the addition/removal of task groups */
@@ -10500,17 +10439,18 @@ void sched_move_task(struct task_struct *tsk)
int queued, running, queue_flags =
DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
struct task_group *group;
- struct rq_flags rf;
struct rq *rq;
- rq = task_rq_lock(tsk, &rf);
+ CLASS(task_rq_lock, rq_guard)(tsk);
+ rq = rq_guard.rq;
+
/*
* Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous
* group changes.
*/
group = sched_get_task_group(tsk);
if (group == tsk->sched_task_group)
- goto unlock;
+ return;
update_rq_clock(rq);
@@ -10535,9 +10475,6 @@ void sched_move_task(struct task_struct *tsk)
*/
resched_curr(rq);
}
-
-unlock:
- task_rq_unlock(rq, tsk, &rf);
}
static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
@@ -10574,11 +10511,9 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
#ifdef CONFIG_UCLAMP_TASK_GROUP
/* Propagate the effective uclamp value for the new group */
- mutex_lock(&uclamp_mutex);
- rcu_read_lock();
+ guard(mutex)(&uclamp_mutex);
+ guard(rcu)();
cpu_util_update_eff(css);
- rcu_read_unlock();
- mutex_unlock(&uclamp_mutex);
#endif
return 0;
@@ -10729,8 +10664,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
static_branch_enable(&sched_uclamp_used);
- mutex_lock(&uclamp_mutex);
- rcu_read_lock();
+ guard(mutex)(&uclamp_mutex);
+ guard(rcu)();
tg = css_tg(of_css(of));
if (tg->uclamp_req[clamp_id].value != req.util)
@@ -10745,9 +10680,6 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
/* Update effective clamps to track the most restrictive value */
cpu_util_update_eff(of_css(of));
- rcu_read_unlock();
- mutex_unlock(&uclamp_mutex);
-
return nbytes;
}
@@ -10773,10 +10705,10 @@ static inline void cpu_uclamp_print(struct seq_file *sf,
u64 percent;
u32 rem;
- rcu_read_lock();
- tg = css_tg(seq_css(sf));
- util_clamp = tg->uclamp_req[clamp_id].value;
- rcu_read_unlock();
+ scoped_guard (rcu) {
+ tg = css_tg(seq_css(sf));
+ util_clamp = tg->uclamp_req[clamp_id].value;
+ }
if (util_clamp == SCHED_CAPACITY_SCALE) {
seq_puts(sf, "max\n");
@@ -10867,11 +10799,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
* Prevent race between setting of cfs_rq->runtime_enabled and
* unthrottle_offline_cfs_rqs().
*/
- cpus_read_lock();
- mutex_lock(&cfs_constraints_mutex);
+ guard(cpus_read_lock)();
+ guard(mutex)(&cfs_constraints_mutex);
+
ret = __cfs_schedulable(tg, period, quota);
if (ret)
- goto out_unlock;
+ return ret;
runtime_enabled = quota != RUNTIME_INF;
runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
@@ -10881,39 +10814,38 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
*/
if (runtime_enabled && !runtime_was_enabled)
cfs_bandwidth_usage_inc();
- raw_spin_lock_irq(&cfs_b->lock);
- cfs_b->period = ns_to_ktime(period);
- cfs_b->quota = quota;
- cfs_b->burst = burst;
- __refill_cfs_bandwidth_runtime(cfs_b);
+ scoped_guard (raw_spinlock_irq, &cfs_b->lock) {
+ cfs_b->period = ns_to_ktime(period);
+ cfs_b->quota = quota;
+ cfs_b->burst = burst;
- /* Restart the period timer (if active) to handle new period expiry: */
- if (runtime_enabled)
- start_cfs_bandwidth(cfs_b);
+ __refill_cfs_bandwidth_runtime(cfs_b);
- raw_spin_unlock_irq(&cfs_b->lock);
+ /*
+ * Restart the period timer (if active) to handle new
+ * period expiry:
+ */
+ if (runtime_enabled)
+ start_cfs_bandwidth(cfs_b);
+ }
for_each_online_cpu(i) {
struct cfs_rq *cfs_rq = tg->cfs_rq[i];
struct rq *rq = cfs_rq->rq;
- struct rq_flags rf;
- rq_lock_irq(rq, &rf);
+ guard(rq_lock_irq)(rq);
cfs_rq->runtime_enabled = runtime_enabled;
cfs_rq->runtime_remaining = 0;
if (cfs_rq->throttled)
unthrottle_cfs_rq(cfs_rq);
- rq_unlock_irq(rq, &rf);
}
+
if (runtime_was_enabled && !runtime_enabled)
cfs_bandwidth_usage_dec();
-out_unlock:
- mutex_unlock(&cfs_constraints_mutex);
- cpus_read_unlock();
- return ret;
+ return 0;
}
static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
@@ -11074,11 +11006,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
/*
* Ensure max(child_quota) <= parent_quota. On cgroup2,
- * always take the min. On cgroup1, only inherit when no
- * limit is set:
+ * always take the non-RUNTIME_INF min. On cgroup1, only
+ * inherit when no limit is set. In both cases this is used
+ * by the scheduler to determine if a given CFS task has a
+ * bandwidth constraint at some higher level.
*/
if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
- quota = min(quota, parent_quota);
+ if (quota == RUNTIME_INF)
+ quota = parent_quota;
+ else if (parent_quota != RUNTIME_INF)
+ quota = min(quota, parent_quota);
} else {
if (quota == RUNTIME_INF)
quota = parent_quota;
@@ -11093,7 +11030,6 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
{
- int ret;
struct cfs_schedulable_data data = {
.tg = tg,
.period = period,
@@ -11105,11 +11041,8 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
do_div(data.quota, NSEC_PER_USEC);
}
- rcu_read_lock();
- ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
- rcu_read_unlock();
-
- return ret;
+ guard(rcu)();
+ return walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
}
static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
@@ -11139,6 +11072,27 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
return 0;
}
+
+static u64 throttled_time_self(struct task_group *tg)
+{
+ int i;
+ u64 total = 0;
+
+ for_each_possible_cpu(i) {
+ total += READ_ONCE(tg->cfs_rq[i]->throttled_clock_self_time);
+ }
+
+ return total;
+}
+
+static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
+{
+ struct task_group *tg = css_tg(seq_css(sf));
+
+ seq_printf(sf, "throttled_time %llu\n", throttled_time_self(tg));
+
+ return 0;
+}
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -11215,6 +11169,10 @@ static struct cftype cpu_legacy_files[] = {
.name = "stat",
.seq_show = cpu_cfs_stat_show,
},
+ {
+ .name = "stat.local",
+ .seq_show = cpu_cfs_local_stat_show,
+ },
#endif
#ifdef CONFIG_RT_GROUP_SCHED
{
@@ -11271,6 +11229,24 @@ static int cpu_extra_stat_show(struct seq_file *sf,
return 0;
}
+static int cpu_local_stat_show(struct seq_file *sf,
+ struct cgroup_subsys_state *css)
+{
+#ifdef CONFIG_CFS_BANDWIDTH
+ {
+ struct task_group *tg = css_tg(css);
+ u64 throttled_self_usec;
+
+ throttled_self_usec = throttled_time_self(tg);
+ do_div(throttled_self_usec, NSEC_PER_USEC);
+
+ seq_printf(sf, "throttled_usec %llu\n",
+ throttled_self_usec);
+ }
+#endif
+ return 0;
+}
+
#ifdef CONFIG_FAIR_GROUP_SCHED
static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
@@ -11449,6 +11425,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
.css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
.css_extra_stat_show = cpu_extra_stat_show,
+ .css_local_stat_show = cpu_local_stat_show,
#ifdef CONFIG_RT_GROUP_SCHED
.can_attach = cpu_cgroup_can_attach,
#endif
@@ -11670,14 +11647,12 @@ int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
* are not the last task to be migrated from this cpu for this mm, so
* there is no need to move src_cid to the destination cpu.
*/
- rcu_read_lock();
+ guard(rcu)();
src_task = rcu_dereference(src_rq->curr);
if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
- rcu_read_unlock();
t->last_mm_cid = -1;
return -1;
}
- rcu_read_unlock();
return src_cid;
}
@@ -11721,18 +11696,17 @@ int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
* the lazy-put flag, this task will be responsible for transitioning
* from lazy-put flag set to MM_CID_UNSET.
*/
- rcu_read_lock();
- src_task = rcu_dereference(src_rq->curr);
- if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
- rcu_read_unlock();
- /*
- * We observed an active task for this mm, there is therefore
- * no point in moving this cid to the destination cpu.
- */
- t->last_mm_cid = -1;
- return -1;
+ scoped_guard (rcu) {
+ src_task = rcu_dereference(src_rq->curr);
+ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
+ /*
+ * We observed an active task for this mm, there is therefore
+ * no point in moving this cid to the destination cpu.
+ */
+ t->last_mm_cid = -1;
+ return -1;
+ }
}
- rcu_read_unlock();
/*
* The src_cid is unused, so it can be unset.
@@ -11805,7 +11779,6 @@ static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_
{
struct rq *rq = cpu_rq(cpu);
struct task_struct *t;
- unsigned long flags;
int cid, lazy_cid;
cid = READ_ONCE(pcpu_cid->cid);
@@ -11840,23 +11813,21 @@ static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_
* the lazy-put flag, that task will be responsible for transitioning
* from lazy-put flag set to MM_CID_UNSET.
*/
- rcu_read_lock();
- t = rcu_dereference(rq->curr);
- if (READ_ONCE(t->mm_cid_active) && t->mm == mm) {
- rcu_read_unlock();
- return;
+ scoped_guard (rcu) {
+ t = rcu_dereference(rq->curr);
+ if (READ_ONCE(t->mm_cid_active) && t->mm == mm)
+ return;
}
- rcu_read_unlock();
/*
* The cid is unused, so it can be unset.
* Disable interrupts to keep the window of cid ownership without rq
* lock small.
*/
- local_irq_save(flags);
- if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
- __mm_cid_put(mm, cid);
- local_irq_restore(flags);
+ scoped_guard (irqsave) {
+ if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
+ __mm_cid_put(mm, cid);
+ }
}
static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
@@ -11878,14 +11849,13 @@ static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
* snapshot associated with this cid if an active task using the mm is
* observed on this rq.
*/
- rcu_read_lock();
- curr = rcu_dereference(rq->curr);
- if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
- WRITE_ONCE(pcpu_cid->time, rq_clock);
- rcu_read_unlock();
- return;
+ scoped_guard (rcu) {
+ curr = rcu_dereference(rq->curr);
+ if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
+ WRITE_ONCE(pcpu_cid->time, rq_clock);
+ return;
+ }
}
- rcu_read_unlock();
if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS)
return;
@@ -11979,7 +11949,6 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
void sched_mm_cid_exit_signals(struct task_struct *t)
{
struct mm_struct *mm = t->mm;
- struct rq_flags rf;
struct rq *rq;
if (!mm)
@@ -11987,7 +11956,7 @@ void sched_mm_cid_exit_signals(struct task_struct *t)
preempt_disable();
rq = this_rq();
- rq_lock_irqsave(rq, &rf);
+ guard(rq_lock_irqsave)(rq);
preempt_enable_no_resched(); /* holding spinlock */
WRITE_ONCE(t->mm_cid_active, 0);
/*
@@ -11997,13 +11966,11 @@ void sched_mm_cid_exit_signals(struct task_struct *t)
smp_mb();
mm_cid_put(mm);
t->last_mm_cid = t->mm_cid = -1;
- rq_unlock_irqrestore(rq, &rf);
}
void sched_mm_cid_before_execve(struct task_struct *t)
{
struct mm_struct *mm = t->mm;
- struct rq_flags rf;
struct rq *rq;
if (!mm)
@@ -12011,7 +11978,7 @@ void sched_mm_cid_before_execve(struct task_struct *t)
preempt_disable();
rq = this_rq();
- rq_lock_irqsave(rq, &rf);
+ guard(rq_lock_irqsave)(rq);
preempt_enable_no_resched(); /* holding spinlock */
WRITE_ONCE(t->mm_cid_active, 0);
/*
@@ -12021,13 +11988,11 @@ void sched_mm_cid_before_execve(struct task_struct *t)
smp_mb();
mm_cid_put(mm);
t->last_mm_cid = t->mm_cid = -1;
- rq_unlock_irqrestore(rq, &rf);
}
void sched_mm_cid_after_execve(struct task_struct *t)
{
struct mm_struct *mm = t->mm;
- struct rq_flags rf;
struct rq *rq;
if (!mm)
@@ -12035,16 +12000,16 @@ void sched_mm_cid_after_execve(struct task_struct *t)
preempt_disable();
rq = this_rq();
- rq_lock_irqsave(rq, &rf);
- preempt_enable_no_resched(); /* holding spinlock */
- WRITE_ONCE(t->mm_cid_active, 1);
- /*
- * Store t->mm_cid_active before loading per-mm/cpu cid.
- * Matches barrier in sched_mm_cid_remote_clear_old().
- */
- smp_mb();
- t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
- rq_unlock_irqrestore(rq, &rf);
+ scoped_guard (rq_lock_irqsave, rq) {
+ preempt_enable_no_resched(); /* holding spinlock */
+ WRITE_ONCE(t->mm_cid_active, 1);
+ /*
+ * Store t->mm_cid_active before loading per-mm/cpu cid.
+ * Matches barrier in sched_mm_cid_remote_clear_old().
+ */
+ smp_mb();
+ t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
+ }
rseq_set_notify_resume(t);
}
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 57c92d751bcd..95baa12a1029 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -131,7 +131,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
if (!dl_task_fits_capacity(p, cpu)) {
cpumask_clear_cpu(cpu, later_mask);
- cap = capacity_orig_of(cpu);
+ cap = arch_scale_cpu_capacity(cpu);
if (cap > max_cap ||
(cpu == task_cpu(p) && cap == max_cap)) {
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4492608b7d7f..5888176354e2 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
* Except when the rq is capped by uclamp_max.
*/
if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
- sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
+ sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
+ !sg_policy->need_freq_update) {
next_f = sg_policy->next_freq;
/* Restore cached freq as next_freq has changed */
@@ -555,6 +556,31 @@ static const struct kobj_type sugov_tunables_ktype = {
/********************** cpufreq governor interface *********************/
+#ifdef CONFIG_ENERGY_MODEL
+static void rebuild_sd_workfn(struct work_struct *work)
+{
+ rebuild_sched_domains_energy();
+}
+
+static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
+
+/*
+ * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
+ * on governor changes to make sure the scheduler knows about it.
+ */
+static void sugov_eas_rebuild_sd(void)
+{
+ /*
+ * When called from the cpufreq_register_driver() path, the
+ * cpu_hotplug_lock is already held, so use a work item to
+ * avoid nested locking in rebuild_sched_domains().
+ */
+ schedule_work(&rebuild_sd_work);
+}
+#else
+static inline void sugov_eas_rebuild_sd(void) { };
+#endif
+
struct cpufreq_governor schedutil_gov;
static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
@@ -709,6 +735,8 @@ static int sugov_init(struct cpufreq_policy *policy)
if (ret)
goto fail;
+ sugov_eas_rebuild_sd();
+
out:
mutex_unlock(&global_tunables_lock);
return 0;
@@ -750,6 +778,8 @@ static void sugov_exit(struct cpufreq_policy *policy)
sugov_kthread_stop(sg_policy);
sugov_policy_free(sg_policy);
cpufreq_disable_fast_switch(policy);
+
+ sugov_eas_rebuild_sd();
}
static int sugov_start(struct cpufreq_policy *policy)
@@ -767,14 +797,6 @@ static int sugov_start(struct cpufreq_policy *policy)
sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
- for_each_cpu(cpu, policy->cpus) {
- struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
-
- memset(sg_cpu, 0, sizeof(*sg_cpu));
- sg_cpu->cpu = cpu;
- sg_cpu->sg_policy = sg_policy;
- }
-
if (policy_is_shared(policy))
uu = sugov_update_shared;
else if (policy->fast_switch_enabled && cpufreq_driver_has_adjust_perf())
@@ -785,6 +807,9 @@ static int sugov_start(struct cpufreq_policy *policy)
for_each_cpu(cpu, policy->cpus) {
struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
+ memset(sg_cpu, 0, sizeof(*sg_cpu));
+ sg_cpu->cpu = cpu;
+ sg_cpu->sg_policy = sg_policy;
cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, uu);
}
return 0;
@@ -838,29 +863,3 @@ struct cpufreq_governor *cpufreq_default_governor(void)
#endif
cpufreq_governor_init(schedutil_gov);
-
-#ifdef CONFIG_ENERGY_MODEL
-static void rebuild_sd_workfn(struct work_struct *work)
-{
- rebuild_sched_domains_energy();
-}
-static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
-
-/*
- * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
- * on governor changes to make sure the scheduler knows about it.
- */
-void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
- struct cpufreq_governor *old_gov)
-{
- if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) {
- /*
- * When called from the cpufreq_register_driver() path, the
- * cpu_hotplug_lock is already held, so use a work item to
- * avoid nested locking in rebuild_sched_domains().
- */
- schedule_work(&rebuild_sd_work);
- }
-
-}
-#endif
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index a286e726eb4b..42c40cfdf836 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -101,6 +101,7 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_mask, vec->mask);
+ cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
/*
* We have to ensure that we have at least one bit
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 58b542bf2893..b28114478b82 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -132,7 +132,7 @@ static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
int i;
for_each_cpu_and(i, mask, cpu_active_mask)
- cap += capacity_orig_of(i);
+ cap += arch_scale_cpu_capacity(i);
return cap;
}
@@ -144,7 +144,7 @@ static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
static inline unsigned long dl_bw_capacity(int i)
{
if (!sched_asym_cpucap_active() &&
- capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
+ arch_scale_cpu_capacity(i) == SCHED_CAPACITY_SCALE) {
return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
} else {
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
@@ -509,7 +509,6 @@ void init_dl_rq(struct dl_rq *dl_rq)
/* zero means no -deadline tasks */
dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
- dl_rq->dl_nr_migratory = 0;
dl_rq->overloaded = 0;
dl_rq->pushable_dl_tasks_root = RB_ROOT_CACHED;
#else
@@ -553,39 +552,6 @@ static inline void dl_clear_overload(struct rq *rq)
cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
}
-static void update_dl_migration(struct dl_rq *dl_rq)
-{
- if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
- if (!dl_rq->overloaded) {
- dl_set_overload(rq_of_dl_rq(dl_rq));
- dl_rq->overloaded = 1;
- }
- } else if (dl_rq->overloaded) {
- dl_clear_overload(rq_of_dl_rq(dl_rq));
- dl_rq->overloaded = 0;
- }
-}
-
-static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
-{
- struct task_struct *p = dl_task_of(dl_se);
-
- if (p->nr_cpus_allowed > 1)
- dl_rq->dl_nr_migratory++;
-
- update_dl_migration(dl_rq);
-}
-
-static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
-{
- struct task_struct *p = dl_task_of(dl_se);
-
- if (p->nr_cpus_allowed > 1)
- dl_rq->dl_nr_migratory--;
-
- update_dl_migration(dl_rq);
-}
-
#define __node_2_pdl(node) \
rb_entry((node), struct task_struct, pushable_dl_tasks)
@@ -594,6 +560,11 @@ static inline bool __pushable_less(struct rb_node *a, const struct rb_node *b)
return dl_entity_preempt(&__node_2_pdl(a)->dl, &__node_2_pdl(b)->dl);
}
+static inline int has_pushable_dl_tasks(struct rq *rq)
+{
+ return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root.rb_root);
+}
+
/*
* The list of pushable -deadline task is not a plist, like in
* sched_rt.c, it is an rb-tree with tasks ordered by deadline.
@@ -609,6 +580,11 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
__pushable_less);
if (leftmost)
rq->dl.earliest_dl.next = p->dl.deadline;
+
+ if (!rq->dl.overloaded) {
+ dl_set_overload(rq);
+ rq->dl.overloaded = 1;
+ }
}
static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
@@ -625,11 +601,11 @@ static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
dl_rq->earliest_dl.next = __node_2_pdl(leftmost)->dl.deadline;
RB_CLEAR_NODE(&p->pushable_dl_tasks);
-}
-static inline int has_pushable_dl_tasks(struct rq *rq)
-{
- return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root.rb_root);
+ if (!has_pushable_dl_tasks(rq) && rq->dl.overloaded) {
+ dl_clear_overload(rq);
+ rq->dl.overloaded = 0;
+ }
}
static int push_dl_task(struct rq *rq);
@@ -763,7 +739,7 @@ static inline void deadline_queue_pull_task(struct rq *rq)
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
-static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, int flags);
+static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags);
static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
struct rq *rq)
@@ -1175,7 +1151,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
if (dl_task(rq->curr))
- check_preempt_curr_dl(rq, p, 0);
+ wakeup_preempt_dl(rq, p, 0);
else
resched_curr(rq);
@@ -1504,7 +1480,6 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
add_nr_running(rq_of_dl_rq(dl_rq), 1);
inc_dl_deadline(dl_rq, deadline);
- inc_dl_migration(dl_se, dl_rq);
}
static inline
@@ -1518,7 +1493,6 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
sub_nr_running(rq_of_dl_rq(dl_rq), 1);
dec_dl_deadline(dl_rq, dl_se->deadline);
- dec_dl_migration(dl_se, dl_rq);
}
static inline bool __dl_less(struct rb_node *a, const struct rb_node *b)
@@ -1939,7 +1913,7 @@ static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
* Only called when both the current and waking task are -deadline
* tasks.
*/
-static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
int flags)
{
if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
@@ -2291,9 +2265,6 @@ static int push_dl_task(struct rq *rq)
struct rq *later_rq;
int ret = 0;
- if (!rq->dl.overloaded)
- return 0;
-
next_task = pick_next_pushable_dl_task(rq);
if (!next_task)
return 0;
@@ -2449,9 +2420,11 @@ skip:
double_unlock_balance(this_rq, src_rq);
if (push_task) {
+ preempt_disable();
raw_spin_rq_unlock(this_rq);
stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
push_task, &src_rq->push_work);
+ preempt_enable();
raw_spin_rq_lock(this_rq);
}
}
@@ -2652,7 +2625,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
deadline_queue_push_tasks(rq);
#endif
if (dl_task(rq->curr))
- check_preempt_curr_dl(rq, p, 0);
+ wakeup_preempt_dl(rq, p, 0);
else
resched_curr(rq);
} else {
@@ -2721,7 +2694,7 @@ DEFINE_SCHED_CLASS(dl) = {
.dequeue_task = dequeue_task_dl,
.yield_task = yield_task_dl,
- .check_preempt_curr = check_preempt_curr_dl,
+ .wakeup_preempt = wakeup_preempt_dl,
.pick_next_task = pick_next_task_dl,
.put_prev_task = put_prev_task_dl,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 066ff1c8ae4e..4580a450700e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -8,7 +8,7 @@
*/
/*
- * This allows printing both to /proc/sched_debug and
+ * This allows printing both to /sys/kernel/debug/sched/debug and
* to the console
*/
#define SEQ_printf(m, x...) \
@@ -347,10 +347,7 @@ static __init int sched_init_debug(void)
debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops);
#endif
- debugfs_create_u32("latency_ns", 0644, debugfs_sched, &sysctl_sched_latency);
- debugfs_create_u32("min_granularity_ns", 0644, debugfs_sched, &sysctl_sched_min_granularity);
- debugfs_create_u32("idle_min_granularity_ns", 0644, debugfs_sched, &sysctl_sched_idle_min_granularity);
- debugfs_create_u32("wakeup_granularity_ns", 0644, debugfs_sched, &sysctl_sched_wakeup_granularity);
+ debugfs_create_u32("base_slice_ns", 0644, debugfs_sched, &sysctl_sched_base_slice);
debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once);
@@ -427,6 +424,7 @@ static void register_sd(struct sched_domain *sd, struct dentry *parent)
#undef SDM
debugfs_create_file("flags", 0444, parent, &sd->flags, &sd_flags_fops);
+ debugfs_create_file("groups_flags", 0444, parent, &sd->groups->flags, &sd_flags_fops);
}
void update_sched_domain_debugfs(void)
@@ -581,9 +579,13 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
else
SEQ_printf(m, " %c", task_state_to_char(p));
- SEQ_printf(m, " %15s %5d %9Ld.%06ld %9Ld %5d ",
+ SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld.%06ld %9Ld %5d ",
p->comm, task_pid_nr(p),
SPLIT_NS(p->se.vruntime),
+ entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N',
+ SPLIT_NS(p->se.deadline),
+ SPLIT_NS(p->se.slice),
+ SPLIT_NS(p->se.sum_exec_runtime),
(long long)(p->nvcsw + p->nivcsw),
p->prio);
@@ -626,10 +628,9 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
- s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
- spread, rq0_min_vruntime, spread0;
+ s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, spread;
+ struct sched_entity *last, *first;
struct rq *rq = cpu_rq(cpu);
- struct sched_entity *last;
unsigned long flags;
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -643,26 +644,25 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
SPLIT_NS(cfs_rq->exec_clock));
raw_spin_rq_lock_irqsave(rq, flags);
- if (rb_first_cached(&cfs_rq->tasks_timeline))
- MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
+ first = __pick_first_entity(cfs_rq);
+ if (first)
+ left_vruntime = first->vruntime;
last = __pick_last_entity(cfs_rq);
if (last)
- max_vruntime = last->vruntime;
+ right_vruntime = last->vruntime;
min_vruntime = cfs_rq->min_vruntime;
- rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
raw_spin_rq_unlock_irqrestore(rq, flags);
- SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime",
- SPLIT_NS(MIN_vruntime));
+
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime",
+ SPLIT_NS(left_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
SPLIT_NS(min_vruntime));
- SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "max_vruntime",
- SPLIT_NS(max_vruntime));
- spread = max_vruntime - MIN_vruntime;
- SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread",
- SPLIT_NS(spread));
- spread0 = min_vruntime - rq0_min_vruntime;
- SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0",
- SPLIT_NS(spread0));
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "avg_vruntime",
+ SPLIT_NS(avg_vruntime(cfs_rq)));
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "right_vruntime",
+ SPLIT_NS(right_vruntime));
+ spread = right_vruntime - left_vruntime;
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread));
SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over",
cfs_rq->nr_spread_over);
SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
@@ -724,9 +724,6 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
PU(rt_nr_running);
-#ifdef CONFIG_SMP
- PU(rt_nr_migratory);
-#endif
P(rt_throttled);
PN(rt_time);
PN(rt_runtime);
@@ -748,7 +745,6 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
PU(dl_nr_running);
#ifdef CONFIG_SMP
- PU(dl_nr_migratory);
dl_bw = &cpu_rq(cpu)->rd->dl_bw;
#else
dl_bw = &dl_rq->dl_bw;
@@ -863,11 +859,7 @@ static void sched_debug_header(struct seq_file *m)
SEQ_printf(m, " .%-40s: %Ld\n", #x, (long long)(x))
#define PN(x) \
SEQ_printf(m, " .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
- PN(sysctl_sched_latency);
- PN(sysctl_sched_min_granularity);
- PN(sysctl_sched_idle_min_granularity);
- PN(sysctl_sched_wakeup_granularity);
- P(sysctl_sched_child_runs_first);
+ PN(sysctl_sched_base_slice);
P(sysctl_sched_features);
#undef PN
#undef P
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b3e25be58e2b..d7a3c63a2171 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -47,32 +47,15 @@
#include <linux/psi.h>
#include <linux/ratelimit.h>
#include <linux/task_work.h>
+#include <linux/rbtree_augmented.h>
#include <asm/switch_to.h>
-#include <linux/sched/cond_resched.h>
-
#include "sched.h"
#include "stats.h"
#include "autogroup.h"
/*
- * Targeted preemption latency for CPU-bound tasks:
- *
- * NOTE: this latency value is not the same as the concept of
- * 'timeslice length' - timeslices in CFS are of variable length
- * and have no persistent notion like in traditional, time-slice
- * based scheduling concepts.
- *
- * (to see the precise effective timeslice length of your workload,
- * run vmstat and monitor the context-switches (cs) field)
- *
- * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
- */
-unsigned int sysctl_sched_latency = 6000000ULL;
-static unsigned int normalized_sysctl_sched_latency = 6000000ULL;
-
-/*
* The initial- and re-scaling of tunables is configurable
*
* Options are:
@@ -90,39 +73,8 @@ unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
*
* (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
-unsigned int sysctl_sched_min_granularity = 750000ULL;
-static unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
-
-/*
- * Minimal preemption granularity for CPU-bound SCHED_IDLE tasks.
- * Applies only when SCHED_IDLE tasks compete with normal tasks.
- *
- * (default: 0.75 msec)
- */
-unsigned int sysctl_sched_idle_min_granularity = 750000ULL;
-
-/*
- * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
- */
-static unsigned int sched_nr_latency = 8;
-
-/*
- * After fork, child runs first. If set to 0 (default) then
- * parent will (try to) run first.
- */
-unsigned int sysctl_sched_child_runs_first __read_mostly;
-
-/*
- * SCHED_OTHER wake-up granularity.
- *
- * This option delays the preemption effects of decoupled workloads
- * and reduces their over-scheduling. Synchronous workloads will still
- * have immediate wakeup/sleep latencies.
- *
- * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
- */
-unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
-static unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
+unsigned int sysctl_sched_base_slice = 750000ULL;
+static unsigned int normalized_sysctl_sched_base_slice = 750000ULL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
@@ -185,13 +137,6 @@ static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
#ifdef CONFIG_SYSCTL
static struct ctl_table sched_fair_sysctls[] = {
- {
- .procname = "sched_child_runs_first",
- .data = &sysctl_sched_child_runs_first,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
#ifdef CONFIG_CFS_BANDWIDTH
{
.procname = "sched_cfs_bandwidth_slice_us",
@@ -277,9 +222,7 @@ static void update_sysctl(void)
#define SET_SYSCTL(name) \
(sysctl_##name = (factor) * normalized_sysctl_##name)
- SET_SYSCTL(sched_min_granularity);
- SET_SYSCTL(sched_latency);
- SET_SYSCTL(sched_wakeup_granularity);
+ SET_SYSCTL(sched_base_slice);
#undef SET_SYSCTL
}
@@ -347,6 +290,16 @@ static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight
return mul_u64_u32_shr(delta_exec, fact, shift);
}
+/*
+ * delta /= w
+ */
+static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
+{
+ if (unlikely(se->load.weight != NICE_0_LOAD))
+ delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
+
+ return delta;
+}
const struct sched_class fair_sched_class;
@@ -601,13 +554,206 @@ static inline bool entity_before(const struct sched_entity *a,
return (s64)(a->vruntime - b->vruntime) < 0;
}
+static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ return (s64)(se->vruntime - cfs_rq->min_vruntime);
+}
+
#define __node_2_se(node) \
rb_entry((node), struct sched_entity, run_node)
+/*
+ * Compute virtual time from the per-task service numbers:
+ *
+ * Fair schedulers conserve lag:
+ *
+ * \Sum lag_i = 0
+ *
+ * Where lag_i is given by:
+ *
+ * lag_i = S - s_i = w_i * (V - v_i)
+ *
+ * Where S is the ideal service time and V is it's virtual time counterpart.
+ * Therefore:
+ *
+ * \Sum lag_i = 0
+ * \Sum w_i * (V - v_i) = 0
+ * \Sum w_i * V - w_i * v_i = 0
+ *
+ * From which we can solve an expression for V in v_i (which we have in
+ * se->vruntime):
+ *
+ * \Sum v_i * w_i \Sum v_i * w_i
+ * V = -------------- = --------------
+ * \Sum w_i W
+ *
+ * Specifically, this is the weighted average of all entity virtual runtimes.
+ *
+ * [[ NOTE: this is only equal to the ideal scheduler under the condition
+ * that join/leave operations happen at lag_i = 0, otherwise the
+ * virtual time has non-continguous motion equivalent to:
+ *
+ * V +-= lag_i / W
+ *
+ * Also see the comment in place_entity() that deals with this. ]]
+ *
+ * However, since v_i is u64, and the multiplcation could easily overflow
+ * transform it into a relative form that uses smaller quantities:
+ *
+ * Substitute: v_i == (v_i - v0) + v0
+ *
+ * \Sum ((v_i - v0) + v0) * w_i \Sum (v_i - v0) * w_i
+ * V = ---------------------------- = --------------------- + v0
+ * W W
+ *
+ * Which we track using:
+ *
+ * v0 := cfs_rq->min_vruntime
+ * \Sum (v_i - v0) * w_i := cfs_rq->avg_vruntime
+ * \Sum w_i := cfs_rq->avg_load
+ *
+ * Since min_vruntime is a monotonic increasing variable that closely tracks
+ * the per-task service, these deltas: (v_i - v), will be in the order of the
+ * maximal (virtual) lag induced in the system due to quantisation.
+ *
+ * Also, we use scale_load_down() to reduce the size.
+ *
+ * As measured, the max (key * weight) value was ~44 bits for a kernel build.
+ */
+static void
+avg_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ unsigned long weight = scale_load_down(se->load.weight);
+ s64 key = entity_key(cfs_rq, se);
+
+ cfs_rq->avg_vruntime += key * weight;
+ cfs_rq->avg_load += weight;
+}
+
+static void
+avg_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ unsigned long weight = scale_load_down(se->load.weight);
+ s64 key = entity_key(cfs_rq, se);
+
+ cfs_rq->avg_vruntime -= key * weight;
+ cfs_rq->avg_load -= weight;
+}
+
+static inline
+void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
+{
+ /*
+ * v' = v + d ==> avg_vruntime' = avg_runtime - d*avg_load
+ */
+ cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta;
+}
+
+/*
+ * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
+ * For this to be so, the result of this function must have a left bias.
+ */
+u64 avg_vruntime(struct cfs_rq *cfs_rq)
+{
+ struct sched_entity *curr = cfs_rq->curr;
+ s64 avg = cfs_rq->avg_vruntime;
+ long load = cfs_rq->avg_load;
+
+ if (curr && curr->on_rq) {
+ unsigned long weight = scale_load_down(curr->load.weight);
+
+ avg += entity_key(cfs_rq, curr) * weight;
+ load += weight;
+ }
+
+ if (load) {
+ /* sign flips effective floor / ceil */
+ if (avg < 0)
+ avg -= (load - 1);
+ avg = div_s64(avg, load);
+ }
+
+ return cfs_rq->min_vruntime + avg;
+}
+
+/*
+ * lag_i = S - s_i = w_i * (V - v_i)
+ *
+ * However, since V is approximated by the weighted average of all entities it
+ * is possible -- by addition/removal/reweight to the tree -- to move V around
+ * and end up with a larger lag than we started with.
+ *
+ * Limit this to either double the slice length with a minimum of TICK_NSEC
+ * since that is the timing granularity.
+ *
+ * EEVDF gives the following limit for a steady state system:
+ *
+ * -r_max < lag < max(r_max, q)
+ *
+ * XXX could add max_slice to the augmented data to track this.
+ */
+static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ s64 lag, limit;
+
+ SCHED_WARN_ON(!se->on_rq);
+ lag = avg_vruntime(cfs_rq) - se->vruntime;
+
+ limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+ se->vlag = clamp(lag, -limit, limit);
+}
+
+/*
+ * Entity is eligible once it received less service than it ought to have,
+ * eg. lag >= 0.
+ *
+ * lag_i = S - s_i = w_i*(V - v_i)
+ *
+ * lag_i >= 0 -> V >= v_i
+ *
+ * \Sum (v_i - v)*w_i
+ * V = ------------------ + v
+ * \Sum w_i
+ *
+ * lag_i >= 0 -> \Sum (v_i - v)*w_i >= (v_i - v)*(\Sum w_i)
+ *
+ * Note: using 'avg_vruntime() > se->vruntime' is inacurate due
+ * to the loss in precision caused by the division.
+ */
+int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ struct sched_entity *curr = cfs_rq->curr;
+ s64 avg = cfs_rq->avg_vruntime;
+ long load = cfs_rq->avg_load;
+
+ if (curr && curr->on_rq) {
+ unsigned long weight = scale_load_down(curr->load.weight);
+
+ avg += entity_key(cfs_rq, curr) * weight;
+ load += weight;
+ }
+
+ return avg >= entity_key(cfs_rq, se) * load;
+}
+
+static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
+{
+ u64 min_vruntime = cfs_rq->min_vruntime;
+ /*
+ * open coded max_vruntime() to allow updating avg_vruntime
+ */
+ s64 delta = (s64)(vruntime - min_vruntime);
+ if (delta > 0) {
+ avg_vruntime_update(cfs_rq, delta);
+ min_vruntime = vruntime;
+ }
+ return min_vruntime;
+}
+
static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
struct sched_entity *curr = cfs_rq->curr;
- struct rb_node *leftmost = rb_first_cached(&cfs_rq->tasks_timeline);
u64 vruntime = cfs_rq->min_vruntime;
@@ -618,9 +764,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
curr = NULL;
}
- if (leftmost) { /* non-empty tree */
- struct sched_entity *se = __node_2_se(leftmost);
-
+ if (se) {
if (!curr)
vruntime = se->vruntime;
else
@@ -629,7 +773,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
/* ensure we never gain time by being placed backwards. */
u64_u32_store(cfs_rq->min_vruntime,
- max_vruntime(cfs_rq->min_vruntime, vruntime));
+ __update_min_vruntime(cfs_rq, vruntime));
}
static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
@@ -637,17 +781,51 @@ static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
return entity_before(__node_2_se(a), __node_2_se(b));
}
+#define deadline_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
+
+static inline void __update_min_deadline(struct sched_entity *se, struct rb_node *node)
+{
+ if (node) {
+ struct sched_entity *rse = __node_2_se(node);
+ if (deadline_gt(min_deadline, se, rse))
+ se->min_deadline = rse->min_deadline;
+ }
+}
+
+/*
+ * se->min_deadline = min(se->deadline, left->min_deadline, right->min_deadline)
+ */
+static inline bool min_deadline_update(struct sched_entity *se, bool exit)
+{
+ u64 old_min_deadline = se->min_deadline;
+ struct rb_node *node = &se->run_node;
+
+ se->min_deadline = se->deadline;
+ __update_min_deadline(se, node->rb_right);
+ __update_min_deadline(se, node->rb_left);
+
+ return se->min_deadline == old_min_deadline;
+}
+
+RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
+ run_node, min_deadline, min_deadline_update);
+
/*
* Enqueue an entity into the rb-tree:
*/
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- rb_add_cached(&se->run_node, &cfs_rq->tasks_timeline, __entity_less);
+ avg_vruntime_add(cfs_rq, se);
+ se->min_deadline = se->deadline;
+ rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
+ __entity_less, &min_deadline_cb);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- rb_erase_cached(&se->run_node, &cfs_rq->tasks_timeline);
+ rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
+ &min_deadline_cb);
+ avg_vruntime_sub(cfs_rq, se);
}
struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
@@ -660,14 +838,132 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
return __node_2_se(left);
}
-static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+/*
+ * Earliest Eligible Virtual Deadline First
+ *
+ * In order to provide latency guarantees for different request sizes
+ * EEVDF selects the best runnable task from two criteria:
+ *
+ * 1) the task must be eligible (must be owed service)
+ *
+ * 2) from those tasks that meet 1), we select the one
+ * with the earliest virtual deadline.
+ *
+ * We can do this in O(log n) time due to an augmented RB-tree. The
+ * tree keeps the entries sorted on service, but also functions as a
+ * heap based on the deadline by keeping:
+ *
+ * se->min_deadline = min(se->deadline, se->{left,right}->min_deadline)
+ *
+ * Which allows an EDF like search on (sub)trees.
+ */
+static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
+{
+ struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
+ struct sched_entity *curr = cfs_rq->curr;
+ struct sched_entity *best = NULL;
+ struct sched_entity *best_left = NULL;
+
+ if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
+ curr = NULL;
+ best = curr;
+
+ /*
+ * Once selected, run a task until it either becomes non-eligible or
+ * until it gets a new slice. See the HACK in set_next_entity().
+ */
+ if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
+ return curr;
+
+ while (node) {
+ struct sched_entity *se = __node_2_se(node);
+
+ /*
+ * If this entity is not eligible, try the left subtree.
+ */
+ if (!entity_eligible(cfs_rq, se)) {
+ node = node->rb_left;
+ continue;
+ }
+
+ /*
+ * Now we heap search eligible trees for the best (min_)deadline
+ */
+ if (!best || deadline_gt(deadline, best, se))
+ best = se;
+
+ /*
+ * Every se in a left branch is eligible, keep track of the
+ * branch with the best min_deadline
+ */
+ if (node->rb_left) {
+ struct sched_entity *left = __node_2_se(node->rb_left);
+
+ if (!best_left || deadline_gt(min_deadline, best_left, left))
+ best_left = left;
+
+ /*
+ * min_deadline is in the left branch. rb_left and all
+ * descendants are eligible, so immediately switch to the second
+ * loop.
+ */
+ if (left->min_deadline == se->min_deadline)
+ break;
+ }
+
+ /* min_deadline is at this node, no need to look right */
+ if (se->deadline == se->min_deadline)
+ break;
+
+ /* else min_deadline is in the right branch. */
+ node = node->rb_right;
+ }
+
+ /*
+ * We ran into an eligible node which is itself the best.
+ * (Or nr_running == 0 and both are NULL)
+ */
+ if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0)
+ return best;
+
+ /*
+ * Now best_left and all of its children are eligible, and we are just
+ * looking for deadline == min_deadline
+ */
+ node = &best_left->run_node;
+ while (node) {
+ struct sched_entity *se = __node_2_se(node);
+
+ /* min_deadline is the current node */
+ if (se->deadline == se->min_deadline)
+ return se;
+
+ /* min_deadline is in the left branch */
+ if (node->rb_left &&
+ __node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
+ node = node->rb_left;
+ continue;
+ }
+
+ /* else min_deadline is in the right branch */
+ node = node->rb_right;
+ }
+ return NULL;
+}
+
+static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
{
- struct rb_node *next = rb_next(&se->run_node);
+ struct sched_entity *se = __pick_eevdf(cfs_rq);
- if (!next)
- return NULL;
+ if (!se) {
+ struct sched_entity *left = __pick_first_entity(cfs_rq);
+ if (left) {
+ pr_err("EEVDF scheduling fail, picking leftmost\n");
+ return left;
+ }
+ }
- return __node_2_se(next);
+ return se;
}
#ifdef CONFIG_SCHED_DEBUG
@@ -684,109 +980,51 @@ struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
/**************************************************************
* Scheduling class statistics methods:
*/
-
+#ifdef CONFIG_SMP
int sched_update_scaling(void)
{
unsigned int factor = get_update_sysctl_factor();
- sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
- sysctl_sched_min_granularity);
-
#define WRT_SYSCTL(name) \
(normalized_sysctl_##name = sysctl_##name / (factor))
- WRT_SYSCTL(sched_min_granularity);
- WRT_SYSCTL(sched_latency);
- WRT_SYSCTL(sched_wakeup_granularity);
+ WRT_SYSCTL(sched_base_slice);
#undef WRT_SYSCTL
return 0;
}
#endif
+#endif
-/*
- * delta /= w
- */
-static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
-{
- if (unlikely(se->load.weight != NICE_0_LOAD))
- delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
-
- return delta;
-}
-
-/*
- * The idea is to set a period in which each task runs once.
- *
- * When there are too many tasks (sched_nr_latency) we have to stretch
- * this period because otherwise the slices get too small.
- *
- * p = (nr <= nl) ? l : l*nr/nl
- */
-static u64 __sched_period(unsigned long nr_running)
-{
- if (unlikely(nr_running > sched_nr_latency))
- return nr_running * sysctl_sched_min_granularity;
- else
- return sysctl_sched_latency;
-}
-
-static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq);
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se);
/*
- * We calculate the wall-time slice from the period by taking a part
- * proportional to the weight.
- *
- * s = p*P[w/rw]
+ * XXX: strictly: vd_i += N*r_i/w_i such that: vd_i > ve_i
+ * this is probably good enough.
*/
-static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- unsigned int nr_running = cfs_rq->nr_running;
- struct sched_entity *init_se = se;
- unsigned int min_gran;
- u64 slice;
-
- if (sched_feat(ALT_PERIOD))
- nr_running = rq_of(cfs_rq)->cfs.h_nr_running;
-
- slice = __sched_period(nr_running + !se->on_rq);
-
- for_each_sched_entity(se) {
- struct load_weight *load;
- struct load_weight lw;
- struct cfs_rq *qcfs_rq;
-
- qcfs_rq = cfs_rq_of(se);
- load = &qcfs_rq->load;
-
- if (unlikely(!se->on_rq)) {
- lw = qcfs_rq->load;
+ if ((s64)(se->vruntime - se->deadline) < 0)
+ return;
- update_load_add(&lw, se->load.weight);
- load = &lw;
- }
- slice = __calc_delta(slice, se->load.weight, load);
- }
+ /*
+ * For EEVDF the virtual time slope is determined by w_i (iow.
+ * nice) while the request time r_i is determined by
+ * sysctl_sched_base_slice.
+ */
+ se->slice = sysctl_sched_base_slice;
- if (sched_feat(BASE_SLICE)) {
- if (se_is_idle(init_se) && !sched_idle_cfs_rq(cfs_rq))
- min_gran = sysctl_sched_idle_min_granularity;
- else
- min_gran = sysctl_sched_min_granularity;
+ /*
+ * EEVDF: vd_i = ve_i + r_i / w_i
+ */
+ se->deadline = se->vruntime + calc_delta_fair(se->slice, se);
- slice = max_t(u64, slice, min_gran);
+ /*
+ * The task has consumed its request, reschedule.
+ */
+ if (cfs_rq->nr_running > 1) {
+ resched_curr(rq_of(cfs_rq));
+ clear_buddies(cfs_rq, se);
}
-
- return slice;
-}
-
-/*
- * We calculate the vruntime slice of a to-be-inserted task.
- *
- * vs = s/w
- */
-static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- return calc_delta_fair(sched_slice(cfs_rq, se), se);
}
#include "pelt.h"
@@ -921,6 +1159,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
schedstat_add(cfs_rq->exec_clock, delta_exec);
curr->vruntime += calc_delta_fair(delta_exec, curr);
+ update_deadline(cfs_rq, curr);
update_min_vruntime(cfs_rq);
if (entity_is_task(curr)) {
@@ -1520,12 +1759,12 @@ static bool pgdat_free_space_enough(struct pglist_data *pgdat)
* The smaller the hint page fault latency, the higher the possibility
* for the page to be hot.
*/
-static int numa_hint_fault_latency(struct page *page)
+static int numa_hint_fault_latency(struct folio *folio)
{
int last_time, time;
time = jiffies_to_msecs(jiffies);
- last_time = xchg_page_access_time(page, time);
+ last_time = folio_xchg_access_time(folio, time);
return (time - last_time) & PAGE_ACCESS_TIME_MASK;
}
@@ -1582,7 +1821,7 @@ static void numa_promotion_adjust_threshold(struct pglist_data *pgdat,
}
}
-bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
+bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
int src_nid, int dst_cpu)
{
struct numa_group *ng = deref_curr_numa_group(p);
@@ -1612,16 +1851,16 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
numa_promotion_adjust_threshold(pgdat, rate_limit, def_th);
th = pgdat->nbp_threshold ? : def_th;
- latency = numa_hint_fault_latency(page);
+ latency = numa_hint_fault_latency(folio);
if (latency >= th)
return false;
return !numa_promotion_rate_limit(pgdat, rate_limit,
- thp_nr_pages(page));
+ folio_nr_pages(folio));
}
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
- last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+ last_cpupid = folio_xchg_last_cpupid(folio, this_cpupid);
if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
!node_is_toptier(src_nid) && !cpupid_valid(last_cpupid))
@@ -2645,19 +2884,7 @@ static void task_numa_placement(struct task_struct *p)
}
/* Cannot migrate task to CPU-less node */
- if (max_nid != NUMA_NO_NODE && !node_state(max_nid, N_CPU)) {
- int near_nid = max_nid;
- int distance, near_distance = INT_MAX;
-
- for_each_node_state(nid, N_CPU) {
- distance = node_distance(max_nid, nid);
- if (distance < near_distance) {
- near_nid = nid;
- near_distance = distance;
- }
- }
- max_nid = near_nid;
- }
+ max_nid = numa_nearest_node(max_nid, N_CPU);
if (ng) {
numa_group_count_active_nodes(ng);
@@ -2928,7 +3155,7 @@ static void reset_ptenuma_scan(struct task_struct *p)
p->mm->numa_scan_offset = 0;
}
-static bool vma_is_accessed(struct vm_area_struct *vma)
+static bool vma_is_accessed(struct mm_struct *mm, struct vm_area_struct *vma)
{
unsigned long pids;
/*
@@ -2940,8 +3167,20 @@ static bool vma_is_accessed(struct vm_area_struct *vma)
if (READ_ONCE(current->mm->numa_scan_seq) < 2)
return true;
- pids = vma->numab_state->access_pids[0] | vma->numab_state->access_pids[1];
- return test_bit(hash_32(current->pid, ilog2(BITS_PER_LONG)), &pids);
+ pids = vma->numab_state->pids_active[0] | vma->numab_state->pids_active[1];
+ if (test_bit(hash_32(current->pid, ilog2(BITS_PER_LONG)), &pids))
+ return true;
+
+ /*
+ * Complete a scan that has already started regardless of PID access, or
+ * some VMAs may never be scanned in multi-threaded applications:
+ */
+ if (mm->numa_scan_offset > vma->vm_start) {
+ trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_IGNORE_PID);
+ return true;
+ }
+
+ return false;
}
#define VMA_PID_RESET_PERIOD (4 * sysctl_numa_balancing_scan_delay)
@@ -2961,6 +3200,8 @@ static void task_numa_work(struct callback_head *work)
unsigned long nr_pte_updates = 0;
long pages, virtpages;
struct vma_iterator vmi;
+ bool vma_pids_skipped;
+ bool vma_pids_forced = false;
SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work));
@@ -3003,7 +3244,6 @@ static void task_numa_work(struct callback_head *work)
*/
p->node_stamp += 2 * TICK_NSEC;
- start = mm->numa_scan_offset;
pages = sysctl_numa_balancing_scan_size;
pages <<= 20 - PAGE_SHIFT; /* MB in pages */
virtpages = pages * 8; /* Scan up to this much virtual space */
@@ -3013,6 +3253,16 @@ static void task_numa_work(struct callback_head *work)
if (!mmap_read_trylock(mm))
return;
+
+ /*
+ * VMAs are skipped if the current PID has not trapped a fault within
+ * the VMA recently. Allow scanning to be forced if there is no
+ * suitable VMA remaining.
+ */
+ vma_pids_skipped = false;
+
+retry_pids:
+ start = mm->numa_scan_offset;
vma_iter_init(&vmi, mm, start);
vma = vma_next(&vmi);
if (!vma) {
@@ -3025,6 +3275,7 @@ static void task_numa_work(struct callback_head *work)
do {
if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
+ trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_UNSUITABLE);
continue;
}
@@ -3035,15 +3286,19 @@ static void task_numa_work(struct callback_head *work)
* as migrating the pages will be of marginal benefit.
*/
if (!vma->vm_mm ||
- (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
+ (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ))) {
+ trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_SHARED_RO);
continue;
+ }
/*
* Skip inaccessible VMAs to avoid any confusion between
* PROT_NONE and NUMA hinting ptes
*/
- if (!vma_is_accessible(vma))
+ if (!vma_is_accessible(vma)) {
+ trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_INACCESSIBLE);
continue;
+ }
/* Initialise new per-VMA NUMAB state. */
if (!vma->numab_state) {
@@ -3056,8 +3311,15 @@ static void task_numa_work(struct callback_head *work)
msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
/* Reset happens after 4 times scan delay of scan start */
- vma->numab_state->next_pid_reset = vma->numab_state->next_scan +
+ vma->numab_state->pids_active_reset = vma->numab_state->next_scan +
msecs_to_jiffies(VMA_PID_RESET_PERIOD);
+
+ /*
+ * Ensure prev_scan_seq does not match numa_scan_seq,
+ * to prevent VMAs being skipped prematurely on the
+ * first scan:
+ */
+ vma->numab_state->prev_scan_seq = mm->numa_scan_seq - 1;
}
/*
@@ -3065,23 +3327,35 @@ static void task_numa_work(struct callback_head *work)
* delay the scan for new VMAs.
*/
if (mm->numa_scan_seq && time_before(jiffies,
- vma->numab_state->next_scan))
+ vma->numab_state->next_scan)) {
+ trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_SCAN_DELAY);
continue;
+ }
+
+ /* RESET access PIDs regularly for old VMAs. */
+ if (mm->numa_scan_seq &&
+ time_after(jiffies, vma->numab_state->pids_active_reset)) {
+ vma->numab_state->pids_active_reset = vma->numab_state->pids_active_reset +
+ msecs_to_jiffies(VMA_PID_RESET_PERIOD);
+ vma->numab_state->pids_active[0] = READ_ONCE(vma->numab_state->pids_active[1]);
+ vma->numab_state->pids_active[1] = 0;
+ }
- /* Do not scan the VMA if task has not accessed */
- if (!vma_is_accessed(vma))
+ /* Do not rescan VMAs twice within the same sequence. */
+ if (vma->numab_state->prev_scan_seq == mm->numa_scan_seq) {
+ mm->numa_scan_offset = vma->vm_end;
+ trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_SEQ_COMPLETED);
continue;
+ }
/*
- * RESET access PIDs regularly for old VMAs. Resetting after checking
- * vma for recent access to avoid clearing PID info before access..
+ * Do not scan the VMA if task has not accessed it, unless no other
+ * VMA candidate exists.
*/
- if (mm->numa_scan_seq &&
- time_after(jiffies, vma->numab_state->next_pid_reset)) {
- vma->numab_state->next_pid_reset = vma->numab_state->next_pid_reset +
- msecs_to_jiffies(VMA_PID_RESET_PERIOD);
- vma->numab_state->access_pids[0] = READ_ONCE(vma->numab_state->access_pids[1]);
- vma->numab_state->access_pids[1] = 0;
+ if (!vma_pids_forced && !vma_is_accessed(mm, vma)) {
+ vma_pids_skipped = true;
+ trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_PID_INACTIVE);
+ continue;
}
do {
@@ -3108,8 +3382,28 @@ static void task_numa_work(struct callback_head *work)
cond_resched();
} while (end != vma->vm_end);
+
+ /* VMA scan is complete, do not scan until next sequence. */
+ vma->numab_state->prev_scan_seq = mm->numa_scan_seq;
+
+ /*
+ * Only force scan within one VMA at a time, to limit the
+ * cost of scanning a potentially uninteresting VMA.
+ */
+ if (vma_pids_forced)
+ break;
} for_each_vma(vmi, vma);
+ /*
+ * If no VMAs are remaining and VMAs were skipped due to the PID
+ * not accessing the VMA previously, then force a scan to ensure
+ * forward progress:
+ */
+ if (!vma && !vma_pids_forced && vma_pids_skipped) {
+ vma_pids_forced = true;
+ goto retry_pids;
+ }
+
out:
/*
* It is possible to reach the end of the VMA list but the last few
@@ -3372,17 +3666,138 @@ static inline void
dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
#endif
+static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
+ unsigned long weight)
+{
+ unsigned long old_weight = se->load.weight;
+ u64 avruntime = avg_vruntime(cfs_rq);
+ s64 vlag, vslice;
+
+ /*
+ * VRUNTIME
+ * ========
+ *
+ * COROLLARY #1: The virtual runtime of the entity needs to be
+ * adjusted if re-weight at !0-lag point.
+ *
+ * Proof: For contradiction assume this is not true, so we can
+ * re-weight without changing vruntime at !0-lag point.
+ *
+ * Weight VRuntime Avg-VRuntime
+ * before w v V
+ * after w' v' V'
+ *
+ * Since lag needs to be preserved through re-weight:
+ *
+ * lag = (V - v)*w = (V'- v')*w', where v = v'
+ * ==> V' = (V - v)*w/w' + v (1)
+ *
+ * Let W be the total weight of the entities before reweight,
+ * since V' is the new weighted average of entities:
+ *
+ * V' = (WV + w'v - wv) / (W + w' - w) (2)
+ *
+ * by using (1) & (2) we obtain:
+ *
+ * (WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
+ * ==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
+ * ==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
+ * ==> (V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
+ *
+ * Since we are doing at !0-lag point which means V != v, we
+ * can simplify (3):
+ *
+ * ==> W / (W + w' - w) = w / w'
+ * ==> Ww' = Ww + ww' - ww
+ * ==> W * (w' - w) = w * (w' - w)
+ * ==> W = w (re-weight indicates w' != w)
+ *
+ * So the cfs_rq contains only one entity, hence vruntime of
+ * the entity @v should always equal to the cfs_rq's weighted
+ * average vruntime @V, which means we will always re-weight
+ * at 0-lag point, thus breach assumption. Proof completed.
+ *
+ *
+ * COROLLARY #2: Re-weight does NOT affect weighted average
+ * vruntime of all the entities.
+ *
+ * Proof: According to corollary #1, Eq. (1) should be:
+ *
+ * (V - v)*w = (V' - v')*w'
+ * ==> v' = V' - (V - v)*w/w' (4)
+ *
+ * According to the weighted average formula, we have:
+ *
+ * V' = (WV - wv + w'v') / (W - w + w')
+ * = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
+ * = (WV - wv + w'V' - Vw + wv) / (W - w + w')
+ * = (WV + w'V' - Vw) / (W - w + w')
+ *
+ * ==> V'*(W - w + w') = WV + w'V' - Vw
+ * ==> V' * (W - w) = (W - w) * V (5)
+ *
+ * If the entity is the only one in the cfs_rq, then reweight
+ * always occurs at 0-lag point, so V won't change. Or else
+ * there are other entities, hence W != w, then Eq. (5) turns
+ * into V' = V. So V won't change in either case, proof done.
+ *
+ *
+ * So according to corollary #1 & #2, the effect of re-weight
+ * on vruntime should be:
+ *
+ * v' = V' - (V - v) * w / w' (4)
+ * = V - (V - v) * w / w'
+ * = V - vl * w / w'
+ * = V - vl'
+ */
+ if (avruntime != se->vruntime) {
+ vlag = (s64)(avruntime - se->vruntime);
+ vlag = div_s64(vlag * old_weight, weight);
+ se->vruntime = avruntime - vlag;
+ }
+
+ /*
+ * DEADLINE
+ * ========
+ *
+ * When the weight changes, the virtual time slope changes and
+ * we should adjust the relative virtual deadline accordingly.
+ *
+ * d' = v' + (d - v)*w/w'
+ * = V' - (V - v)*w/w' + (d - v)*w/w'
+ * = V - (V - v)*w/w' + (d - v)*w/w'
+ * = V + (d - V)*w/w'
+ */
+ vslice = (s64)(se->deadline - avruntime);
+ vslice = div_s64(vslice * old_weight, weight);
+ se->deadline = avruntime + vslice;
+}
+
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
unsigned long weight)
{
+ bool curr = cfs_rq->curr == se;
+
if (se->on_rq) {
/* commit outstanding execution time */
- if (cfs_rq->curr == se)
+ if (curr)
update_curr(cfs_rq);
+ else
+ __dequeue_entity(cfs_rq, se);
update_load_sub(&cfs_rq->load, se->load.weight);
}
dequeue_load_avg(cfs_rq, se);
+ if (!se->on_rq) {
+ /*
+ * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
+ * we need to scale se->vlag when w_i changes.
+ */
+ se->vlag = div_s64(se->vlag * se->load.weight, weight);
+ } else {
+ reweight_eevdf(cfs_rq, se, weight);
+ }
+
update_load_set(&se->load, weight);
#ifdef CONFIG_SMP
@@ -3394,9 +3809,20 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
#endif
enqueue_load_avg(cfs_rq, se);
- if (se->on_rq)
+ if (se->on_rq) {
update_load_add(&cfs_rq->load, se->load.weight);
-
+ if (!curr) {
+ /*
+ * The entity's vruntime has been adjusted, so let's check
+ * whether the rq-wide min_vruntime needs updated too. Since
+ * the calculations above require stable min_vruntime rather
+ * than up-to-date one, we do the update at the end of the
+ * reweight process.
+ */
+ __enqueue_entity(cfs_rq, se);
+ update_min_vruntime(cfs_rq);
+ }
+ }
}
void reweight_task(struct task_struct *p, int prio)
@@ -3539,14 +3965,11 @@ static void update_cfs_group(struct sched_entity *se)
#ifndef CONFIG_SMP
shares = READ_ONCE(gcfs_rq->tg->shares);
-
- if (likely(se->load.weight == shares))
- return;
#else
- shares = calc_group_shares(gcfs_rq);
+ shares = calc_group_shares(gcfs_rq);
#endif
-
- reweight_entity(cfs_rq_of(se), se, shares);
+ if (unlikely(se->load.weight != shares))
+ reweight_entity(cfs_rq_of(se), se, shares);
}
#else /* CONFIG_FAIR_GROUP_SCHED */
@@ -3664,7 +4087,8 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
*/
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
{
- long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
+ long delta;
+ u64 now;
/*
* No need to update load_avg for root_task_group as it is not used.
@@ -3672,9 +4096,19 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
if (cfs_rq->tg == &root_task_group)
return;
+ /*
+ * For migration heavy workloads, access to tg->load_avg can be
+ * unbound. Limit the update rate to at most once per ms.
+ */
+ now = sched_clock_cpu(cpu_of(rq_of(cfs_rq)));
+ if (now - cfs_rq->last_update_tg_load_avg < NSEC_PER_MSEC)
+ return;
+
+ delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
if (abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
atomic_long_add(delta, &cfs_rq->tg->load_avg);
cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
+ cfs_rq->last_update_tg_load_avg = now;
}
}
@@ -4348,22 +4782,6 @@ static inline unsigned long task_util_est(struct task_struct *p)
return max(task_util(p), _task_util_est(p));
}
-#ifdef CONFIG_UCLAMP_TASK
-static inline unsigned long uclamp_task_util(struct task_struct *p,
- unsigned long uclamp_min,
- unsigned long uclamp_max)
-{
- return clamp(task_util_est(p), uclamp_min, uclamp_max);
-}
-#else
-static inline unsigned long uclamp_task_util(struct task_struct *p,
- unsigned long uclamp_min,
- unsigned long uclamp_max)
-{
- return task_util_est(p);
-}
-#endif
-
static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
struct task_struct *p)
{
@@ -4467,7 +4885,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
* To avoid overestimation of actual task utilization, skip updates if
* we cannot grant there is idle time in this CPU.
*/
- if (task_util(p) > capacity_orig_of(cpu_of(rq_of(cfs_rq))))
+ if (task_util(p) > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
return;
/*
@@ -4515,14 +4933,14 @@ static inline int util_fits_cpu(unsigned long util,
return fits;
/*
- * We must use capacity_orig_of() for comparing against uclamp_min and
+ * We must use arch_scale_cpu_capacity() for comparing against uclamp_min and
* uclamp_max. We only care about capacity pressure (by using
* capacity_of()) for comparing against the real util.
*
* If a task is boosted to 1024 for example, we don't want a tiny
* pressure to skew the check whether it fits a CPU or not.
*
- * Similarly if a task is capped to capacity_orig_of(little_cpu), it
+ * Similarly if a task is capped to arch_scale_cpu_capacity(little_cpu), it
* should fit a little cpu even if there's some pressure.
*
* Only exception is for thermal pressure since it has a direct impact
@@ -4534,7 +4952,7 @@ static inline int util_fits_cpu(unsigned long util,
* For uclamp_max, we can tolerate a drop in performance level as the
* goal is to cap the task. So it's okay if it's getting less.
*/
- capacity_orig = capacity_orig_of(cpu);
+ capacity_orig = arch_scale_cpu_capacity(cpu);
capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu);
/*
@@ -4654,7 +5072,7 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
{
- return true;
+ return !cfs_rq->nr_running;
}
#define UPDATE_TG 0x0
@@ -4692,159 +5110,127 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
#endif /* CONFIG_SMP */
-static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void
+place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
-#ifdef CONFIG_SCHED_DEBUG
- s64 d = se->vruntime - cfs_rq->min_vruntime;
+ u64 vslice, vruntime = avg_vruntime(cfs_rq);
+ s64 lag = 0;
- if (d < 0)
- d = -d;
-
- if (d > 3*sysctl_sched_latency)
- schedstat_inc(cfs_rq->nr_spread_over);
-#endif
-}
-
-static inline bool entity_is_long_sleeper(struct sched_entity *se)
-{
- struct cfs_rq *cfs_rq;
- u64 sleep_time;
+ se->slice = sysctl_sched_base_slice;
+ vslice = calc_delta_fair(se->slice, se);
- if (se->exec_start == 0)
- return false;
-
- cfs_rq = cfs_rq_of(se);
-
- sleep_time = rq_clock_task(rq_of(cfs_rq));
+ /*
+ * Due to how V is constructed as the weighted average of entities,
+ * adding tasks with positive lag, or removing tasks with negative lag
+ * will move 'time' backwards, this can screw around with the lag of
+ * other tasks.
+ *
+ * EEVDF: placement strategy #1 / #2
+ */
+ if (sched_feat(PLACE_LAG) && cfs_rq->nr_running) {
+ struct sched_entity *curr = cfs_rq->curr;
+ unsigned long load;
- /* Happen while migrating because of clock task divergence */
- if (sleep_time <= se->exec_start)
- return false;
+ lag = se->vlag;
- sleep_time -= se->exec_start;
- if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD)))
- return true;
+ /*
+ * If we want to place a task and preserve lag, we have to
+ * consider the effect of the new entity on the weighted
+ * average and compensate for this, otherwise lag can quickly
+ * evaporate.
+ *
+ * Lag is defined as:
+ *
+ * lag_i = S - s_i = w_i * (V - v_i)
+ *
+ * To avoid the 'w_i' term all over the place, we only track
+ * the virtual lag:
+ *
+ * vl_i = V - v_i <=> v_i = V - vl_i
+ *
+ * And we take V to be the weighted average of all v:
+ *
+ * V = (\Sum w_j*v_j) / W
+ *
+ * Where W is: \Sum w_j
+ *
+ * Then, the weighted average after adding an entity with lag
+ * vl_i is given by:
+ *
+ * V' = (\Sum w_j*v_j + w_i*v_i) / (W + w_i)
+ * = (W*V + w_i*(V - vl_i)) / (W + w_i)
+ * = (W*V + w_i*V - w_i*vl_i) / (W + w_i)
+ * = (V*(W + w_i) - w_i*l) / (W + w_i)
+ * = V - w_i*vl_i / (W + w_i)
+ *
+ * And the actual lag after adding an entity with vl_i is:
+ *
+ * vl'_i = V' - v_i
+ * = V - w_i*vl_i / (W + w_i) - (V - vl_i)
+ * = vl_i - w_i*vl_i / (W + w_i)
+ *
+ * Which is strictly less than vl_i. So in order to preserve lag
+ * we should inflate the lag before placement such that the
+ * effective lag after placement comes out right.
+ *
+ * As such, invert the above relation for vl'_i to get the vl_i
+ * we need to use such that the lag after placement is the lag
+ * we computed before dequeue.
+ *
+ * vl'_i = vl_i - w_i*vl_i / (W + w_i)
+ * = ((W + w_i)*vl_i - w_i*vl_i) / (W + w_i)
+ *
+ * (W + w_i)*vl'_i = (W + w_i)*vl_i - w_i*vl_i
+ * = W*vl_i
+ *
+ * vl_i = (W + w_i)*vl'_i / W
+ */
+ load = cfs_rq->avg_load;
+ if (curr && curr->on_rq)
+ load += scale_load_down(curr->load.weight);
- return false;
-}
+ lag *= load + scale_load_down(se->load.weight);
+ if (WARN_ON_ONCE(!load))
+ load = 1;
+ lag = div_s64(lag, load);
+ }
-static void
-place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
-{
- u64 vruntime = cfs_rq->min_vruntime;
+ se->vruntime = vruntime - lag;
/*
- * The 'current' period is already promised to the current tasks,
- * however the extra weight of the new task will slow them down a
- * little, place the new task so that it fits in the slot that
- * stays open at the end.
+ * When joining the competition; the exisiting tasks will be,
+ * on average, halfway through their slice, as such start tasks
+ * off with half a slice to ease into the competition.
*/
- if (initial && sched_feat(START_DEBIT))
- vruntime += sched_vslice(cfs_rq, se);
-
- /* sleeps up to a single latency don't count. */
- if (!initial) {
- unsigned long thresh;
-
- if (se_is_idle(se))
- thresh = sysctl_sched_min_granularity;
- else
- thresh = sysctl_sched_latency;
+ if (sched_feat(PLACE_DEADLINE_INITIAL) && (flags & ENQUEUE_INITIAL))
+ vslice /= 2;
- /*
- * Halve their sleep time's effect, to allow
- * for a gentler effect of sleepers:
- */
- if (sched_feat(GENTLE_FAIR_SLEEPERS))
- thresh >>= 1;
-
- vruntime -= thresh;
- }
-
- /*
- * Pull vruntime of the entity being placed to the base level of
- * cfs_rq, to prevent boosting it if placed backwards.
- * However, min_vruntime can advance much faster than real time, with
- * the extreme being when an entity with the minimal weight always runs
- * on the cfs_rq. If the waking entity slept for a long time, its
- * vruntime difference from min_vruntime may overflow s64 and their
- * comparison may get inversed, so ignore the entity's original
- * vruntime in that case.
- * The maximal vruntime speedup is given by the ratio of normal to
- * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES.
- * When placing a migrated waking entity, its exec_start has been set
- * from a different rq. In order to take into account a possible
- * divergence between new and prev rq's clocks task because of irq and
- * stolen time, we take an additional margin.
- * So, cutting off on the sleep time of
- * 2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days
- * should be safe.
- */
- if (entity_is_long_sleeper(se))
- se->vruntime = vruntime;
- else
- se->vruntime = max_vruntime(se->vruntime, vruntime);
+ /*
+ * EEVDF: vd_i = ve_i + r_i/w_i
+ */
+ se->deadline = se->vruntime + vslice;
}
static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
+static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq);
static inline bool cfs_bandwidth_used(void);
-/*
- * MIGRATION
- *
- * dequeue
- * update_curr()
- * update_min_vruntime()
- * vruntime -= min_vruntime
- *
- * enqueue
- * update_curr()
- * update_min_vruntime()
- * vruntime += min_vruntime
- *
- * this way the vruntime transition between RQs is done when both
- * min_vruntime are up-to-date.
- *
- * WAKEUP (remote)
- *
- * ->migrate_task_rq_fair() (p->state == TASK_WAKING)
- * vruntime -= min_vruntime
- *
- * enqueue
- * update_curr()
- * update_min_vruntime()
- * vruntime += min_vruntime
- *
- * this way we don't have the most up-to-date min_vruntime on the originating
- * CPU and an up-to-date min_vruntime on the destination CPU.
- */
-
static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
- bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATED);
bool curr = cfs_rq->curr == se;
/*
* If we're the current task, we must renormalise before calling
* update_curr().
*/
- if (renorm && curr)
- se->vruntime += cfs_rq->min_vruntime;
+ if (curr)
+ place_entity(cfs_rq, se, flags);
update_curr(cfs_rq);
/*
- * Otherwise, renormalise after, such that we're placed at the current
- * moment in time, instead of some random moment in the past. Being
- * placed in the past could significantly boost this task to the
- * fairness detriment of existing tasks.
- */
- if (renorm && !curr)
- se->vruntime += cfs_rq->min_vruntime;
-
- /*
* When enqueuing a sched_entity, we must:
* - Update loads to have both entity and cfs_rq synced with now.
* - For group_entity, update its runnable_weight to reflect the new
@@ -4855,37 +5241,46 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
*/
update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
se_update_runnable(se);
+ /*
+ * XXX update_load_avg() above will have attached us to the pelt sum;
+ * but update_cfs_group() here will re-adjust the weight and have to
+ * undo/redo all that. Seems wasteful.
+ */
update_cfs_group(se);
+
+ /*
+ * XXX now that the entity has been re-weighted, and it's lag adjusted,
+ * we can place the entity.
+ */
+ if (!curr)
+ place_entity(cfs_rq, se, flags);
+
account_entity_enqueue(cfs_rq, se);
- if (flags & ENQUEUE_WAKEUP)
- place_entity(cfs_rq, se, 0);
/* Entity has migrated, no longer consider this task hot */
if (flags & ENQUEUE_MIGRATED)
se->exec_start = 0;
check_schedstat_required();
update_stats_enqueue_fair(cfs_rq, se, flags);
- check_spread(cfs_rq, se);
if (!curr)
__enqueue_entity(cfs_rq, se);
se->on_rq = 1;
if (cfs_rq->nr_running == 1) {
check_enqueue_throttle(cfs_rq);
- if (!throttled_hierarchy(cfs_rq))
+ if (!throttled_hierarchy(cfs_rq)) {
list_add_leaf_cfs_rq(cfs_rq);
- }
-}
-
-static void __clear_buddies_last(struct sched_entity *se)
-{
- for_each_sched_entity(se) {
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
- if (cfs_rq->last != se)
- break;
+ } else {
+#ifdef CONFIG_CFS_BANDWIDTH
+ struct rq *rq = rq_of(cfs_rq);
- cfs_rq->last = NULL;
+ if (cfs_rq_throttled(cfs_rq) && !cfs_rq->throttled_clock)
+ cfs_rq->throttled_clock = rq_clock(rq);
+ if (!cfs_rq->throttled_clock_self)
+ cfs_rq->throttled_clock_self = rq_clock(rq);
+#endif
+ }
}
}
@@ -4900,27 +5295,10 @@ static void __clear_buddies_next(struct sched_entity *se)
}
}
-static void __clear_buddies_skip(struct sched_entity *se)
-{
- for_each_sched_entity(se) {
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
- if (cfs_rq->skip != se)
- break;
-
- cfs_rq->skip = NULL;
- }
-}
-
static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (cfs_rq->last == se)
- __clear_buddies_last(se);
-
if (cfs_rq->next == se)
__clear_buddies_next(se);
-
- if (cfs_rq->skip == se)
- __clear_buddies_skip(se);
}
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -4954,20 +5332,12 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
clear_buddies(cfs_rq, se);
+ update_entity_lag(cfs_rq, se);
if (se != cfs_rq->curr)
__dequeue_entity(cfs_rq, se);
se->on_rq = 0;
account_entity_dequeue(cfs_rq, se);
- /*
- * Normalize after update_curr(); which will also have moved
- * min_vruntime if @se is the one holding it back. But before doing
- * update_min_vruntime() again, which will discount @se's position and
- * can move min_vruntime forward still more.
- */
- if (!(flags & DEQUEUE_SLEEP))
- se->vruntime -= cfs_rq->min_vruntime;
-
/* return excess runtime on last dequeue */
return_cfs_rq_runtime(cfs_rq);
@@ -4986,52 +5356,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
update_idle_cfs_rq_clock_pelt(cfs_rq);
}
-/*
- * Preempt the current task with a newly woken task if needed:
- */
-static void
-check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
-{
- unsigned long ideal_runtime, delta_exec;
- struct sched_entity *se;
- s64 delta;
-
- /*
- * When many tasks blow up the sched_period; it is possible that
- * sched_slice() reports unusually large results (when many tasks are
- * very light for example). Therefore impose a maximum.
- */
- ideal_runtime = min_t(u64, sched_slice(cfs_rq, curr), sysctl_sched_latency);
-
- delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
- if (delta_exec > ideal_runtime) {
- resched_curr(rq_of(cfs_rq));
- /*
- * The current task ran long enough, ensure it doesn't get
- * re-elected due to buddy favours.
- */
- clear_buddies(cfs_rq, curr);
- return;
- }
-
- /*
- * Ensure that a task that missed wakeup preemption by a
- * narrow margin doesn't have to wait for a full slice.
- * This also mitigates buddy induced latencies under load.
- */
- if (delta_exec < sysctl_sched_min_granularity)
- return;
-
- se = __pick_first_entity(cfs_rq);
- delta = curr->vruntime - se->vruntime;
-
- if (delta < 0)
- return;
-
- if (delta > ideal_runtime)
- resched_curr(rq_of(cfs_rq));
-}
-
static void
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
@@ -5047,6 +5371,11 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_stats_wait_end_fair(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
update_load_avg(cfs_rq, se, UPDATE_TG);
+ /*
+ * HACK, stash a copy of deadline at the point of pick in vlag,
+ * which isn't used until dequeue.
+ */
+ se->vlag = se->deadline;
}
update_stats_curr_start(cfs_rq, se);
@@ -5070,9 +5399,6 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
-
/*
* Pick the next process, keeping these things in mind, in this order:
* 1) keep things fair between processes/task groups
@@ -5081,52 +5407,16 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
* 4) do not run the "skip" process, if something else is available
*/
static struct sched_entity *
-pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+pick_next_entity(struct cfs_rq *cfs_rq)
{
- struct sched_entity *left = __pick_first_entity(cfs_rq);
- struct sched_entity *se;
-
/*
- * If curr is set we have to see if its left of the leftmost entity
- * still in the tree, provided there was anything in the tree at all.
+ * Enabling NEXT_BUDDY will affect latency but not fairness.
*/
- if (!left || (curr && entity_before(curr, left)))
- left = curr;
+ if (sched_feat(NEXT_BUDDY) &&
+ cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next))
+ return cfs_rq->next;
- se = left; /* ideally we run the leftmost entity */
-
- /*
- * Avoid running the skip buddy, if running something else can
- * be done without getting too unfair.
- */
- if (cfs_rq->skip && cfs_rq->skip == se) {
- struct sched_entity *second;
-
- if (se == curr) {
- second = __pick_first_entity(cfs_rq);
- } else {
- second = __pick_next_entity(se);
- if (!second || (curr && entity_before(curr, second)))
- second = curr;
- }
-
- if (second && wakeup_preempt_entity(second, left) < 1)
- se = second;
- }
-
- if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) {
- /*
- * Someone really wants this to run. If it's not unfair, run it.
- */
- se = cfs_rq->next;
- } else if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) {
- /*
- * Prefer last buddy, try to return the CPU to a preempted task.
- */
- se = cfs_rq->last;
- }
-
- return se;
+ return pick_eevdf(cfs_rq);
}
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -5143,8 +5433,6 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
/* throttle cfs_rqs exceeding runtime */
check_cfs_rq_runtime(cfs_rq);
- check_spread(cfs_rq, prev);
-
if (prev->on_rq) {
update_stats_wait_start_fair(cfs_rq, prev);
/* Put 'current' back into the tree. */
@@ -5185,9 +5473,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
return;
#endif
-
- if (cfs_rq->nr_running > 1)
- check_preempt_tick(cfs_rq, curr);
}
@@ -5377,6 +5662,17 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
/* Add cfs_rq with load or one or more already running entities to the list */
if (!cfs_rq_is_decayed(cfs_rq))
list_add_leaf_cfs_rq(cfs_rq);
+
+ if (cfs_rq->throttled_clock_self) {
+ u64 delta = rq_clock(rq) - cfs_rq->throttled_clock_self;
+
+ cfs_rq->throttled_clock_self = 0;
+
+ if (SCHED_WARN_ON((s64)delta < 0))
+ delta = 0;
+
+ cfs_rq->throttled_clock_self_time += delta;
+ }
}
return 0;
@@ -5391,6 +5687,10 @@ static int tg_throttle_down(struct task_group *tg, void *data)
if (!cfs_rq->throttle_count) {
cfs_rq->throttled_clock_pelt = rq_clock_pelt(rq);
list_del_leaf_cfs_rq(cfs_rq);
+
+ SCHED_WARN_ON(cfs_rq->throttled_clock_self);
+ if (cfs_rq->nr_running)
+ cfs_rq->throttled_clock_self = rq_clock(rq);
}
cfs_rq->throttle_count++;
@@ -5480,7 +5780,9 @@ done:
* throttled-list. rq->lock protects completion.
*/
cfs_rq->throttled = 1;
- cfs_rq->throttled_clock = rq_clock(rq);
+ SCHED_WARN_ON(cfs_rq->throttled_clock);
+ if (cfs_rq->nr_running)
+ cfs_rq->throttled_clock = rq_clock(rq);
return true;
}
@@ -5498,7 +5800,10 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
update_rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
- cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
+ if (cfs_rq->throttled_clock) {
+ cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
+ cfs_rq->throttled_clock = 0;
+ }
list_del_rcu(&cfs_rq->throttled_list);
raw_spin_unlock(&cfs_b->lock);
@@ -5646,13 +5951,13 @@ static void unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
{
- struct cfs_rq *local_unthrottle = NULL;
int this_cpu = smp_processor_id();
u64 runtime, remaining = 1;
bool throttled = false;
- struct cfs_rq *cfs_rq;
+ struct cfs_rq *cfs_rq, *tmp;
struct rq_flags rf;
struct rq *rq;
+ LIST_HEAD(local_unthrottle);
rcu_read_lock();
list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
@@ -5668,11 +5973,9 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
if (!cfs_rq_throttled(cfs_rq))
goto next;
-#ifdef CONFIG_SMP
/* Already queued for async unthrottle */
if (!list_empty(&cfs_rq->throttled_csd_list))
goto next;
-#endif
/* By the above checks, this should never be true */
SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
@@ -5689,11 +5992,17 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
/* we check whether we're throttled above */
if (cfs_rq->runtime_remaining > 0) {
- if (cpu_of(rq) != this_cpu ||
- SCHED_WARN_ON(local_unthrottle))
+ if (cpu_of(rq) != this_cpu) {
unthrottle_cfs_rq_async(cfs_rq);
- else
- local_unthrottle = cfs_rq;
+ } else {
+ /*
+ * We currently only expect to be unthrottling
+ * a single cfs_rq locally.
+ */
+ SCHED_WARN_ON(!list_empty(&local_unthrottle));
+ list_add_tail(&cfs_rq->throttled_csd_list,
+ &local_unthrottle);
+ }
} else {
throttled = true;
}
@@ -5701,15 +6010,23 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
next:
rq_unlock_irqrestore(rq, &rf);
}
- rcu_read_unlock();
- if (local_unthrottle) {
- rq = cpu_rq(this_cpu);
+ list_for_each_entry_safe(cfs_rq, tmp, &local_unthrottle,
+ throttled_csd_list) {
+ struct rq *rq = rq_of(cfs_rq);
+
rq_lock_irqsave(rq, &rf);
- if (cfs_rq_throttled(local_unthrottle))
- unthrottle_cfs_rq(local_unthrottle);
+
+ list_del_init(&cfs_rq->throttled_csd_list);
+
+ if (cfs_rq_throttled(cfs_rq))
+ unthrottle_cfs_rq(cfs_rq);
+
rq_unlock_irqrestore(rq, &rf);
}
+ SCHED_WARN_ON(!list_empty(&local_unthrottle));
+
+ rcu_read_unlock();
return throttled;
}
@@ -6014,13 +6331,14 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}
-void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent)
{
raw_spin_lock_init(&cfs_b->lock);
cfs_b->runtime = 0;
cfs_b->quota = RUNTIME_INF;
cfs_b->period = ns_to_ktime(default_cfs_period());
cfs_b->burst = 0;
+ cfs_b->hierarchical_quota = parent ? parent->hierarchical_quota : RUNTIME_INF;
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
@@ -6038,9 +6356,7 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
cfs_rq->runtime_enabled = 0;
INIT_LIST_HEAD(&cfs_rq->throttled_list);
-#ifdef CONFIG_SMP
INIT_LIST_HEAD(&cfs_rq->throttled_csd_list);
-#endif
}
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
@@ -6157,6 +6473,46 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
rq_clock_stop_loop_update(rq);
}
+bool cfs_task_bw_constrained(struct task_struct *p)
+{
+ struct cfs_rq *cfs_rq = task_cfs_rq(p);
+
+ if (!cfs_bandwidth_used())
+ return false;
+
+ if (cfs_rq->runtime_enabled ||
+ tg_cfs_bandwidth(cfs_rq->tg)->hierarchical_quota != RUNTIME_INF)
+ return true;
+
+ return false;
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+/* called from pick_next_task_fair() */
+static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p)
+{
+ int cpu = cpu_of(rq);
+
+ if (!sched_feat(HZ_BW) || !cfs_bandwidth_used())
+ return;
+
+ if (!tick_nohz_full_cpu(cpu))
+ return;
+
+ if (rq->nr_running != 1)
+ return;
+
+ /*
+ * We know there is only one task runnable and we've just picked it. The
+ * normal enqueue path will have cleared TICK_DEP_BIT_SCHED if we will
+ * be otherwise able to stop the tick. Just need to check if we are using
+ * bandwidth control.
+ */
+ if (cfs_task_bw_constrained(p))
+ tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
+}
+#endif
+
#else /* CONFIG_CFS_BANDWIDTH */
static inline bool cfs_bandwidth_used(void)
@@ -6186,9 +6542,8 @@ static inline int throttled_lb_pair(struct task_group *tg,
return 0;
}
-void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
-
#ifdef CONFIG_FAIR_GROUP_SCHED
+void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent) {}
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
#endif
@@ -6199,9 +6554,18 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
static inline void update_runtime_enabled(struct rq *rq) {}
static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
-
+#ifdef CONFIG_CGROUP_SCHED
+bool cfs_task_bw_constrained(struct task_struct *p)
+{
+ return false;
+}
+#endif
#endif /* CONFIG_CFS_BANDWIDTH */
+#if !defined(CONFIG_CFS_BANDWIDTH) || !defined(CONFIG_NO_HZ_FULL)
+static inline void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p) {}
+#endif
+
/**************************************************
* CFS operations on tasks:
*/
@@ -6210,13 +6574,12 @@ static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
struct sched_entity *se = &p->se;
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
SCHED_WARN_ON(task_rq(p) != rq);
if (rq->cfs.h_nr_running > 1) {
- u64 slice = sched_slice(cfs_rq, se);
u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+ u64 slice = se->slice;
s64 delta = slice - ran;
if (delta < 0) {
@@ -6240,8 +6603,7 @@ static void hrtick_update(struct rq *rq)
if (!hrtick_enabled_fair(rq) || curr->sched_class != &fair_sched_class)
return;
- if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
- hrtick_start_fair(rq, curr);
+ hrtick_start_fair(rq, curr);
}
#else /* !CONFIG_SCHED_HRTICK */
static inline void
@@ -6282,17 +6644,6 @@ static int sched_idle_rq(struct rq *rq)
rq->nr_running);
}
-/*
- * Returns true if cfs_rq only has SCHED_IDLE entities enqueued. Note the use
- * of idle_nr_running, which does not consider idle descendants of normal
- * entities.
- */
-static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq)
-{
- return cfs_rq->nr_running &&
- cfs_rq->nr_running == cfs_rq->idle_nr_running;
-}
-
#ifdef CONFIG_SMP
static int sched_idle_cpu(int cpu)
{
@@ -6474,6 +6825,7 @@ dequeue_throttle:
/* Working cpumask for: load_balance, load_balance_newidle. */
static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
+static DEFINE_PER_CPU(cpumask_var_t, should_we_balance_tmpmask);
#ifdef CONFIG_NO_HZ_COMMON
@@ -6962,45 +7314,9 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
int i, cpu, idle_cpu = -1, nr = INT_MAX;
struct sched_domain_shared *sd_share;
- struct rq *this_rq = this_rq();
- int this = smp_processor_id();
- struct sched_domain *this_sd = NULL;
- u64 time = 0;
cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
- if (sched_feat(SIS_PROP) && !has_idle_core) {
- u64 avg_cost, avg_idle, span_avg;
- unsigned long now = jiffies;
-
- this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
- if (!this_sd)
- return -1;
-
- /*
- * If we're busy, the assumption that the last idle period
- * predicts the future is flawed; age away the remaining
- * predicted idle time.
- */
- if (unlikely(this_rq->wake_stamp < now)) {
- while (this_rq->wake_stamp < now && this_rq->wake_avg_idle) {
- this_rq->wake_stamp++;
- this_rq->wake_avg_idle >>= 1;
- }
- }
-
- avg_idle = this_rq->wake_avg_idle;
- avg_cost = this_sd->avg_scan_cost + 1;
-
- span_avg = sd->span_weight * avg_idle;
- if (span_avg > 4*avg_cost)
- nr = div_u64(span_avg, avg_cost);
- else
- nr = 4;
-
- time = cpu_clock(this);
- }
-
if (sched_feat(SIS_UTIL)) {
sd_share = rcu_dereference(per_cpu(sd_llc_shared, target));
if (sd_share) {
@@ -7012,6 +7328,30 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
}
}
+ if (static_branch_unlikely(&sched_cluster_active)) {
+ struct sched_group *sg = sd->groups;
+
+ if (sg->flags & SD_CLUSTER) {
+ for_each_cpu_wrap(cpu, sched_group_span(sg), target + 1) {
+ if (!cpumask_test_cpu(cpu, cpus))
+ continue;
+
+ if (has_idle_core) {
+ i = select_idle_core(p, cpu, cpus, &idle_cpu);
+ if ((unsigned int)i < nr_cpumask_bits)
+ return i;
+ } else {
+ if (--nr <= 0)
+ return -1;
+ idle_cpu = __select_idle_cpu(cpu, p);
+ if ((unsigned int)idle_cpu < nr_cpumask_bits)
+ return idle_cpu;
+ }
+ }
+ cpumask_andnot(cpus, cpus, sched_group_span(sg));
+ }
+ }
+
for_each_cpu_wrap(cpu, cpus, target + 1) {
if (has_idle_core) {
i = select_idle_core(p, cpu, cpus, &idle_cpu);
@@ -7019,7 +7359,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
return i;
} else {
- if (!--nr)
+ if (--nr <= 0)
return -1;
idle_cpu = __select_idle_cpu(cpu, p);
if ((unsigned int)idle_cpu < nr_cpumask_bits)
@@ -7030,18 +7370,6 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
if (has_idle_core)
set_idle_cores(target, false);
- if (sched_feat(SIS_PROP) && this_sd && !has_idle_core) {
- time = cpu_clock(this) - time;
-
- /*
- * Account for the scan cost of wakeups against the average
- * idle time.
- */
- this_rq->wake_avg_idle -= min(this_rq->wake_avg_idle, time);
-
- update_avg(&this_sd->avg_scan_cost, time);
- }
-
return idle_cpu;
}
@@ -7065,7 +7393,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
util_min = uclamp_eff_value(p, UCLAMP_MIN);
util_max = uclamp_eff_value(p, UCLAMP_MAX);
- for_each_cpu_wrap(cpu, cpus, target + 1) {
+ for_each_cpu_wrap(cpu, cpus, target) {
unsigned long cpu_cap = capacity_of(cpu);
if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
@@ -7081,7 +7409,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
* Look for the CPU with best capacity.
*/
else if (fits < 0)
- cpu_cap = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu));
+ cpu_cap = arch_scale_cpu_capacity(cpu) - thermal_load_avg(cpu_rq(cpu));
/*
* First, select CPU which fits better (-1 being better than 0).
@@ -7121,7 +7449,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
bool has_idle_core = false;
struct sched_domain *sd;
unsigned long task_util, util_min, util_max;
- int i, recent_used_cpu;
+ int i, recent_used_cpu, prev_aff = -1;
/*
* On asymmetric system, update task utilization because we will check
@@ -7148,8 +7476,14 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
*/
if (prev != target && cpus_share_cache(prev, target) &&
(available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
- asym_fits_cpu(task_util, util_min, util_max, prev))
- return prev;
+ asym_fits_cpu(task_util, util_min, util_max, prev)) {
+
+ if (!static_branch_unlikely(&sched_cluster_active) ||
+ cpus_share_resources(prev, target))
+ return prev;
+
+ prev_aff = prev;
+ }
/*
* Allow a per-cpu kthread to stack with the wakee if the
@@ -7176,7 +7510,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
(available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) &&
asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
- return recent_used_cpu;
+
+ if (!static_branch_unlikely(&sched_cluster_active) ||
+ cpus_share_resources(recent_used_cpu, target))
+ return recent_used_cpu;
+
+ } else {
+ recent_used_cpu = -1;
}
/*
@@ -7217,6 +7557,17 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
if ((unsigned)i < nr_cpumask_bits)
return i;
+ /*
+ * For cluster machines which have lower sharing cache like L2 or
+ * LLC Tag, we tend to find an idle CPU in the target's cluster
+ * first. But prev_cpu or recent_used_cpu may also be a good candidate,
+ * use them if possible when no idle CPU found in select_idle_cpu().
+ */
+ if ((unsigned int)prev_aff < nr_cpumask_bits)
+ return prev_aff;
+ if ((unsigned int)recent_used_cpu < nr_cpumask_bits)
+ return recent_used_cpu;
+
return target;
}
@@ -7289,9 +7640,6 @@ cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost)
util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
- if (boost)
- util_est = max(util_est, runnable);
-
/*
* During wake-up @p isn't enqueued yet and doesn't contribute
* to any cpu_rq(cpu)->cfs.avg.util_est.enqueued.
@@ -7326,7 +7674,7 @@ cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost)
util = max(util, util_est);
}
- return min(util, capacity_orig_of(cpu));
+ return min(util, arch_scale_cpu_capacity(cpu));
}
unsigned long cpu_util_cfs(int cpu)
@@ -7478,11 +7826,16 @@ compute_energy(struct energy_env *eenv, struct perf_domain *pd,
{
unsigned long max_util = eenv_pd_max_util(eenv, pd_cpus, p, dst_cpu);
unsigned long busy_time = eenv->pd_busy_time;
+ unsigned long energy;
if (dst_cpu >= 0)
busy_time = min(eenv->pd_cap, busy_time + eenv->task_busy_time);
- return em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap);
+ energy = em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap);
+
+ trace_sched_compute_energy_tp(p, dst_cpu, energy, max_util, busy_time);
+
+ return energy;
}
/*
@@ -7557,7 +7910,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
target = prev_cpu;
sync_entity_load_avg(&p->se);
- if (!uclamp_task_util(p, p_util_min, p_util_max))
+ if (!task_util_est(p) && p_util_min == 0)
goto unlock;
eenv_task_busy_time(&eenv, p, prev_cpu);
@@ -7565,11 +7918,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
for (; pd; pd = pd->next) {
unsigned long util_min = p_util_min, util_max = p_util_max;
unsigned long cpu_cap, cpu_thermal_cap, util;
- unsigned long cur_delta, max_spare_cap = 0;
+ long prev_spare_cap = -1, max_spare_cap = -1;
unsigned long rq_util_min, rq_util_max;
- unsigned long prev_spare_cap = 0;
+ unsigned long cur_delta, base_energy;
int max_spare_cap_cpu = -1;
- unsigned long base_energy;
int fits, max_fits = -1;
cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask);
@@ -7632,7 +7984,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
prev_spare_cap = cpu_cap;
prev_fits = fits;
} else if ((fits > max_fits) ||
- ((fits == max_fits) && (cpu_cap > max_spare_cap))) {
+ ((fits == max_fits) && ((long)cpu_cap > max_spare_cap))) {
/*
* Find the CPU with the maximum spare capacity
* among the remaining CPUs in the performance
@@ -7644,7 +7996,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
}
}
- if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
+ if (max_spare_cap_cpu < 0 && prev_spare_cap < 0)
continue;
eenv_pd_busy_time(&eenv, cpus, p);
@@ -7652,7 +8004,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
base_energy = compute_energy(&eenv, pd, cpus, p, -1);
/* Evaluate the energy impact of using prev_cpu. */
- if (prev_spare_cap > 0) {
+ if (prev_spare_cap > -1) {
prev_delta = compute_energy(&eenv, pd, cpus, p,
prev_cpu);
/* CPU utilization has changed */
@@ -7741,6 +8093,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
if (wake_flags & WF_TTWU) {
record_wakee(p);
+ if ((wake_flags & WF_CURRENT_CPU) &&
+ cpumask_test_cpu(cpu, p->cpus_ptr))
+ return cpu;
+
if (sched_energy_enabled()) {
new_cpu = find_energy_efficient_cpu(p, prev_cpu);
if (new_cpu >= 0)
@@ -7798,18 +8154,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
{
struct sched_entity *se = &p->se;
- /*
- * As blocked tasks retain absolute vruntime the migration needs to
- * deal with this by subtracting the old and adding the new
- * min_vruntime -- the latter is done by enqueue_entity() when placing
- * the task on the new runqueue.
- */
- if (READ_ONCE(p->__state) == TASK_WAKING) {
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
-
- se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
- }
-
if (!task_on_rq_migrating(p)) {
remove_entity_load_avg(se);
@@ -7847,66 +8191,6 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
}
#endif /* CONFIG_SMP */
-static unsigned long wakeup_gran(struct sched_entity *se)
-{
- unsigned long gran = sysctl_sched_wakeup_granularity;
-
- /*
- * Since its curr running now, convert the gran from real-time
- * to virtual-time in his units.
- *
- * By using 'se' instead of 'curr' we penalize light tasks, so
- * they get preempted easier. That is, if 'se' < 'curr' then
- * the resulting gran will be larger, therefore penalizing the
- * lighter, if otoh 'se' > 'curr' then the resulting gran will
- * be smaller, again penalizing the lighter task.
- *
- * This is especially important for buddies when the leftmost
- * task is higher priority than the buddy.
- */
- return calc_delta_fair(gran, se);
-}
-
-/*
- * Should 'se' preempt 'curr'.
- *
- * |s1
- * |s2
- * |s3
- * g
- * |<--->|c
- *
- * w(c, s1) = -1
- * w(c, s2) = 0
- * w(c, s3) = 1
- *
- */
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
-{
- s64 gran, vdiff = curr->vruntime - se->vruntime;
-
- if (vdiff <= 0)
- return -1;
-
- gran = wakeup_gran(se);
- if (vdiff > gran)
- return 1;
-
- return 0;
-}
-
-static void set_last_buddy(struct sched_entity *se)
-{
- for_each_sched_entity(se) {
- if (SCHED_WARN_ON(!se->on_rq))
- return;
- if (se_is_idle(se))
- return;
- cfs_rq_of(se)->last = se;
- }
-}
-
static void set_next_buddy(struct sched_entity *se)
{
for_each_sched_entity(se) {
@@ -7918,21 +8202,14 @@ static void set_next_buddy(struct sched_entity *se)
}
}
-static void set_skip_buddy(struct sched_entity *se)
-{
- for_each_sched_entity(se)
- cfs_rq_of(se)->skip = se;
-}
-
/*
* Preempt the current task with a newly woken task if needed:
*/
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
+static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int wake_flags)
{
struct task_struct *curr = rq->curr;
struct sched_entity *se = &curr->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
- int scale = cfs_rq->nr_running >= sched_nr_latency;
int next_buddy_marked = 0;
int cse_is_idle, pse_is_idle;
@@ -7941,14 +8218,14 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
/*
* This is possible from callers such as attach_tasks(), in which we
- * unconditionally check_preempt_curr() after an enqueue (which may have
+ * unconditionally wakeup_preempt() after an enqueue (which may have
* lead to a throttle). This both saves work and prevents false
* next-buddy nomination below.
*/
if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
return;
- if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
+ if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) {
set_next_buddy(pse);
next_buddy_marked = 1;
}
@@ -7993,35 +8270,19 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
if (cse_is_idle != pse_is_idle)
return;
- update_curr(cfs_rq_of(se));
- if (wakeup_preempt_entity(se, pse) == 1) {
- /*
- * Bias pick_next to pick the sched entity that is
- * triggering this preemption.
- */
- if (!next_buddy_marked)
- set_next_buddy(pse);
+ cfs_rq = cfs_rq_of(se);
+ update_curr(cfs_rq);
+
+ /*
+ * XXX pick_eevdf(cfs_rq) != se ?
+ */
+ if (pick_eevdf(cfs_rq) == pse)
goto preempt;
- }
return;
preempt:
resched_curr(rq);
- /*
- * Only set the backward buddy when the current task is still
- * on the rq. This can happen when a wakeup gets interleaved
- * with schedule on the ->pre_schedule() or idle_balance()
- * point, either of which can * drop the rq lock.
- *
- * Also, during early boot the idle thread is in the fair class,
- * for obvious reasons its a bad idea to schedule back to it.
- */
- if (unlikely(!se->on_rq || curr == rq->idle))
- return;
-
- if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
- set_last_buddy(se);
}
#ifdef CONFIG_SMP
@@ -8049,7 +8310,7 @@ again:
goto again;
}
- se = pick_next_entity(cfs_rq, curr);
+ se = pick_next_entity(cfs_rq);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
@@ -8112,7 +8373,7 @@ again:
}
}
- se = pick_next_entity(cfs_rq, curr);
+ se = pick_next_entity(cfs_rq);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
@@ -8151,7 +8412,7 @@ simple:
put_prev_task(rq, prev);
do {
- se = pick_next_entity(cfs_rq, NULL);
+ se = pick_next_entity(cfs_rq);
set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
@@ -8172,6 +8433,7 @@ done: __maybe_unused;
hrtick_start_fair(rq, p);
update_misfit_status(p, rq);
+ sched_fair_update_stop_tick(rq, p);
return p;
@@ -8222,8 +8484,6 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
/*
* sched_yield() is very simple
- *
- * The magic of dealing with the ->skip buddy is in pick_next_entity.
*/
static void yield_task_fair(struct rq *rq)
{
@@ -8239,21 +8499,19 @@ static void yield_task_fair(struct rq *rq)
clear_buddies(cfs_rq, se);
- if (curr->policy != SCHED_BATCH) {
- update_rq_clock(rq);
- /*
- * Update run-time statistics of the 'current'.
- */
- update_curr(cfs_rq);
- /*
- * Tell update_rq_clock() that we've just updated,
- * so we don't do microscopic update in schedule()
- * and double the fastpath cost.
- */
- rq_clock_skip_update(rq);
- }
+ update_rq_clock(rq);
+ /*
+ * Update run-time statistics of the 'current'.
+ */
+ update_curr(cfs_rq);
+ /*
+ * Tell update_rq_clock() that we've just updated,
+ * so we don't do microscopic update in schedule()
+ * and double the fastpath cost.
+ */
+ rq_clock_skip_update(rq);
- set_skip_buddy(se);
+ se->deadline += calc_delta_fair(se->slice, se);
}
static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
@@ -8416,6 +8674,11 @@ enum group_type {
*/
group_misfit_task,
/*
+ * Balance SMT group that's fully busy. Can benefit from migration
+ * a task on SMT with busy sibling to another CPU on idle core.
+ */
+ group_smt_balance,
+ /*
* SD_ASYM_PACKING only: One local CPU with higher capacity is available,
* and the task should be migrated to it instead of running on the
* current CPU.
@@ -8496,8 +8759,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
* Buddy candidates are cache hot:
*/
if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running &&
- (&p->se == cfs_rq_of(&p->se)->next ||
- &p->se == cfs_rq_of(&p->se)->last))
+ (&p->se == cfs_rq_of(&p->se)->next))
return 1;
if (sysctl_sched_migration_cost == -1)
@@ -8863,7 +9125,7 @@ static void attach_task(struct rq *rq, struct task_struct *p)
WARN_ON_ONCE(task_rq(p) != rq);
activate_task(rq, p, ENQUEUE_NOCLOCK);
- check_preempt_curr(rq, p, 0);
+ wakeup_preempt(rq, p, 0);
}
/*
@@ -9123,6 +9385,7 @@ struct sg_lb_stats {
unsigned int group_weight;
enum group_type group_type;
unsigned int group_asym_packing; /* Tasks should be moved to preferred CPU */
+ unsigned int group_smt_balance; /* Task on busy SMT be moved */
unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
@@ -9202,8 +9465,6 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
unsigned long capacity = scale_rt_capacity(cpu);
struct sched_group *sdg = sd->groups;
- cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);
-
if (!capacity)
capacity = 1;
@@ -9279,7 +9540,7 @@ static inline int
check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
{
return ((rq->cpu_capacity * sd->imbalance_pct) <
- (rq->cpu_capacity_orig * 100));
+ (arch_scale_cpu_capacity(cpu_of(rq)) * 100));
}
/*
@@ -9290,7 +9551,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
{
return rq->misfit_task_load &&
- (rq->cpu_capacity_orig < rq->rd->max_cpu_capacity ||
+ (arch_scale_cpu_capacity(rq->cpu) < rq->rd->max_cpu_capacity ||
check_cpu_capacity(rq, sd));
}
@@ -9396,6 +9657,9 @@ group_type group_classify(unsigned int imbalance_pct,
if (sgs->group_asym_packing)
return group_asym_packing;
+ if (sgs->group_smt_balance)
+ return group_smt_balance;
+
if (sgs->group_misfit_task_load)
return group_misfit_task;
@@ -9439,7 +9703,7 @@ static bool sched_use_asym_prio(struct sched_domain *sd, int cpu)
* can only do it if @group is an SMT group and has exactly on busy CPU. Larger
* imbalances in the number of CPUS are dealt with in find_busiest_group().
*
- * If we are balancing load within an SMT core, or at DIE domain level, always
+ * If we are balancing load within an SMT core, or at PKG domain level, always
* proceed.
*
* Return: true if @env::dst_cpu can do with asym_packing load balance. False
@@ -9465,6 +9729,71 @@ sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs
return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
}
+/* One group has more than one SMT CPU while the other group does not */
+static inline bool smt_vs_nonsmt_groups(struct sched_group *sg1,
+ struct sched_group *sg2)
+{
+ if (!sg1 || !sg2)
+ return false;
+
+ return (sg1->flags & SD_SHARE_CPUCAPACITY) !=
+ (sg2->flags & SD_SHARE_CPUCAPACITY);
+}
+
+static inline bool smt_balance(struct lb_env *env, struct sg_lb_stats *sgs,
+ struct sched_group *group)
+{
+ if (env->idle == CPU_NOT_IDLE)
+ return false;
+
+ /*
+ * For SMT source group, it is better to move a task
+ * to a CPU that doesn't have multiple tasks sharing its CPU capacity.
+ * Note that if a group has a single SMT, SD_SHARE_CPUCAPACITY
+ * will not be on.
+ */
+ if (group->flags & SD_SHARE_CPUCAPACITY &&
+ sgs->sum_h_nr_running > 1)
+ return true;
+
+ return false;
+}
+
+static inline long sibling_imbalance(struct lb_env *env,
+ struct sd_lb_stats *sds,
+ struct sg_lb_stats *busiest,
+ struct sg_lb_stats *local)
+{
+ int ncores_busiest, ncores_local;
+ long imbalance;
+
+ if (env->idle == CPU_NOT_IDLE || !busiest->sum_nr_running)
+ return 0;
+
+ ncores_busiest = sds->busiest->cores;
+ ncores_local = sds->local->cores;
+
+ if (ncores_busiest == ncores_local) {
+ imbalance = busiest->sum_nr_running;
+ lsub_positive(&imbalance, local->sum_nr_running);
+ return imbalance;
+ }
+
+ /* Balance such that nr_running/ncores ratio are same on both groups */
+ imbalance = ncores_local * busiest->sum_nr_running;
+ lsub_positive(&imbalance, ncores_busiest * local->sum_nr_running);
+ /* Normalize imbalance and do rounding on normalization */
+ imbalance = 2 * imbalance + ncores_local + ncores_busiest;
+ imbalance /= ncores_local + ncores_busiest;
+
+ /* Take advantage of resource in an empty sched group */
+ if (imbalance <= 1 && local->sum_nr_running == 0 &&
+ busiest->sum_nr_running > 1)
+ imbalance = 2;
+
+ return imbalance;
+}
+
static inline bool
sched_reduced_capacity(struct rq *rq, struct sched_domain *sd)
{
@@ -9557,6 +9886,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->group_asym_packing = 1;
}
+ /* Check for loaded SMT group to be balanced to dst CPU */
+ if (!local_group && smt_balance(env, sgs, group))
+ sgs->group_smt_balance = 1;
+
sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
/* Computing avg_load makes sense only when group is overloaded */
@@ -9641,6 +9974,16 @@ static bool update_sd_pick_busiest(struct lb_env *env,
return false;
break;
+ case group_smt_balance:
+ /*
+ * Check if we have spare CPUs on either SMT group to
+ * choose has spare or fully busy handling.
+ */
+ if (sgs->idle_cpus != 0 || busiest->idle_cpus != 0)
+ goto has_spare;
+
+ fallthrough;
+
case group_fully_busy:
/*
* Select the fully busy group with highest avg_load. In
@@ -9670,6 +10013,19 @@ static bool update_sd_pick_busiest(struct lb_env *env,
case group_has_spare:
/*
+ * Do not pick sg with SMT CPUs over sg with pure CPUs,
+ * as we do not want to pull task off SMT core with one task
+ * and make the core idle.
+ */
+ if (smt_vs_nonsmt_groups(sds->busiest, sg)) {
+ if (sg->flags & SD_SHARE_CPUCAPACITY && sgs->sum_h_nr_running <= 1)
+ return false;
+ else
+ return true;
+ }
+has_spare:
+
+ /*
* Select not overloaded group with lowest number of idle cpus
* and highest number of running tasks. We could also compare
* the spare capacity which is more stable but it can end up
@@ -9865,6 +10221,7 @@ static bool update_pick_idlest(struct sched_group *idlest,
case group_imbalanced:
case group_asym_packing:
+ case group_smt_balance:
/* Those types are not used in the slow wakeup path */
return false;
@@ -9996,6 +10353,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
case group_imbalanced:
case group_asym_packing:
+ case group_smt_balance:
/* Those type are not used in the slow wakeup path */
return NULL;
@@ -10250,6 +10608,13 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
return;
}
+ if (busiest->group_type == group_smt_balance) {
+ /* Reduce number of tasks sharing CPU capacity */
+ env->migration_type = migrate_task;
+ env->imbalance = 1;
+ return;
+ }
+
if (busiest->group_type == group_imbalanced) {
/*
* In the group_imb case we cannot rely on group-wide averages
@@ -10297,14 +10662,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
}
if (busiest->group_weight == 1 || sds->prefer_sibling) {
- unsigned int nr_diff = busiest->sum_nr_running;
/*
* When prefer sibling, evenly spread running tasks on
* groups.
*/
env->migration_type = migrate_task;
- lsub_positive(&nr_diff, local->sum_nr_running);
- env->imbalance = nr_diff;
+ env->imbalance = sibling_imbalance(env, sds, busiest, local);
} else {
/*
@@ -10501,20 +10864,27 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
* group's child domain.
*/
if (sds.prefer_sibling && local->group_type == group_has_spare &&
- busiest->sum_nr_running > local->sum_nr_running + 1)
+ sibling_imbalance(env, &sds, busiest, local) > 1)
goto force_balance;
if (busiest->group_type != group_overloaded) {
- if (env->idle == CPU_NOT_IDLE)
+ if (env->idle == CPU_NOT_IDLE) {
/*
* If the busiest group is not overloaded (and as a
* result the local one too) but this CPU is already
* busy, let another idle CPU try to pull task.
*/
goto out_balanced;
+ }
+
+ if (busiest->group_type == group_smt_balance &&
+ smt_vs_nonsmt_groups(sds.local, sds.busiest)) {
+ /* Let non SMT CPU pull from SMT CPU sharing with sibling */
+ goto force_balance;
+ }
if (busiest->group_weight > 1 &&
- local->idle_cpus <= (busiest->idle_cpus + 1))
+ local->idle_cpus <= (busiest->idle_cpus + 1)) {
/*
* If the busiest group is not overloaded
* and there is no imbalance between this and busiest
@@ -10525,12 +10895,14 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
* there is more than 1 CPU per group.
*/
goto out_balanced;
+ }
- if (busiest->sum_h_nr_running == 1)
+ if (busiest->sum_h_nr_running == 1) {
/*
* busiest doesn't have any tasks waiting to run
*/
goto out_balanced;
+ }
}
force_balance:
@@ -10763,8 +11135,9 @@ static int active_load_balance_cpu_stop(void *data);
static int should_we_balance(struct lb_env *env)
{
+ struct cpumask *swb_cpus = this_cpu_cpumask_var_ptr(should_we_balance_tmpmask);
struct sched_group *sg = env->sd->groups;
- int cpu;
+ int cpu, idle_smt = -1;
/*
* Ensure the balancing environment is consistent; can happen
@@ -10786,15 +11159,42 @@ static int should_we_balance(struct lb_env *env)
return 1;
}
+ cpumask_copy(swb_cpus, group_balance_mask(sg));
/* Try to find first idle CPU */
- for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
+ for_each_cpu_and(cpu, swb_cpus, env->cpus) {
if (!idle_cpu(cpu))
continue;
- /* Are we the first idle CPU? */
+ /*
+ * Don't balance to idle SMT in busy core right away when
+ * balancing cores, but remember the first idle SMT CPU for
+ * later consideration. Find CPU on an idle core first.
+ */
+ if (!(env->sd->flags & SD_SHARE_CPUCAPACITY) && !is_core_idle(cpu)) {
+ if (idle_smt == -1)
+ idle_smt = cpu;
+ /*
+ * If the core is not idle, and first SMT sibling which is
+ * idle has been found, then its not needed to check other
+ * SMT siblings for idleness:
+ */
+#ifdef CONFIG_SCHED_SMT
+ cpumask_andnot(swb_cpus, swb_cpus, cpu_smt_mask(cpu));
+#endif
+ continue;
+ }
+
+ /*
+ * Are we the first idle core in a non-SMT domain or higher,
+ * or the first idle CPU in a SMT domain?
+ */
return cpu == env->dst_cpu;
}
+ /* Are we the first idle CPU with busy siblings? */
+ if (idle_smt != -1)
+ return idle_smt == env->dst_cpu;
+
/* Are we the first CPU of this group ? */
return group_balance_cpu(sg) == env->dst_cpu;
}
@@ -11006,13 +11406,15 @@ more_balance:
busiest->push_cpu = this_cpu;
active_balance = 1;
}
- raw_spin_rq_unlock_irqrestore(busiest, flags);
+ preempt_disable();
+ raw_spin_rq_unlock_irqrestore(busiest, flags);
if (active_balance) {
stop_one_cpu_nowait(cpu_of(busiest),
active_load_balance_cpu_stop, busiest,
&busiest->active_balance_work);
}
+ preempt_enable();
}
} else {
sd->nr_balance_failed = 0;
@@ -11320,36 +11722,39 @@ static inline int on_null_domain(struct rq *rq)
#ifdef CONFIG_NO_HZ_COMMON
/*
- * idle load balancing details
- * - When one of the busy CPUs notice that there may be an idle rebalancing
+ * NOHZ idle load balancing (ILB) details:
+ *
+ * - When one of the busy CPUs notices that there may be an idle rebalancing
* needed, they will kick the idle load balancer, which then does idle
* load balancing for all the idle CPUs.
- * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED not set
+ *
+ * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED is not set
* anywhere yet.
*/
-
static inline int find_new_ilb(void)
{
- int ilb;
const struct cpumask *hk_mask;
+ int ilb_cpu;
hk_mask = housekeeping_cpumask(HK_TYPE_MISC);
- for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) {
+ for_each_cpu_and(ilb_cpu, nohz.idle_cpus_mask, hk_mask) {
- if (ilb == smp_processor_id())
+ if (ilb_cpu == smp_processor_id())
continue;
- if (idle_cpu(ilb))
- return ilb;
+ if (idle_cpu(ilb_cpu))
+ return ilb_cpu;
}
- return nr_cpu_ids;
+ return -1;
}
/*
- * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
- * idle CPU in the HK_TYPE_MISC housekeeping set (if there is one).
+ * Kick a CPU to do the NOHZ balancing, if it is time for it, via a cross-CPU
+ * SMP function call (IPI).
+ *
+ * We pick the first idle CPU in the HK_TYPE_MISC housekeeping set (if there is one).
*/
static void kick_ilb(unsigned int flags)
{
@@ -11363,8 +11768,7 @@ static void kick_ilb(unsigned int flags)
nohz.next_balance = jiffies+1;
ilb_cpu = find_new_ilb();
-
- if (ilb_cpu >= nr_cpu_ids)
+ if (ilb_cpu < 0)
return;
/*
@@ -11377,7 +11781,7 @@ static void kick_ilb(unsigned int flags)
/*
* This way we generate an IPI on the target CPU which
- * is idle. And the softirq performing nohz idle load balance
+ * is idle, and the softirq performing NOHZ idle load balancing
* will be run before returning from the IPI.
*/
smp_call_function_single_async(ilb_cpu, &cpu_rq(ilb_cpu)->nohz_csd);
@@ -11406,7 +11810,7 @@ static void nohz_balancer_kick(struct rq *rq)
/*
* None are in tickless mode and hence no need for NOHZ idle load
- * balancing.
+ * balancing:
*/
if (likely(!atomic_read(&nohz.nr_cpus)))
return;
@@ -11428,9 +11832,8 @@ static void nohz_balancer_kick(struct rq *rq)
sd = rcu_dereference(rq->sd);
if (sd) {
/*
- * If there's a CFS task and the current CPU has reduced
- * capacity; kick the ILB to see if there's a better CPU to run
- * on.
+ * If there's a runnable CFS task and the current CPU has reduced
+ * capacity, kick the ILB to see if there's a better CPU to run on:
*/
if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) {
flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
@@ -11482,11 +11885,11 @@ static void nohz_balancer_kick(struct rq *rq)
if (sds) {
/*
* If there is an imbalance between LLC domains (IOW we could
- * increase the overall cache use), we need some less-loaded LLC
- * domain to pull some load. Likewise, we may need to spread
+ * increase the overall cache utilization), we need a less-loaded LLC
+ * domain to pull some load from. Likewise, we may need to spread
* load within the current LLC domain (e.g. packed SMT cores but
* other CPUs are idle). We can't really know from here how busy
- * the others are - so just get a nohz balance going if it looks
+ * the others are - so just get a NOHZ balance going if it looks
* like this LLC domain has tasks we could move.
*/
nr_busy = atomic_read(&sds->nr_busy_cpus);
@@ -11756,8 +12159,19 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
}
/*
- * Check if we need to run the ILB for updating blocked load before entering
- * idle state.
+ * Check if we need to directly run the ILB for updating blocked load before
+ * entering idle state. Here we run ILB directly without issuing IPIs.
+ *
+ * Note that when this function is called, the tick may not yet be stopped on
+ * this CPU yet. nohz.idle_cpus_mask is updated only when tick is stopped and
+ * cleared on the next busy tick. In other words, nohz.idle_cpus_mask updates
+ * don't align with CPUs enter/exit idle to avoid bottlenecks due to high idle
+ * entry/exit rate (usec). So it is possible that _nohz_idle_balance() is
+ * called from this function on (this) CPU that's not yet in the mask. That's
+ * OK because the goal of nohz_run_idle_balance() is to run ILB only for
+ * updating the blocked load of already idle CPUs without waking up one of
+ * those idle CPUs and outside the preempt disable / irq off phase of the local
+ * cpu about to enter idle, because it can take a long time.
*/
void nohz_run_idle_balance(int cpu)
{
@@ -12007,8 +12421,8 @@ static void rq_offline_fair(struct rq *rq)
static inline bool
__entity_slice_used(struct sched_entity *se, int min_nr_tasks)
{
- u64 slice = sched_slice(cfs_rq_of(se), se);
u64 rtime = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+ u64 slice = se->slice;
return (rtime * min_nr_tasks > slice);
}
@@ -12164,8 +12578,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
*/
static void task_fork_fair(struct task_struct *p)
{
- struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se, *curr;
+ struct cfs_rq *cfs_rq;
struct rq *rq = this_rq();
struct rq_flags rf;
@@ -12174,22 +12588,9 @@ static void task_fork_fair(struct task_struct *p)
cfs_rq = task_cfs_rq(current);
curr = cfs_rq->curr;
- if (curr) {
+ if (curr)
update_curr(cfs_rq);
- se->vruntime = curr->vruntime;
- }
- place_entity(cfs_rq, se, 1);
-
- if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
- /*
- * Upon rescheduling, sched_class::put_prev_task() will place
- * 'current' within the tree based on its new key value.
- */
- swap(curr->vruntime, se->vruntime);
- resched_curr(rq);
- }
-
- se->vruntime -= cfs_rq->min_vruntime;
+ place_entity(cfs_rq, se, ENQUEUE_INITIAL);
rq_unlock(rq, &rf);
}
@@ -12215,35 +12616,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
if (p->prio > oldprio)
resched_curr(rq);
} else
- check_preempt_curr(rq, p, 0);
-}
-
-static inline bool vruntime_normalized(struct task_struct *p)
-{
- struct sched_entity *se = &p->se;
-
- /*
- * In both the TASK_ON_RQ_QUEUED and TASK_ON_RQ_MIGRATING cases,
- * the dequeue_entity(.flags=0) will already have normalized the
- * vruntime.
- */
- if (p->on_rq)
- return true;
-
- /*
- * When !on_rq, vruntime of the task has usually NOT been normalized.
- * But there are some cases where it has already been normalized:
- *
- * - A forked child which is waiting for being woken up by
- * wake_up_new_task().
- * - A task which has been woken up by try_to_wake_up() and
- * waiting for actually being woken up by sched_ttwu_pending().
- */
- if (!se->sum_exec_runtime ||
- (READ_ONCE(p->__state) == TASK_WAKING && p->sched_remote_wakeup))
- return true;
-
- return false;
+ wakeup_preempt(rq, p, 0);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -12316,16 +12689,6 @@ static void attach_entity_cfs_rq(struct sched_entity *se)
static void detach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
-
- if (!vruntime_normalized(p)) {
- /*
- * Fix up our vruntime so that the current sleep doesn't
- * cause 'unlimited' sleep bonus.
- */
- place_entity(cfs_rq, se, 0);
- se->vruntime -= cfs_rq->min_vruntime;
- }
detach_entity_cfs_rq(se);
}
@@ -12333,12 +12696,8 @@ static void detach_task_cfs_rq(struct task_struct *p)
static void attach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
attach_entity_cfs_rq(se);
-
- if (!vruntime_normalized(p))
- se->vruntime += cfs_rq->min_vruntime;
}
static void switched_from_fair(struct rq *rq, struct task_struct *p)
@@ -12359,7 +12718,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
if (task_current(rq, p))
resched_curr(rq);
else
- check_preempt_curr(rq, p, 0);
+ wakeup_preempt(rq, p, 0);
}
}
@@ -12450,7 +12809,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
tg->shares = NICE_0_LOAD;
- init_cfs_bandwidth(tg_cfs_bandwidth(tg));
+ init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent));
for_each_possible_cpu(i) {
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
@@ -12703,7 +13062,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
* idle runqueue:
*/
if (rq->cfs.load.weight)
- rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
+ rr_interval = NS_TO_JIFFIES(se->slice);
return rr_interval;
}
@@ -12718,7 +13077,7 @@ DEFINE_SCHED_CLASS(fair) = {
.yield_task = yield_task_fair,
.yield_to_task = yield_to_task_fair,
- .check_preempt_curr = check_preempt_wakeup,
+ .wakeup_preempt = check_preempt_wakeup_fair,
.pick_next_task = __pick_next_task_fair,
.put_prev_task = put_prev_task_fair,
@@ -12805,6 +13164,8 @@ __init void init_sched_fair_class(void)
for_each_possible_cpu(i) {
zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i));
zalloc_cpumask_var_node(&per_cpu(select_rq_mask, i), GFP_KERNEL, cpu_to_node(i));
+ zalloc_cpumask_var_node(&per_cpu(should_we_balance_tmpmask, i),
+ GFP_KERNEL, cpu_to_node(i));
#ifdef CONFIG_CFS_BANDWIDTH
INIT_CSD(&cpu_rq(i)->cfsb_csd, __cfsb_csd_unthrottle, cpu_rq(i));
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index ee7f23c76bd3..a3ddf84de430 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -1,16 +1,12 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Only give sleepers 50% of their service deficit. This allows
- * them to run sooner, but does not allow tons of sleepers to
- * rip the spread apart.
- */
-SCHED_FEAT(GENTLE_FAIR_SLEEPERS, true)
/*
- * Place new tasks ahead so that they do not starve already running
- * tasks
+ * Using the avg_vruntime, do the right thing and preserve lag across
+ * sleep+wake cycles. EEVDF placement strategy #1, #2 if disabled.
*/
-SCHED_FEAT(START_DEBIT, true)
+SCHED_FEAT(PLACE_LAG, true)
+SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
+SCHED_FEAT(RUN_TO_PARITY, true)
/*
* Prefer to schedule the task we woke last (assuming it failed
@@ -20,13 +16,6 @@ SCHED_FEAT(START_DEBIT, true)
SCHED_FEAT(NEXT_BUDDY, false)
/*
- * Prefer to schedule the task that ran last (when we did
- * wake-preempt) as that likely will touch the same data, increases
- * cache locality.
- */
-SCHED_FEAT(LAST_BUDDY, true)
-
-/*
* Consider buddies to be cache hot, decreases the likeliness of a
* cache buddy being migrated away, increases cache locality.
*/
@@ -60,7 +49,6 @@ SCHED_FEAT(TTWU_QUEUE, true)
/*
* When doing wakeups, attempt to limit superfluous scans of the LLC domain.
*/
-SCHED_FEAT(SIS_PROP, false)
SCHED_FEAT(SIS_UTIL, true)
/*
@@ -99,5 +87,4 @@ SCHED_FEAT(UTIL_EST_FASTUP, true)
SCHED_FEAT(LATENCY_WARN, false)
-SCHED_FEAT(ALT_PERIOD, true)
-SCHED_FEAT(BASE_SLICE, true)
+SCHED_FEAT(HZ_BW, true)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 342f58a329f5..565f8374ddbb 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -373,6 +373,7 @@ EXPORT_SYMBOL_GPL(play_idle_precise);
void cpu_startup_entry(enum cpuhp_state state)
{
+ current->flags |= PF_IDLE;
arch_cpu_idle_prepare();
cpuhp_online_idle(state);
while (1)
@@ -400,7 +401,7 @@ balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
/*
* Idle tasks are unconditionally rescheduled:
*/
-static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
+static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
{
resched_curr(rq);
}
@@ -481,7 +482,7 @@ DEFINE_SCHED_CLASS(idle) = {
/* dequeue is not valid, we print a debug message there: */
.dequeue_task = dequeue_task_idle,
- .check_preempt_curr = check_preempt_curr_idle,
+ .wakeup_preempt = wakeup_preempt_idle,
.pick_next_task = pick_next_task_idle,
.put_prev_task = put_prev_task_idle,
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index 0f310768260c..63b6cf898220 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * Per Entity Load Tracking
+ * Per Entity Load Tracking (PELT)
*
* Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 9bb3f2b3ccfc..7b4aa5809c0f 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -140,7 +140,7 @@
static int psi_bug __read_mostly;
DEFINE_STATIC_KEY_FALSE(psi_disabled);
-DEFINE_STATIC_KEY_TRUE(psi_cgroups_enabled);
+static DEFINE_STATIC_KEY_TRUE(psi_cgroups_enabled);
#ifdef CONFIG_PSI_DEFAULT_DISABLED
static bool psi_enable;
@@ -434,14 +434,13 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
return growth;
}
-static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
+static void update_triggers(struct psi_group *group, u64 now,
enum psi_aggregators aggregator)
{
struct psi_trigger *t;
u64 *total = group->total[aggregator];
struct list_head *triggers;
u64 *aggregator_total;
- *update_total = false;
if (aggregator == PSI_AVGS) {
triggers = &group->avg_triggers;
@@ -471,14 +470,6 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
* events without dropping any).
*/
if (new_stall) {
- /*
- * Multiple triggers might be looking at the same state,
- * remember to update group->polling_total[] once we've
- * been through all of them. Also remember to extend the
- * polling time if we see new stall activity.
- */
- *update_total = true;
-
/* Calculate growth since last update */
growth = window_update(&t->win, now, total[t->state]);
if (!t->pending_event) {
@@ -503,8 +494,6 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
/* Reset threshold breach flag once event got generated */
t->pending_event = false;
}
-
- return now + group->rtpoll_min_period;
}
static u64 update_averages(struct psi_group *group, u64 now)
@@ -565,7 +554,6 @@ static void psi_avgs_work(struct work_struct *work)
struct delayed_work *dwork;
struct psi_group *group;
u32 changed_states;
- bool update_total;
u64 now;
dwork = to_delayed_work(work);
@@ -584,7 +572,7 @@ static void psi_avgs_work(struct work_struct *work)
* go - see calc_avgs() and missed_periods.
*/
if (now >= group->avg_next_update) {
- update_triggers(group, now, &update_total, PSI_AVGS);
+ update_triggers(group, now, PSI_AVGS);
group->avg_next_update = update_averages(group, now);
}
@@ -608,7 +596,7 @@ static void init_rtpoll_triggers(struct psi_group *group, u64 now)
group->rtpoll_next_update = now + group->rtpoll_min_period;
}
-/* Schedule polling if it's not already scheduled or forced. */
+/* Schedule rtpolling if it's not already scheduled or forced. */
static void psi_schedule_rtpoll_work(struct psi_group *group, unsigned long delay,
bool force)
{
@@ -640,7 +628,6 @@ static void psi_rtpoll_work(struct psi_group *group)
{
bool force_reschedule = false;
u32 changed_states;
- bool update_total;
u64 now;
mutex_lock(&group->rtpoll_trigger_lock);
@@ -649,37 +636,37 @@ static void psi_rtpoll_work(struct psi_group *group)
if (now > group->rtpoll_until) {
/*
- * We are either about to start or might stop polling if no
- * state change was recorded. Resetting poll_scheduled leaves
+ * We are either about to start or might stop rtpolling if no
+ * state change was recorded. Resetting rtpoll_scheduled leaves
* a small window for psi_group_change to sneak in and schedule
- * an immediate poll_work before we get to rescheduling. One
- * potential extra wakeup at the end of the polling window
- * should be negligible and polling_next_update still keeps
+ * an immediate rtpoll_work before we get to rescheduling. One
+ * potential extra wakeup at the end of the rtpolling window
+ * should be negligible and rtpoll_next_update still keeps
* updates correctly on schedule.
*/
atomic_set(&group->rtpoll_scheduled, 0);
/*
- * A task change can race with the poll worker that is supposed to
+ * A task change can race with the rtpoll worker that is supposed to
* report on it. To avoid missing events, ensure ordering between
- * poll_scheduled and the task state accesses, such that if the poll
- * worker misses the state update, the task change is guaranteed to
- * reschedule the poll worker:
+ * rtpoll_scheduled and the task state accesses, such that if the
+ * rtpoll worker misses the state update, the task change is
+ * guaranteed to reschedule the rtpoll worker:
*
- * poll worker:
- * atomic_set(poll_scheduled, 0)
+ * rtpoll worker:
+ * atomic_set(rtpoll_scheduled, 0)
* smp_mb()
* LOAD states
*
* task change:
* STORE states
- * if atomic_xchg(poll_scheduled, 1) == 0:
- * schedule poll worker
+ * if atomic_xchg(rtpoll_scheduled, 1) == 0:
+ * schedule rtpoll worker
*
* The atomic_xchg() implies a full barrier.
*/
smp_mb();
} else {
- /* Polling window is not over, keep rescheduling */
+ /* The rtpolling window is not over, keep rescheduling */
force_reschedule = true;
}
@@ -687,7 +674,7 @@ static void psi_rtpoll_work(struct psi_group *group)
collect_percpu_times(group, PSI_POLL, &changed_states);
if (changed_states & group->rtpoll_states) {
- /* Initialize trigger windows when entering polling mode */
+ /* Initialize trigger windows when entering rtpolling mode */
if (now > group->rtpoll_until)
init_rtpoll_triggers(group, now);
@@ -706,10 +693,12 @@ static void psi_rtpoll_work(struct psi_group *group)
}
if (now >= group->rtpoll_next_update) {
- group->rtpoll_next_update = update_triggers(group, now, &update_total, PSI_POLL);
- if (update_total)
+ if (changed_states & group->rtpoll_states) {
+ update_triggers(group, now, PSI_POLL);
memcpy(group->rtpoll_total, group->total[PSI_POLL],
sizeof(group->rtpoll_total));
+ }
+ group->rtpoll_next_update = now + group->rtpoll_min_period;
}
psi_schedule_rtpoll_work(group,
@@ -1009,6 +998,9 @@ void psi_account_irqtime(struct task_struct *task, u32 delta)
struct psi_group_cpu *groupc;
u64 now;
+ if (static_branch_likely(&psi_disabled))
+ return;
+
if (!task->pid)
return;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 00e0e5074115..6aaf0a3d6081 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -16,7 +16,7 @@ struct rt_bandwidth def_rt_bandwidth;
* period over which we measure -rt task CPU usage in us.
* default: 1s
*/
-unsigned int sysctl_sched_rt_period = 1000000;
+int sysctl_sched_rt_period = 1000000;
/*
* part of the period that we allow rt tasks to run in us.
@@ -25,7 +25,7 @@ unsigned int sysctl_sched_rt_period = 1000000;
int sysctl_sched_rt_runtime = 950000;
#ifdef CONFIG_SYSCTL
-static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC * RR_TIMESLICE) / HZ;
static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos);
static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
@@ -34,9 +34,11 @@ static struct ctl_table sched_rt_sysctls[] = {
{
.procname = "sched_rt_period_us",
.data = &sysctl_sched_rt_period,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(int),
.mode = 0644,
.proc_handler = sched_rt_handler,
+ .extra1 = SYSCTL_ONE,
+ .extra2 = SYSCTL_INT_MAX,
},
{
.procname = "sched_rt_runtime_us",
@@ -44,6 +46,8 @@ static struct ctl_table sched_rt_sysctls[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = sched_rt_handler,
+ .extra1 = SYSCTL_NEG_ONE,
+ .extra2 = (void *)&sysctl_sched_rt_period,
},
{
.procname = "sched_rr_timeslice_ms",
@@ -143,7 +147,6 @@ void init_rt_rq(struct rt_rq *rt_rq)
#if defined CONFIG_SMP
rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
rt_rq->highest_prio.next = MAX_RT_PRIO-1;
- rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
plist_head_init(&rt_rq->pushable_tasks);
#endif /* CONFIG_SMP */
@@ -358,53 +361,6 @@ static inline void rt_clear_overload(struct rq *rq)
cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
}
-static void update_rt_migration(struct rt_rq *rt_rq)
-{
- if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
- if (!rt_rq->overloaded) {
- rt_set_overload(rq_of_rt_rq(rt_rq));
- rt_rq->overloaded = 1;
- }
- } else if (rt_rq->overloaded) {
- rt_clear_overload(rq_of_rt_rq(rt_rq));
- rt_rq->overloaded = 0;
- }
-}
-
-static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
- struct task_struct *p;
-
- if (!rt_entity_is_task(rt_se))
- return;
-
- p = rt_task_of(rt_se);
- rt_rq = &rq_of_rt_rq(rt_rq)->rt;
-
- rt_rq->rt_nr_total++;
- if (p->nr_cpus_allowed > 1)
- rt_rq->rt_nr_migratory++;
-
- update_rt_migration(rt_rq);
-}
-
-static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
- struct task_struct *p;
-
- if (!rt_entity_is_task(rt_se))
- return;
-
- p = rt_task_of(rt_se);
- rt_rq = &rq_of_rt_rq(rt_rq)->rt;
-
- rt_rq->rt_nr_total--;
- if (p->nr_cpus_allowed > 1)
- rt_rq->rt_nr_migratory--;
-
- update_rt_migration(rt_rq);
-}
-
static inline int has_pushable_tasks(struct rq *rq)
{
return !plist_head_empty(&rq->rt.pushable_tasks);
@@ -438,6 +394,11 @@ static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
/* Update the highest prio pushable task */
if (p->prio < rq->rt.highest_prio.next)
rq->rt.highest_prio.next = p->prio;
+
+ if (!rq->rt.overloaded) {
+ rt_set_overload(rq);
+ rq->rt.overloaded = 1;
+ }
}
static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
@@ -451,6 +412,11 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
rq->rt.highest_prio.next = p->prio;
} else {
rq->rt.highest_prio.next = MAX_RT_PRIO-1;
+
+ if (rq->rt.overloaded) {
+ rt_clear_overload(rq);
+ rq->rt.overloaded = 0;
+ }
}
}
@@ -464,16 +430,6 @@ static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
{
}
-static inline
-void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-}
-
-static inline
-void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-}
-
static inline void rt_queue_push_tasks(struct rq *rq)
{
}
@@ -515,7 +471,7 @@ static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
min_cap = uclamp_eff_value(p, UCLAMP_MIN);
max_cap = uclamp_eff_value(p, UCLAMP_MAX);
- cpu_cap = capacity_orig_of(cpu);
+ cpu_cap = arch_scale_cpu_capacity(cpu);
return cpu_cap >= min(min_cap, max_cap);
}
@@ -953,7 +909,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
/*
* When we're idle and a woken (rt) task is
- * throttled check_preempt_curr() will set
+ * throttled wakeup_preempt() will set
* skip_update and the time between the wakeup
* and this unthrottle will get accounted as
* 'runtime'.
@@ -1281,7 +1237,6 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se);
inc_rt_prio(rt_rq, prio);
- inc_rt_migration(rt_se, rt_rq);
inc_rt_group(rt_se, rt_rq);
}
@@ -1294,7 +1249,6 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se);
dec_rt_prio(rt_rq, rt_se_prio(rt_se));
- dec_rt_migration(rt_se, rt_rq);
dec_rt_group(rt_se, rt_rq);
}
@@ -1715,7 +1669,7 @@ static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
/*
* Preempt the current task with a newly woken task if needed:
*/
-static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
+static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
{
if (p->prio < rq->curr->prio) {
resched_curr(rq);
@@ -2109,9 +2063,11 @@ retry:
*/
push_task = get_push_task(rq);
if (push_task) {
+ preempt_disable();
raw_spin_rq_unlock(rq);
stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
push_task, &rq->push_work);
+ preempt_enable();
raw_spin_rq_lock(rq);
}
@@ -2448,9 +2404,11 @@ skip:
double_unlock_balance(this_rq, src_rq);
if (push_task) {
+ preempt_disable();
raw_spin_rq_unlock(this_rq);
stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
push_task, &src_rq->push_work);
+ preempt_enable();
raw_spin_rq_lock(this_rq);
}
}
@@ -2702,7 +2660,7 @@ DEFINE_SCHED_CLASS(rt) = {
.dequeue_task = dequeue_task_rt,
.yield_task = yield_task_rt,
- .check_preempt_curr = check_preempt_curr_rt,
+ .wakeup_preempt = wakeup_preempt_rt,
.pick_next_task = pick_next_task_rt,
.put_prev_task = put_prev_task_rt,
@@ -2985,9 +2943,6 @@ static int sched_rt_global_constraints(void)
#ifdef CONFIG_SYSCTL
static int sched_rt_global_validate(void)
{
- if (sysctl_sched_rt_period <= 0)
- return -EINVAL;
-
if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
((u64)sysctl_sched_rt_runtime *
@@ -3018,7 +2973,7 @@ static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
old_period = sysctl_sched_rt_period;
old_runtime = sysctl_sched_rt_runtime;
- ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!ret && write) {
ret = sched_rt_global_validate();
@@ -3062,6 +3017,9 @@ static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
sched_rr_timeslice =
sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
msecs_to_jiffies(sysctl_sched_rr_timeslice);
+
+ if (sysctl_sched_rr_timeslice <= 0)
+ sysctl_sched_rr_timeslice = jiffies_to_msecs(RR_TIMESLICE);
}
mutex_unlock(&mutex);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e93e006a942b..2e5a95486a42 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -74,15 +74,6 @@
#include "../workqueue_internal.h"
-#ifdef CONFIG_CGROUP_SCHED
-#include <linux/cgroup.h>
-#include <linux/psi.h>
-#endif
-
-#ifdef CONFIG_SCHED_DEBUG
-# include <linux/static_key.h>
-#endif
-
#ifdef CONFIG_PARAVIRT
# include <asm/paravirt.h>
# include <asm/paravirt_api_clock.h>
@@ -109,14 +100,12 @@ extern __read_mostly int scheduler_running;
extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;
-extern unsigned int sysctl_sched_child_runs_first;
-
extern void calc_global_load_tick(struct rq *this_rq);
extern long calc_load_fold_active(struct rq *this_rq, long adjust);
extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
-extern unsigned int sysctl_sched_rt_period;
+extern int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
extern int sched_rr_timeslice;
@@ -454,11 +443,12 @@ extern void unregister_fair_sched_group(struct task_group *tg);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
-extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
+extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent);
extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
+extern bool cfs_task_bw_constrained(struct task_struct *p);
extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
struct sched_rt_entity *rt_se, int cpu,
@@ -494,6 +484,7 @@ static inline void set_task_rq_fair(struct sched_entity *se,
#else /* CONFIG_CGROUP_SCHED */
struct cfs_bandwidth { };
+static inline bool cfs_task_bw_constrained(struct task_struct *p) { return false; }
#endif /* CONFIG_CGROUP_SCHED */
@@ -548,6 +539,9 @@ struct cfs_rq {
unsigned int idle_nr_running; /* SCHED_IDLE */
unsigned int idle_h_nr_running; /* SCHED_IDLE */
+ s64 avg_vruntime;
+ u64 avg_load;
+
u64 exec_clock;
u64 min_vruntime;
#ifdef CONFIG_SCHED_CORE
@@ -567,8 +561,6 @@ struct cfs_rq {
*/
struct sched_entity *curr;
struct sched_entity *next;
- struct sched_entity *last;
- struct sched_entity *skip;
#ifdef CONFIG_SCHED_DEBUG
unsigned int nr_spread_over;
@@ -591,6 +583,7 @@ struct cfs_rq {
} removed;
#ifdef CONFIG_FAIR_GROUP_SCHED
+ u64 last_update_tg_load_avg;
unsigned long tg_load_avg_contrib;
long propagate;
long prop_runnable_sum;
@@ -636,12 +629,12 @@ struct cfs_rq {
u64 throttled_clock;
u64 throttled_clock_pelt;
u64 throttled_clock_pelt_time;
+ u64 throttled_clock_self;
+ u64 throttled_clock_self_time;
int throttled;
int throttle_count;
struct list_head throttled_list;
-#ifdef CONFIG_SMP
struct list_head throttled_csd_list;
-#endif
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
};
@@ -670,8 +663,6 @@ struct rt_rq {
} highest_prio;
#endif
#ifdef CONFIG_SMP
- unsigned int rt_nr_migratory;
- unsigned int rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
@@ -716,7 +707,6 @@ struct dl_rq {
u64 next;
} earliest_dl;
- unsigned int dl_nr_migratory;
int overloaded;
/*
@@ -958,10 +948,6 @@ struct rq {
/* runqueue lock: */
raw_spinlock_t __lock;
- /*
- * nr_running and cpu_load should be in the same cacheline because
- * remote CPUs use both these fields when doing load calculation.
- */
unsigned int nr_running;
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
@@ -1043,7 +1029,6 @@ struct rq {
struct sched_domain __rcu *sd;
unsigned long cpu_capacity;
- unsigned long cpu_capacity_orig;
struct balance_callback *balance_callback;
@@ -1074,9 +1059,6 @@ struct rq {
u64 idle_stamp;
u64 avg_idle;
- unsigned long wake_stamp;
- u64 wake_avg_idle;
-
/* This is used to determine avg_idle's max value */
u64 max_idle_balance_cost;
@@ -1245,6 +1227,7 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
bool fi);
+void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
/*
* Helpers to check if the CPU's core cookie matches with the task's cookie
@@ -1652,6 +1635,11 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
}
+DEFINE_LOCK_GUARD_1(task_rq_lock, struct task_struct,
+ _T->rq = task_rq_lock(_T->lock, &_T->rf),
+ task_rq_unlock(_T->rq, _T->lock, &_T->rf),
+ struct rq *rq; struct rq_flags rf)
+
static inline void
rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
__acquires(rq->lock)
@@ -1700,6 +1688,21 @@ rq_unlock(struct rq *rq, struct rq_flags *rf)
raw_spin_rq_unlock(rq);
}
+DEFINE_LOCK_GUARD_1(rq_lock, struct rq,
+ rq_lock(_T->lock, &_T->rf),
+ rq_unlock(_T->lock, &_T->rf),
+ struct rq_flags rf)
+
+DEFINE_LOCK_GUARD_1(rq_lock_irq, struct rq,
+ rq_lock_irq(_T->lock, &_T->rf),
+ rq_unlock_irq(_T->lock, &_T->rf),
+ struct rq_flags rf)
+
+DEFINE_LOCK_GUARD_1(rq_lock_irqsave, struct rq,
+ rq_lock_irqsave(_T->lock, &_T->rf),
+ rq_unlock_irqrestore(_T->lock, &_T->rf),
+ struct rq_flags rf)
+
static inline struct rq *
this_rq_lock_irq(struct rq_flags *rf)
__acquires(rq->lock)
@@ -1847,11 +1850,13 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
+DECLARE_PER_CPU(int, sd_share_id);
DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
extern struct static_key_false sched_asym_cpucapacity;
+extern struct static_key_false sched_cluster_active;
static __always_inline bool sched_asym_cpucap_active(void)
{
@@ -1882,6 +1887,7 @@ struct sched_group {
atomic_t ref;
unsigned int group_weight;
+ unsigned int cores;
struct sched_group_capacity *sgc;
int asym_prefer_cpu; /* CPU of highest priority in group */
int flags;
@@ -2131,12 +2137,13 @@ static inline int task_on_rq_migrating(struct task_struct *p)
}
/* Wake flags. The first three directly map to some SD flag value */
-#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
-#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
-#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
+#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
+#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
+#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
-#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
-#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */
#ifdef CONFIG_SMP
static_assert(WF_EXEC == SD_BALANCE_EXEC);
@@ -2195,6 +2202,7 @@ extern const u32 sched_prio_to_wmult[40];
#else
#define ENQUEUE_MIGRATED 0x00
#endif
+#define ENQUEUE_INITIAL 0x80
#define RETRY_TASK ((void *)-1UL)
@@ -2215,7 +2223,7 @@ struct sched_class {
void (*yield_task) (struct rq *rq);
bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
- void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
+ void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
struct task_struct *(*pick_next_task)(struct rq *rq);
@@ -2398,6 +2406,7 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq)
#endif
extern void schedule_idle(void);
+asmlinkage void schedule_user(void);
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
@@ -2488,7 +2497,7 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
-extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
+extern void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags);
#ifdef CONFIG_PREEMPT_RT
#define SCHED_NR_MIGRATE_BREAK 8
@@ -2499,11 +2508,9 @@ extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;
+extern unsigned int sysctl_sched_base_slice;
+
#ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_latency;
-extern unsigned int sysctl_sched_min_granularity;
-extern unsigned int sysctl_sched_idle_min_granularity;
-extern unsigned int sysctl_sched_wakeup_granularity;
extern int sysctl_resched_latency_warn_ms;
extern int sysctl_resched_latency_warn_once;
@@ -2609,6 +2616,12 @@ static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {}
#endif
+#define DEFINE_LOCK_GUARD_2(name, type, _lock, _unlock, ...) \
+__DEFINE_UNLOCK_GUARD(name, type, _unlock, type *lock2; __VA_ARGS__) \
+static inline class_##name##_t class_##name##_constructor(type *lock, type *lock2) \
+{ class_##name##_t _t = { .lock = lock, .lock2 = lock2 }, *_T = &_t; \
+ _lock; return _t; }
+
#ifdef CONFIG_SMP
static inline bool rq_order_less(struct rq *rq1, struct rq *rq2)
@@ -2738,6 +2751,16 @@ static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}
+static inline void double_raw_unlock(raw_spinlock_t *l1, raw_spinlock_t *l2)
+{
+ raw_spin_unlock(l1);
+ raw_spin_unlock(l2);
+}
+
+DEFINE_LOCK_GUARD_2(double_raw_spinlock, raw_spinlock_t,
+ double_raw_lock(_T->lock, _T->lock2),
+ double_raw_unlock(_T->lock, _T->lock2))
+
/*
* double_rq_unlock - safely unlock two runqueues
*
@@ -2795,6 +2818,10 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
#endif
+DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
+ double_rq_lock(_T->lock, _T->lock2),
+ double_rq_unlock(_T->lock, _T->lock2))
+
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
@@ -2934,11 +2961,6 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif
#ifdef CONFIG_SMP
-static inline unsigned long capacity_orig_of(int cpu)
-{
- return cpu_rq(cpu)->cpu_capacity_orig;
-}
-
/**
* enum cpu_util_type - CPU utilization type
* @FREQUENCY_UTIL: Utilization used to select frequency
@@ -3176,6 +3198,8 @@ static inline bool sched_energy_enabled(void)
return static_branch_unlikely(&sched_energy_present);
}
+extern struct cpufreq_governor schedutil_gov;
+
#else /* ! (CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL) */
#define perf_domain_span(pd) NULL
@@ -3229,6 +3253,8 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
extern void swake_up_all_locked(struct swait_queue_head *q);
extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
+
#ifdef CONFIG_PREEMPT_DYNAMIC
extern int preempt_dynamic_mode;
extern int sched_dynamic_mode(const char *str);
@@ -3480,4 +3506,7 @@ static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
static inline void init_sched_mm_cid(struct task_struct *t) { }
#endif
+extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
+extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
#endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 85590599b4d6..6cf7304e6449 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,7 +23,7 @@ balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
#endif /* CONFIG_SMP */
static void
-check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
+wakeup_preempt_stop(struct rq *rq, struct task_struct *p, int flags)
{
/* we're never preempted */
}
@@ -120,7 +120,7 @@ DEFINE_SCHED_CLASS(stop) = {
.dequeue_task = dequeue_task_stop,
.yield_task = yield_task_stop,
- .check_preempt_curr = check_preempt_curr_stop,
+ .wakeup_preempt = wakeup_preempt_stop,
.pick_next_task = pick_next_task_stop,
.put_prev_task = put_prev_task_stop,
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index 76b9b796e695..72505cd3b60a 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -18,7 +18,7 @@ EXPORT_SYMBOL(__init_swait_queue_head);
* If for some reason it would return 0, that means the previously waiting
* task is already running, so it will observe condition true (or has already).
*/
-void swake_up_locked(struct swait_queue_head *q)
+void swake_up_locked(struct swait_queue_head *q, int wake_flags)
{
struct swait_queue *curr;
@@ -26,7 +26,7 @@ void swake_up_locked(struct swait_queue_head *q)
return;
curr = list_first_entry(&q->task_list, typeof(*curr), task_list);
- wake_up_process(curr->task);
+ try_to_wake_up(curr->task, TASK_NORMAL, wake_flags);
list_del_init(&curr->task_list);
}
EXPORT_SYMBOL(swake_up_locked);
@@ -41,7 +41,7 @@ EXPORT_SYMBOL(swake_up_locked);
void swake_up_all_locked(struct swait_queue_head *q)
{
while (!list_empty(&q->task_list))
- swake_up_locked(q);
+ swake_up_locked(q, 0);
}
void swake_up_one(struct swait_queue_head *q)
@@ -49,7 +49,7 @@ void swake_up_one(struct swait_queue_head *q)
unsigned long flags;
raw_spin_lock_irqsave(&q->lock, flags);
- swake_up_locked(q);
+ swake_up_locked(q, 0);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(swake_up_one);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index d3a3b2646ec4..10d1391e7416 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -212,6 +212,69 @@ static unsigned int sysctl_sched_energy_aware = 1;
static DEFINE_MUTEX(sched_energy_mutex);
static bool sched_energy_update;
+static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
+{
+ bool any_asym_capacity = false;
+ struct cpufreq_policy *policy;
+ struct cpufreq_governor *gov;
+ int i;
+
+ /* EAS is enabled for asymmetric CPU capacity topologies. */
+ for_each_cpu(i, cpu_mask) {
+ if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, i))) {
+ any_asym_capacity = true;
+ break;
+ }
+ }
+ if (!any_asym_capacity) {
+ if (sched_debug()) {
+ pr_info("rd %*pbl: Checking EAS, CPUs do not have asymmetric capacities\n",
+ cpumask_pr_args(cpu_mask));
+ }
+ return false;
+ }
+
+ /* EAS definitely does *not* handle SMT */
+ if (sched_smt_active()) {
+ if (sched_debug()) {
+ pr_info("rd %*pbl: Checking EAS, SMT is not supported\n",
+ cpumask_pr_args(cpu_mask));
+ }
+ return false;
+ }
+
+ if (!arch_scale_freq_invariant()) {
+ if (sched_debug()) {
+ pr_info("rd %*pbl: Checking EAS: frequency-invariant load tracking not yet supported",
+ cpumask_pr_args(cpu_mask));
+ }
+ return false;
+ }
+
+ /* Do not attempt EAS if schedutil is not being used. */
+ for_each_cpu(i, cpu_mask) {
+ policy = cpufreq_cpu_get(i);
+ if (!policy) {
+ if (sched_debug()) {
+ pr_info("rd %*pbl: Checking EAS, cpufreq policy not set for CPU: %d",
+ cpumask_pr_args(cpu_mask), i);
+ }
+ return false;
+ }
+ gov = policy->governor;
+ cpufreq_cpu_put(policy);
+ if (gov != &schedutil_gov) {
+ if (sched_debug()) {
+ pr_info("rd %*pbl: Checking EAS, schedutil is mandatory\n",
+ cpumask_pr_args(cpu_mask));
+ }
+ return false;
+ }
+ }
+
+ return true;
+}
+
void rebuild_sched_domains_energy(void)
{
mutex_lock(&sched_energy_mutex);
@@ -230,6 +293,15 @@ static int sched_energy_aware_handler(struct ctl_table *table, int write,
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (!sched_is_eas_possible(cpu_active_mask)) {
+ if (write) {
+ return -EOPNOTSUPP;
+ } else {
+ *lenp = 0;
+ return 0;
+ }
+ }
+
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!ret && write) {
state = static_branch_unlikely(&sched_energy_present);
@@ -348,103 +420,33 @@ static void sched_energy_set(bool has_eas)
* 1. an Energy Model (EM) is available;
* 2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
* 3. no SMT is detected.
- * 4. the EM complexity is low enough to keep scheduling overheads low;
- * 5. schedutil is driving the frequency of all CPUs of the rd;
- * 6. frequency invariance support is present;
- *
- * The complexity of the Energy Model is defined as:
- *
- * C = nr_pd * (nr_cpus + nr_ps)
- *
- * with parameters defined as:
- * - nr_pd: the number of performance domains
- * - nr_cpus: the number of CPUs
- * - nr_ps: the sum of the number of performance states of all performance
- * domains (for example, on a system with 2 performance domains,
- * with 10 performance states each, nr_ps = 2 * 10 = 20).
- *
- * It is generally not a good idea to use such a model in the wake-up path on
- * very complex platforms because of the associated scheduling overheads. The
- * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
- * with per-CPU DVFS and less than 8 performance states each, for example.
+ * 4. schedutil is driving the frequency of all CPUs of the rd;
+ * 5. frequency invariance support is present;
*/
-#define EM_MAX_COMPLEXITY 2048
-
-extern struct cpufreq_governor schedutil_gov;
static bool build_perf_domains(const struct cpumask *cpu_map)
{
- int i, nr_pd = 0, nr_ps = 0, nr_cpus = cpumask_weight(cpu_map);
+ int i;
struct perf_domain *pd = NULL, *tmp;
int cpu = cpumask_first(cpu_map);
struct root_domain *rd = cpu_rq(cpu)->rd;
- struct cpufreq_policy *policy;
- struct cpufreq_governor *gov;
if (!sysctl_sched_energy_aware)
goto free;
- /* EAS is enabled for asymmetric CPU capacity topologies. */
- if (!per_cpu(sd_asym_cpucapacity, cpu)) {
- if (sched_debug()) {
- pr_info("rd %*pbl: CPUs do not have asymmetric capacities\n",
- cpumask_pr_args(cpu_map));
- }
+ if (!sched_is_eas_possible(cpu_map))
goto free;
- }
-
- /* EAS definitely does *not* handle SMT */
- if (sched_smt_active()) {
- pr_warn("rd %*pbl: Disabling EAS, SMT is not supported\n",
- cpumask_pr_args(cpu_map));
- goto free;
- }
-
- if (!arch_scale_freq_invariant()) {
- if (sched_debug()) {
- pr_warn("rd %*pbl: Disabling EAS: frequency-invariant load tracking not yet supported",
- cpumask_pr_args(cpu_map));
- }
- goto free;
- }
for_each_cpu(i, cpu_map) {
/* Skip already covered CPUs. */
if (find_pd(pd, i))
continue;
- /* Do not attempt EAS if schedutil is not being used. */
- policy = cpufreq_cpu_get(i);
- if (!policy)
- goto free;
- gov = policy->governor;
- cpufreq_cpu_put(policy);
- if (gov != &schedutil_gov) {
- if (rd->pd)
- pr_warn("rd %*pbl: Disabling EAS, schedutil is mandatory\n",
- cpumask_pr_args(cpu_map));
- goto free;
- }
-
/* Create the new pd and add it to the local list. */
tmp = pd_init(i);
if (!tmp)
goto free;
tmp->next = pd;
pd = tmp;
-
- /*
- * Count performance domains and performance states for the
- * complexity check.
- */
- nr_pd++;
- nr_ps += em_pd_nr_perf_states(pd->em_pd);
- }
-
- /* Bail out if the Energy Model complexity is too high. */
- if (nr_pd * (nr_ps + nr_cpus) > EM_MAX_COMPLEXITY) {
- WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n",
- cpumask_pr_args(cpu_map));
- goto free;
}
perf_domain_debug(cpu_map, pd);
@@ -666,11 +668,14 @@ static void destroy_sched_domains(struct sched_domain *sd)
DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(int, sd_share_id);
DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
+
DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
+DEFINE_STATIC_KEY_FALSE(sched_cluster_active);
static void update_top_cache_domain(int cpu)
{
@@ -691,6 +696,17 @@ static void update_top_cache_domain(int cpu)
per_cpu(sd_llc_id, cpu) = id;
rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
+ sd = lowest_flag_domain(cpu, SD_CLUSTER);
+ if (sd)
+ id = cpumask_first(sched_domain_span(sd));
+
+ /*
+ * This assignment should be placed after the sd_llc_id as
+ * we want this id equals to cluster id on cluster machines
+ * but equals to LLC id on non-Cluster machines.
+ */
+ per_cpu(sd_share_id, cpu) = id;
+
sd = lowest_flag_domain(cpu, SD_NUMA);
rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
@@ -722,8 +738,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
if (parent->parent) {
parent->parent->child = tmp;
- if (tmp->flags & SD_SHARE_CPUCAPACITY)
- parent->parent->groups->flags |= SD_SHARE_CPUCAPACITY;
+ parent->parent->groups->flags = tmp->flags;
}
/*
@@ -1118,7 +1133,7 @@ fail:
*
* - Simultaneous multithreading (SMT)
* - Multi-Core Cache (MC)
- * - Package (DIE)
+ * - Package (PKG)
*
* Where the last one more or less denotes everything up to a NUMA node.
*
@@ -1140,13 +1155,13 @@ fail:
*
* CPU 0 1 2 3 4 5 6 7
*
- * DIE [ ]
+ * PKG [ ]
* MC [ ] [ ]
* SMT [ ] [ ] [ ] [ ]
*
* - or -
*
- * DIE 0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
+ * PKG 0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
* MC 0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
* SMT 0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
*
@@ -1275,14 +1290,24 @@ build_sched_groups(struct sched_domain *sd, int cpu)
static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
{
struct sched_group *sg = sd->groups;
+ struct cpumask *mask = sched_domains_tmpmask2;
WARN_ON(!sg);
do {
- int cpu, max_cpu = -1;
+ int cpu, cores = 0, max_cpu = -1;
sg->group_weight = cpumask_weight(sched_group_span(sg));
+ cpumask_copy(mask, sched_group_span(sg));
+ for_each_cpu(cpu, mask) {
+ cores++;
+#ifdef CONFIG_SCHED_SMT
+ cpumask_andnot(mask, mask, cpu_smt_mask(cpu));
+#endif
+ }
+ sg->cores = cores;
+
if (!(sd->flags & SD_ASYM_PACKING))
goto next;
@@ -1539,6 +1564,7 @@ static struct cpumask ***sched_domains_numa_masks;
*/
#define TOPOLOGY_SD_FLAGS \
(SD_SHARE_CPUCAPACITY | \
+ SD_CLUSTER | \
SD_SHARE_PKG_RESOURCES | \
SD_NUMA | \
SD_ASYM_PACKING)
@@ -1670,7 +1696,7 @@ static struct sched_domain_topology_level default_topology[] = {
#ifdef CONFIG_SCHED_MC
{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
#endif
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { cpu_cpu_mask, SD_INIT_NAME(PKG) },
{ NULL, },
};
@@ -2103,22 +2129,31 @@ static int hop_cmp(const void *a, const void *b)
return -1;
}
-/*
- * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth next cpu
- * closest to @cpu from @cpumask.
- * cpumask: cpumask to find a cpu from
- * cpu: Nth cpu to find
- *
- * returns: cpu, or nr_cpu_ids when nothing found.
+/**
+ * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth closest CPU
+ * from @cpus to @cpu, taking into account distance
+ * from a given @node.
+ * @cpus: cpumask to find a cpu from
+ * @cpu: CPU to start searching
+ * @node: NUMA node to order CPUs by distance
+ *
+ * Return: cpu, or nr_cpu_ids when nothing found.
*/
int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
{
- struct __cmp_key k = { .cpus = cpus, .node = node, .cpu = cpu };
+ struct __cmp_key k = { .cpus = cpus, .cpu = cpu };
struct cpumask ***hop_masks;
int hop, ret = nr_cpu_ids;
+ if (node == NUMA_NO_NODE)
+ return cpumask_nth_and(cpu, cpus, cpu_online_mask);
+
rcu_read_lock();
+ /* CPU-less node entries are uninitialized in sched_domains_numa_masks */
+ node = numa_nearest_node(node, N_CPU);
+ k.node = node;
+
k.masks = rcu_dereference(sched_domains_numa_masks);
if (!k.masks)
goto unlock;
@@ -2353,6 +2388,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
struct rq *rq = NULL;
int i, ret = -ENOMEM;
bool has_asym = false;
+ bool has_cluster = false;
if (WARN_ON(cpumask_empty(cpu_map)))
goto error;
@@ -2470,20 +2506,29 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
/* Attach the domains */
rcu_read_lock();
for_each_cpu(i, cpu_map) {
+ unsigned long capacity;
+
rq = cpu_rq(i);
sd = *per_cpu_ptr(d.sd, i);
+ capacity = arch_scale_cpu_capacity(i);
/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
- if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
- WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
+ if (capacity > READ_ONCE(d.rd->max_cpu_capacity))
+ WRITE_ONCE(d.rd->max_cpu_capacity, capacity);
cpu_attach_domain(sd, d.rd, i);
+
+ if (lowest_flag_domain(i, SD_CLUSTER))
+ has_cluster = true;
}
rcu_read_unlock();
if (has_asym)
static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
+ if (has_cluster)
+ static_branch_inc_cpuslocked(&sched_cluster_active);
+
if (rq && sched_debug_verbose) {
pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
@@ -2583,6 +2628,9 @@ static void detach_destroy_domains(const struct cpumask *cpu_map)
if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))
static_branch_dec_cpuslocked(&sched_asym_cpucapacity);
+ if (static_branch_unlikely(&sched_cluster_active))
+ static_branch_dec_cpuslocked(&sched_cluster_active);
+
rcu_read_lock();
for_each_cpu(i, cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 48c53e4739ea..51e38f5f4701 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -58,13 +58,6 @@ void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry
EXPORT_SYMBOL(remove_wait_queue);
/*
- * Scan threshold to break wait queue walk.
- * This allows a waker to take a break from holding the
- * wait queue lock during the wait queue walk.
- */
-#define WAITQUEUE_WALK_BREAK_CNT 64
-
-/*
* The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
* wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
* number) then we wake that number of exclusive tasks, and potentially all
@@ -78,21 +71,13 @@ EXPORT_SYMBOL(remove_wait_queue);
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
- int nr_exclusive, int wake_flags, void *key,
- wait_queue_entry_t *bookmark)
+ int nr_exclusive, int wake_flags, void *key)
{
wait_queue_entry_t *curr, *next;
- int cnt = 0;
lockdep_assert_held(&wq_head->lock);
- if (bookmark && (bookmark->flags & WQ_FLAG_BOOKMARK)) {
- curr = list_next_entry(bookmark, entry);
-
- list_del(&bookmark->entry);
- bookmark->flags = 0;
- } else
- curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
+ curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
if (&curr->entry == &wq_head->head)
return nr_exclusive;
@@ -101,21 +86,11 @@ static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
unsigned flags = curr->flags;
int ret;
- if (flags & WQ_FLAG_BOOKMARK)
- continue;
-
ret = curr->func(curr, mode, wake_flags, key);
if (ret < 0)
break;
if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
break;
-
- if (bookmark && (++cnt > WAITQUEUE_WALK_BREAK_CNT) &&
- (&next->entry != &wq_head->head)) {
- bookmark->flags = WQ_FLAG_BOOKMARK;
- list_add_tail(&bookmark->entry, &next->entry);
- break;
- }
}
return nr_exclusive;
@@ -125,20 +100,12 @@ static int __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int m
int nr_exclusive, int wake_flags, void *key)
{
unsigned long flags;
- wait_queue_entry_t bookmark;
- int remaining = nr_exclusive;
-
- bookmark.flags = 0;
- bookmark.private = NULL;
- bookmark.func = NULL;
- INIT_LIST_HEAD(&bookmark.entry);
+ int remaining;
- do {
- spin_lock_irqsave(&wq_head->lock, flags);
- remaining = __wake_up_common(wq_head, mode, remaining,
- wake_flags, key, &bookmark);
- spin_unlock_irqrestore(&wq_head->lock, flags);
- } while (bookmark.flags & WQ_FLAG_BOOKMARK);
+ spin_lock_irqsave(&wq_head->lock, flags);
+ remaining = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags,
+ key);
+ spin_unlock_irqrestore(&wq_head->lock, flags);
return nr_exclusive - remaining;
}
@@ -161,28 +128,26 @@ int __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
}
EXPORT_SYMBOL(__wake_up);
+void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key)
+{
+ __wake_up_common_lock(wq_head, mode, 1, WF_CURRENT_CPU, key);
+}
+
/*
* Same as __wake_up but called with the spinlock in wait_queue_head_t held.
*/
void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr)
{
- __wake_up_common(wq_head, mode, nr, 0, NULL, NULL);
+ __wake_up_common(wq_head, mode, nr, 0, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_locked);
void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key)
{
- __wake_up_common(wq_head, mode, 1, 0, key, NULL);
+ __wake_up_common(wq_head, mode, 1, 0, key);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_key);
-void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
- unsigned int mode, void *key, wait_queue_entry_t *bookmark)
-{
- __wake_up_common(wq_head, mode, 1, 0, key, bookmark);
-}
-EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
-
/**
* __wake_up_sync_key - wake up threads blocked on a waitqueue.
* @wq_head: the waitqueue
@@ -228,7 +193,7 @@ EXPORT_SYMBOL_GPL(__wake_up_sync_key);
void __wake_up_locked_sync_key(struct wait_queue_head *wq_head,
unsigned int mode, void *key)
{
- __wake_up_common(wq_head, mode, 1, WF_SYNC, key, NULL);
+ __wake_up_common(wq_head, mode, 1, WF_SYNC, key);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d3e584065c7f..255999ba9190 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -110,11 +110,13 @@ struct seccomp_knotif {
* @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
* is allowed.
* @ioctl_flags: The flags used for the seccomp_addfd ioctl.
+ * @setfd: whether or not SECCOMP_ADDFD_FLAG_SETFD was set during notify_addfd
* @ret: The return value of the installing process. It is set to the fd num
* upon success (>= 0).
* @completion: Indicates that the installing process has completed fd
* installation, or gone away (either due to successful
* reply, or signal)
+ * @list: list_head for chaining seccomp_kaddfd together.
*
*/
struct seccomp_kaddfd {
@@ -138,14 +140,17 @@ struct seccomp_kaddfd {
* structure is fairly large, we store the notification-specific stuff in a
* separate structure.
*
- * @request: A semaphore that users of this notification can wait on for
- * changes. Actual reads and writes are still controlled with
- * filter->notify_lock.
+ * @requests: A semaphore that users of this notification can wait on for
+ * changes. Actual reads and writes are still controlled with
+ * filter->notify_lock.
+ * @flags: A set of SECCOMP_USER_NOTIF_FD_* flags.
* @next_id: The id of the next request.
* @notifications: A list of struct seccomp_knotif elements.
*/
+
struct notification {
- struct semaphore request;
+ atomic_t requests;
+ u32 flags;
u64 next_id;
struct list_head notifications;
};
@@ -555,6 +560,8 @@ static void __seccomp_filter_release(struct seccomp_filter *orig)
* drop its reference count, and notify
* about unused filters
*
+ * @tsk: task the filter should be released from.
+ *
* This function should only be called when the task is exiting as
* it detaches it from its filter tree. As such, READ_ONCE() and
* barriers are not needed here, as would normally be needed.
@@ -574,6 +581,8 @@ void seccomp_filter_release(struct task_struct *tsk)
/**
* seccomp_sync_threads: sets all threads to use current's filter
*
+ * @flags: SECCOMP_FILTER_FLAG_* flags to set during sync.
+ *
* Expects sighand and cred_guard_mutex locks to be held, and for
* seccomp_can_sync_threads() to have returned success already
* without dropping the locks.
@@ -1116,8 +1125,11 @@ static int seccomp_do_user_notification(int this_syscall,
list_add_tail(&n.list, &match->notif->notifications);
INIT_LIST_HEAD(&n.addfd);
- up(&match->notif->request);
- wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
+ atomic_inc(&match->notif->requests);
+ if (match->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ wake_up_poll_on_current_cpu(&match->wqh, EPOLLIN | EPOLLRDNORM);
+ else
+ wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
/*
* This is where we wait for a reply from userspace.
@@ -1450,6 +1462,37 @@ find_notification(struct seccomp_filter *filter, u64 id)
return NULL;
}
+static int recv_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync,
+ void *key)
+{
+ /* Avoid a wakeup if event not interesting for us. */
+ if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR)))
+ return 0;
+ return autoremove_wake_function(wait, mode, sync, key);
+}
+
+static int recv_wait_event(struct seccomp_filter *filter)
+{
+ DEFINE_WAIT_FUNC(wait, recv_wake_function);
+ int ret;
+
+ if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
+ return 0;
+
+ for (;;) {
+ ret = prepare_to_wait_event(&filter->wqh, &wait, TASK_INTERRUPTIBLE);
+
+ if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
+ break;
+
+ if (ret)
+ return ret;
+
+ schedule();
+ }
+ finish_wait(&filter->wqh, &wait);
+ return 0;
+}
static long seccomp_notify_recv(struct seccomp_filter *filter,
void __user *buf)
@@ -1467,7 +1510,7 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
memset(&unotif, 0, sizeof(unotif));
- ret = down_interruptible(&filter->notif->request);
+ ret = recv_wait_event(filter);
if (ret < 0)
return ret;
@@ -1515,7 +1558,8 @@ out:
if (should_sleep_killable(filter, knotif))
complete(&knotif->ready);
knotif->state = SECCOMP_NOTIFY_INIT;
- up(&filter->notif->request);
+ atomic_inc(&filter->notif->requests);
+ wake_up_poll(&filter->wqh, EPOLLIN | EPOLLRDNORM);
}
mutex_unlock(&filter->notify_lock);
}
@@ -1561,7 +1605,10 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
knotif->error = resp.error;
knotif->val = resp.val;
knotif->flags = resp.flags;
- complete(&knotif->ready);
+ if (filter->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ complete_on_current_cpu(&knotif->ready);
+ else
+ complete(&knotif->ready);
out:
mutex_unlock(&filter->notify_lock);
return ret;
@@ -1591,6 +1638,22 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
return ret;
}
+static long seccomp_notify_set_flags(struct seccomp_filter *filter,
+ unsigned long flags)
+{
+ long ret;
+
+ if (flags & ~SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ return -EINVAL;
+
+ ret = mutex_lock_interruptible(&filter->notify_lock);
+ if (ret < 0)
+ return ret;
+ filter->notif->flags = flags;
+ mutex_unlock(&filter->notify_lock);
+ return 0;
+}
+
static long seccomp_notify_addfd(struct seccomp_filter *filter,
struct seccomp_notif_addfd __user *uaddfd,
unsigned int size)
@@ -1720,6 +1783,8 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
case SECCOMP_IOCTL_NOTIF_ID_VALID:
return seccomp_notify_id_valid(filter, buf);
+ case SECCOMP_IOCTL_NOTIF_SET_FLAGS:
+ return seccomp_notify_set_flags(filter, arg);
}
/* Extensible Argument ioctls */
@@ -1777,7 +1842,6 @@ static struct file *init_listener(struct seccomp_filter *filter)
if (!filter->notif)
goto out;
- sema_init(&filter->notif->request, 0);
filter->notif->next_id = get_random_u64();
INIT_LIST_HEAD(&filter->notif->notifications);
diff --git a/kernel/signal.c b/kernel/signal.c
index 128e9bb3d1a2..47a7602dfe8d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -22,6 +22,7 @@
#include <linux/sched/cputime.h>
#include <linux/file.h>
#include <linux/fs.h>
+#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
@@ -414,7 +415,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
int override_rlimit, const unsigned int sigqueue_flags)
{
struct sigqueue *q = NULL;
- struct ucounts *ucounts = NULL;
+ struct ucounts *ucounts;
long sigpending;
/*
@@ -1057,12 +1058,11 @@ static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
signal->flags = SIGNAL_GROUP_EXIT;
signal->group_exit_code = sig;
signal->group_stop_count = 0;
- t = p;
- do {
+ __for_each_thread(signal, t) {
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
sigaddset(&t->pending.signal, SIGKILL);
signal_wake_up(t, 1);
- } while_each_thread(p, t);
+ }
return;
}
}
@@ -1260,7 +1260,17 @@ int send_signal_locked(int sig, struct kernel_siginfo *info,
static void print_fatal_signal(int signr)
{
struct pt_regs *regs = task_pt_regs(current);
- pr_info("potentially unexpected fatal signal %d.\n", signr);
+ struct file *exe_file;
+
+ exe_file = get_task_exe_file(current);
+ if (exe_file) {
+ pr_info("%pD: %s: potentially unexpected fatal signal %d.\n",
+ exe_file, current->comm, signr);
+ fput(exe_file);
+ } else {
+ pr_info("%s: potentially unexpected fatal signal %d.\n",
+ current->comm, signr);
+ }
#if defined(__i386__) && !defined(__arch_um__)
pr_info("code at %08lx: ", regs->ip);
@@ -1460,16 +1470,21 @@ int group_send_sig_info(int sig, struct kernel_siginfo *info,
int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
{
struct task_struct *p = NULL;
- int retval, success;
+ int ret = -ESRCH;
- success = 0;
- retval = -ESRCH;
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
int err = group_send_sig_info(sig, info, p, PIDTYPE_PGID);
- success |= !err;
- retval = err;
+ /*
+ * If group_send_sig_info() succeeds at least once ret
+ * becomes 0 and after that the code below has no effect.
+ * Otherwise we return the last err or -ESRCH if this
+ * process group is empty.
+ */
+ if (ret)
+ ret = err;
} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
- return success ? 0 : retval;
+
+ return ret;
}
int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
@@ -1707,9 +1722,8 @@ void force_sigsegv(int sig)
force_sig(SIGSEGV);
}
-int force_sig_fault_to_task(int sig, int code, void __user *addr
- ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
- , struct task_struct *t)
+int force_sig_fault_to_task(int sig, int code, void __user *addr,
+ struct task_struct *t)
{
struct kernel_siginfo info;
@@ -1718,24 +1732,15 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
-#ifdef __ia64__
- info.si_imm = imm;
- info.si_flags = flags;
- info.si_isr = isr;
-#endif
return force_sig_info_to_task(&info, t, HANDLER_CURRENT);
}
-int force_sig_fault(int sig, int code, void __user *addr
- ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr))
+int force_sig_fault(int sig, int code, void __user *addr)
{
- return force_sig_fault_to_task(sig, code, addr
- ___ARCH_SI_IA64(imm, flags, isr), current);
+ return force_sig_fault_to_task(sig, code, addr, current);
}
-int send_sig_fault(int sig, int code, void __user *addr
- ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
- , struct task_struct *t)
+int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t)
{
struct kernel_siginfo info;
@@ -1744,11 +1749,6 @@ int send_sig_fault(int sig, int code, void __user *addr
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
-#ifdef __ia64__
- info.si_imm = imm;
- info.si_flags = flags;
- info.si_isr = isr;
-#endif
return send_sig_info(info.si_signo, &info, t);
}
@@ -2318,15 +2318,38 @@ static int ptrace_stop(int exit_code, int why, unsigned long message,
do_notify_parent_cldstop(current, false, why);
/*
- * Don't want to allow preemption here, because
- * sys_ptrace() needs this task to be inactive.
+ * The previous do_notify_parent_cldstop() invocation woke ptracer.
+ * One a PREEMPTION kernel this can result in preemption requirement
+ * which will be fulfilled after read_unlock() and the ptracer will be
+ * put on the CPU.
+ * The ptracer is in wait_task_inactive(, __TASK_TRACED) waiting for
+ * this task wait in schedule(). If this task gets preempted then it
+ * remains enqueued on the runqueue. The ptracer will observe this and
+ * then sleep for a delay of one HZ tick. In the meantime this task
+ * gets scheduled, enters schedule() and will wait for the ptracer.
*
- * XXX: implement read_unlock_no_resched().
+ * This preemption point is not bad from a correctness point of
+ * view but extends the runtime by one HZ tick time due to the
+ * ptracer's sleep. The preempt-disable section ensures that there
+ * will be no preemption between unlock and schedule() and so
+ * improving the performance since the ptracer will observe that
+ * the tracee is scheduled out once it gets on the CPU.
+ *
+ * On PREEMPT_RT locking tasklist_lock does not disable preemption.
+ * Therefore the task can be preempted after do_notify_parent_cldstop()
+ * before unlocking tasklist_lock so there is no benefit in doing this.
+ *
+ * In fact disabling preemption is harmful on PREEMPT_RT because
+ * the spinlock_t in cgroup_enter_frozen() must not be acquired
+ * with preemption disabled due to the 'sleeping' spinlock
+ * substitution of RT.
*/
- preempt_disable();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
read_unlock(&tasklist_lock);
cgroup_enter_frozen();
- preempt_enable_no_resched();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable_no_resched();
schedule();
cgroup_leave_frozen(true);
diff --git a/kernel/smp.c b/kernel/smp.c
index 385179dae360..f085ebcdf9e7 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -46,6 +46,8 @@ static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data);
static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
+static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1);
+
static void __flush_smp_call_function_queue(bool warn_cpu_offline);
int smpcfd_prepare_cpu(unsigned int cpu)
@@ -125,7 +127,7 @@ send_call_function_ipi_mask(struct cpumask *mask)
}
static __always_inline void
-csd_do_func(smp_call_func_t func, void *info, struct __call_single_data *csd)
+csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd)
{
trace_csd_function_entry(func, csd);
func(info);
@@ -168,11 +170,13 @@ static DEFINE_PER_CPU(void *, cur_csd_info);
static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */
module_param(csd_lock_timeout, ulong, 0444);
+static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */
+module_param(panic_on_ipistall, int, 0444);
static atomic_t csd_bug_count = ATOMIC_INIT(0);
/* Record current CSD work for current CPU, NULL to erase. */
-static void __csd_lock_record(struct __call_single_data *csd)
+static void __csd_lock_record(call_single_data_t *csd)
{
if (!csd) {
smp_mb(); /* NULL cur_csd after unlock. */
@@ -187,13 +191,13 @@ static void __csd_lock_record(struct __call_single_data *csd)
/* Or before unlock, as the case may be. */
}
-static __always_inline void csd_lock_record(struct __call_single_data *csd)
+static __always_inline void csd_lock_record(call_single_data_t *csd)
{
if (static_branch_unlikely(&csdlock_debug_enabled))
__csd_lock_record(csd);
}
-static int csd_lock_wait_getcpu(struct __call_single_data *csd)
+static int csd_lock_wait_getcpu(call_single_data_t *csd)
{
unsigned int csd_type;
@@ -208,7 +212,7 @@ static int csd_lock_wait_getcpu(struct __call_single_data *csd)
* the CSD_TYPE_SYNC/ASYNC types provide the destination CPU,
* so waiting on other types gets much less information.
*/
-static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *ts1, int *bug_id)
+static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id)
{
int cpu = -1;
int cpux;
@@ -228,6 +232,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
}
ts2 = sched_clock();
+ /* How long since we last checked for a stuck CSD lock.*/
ts_delta = ts2 - *ts1;
if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0))
return false;
@@ -241,9 +246,17 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
else
cpux = cpu;
cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */
+ /* How long since this CSD lock was stuck. */
+ ts_delta = ts2 - ts0;
pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n",
- firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts2 - ts0,
+ firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts_delta,
cpu, csd->func, csd->info);
+ /*
+ * If the CSD lock is still stuck after 5 minutes, it is unlikely
+ * to become unstuck. Use a signed comparison to avoid triggering
+ * on underflows when the TSC is out of sync between sockets.
+ */
+ BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC));
if (cpu_cur_csd && csd != cpu_cur_csd) {
pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n",
*bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)),
@@ -253,13 +266,15 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
*bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request");
}
if (cpu >= 0) {
- dump_cpu_task(cpu);
+ if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0))
+ dump_cpu_task(cpu);
if (!cpu_cur_csd) {
pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu);
arch_send_call_function_single_ipi(cpu);
}
}
- dump_stack();
+ if (firsttime)
+ dump_stack();
*ts1 = ts2;
return false;
@@ -272,7 +287,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
* previous function call. For multi-cpu calls its even more interesting
* as we'll have to ensure no other cpu is observing our csd.
*/
-static void __csd_lock_wait(struct __call_single_data *csd)
+static void __csd_lock_wait(call_single_data_t *csd)
{
int bug_id = 0;
u64 ts0, ts1;
@@ -286,7 +301,7 @@ static void __csd_lock_wait(struct __call_single_data *csd)
smp_acquire__after_ctrl_dep();
}
-static __always_inline void csd_lock_wait(struct __call_single_data *csd)
+static __always_inline void csd_lock_wait(call_single_data_t *csd)
{
if (static_branch_unlikely(&csdlock_debug_enabled)) {
__csd_lock_wait(csd);
@@ -296,17 +311,17 @@ static __always_inline void csd_lock_wait(struct __call_single_data *csd)
smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
}
#else
-static void csd_lock_record(struct __call_single_data *csd)
+static void csd_lock_record(call_single_data_t *csd)
{
}
-static __always_inline void csd_lock_wait(struct __call_single_data *csd)
+static __always_inline void csd_lock_wait(call_single_data_t *csd)
{
smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
}
#endif
-static __always_inline void csd_lock(struct __call_single_data *csd)
+static __always_inline void csd_lock(call_single_data_t *csd)
{
csd_lock_wait(csd);
csd->node.u_flags |= CSD_FLAG_LOCK;
@@ -319,7 +334,7 @@ static __always_inline void csd_lock(struct __call_single_data *csd)
smp_wmb();
}
-static __always_inline void csd_unlock(struct __call_single_data *csd)
+static __always_inline void csd_unlock(call_single_data_t *csd)
{
WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK));
@@ -372,7 +387,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node)
* for execution on the given CPU. data must already have
* ->func, ->info, and ->flags set.
*/
-static int generic_exec_single(int cpu, struct __call_single_data *csd)
+static int generic_exec_single(int cpu, call_single_data_t *csd)
{
if (cpu == smp_processor_id()) {
smp_call_func_t func = csd->func;
@@ -433,9 +448,14 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline)
struct llist_node *entry, *prev;
struct llist_head *head;
static bool warned;
+ atomic_t *tbt;
lockdep_assert_irqs_disabled();
+ /* Allow waiters to send backtrace NMI from here onwards */
+ tbt = this_cpu_ptr(&trigger_backtrace);
+ atomic_set_release(tbt, 1);
+
head = this_cpu_ptr(&call_single_queue);
entry = llist_del_all(head);
entry = llist_reverse_order(entry);
@@ -658,7 +678,7 @@ EXPORT_SYMBOL(smp_call_function_single);
*
* Return: %0 on success or negative errno value on error
*/
-int smp_call_function_single_async(int cpu, struct __call_single_data *csd)
+int smp_call_function_single_async(int cpu, call_single_data_t *csd)
{
int err = 0;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index f47d8f375946..1992b62e980b 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -272,8 +272,7 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
if (tsk) {
- kthread_stop(tsk);
- put_task_struct(tsk);
+ kthread_stop_put(tsk);
*per_cpu_ptr(ht->store, cpu) = NULL;
}
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 807b34ccd797..210cf5f8d92c 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -612,7 +612,7 @@ static inline void tick_irq_exit(void)
int cpu = smp_processor_id();
/* Make sure that timer wheel updates are propagated */
- if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
+ if ((sched_core_idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
if (!in_hardirq())
tick_nohz_irq_exit();
}
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 9ed5ce989415..4f65824879ab 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -151,6 +151,7 @@ unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store,
put_task_stack(tsk);
return c.len;
}
+EXPORT_SYMBOL_GPL(stack_trace_save_tsk);
/**
* stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
@@ -301,6 +302,7 @@ unsigned int stack_trace_save_tsk(struct task_struct *task,
save_stack_trace_tsk(task, &trace);
return trace.nr_entries;
}
+EXPORT_SYMBOL_GPL(stack_trace_save_tsk);
/**
* stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
diff --git a/kernel/sys.c b/kernel/sys.c
index 2410e3999ebe..e219fcfa112d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1786,6 +1786,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
unsigned long flags;
u64 tgutime, tgstime, utime, stime;
unsigned long maxrss = 0;
+ struct signal_struct *sig = p->signal;
memset((char *)r, 0, sizeof (*r));
utime = stime = 0;
@@ -1793,7 +1794,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
if (who == RUSAGE_THREAD) {
task_cputime_adjusted(current, &utime, &stime);
accumulate_thread_rusage(p, r);
- maxrss = p->signal->maxrss;
+ maxrss = sig->maxrss;
goto out;
}
@@ -1803,15 +1804,15 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
switch (who) {
case RUSAGE_BOTH:
case RUSAGE_CHILDREN:
- utime = p->signal->cutime;
- stime = p->signal->cstime;
- r->ru_nvcsw = p->signal->cnvcsw;
- r->ru_nivcsw = p->signal->cnivcsw;
- r->ru_minflt = p->signal->cmin_flt;
- r->ru_majflt = p->signal->cmaj_flt;
- r->ru_inblock = p->signal->cinblock;
- r->ru_oublock = p->signal->coublock;
- maxrss = p->signal->cmaxrss;
+ utime = sig->cutime;
+ stime = sig->cstime;
+ r->ru_nvcsw = sig->cnvcsw;
+ r->ru_nivcsw = sig->cnivcsw;
+ r->ru_minflt = sig->cmin_flt;
+ r->ru_majflt = sig->cmaj_flt;
+ r->ru_inblock = sig->cinblock;
+ r->ru_oublock = sig->coublock;
+ maxrss = sig->cmaxrss;
if (who == RUSAGE_CHILDREN)
break;
@@ -1821,18 +1822,16 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
thread_group_cputime_adjusted(p, &tgutime, &tgstime);
utime += tgutime;
stime += tgstime;
- r->ru_nvcsw += p->signal->nvcsw;
- r->ru_nivcsw += p->signal->nivcsw;
- r->ru_minflt += p->signal->min_flt;
- r->ru_majflt += p->signal->maj_flt;
- r->ru_inblock += p->signal->inblock;
- r->ru_oublock += p->signal->oublock;
- if (maxrss < p->signal->maxrss)
- maxrss = p->signal->maxrss;
- t = p;
- do {
+ r->ru_nvcsw += sig->nvcsw;
+ r->ru_nivcsw += sig->nivcsw;
+ r->ru_minflt += sig->min_flt;
+ r->ru_majflt += sig->maj_flt;
+ r->ru_inblock += sig->inblock;
+ r->ru_oublock += sig->oublock;
+ if (maxrss < sig->maxrss)
+ maxrss = sig->maxrss;
+ __for_each_thread(sig, t)
accumulate_thread_rusage(t, r);
- } while_each_thread(p, t);
break;
default:
@@ -2368,19 +2367,45 @@ static int prctl_set_vma(unsigned long opt, unsigned long start,
}
#endif /* CONFIG_ANON_VMA_NAME */
+static inline unsigned long get_current_mdwe(void)
+{
+ unsigned long ret = 0;
+
+ if (test_bit(MMF_HAS_MDWE, &current->mm->flags))
+ ret |= PR_MDWE_REFUSE_EXEC_GAIN;
+ if (test_bit(MMF_HAS_MDWE_NO_INHERIT, &current->mm->flags))
+ ret |= PR_MDWE_NO_INHERIT;
+
+ return ret;
+}
+
static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
+ unsigned long current_bits;
+
if (arg3 || arg4 || arg5)
return -EINVAL;
- if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN))
+ if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT))
return -EINVAL;
+ /* NO_INHERIT only makes sense with REFUSE_EXEC_GAIN */
+ if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN))
+ return -EINVAL;
+
+ /* PARISC cannot allow mdwe as it needs writable stacks */
+ if (IS_ENABLED(CONFIG_PARISC))
+ return -EINVAL;
+
+ current_bits = get_current_mdwe();
+ if (current_bits && current_bits != bits)
+ return -EPERM; /* Cannot unset the flags */
+
+ if (bits & PR_MDWE_NO_INHERIT)
+ set_bit(MMF_HAS_MDWE_NO_INHERIT, &current->mm->flags);
if (bits & PR_MDWE_REFUSE_EXEC_GAIN)
set_bit(MMF_HAS_MDWE, &current->mm->flags);
- else if (test_bit(MMF_HAS_MDWE, &current->mm->flags))
- return -EPERM; /* Cannot unset the flag */
return 0;
}
@@ -2390,9 +2415,7 @@ static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3,
{
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
-
- return test_bit(MMF_HAS_MDWE, &current->mm->flags) ?
- PR_MDWE_REFUSE_EXEC_GAIN : 0;
+ return get_current_mdwe();
}
static int prctl_get_auxv(void __user *addr, unsigned long len)
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 781de7cc6a4e..9a846439b36a 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -51,8 +51,6 @@ COND_SYSCALL_COMPAT(io_pgetevents);
COND_SYSCALL(io_uring_setup);
COND_SYSCALL(io_uring_enter);
COND_SYSCALL(io_uring_register);
-COND_SYSCALL(lookup_dcookie);
-COND_SYSCALL_COMPAT(lookup_dcookie);
COND_SYSCALL(eventfd2);
COND_SYSCALL(epoll_create1);
COND_SYSCALL(epoll_ctl);
@@ -87,6 +85,9 @@ COND_SYSCALL_COMPAT(set_robust_list);
COND_SYSCALL(get_robust_list);
COND_SYSCALL_COMPAT(get_robust_list);
COND_SYSCALL(futex_waitv);
+COND_SYSCALL(futex_wake);
+COND_SYSCALL(futex_wait);
+COND_SYSCALL(futex_requeue);
COND_SYSCALL(kexec_load);
COND_SYSCALL_COMPAT(kexec_load);
COND_SYSCALL(init_module);
@@ -200,6 +201,20 @@ COND_SYSCALL(recvmmsg_time32);
COND_SYSCALL_COMPAT(recvmmsg_time32);
COND_SYSCALL_COMPAT(recvmmsg_time64);
+/* Posix timer syscalls may be configured out */
+COND_SYSCALL(timer_create);
+COND_SYSCALL(timer_gettime);
+COND_SYSCALL(timer_getoverrun);
+COND_SYSCALL(timer_settime);
+COND_SYSCALL(timer_delete);
+COND_SYSCALL(clock_adjtime);
+COND_SYSCALL(getitimer);
+COND_SYSCALL(setitimer);
+COND_SYSCALL(alarm);
+COND_SYSCALL_COMPAT(timer_create);
+COND_SYSCALL_COMPAT(getitimer);
+COND_SYSCALL_COMPAT(setitimer);
+
/*
* Architecture specific syscalls: see further below
*/
@@ -274,6 +289,7 @@ COND_SYSCALL(vm86old);
COND_SYSCALL(modify_ldt);
COND_SYSCALL(vm86);
COND_SYSCALL(kexec_file_load);
+COND_SYSCALL(map_shadow_stack);
/* s390 */
COND_SYSCALL(s390_pci_mmio_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 354a2d294f52..157f7ce2942d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1939,15 +1939,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
-#ifdef CONFIG_IA64
- {
- .procname = "unaligned-dump-stack",
- .data = &unaligned_dump_stack,
- .maxlen = sizeof (int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
#ifdef CONFIG_RT_MUTEXES
{
.procname = "max_lock_depth",
@@ -1983,7 +1974,7 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_perf_event_sample_rate,
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
- .proc_handler = perf_proc_update_handler,
+ .proc_handler = perf_event_max_sample_rate_handler,
.extra1 = SYSCTL_ONE,
},
{
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 065e1ef8fc8d..95a7e1b7f1da 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -78,6 +78,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
* task_work_cancel_match - cancel a pending work added by task_work_add()
* @task: the task which should execute the work
* @match: match function to call
+ * @data: data to be passed in to match function
*
* RETURNS:
* The found work or NULL if not found.
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 8ce3fa0c19e2..4354ea231fab 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -233,9 +233,8 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
else
memset(stats, 0, sizeof(*stats));
- tsk = first;
start_time = ktime_get_ns();
- do {
+ for_each_thread(first, tsk) {
if (tsk->exit_state)
continue;
/*
@@ -258,7 +257,7 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
stats->nvcsw += tsk->nvcsw;
stats->nivcsw += tsk->nivcsw;
- } while_each_thread(first, tsk);
+ }
unlock_task_sighand(first, &flags);
rc = 0;
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 8d9f13d847f0..4657cb8e8b1f 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -290,6 +290,17 @@ static int alarmtimer_suspend(struct device *dev)
rtc_timer_cancel(rtc, &rtctimer);
rtc_read_time(rtc, &tm);
now = rtc_tm_to_ktime(tm);
+
+ /*
+ * If the RTC alarm timer only supports a limited time offset, set the
+ * alarm time to the maximum supported value.
+ * The system may wake up earlier (possibly much earlier) than expected
+ * when the alarmtimer runs. This is the best the kernel can do if
+ * the alarmtimer exceeds the time that the rtc device can be programmed
+ * for.
+ */
+ min = rtc_bound_alarmtime(rtc, min);
+
now = ktime_add(now, min);
/* Set alarm, if in the past reject suspend briefly to handle */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 88cbc1181b23..c108ed8a9804 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -473,8 +473,8 @@ static void clocksource_watchdog(struct timer_list *unused)
/* Check the deviation from the watchdog clocksource. */
md = cs->uncertainty_margin + watchdog->uncertainty_margin;
if (abs(cs_nsec - wd_nsec) > md) {
- u64 cs_wd_msec;
- u64 wd_msec;
+ s64 cs_wd_msec;
+ s64 wd_msec;
u32 wd_rem;
pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n",
@@ -483,8 +483,8 @@ static void clocksource_watchdog(struct timer_list *unused)
watchdog->name, wd_nsec, wdnow, wdlast, watchdog->mask);
pr_warn(" '%s' cs_nsec: %lld cs_now: %llx cs_last: %llx mask: %llx\n",
cs->name, cs_nsec, csnow, cslast, cs->mask);
- cs_wd_msec = div_u64_rem(cs_nsec - wd_nsec, 1000U * 1000U, &wd_rem);
- wd_msec = div_u64_rem(wd_nsec, 1000U * 1000U, &wd_rem);
+ cs_wd_msec = div_s64_rem(cs_nsec - wd_nsec, 1000 * 1000, &wd_rem);
+ wd_msec = div_s64_rem(wd_nsec, 1000 * 1000, &wd_rem);
pr_warn(" Clocksource '%s' skewed %lld ns (%lld ms) over watchdog '%s' interval of %lld ns (%lld ms)\n",
cs->name, cs_nsec - wd_nsec, cs_wd_msec, watchdog->name, wd_nsec, wd_msec);
if (curr_clocksource == cs)
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 238262e4aba7..760793998cdd 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2219,29 +2219,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
}
}
-int hrtimers_dead_cpu(unsigned int scpu)
+int hrtimers_cpu_dying(unsigned int dying_cpu)
{
struct hrtimer_cpu_base *old_base, *new_base;
- int i;
+ int i, ncpu = cpumask_first(cpu_active_mask);
- BUG_ON(cpu_online(scpu));
- tick_cancel_sched_timer(scpu);
+ tick_cancel_sched_timer(dying_cpu);
+
+ old_base = this_cpu_ptr(&hrtimer_bases);
+ new_base = &per_cpu(hrtimer_bases, ncpu);
- /*
- * this BH disable ensures that raise_softirq_irqoff() does
- * not wakeup ksoftirqd (and acquire the pi-lock) while
- * holding the cpu_base lock
- */
- local_bh_disable();
- local_irq_disable();
- old_base = &per_cpu(hrtimer_bases, scpu);
- new_base = this_cpu_ptr(&hrtimer_bases);
/*
* The caller is globally serialized and nobody else
* takes two locks at once, deadlock is not possible.
*/
- raw_spin_lock(&new_base->lock);
- raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock(&old_base->lock);
+ raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
migrate_hrtimer_list(&old_base->clock_base[i],
@@ -2252,15 +2245,13 @@ int hrtimers_dead_cpu(unsigned int scpu)
* The migration might have changed the first expiring softirq
* timer on this CPU. Update it.
*/
- hrtimer_update_softirq_timer(new_base, false);
+ __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT);
+ /* Tell the other CPU to retrigger the next event */
+ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
- raw_spin_unlock(&old_base->lock);
raw_spin_unlock(&new_base->lock);
+ raw_spin_unlock(&old_base->lock);
- /* Check, if we got expired work to do */
- __hrtimer_peek_ahead_timers();
- local_irq_enable();
- local_bh_enable();
return 0;
}
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 77c0c2370b6d..9de66bbbb3d1 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -19,7 +19,8 @@
*/
static struct posix_clock *get_posix_clock(struct file *fp)
{
- struct posix_clock *clk = fp->private_data;
+ struct posix_clock_context *pccontext = fp->private_data;
+ struct posix_clock *clk = pccontext->clk;
down_read(&clk->rwsem);
@@ -39,6 +40,7 @@ static void put_posix_clock(struct posix_clock *clk)
static ssize_t posix_clock_read(struct file *fp, char __user *buf,
size_t count, loff_t *ppos)
{
+ struct posix_clock_context *pccontext = fp->private_data;
struct posix_clock *clk = get_posix_clock(fp);
int err = -EINVAL;
@@ -46,7 +48,7 @@ static ssize_t posix_clock_read(struct file *fp, char __user *buf,
return -ENODEV;
if (clk->ops.read)
- err = clk->ops.read(clk, fp->f_flags, buf, count);
+ err = clk->ops.read(pccontext, fp->f_flags, buf, count);
put_posix_clock(clk);
@@ -55,6 +57,7 @@ static ssize_t posix_clock_read(struct file *fp, char __user *buf,
static __poll_t posix_clock_poll(struct file *fp, poll_table *wait)
{
+ struct posix_clock_context *pccontext = fp->private_data;
struct posix_clock *clk = get_posix_clock(fp);
__poll_t result = 0;
@@ -62,7 +65,7 @@ static __poll_t posix_clock_poll(struct file *fp, poll_table *wait)
return EPOLLERR;
if (clk->ops.poll)
- result = clk->ops.poll(clk, fp, wait);
+ result = clk->ops.poll(pccontext, fp, wait);
put_posix_clock(clk);
@@ -72,6 +75,7 @@ static __poll_t posix_clock_poll(struct file *fp, poll_table *wait)
static long posix_clock_ioctl(struct file *fp,
unsigned int cmd, unsigned long arg)
{
+ struct posix_clock_context *pccontext = fp->private_data;
struct posix_clock *clk = get_posix_clock(fp);
int err = -ENOTTY;
@@ -79,7 +83,7 @@ static long posix_clock_ioctl(struct file *fp,
return -ENODEV;
if (clk->ops.ioctl)
- err = clk->ops.ioctl(clk, cmd, arg);
+ err = clk->ops.ioctl(pccontext, cmd, arg);
put_posix_clock(clk);
@@ -90,6 +94,7 @@ static long posix_clock_ioctl(struct file *fp,
static long posix_clock_compat_ioctl(struct file *fp,
unsigned int cmd, unsigned long arg)
{
+ struct posix_clock_context *pccontext = fp->private_data;
struct posix_clock *clk = get_posix_clock(fp);
int err = -ENOTTY;
@@ -97,7 +102,7 @@ static long posix_clock_compat_ioctl(struct file *fp,
return -ENODEV;
if (clk->ops.ioctl)
- err = clk->ops.ioctl(clk, cmd, arg);
+ err = clk->ops.ioctl(pccontext, cmd, arg);
put_posix_clock(clk);
@@ -110,6 +115,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
int err;
struct posix_clock *clk =
container_of(inode->i_cdev, struct posix_clock, cdev);
+ struct posix_clock_context *pccontext;
down_read(&clk->rwsem);
@@ -117,14 +123,20 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
err = -ENODEV;
goto out;
}
+ pccontext = kzalloc(sizeof(*pccontext), GFP_KERNEL);
+ if (!pccontext) {
+ err = -ENOMEM;
+ goto out;
+ }
+ pccontext->clk = clk;
+ fp->private_data = pccontext;
if (clk->ops.open)
- err = clk->ops.open(clk, fp->f_mode);
+ err = clk->ops.open(pccontext, fp->f_mode);
else
err = 0;
if (!err) {
get_device(clk->dev);
- fp->private_data = clk;
}
out:
up_read(&clk->rwsem);
@@ -133,14 +145,20 @@ out:
static int posix_clock_release(struct inode *inode, struct file *fp)
{
- struct posix_clock *clk = fp->private_data;
+ struct posix_clock_context *pccontext = fp->private_data;
+ struct posix_clock *clk;
int err = 0;
+ if (!pccontext)
+ return -ENODEV;
+ clk = pccontext->clk;
+
if (clk->ops.release)
- err = clk->ops.release(clk);
+ err = clk->ops.release(pccontext);
put_device(clk->dev);
+ kfree(pccontext);
fp->private_data = NULL;
return err;
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 828aeecbd1e8..9b6fcb8d85e7 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -17,40 +17,6 @@
#include <linux/time_namespace.h>
#include <linux/compat.h>
-#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
-/* Architectures may override SYS_NI and COMPAT_SYS_NI */
-#include <asm/syscall_wrapper.h>
-#endif
-
-asmlinkage long sys_ni_posix_timers(void)
-{
- pr_err_once("process %d (%s) attempted a POSIX timer syscall "
- "while CONFIG_POSIX_TIMERS is not set\n",
- current->pid, current->comm);
- return -ENOSYS;
-}
-
-#ifndef SYS_NI
-#define SYS_NI(name) SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers)
-#endif
-
-#ifndef COMPAT_SYS_NI
-#define COMPAT_SYS_NI(name) SYSCALL_ALIAS(compat_sys_##name, sys_ni_posix_timers)
-#endif
-
-SYS_NI(timer_create);
-SYS_NI(timer_gettime);
-SYS_NI(timer_getoverrun);
-SYS_NI(timer_settime);
-SYS_NI(timer_delete);
-SYS_NI(clock_adjtime);
-SYS_NI(getitimer);
-SYS_NI(setitimer);
-SYS_NI(clock_adjtime32);
-#ifdef __ARCH_WANT_SYS_ALARM
-SYS_NI(alarm);
-#endif
-
/*
* We preserve minimal support for CLOCK_REALTIME and CLOCK_MONOTONIC
* as it is easy to remain compatible with little code. CLOCK_BOOTTIME
@@ -158,18 +124,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
which_clock);
}
-#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
-
#ifdef CONFIG_COMPAT_32BIT_TIME
-SYS_NI(timer_settime32);
-SYS_NI(timer_gettime32);
SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock,
struct old_timespec32 __user *, tp)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 4df14db4da49..be77b021e5d6 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -4,7 +4,7 @@
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
*
- * No idle tick implementation for low and high resolution timers
+ * NOHZ implementation for low and high resolution timers
*
* Started by: Thomas Gleixner and Ingo Molnar
*/
@@ -45,7 +45,7 @@ struct tick_sched *tick_get_tick_sched(int cpu)
#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
/*
- * The time, when the last jiffy update happened. Write access must hold
+ * The time when the last jiffy update happened. Write access must hold
* jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a
* consistent view of jiffies and last_jiffies_update.
*/
@@ -60,13 +60,13 @@ static void tick_do_update_jiffies64(ktime_t now)
ktime_t delta, nextp;
/*
- * 64bit can do a quick check without holding jiffies lock and
+ * 64-bit can do a quick check without holding the jiffies lock and
* without looking at the sequence count. The smp_load_acquire()
* pairs with the update done later in this function.
*
- * 32bit cannot do that because the store of tick_next_period
- * consists of two 32bit stores and the first store could move it
- * to a random point in the future.
+ * 32-bit cannot do that because the store of 'tick_next_period'
+ * consists of two 32-bit stores, and the first store could be
+ * moved by the CPU to a random point in the future.
*/
if (IS_ENABLED(CONFIG_64BIT)) {
if (ktime_before(now, smp_load_acquire(&tick_next_period)))
@@ -75,7 +75,7 @@ static void tick_do_update_jiffies64(ktime_t now)
unsigned int seq;
/*
- * Avoid contention on jiffies_lock and protect the quick
+ * Avoid contention on 'jiffies_lock' and protect the quick
* check with the sequence count.
*/
do {
@@ -90,7 +90,7 @@ static void tick_do_update_jiffies64(ktime_t now)
/* Quick check failed, i.e. update is required. */
raw_spin_lock(&jiffies_lock);
/*
- * Reevaluate with the lock held. Another CPU might have done the
+ * Re-evaluate with the lock held. Another CPU might have done the
* update already.
*/
if (ktime_before(now, tick_next_period)) {
@@ -114,25 +114,23 @@ static void tick_do_update_jiffies64(ktime_t now)
TICK_NSEC);
}
- /* Advance jiffies to complete the jiffies_seq protected job */
+ /* Advance jiffies to complete the 'jiffies_seq' protected job */
jiffies_64 += ticks;
- /*
- * Keep the tick_next_period variable up to date.
- */
+ /* Keep the tick_next_period variable up to date */
nextp = ktime_add_ns(last_jiffies_update, TICK_NSEC);
if (IS_ENABLED(CONFIG_64BIT)) {
/*
* Pairs with smp_load_acquire() in the lockless quick
- * check above and ensures that the update to jiffies_64 is
- * not reordered vs. the store to tick_next_period, neither
+ * check above, and ensures that the update to 'jiffies_64' is
+ * not reordered vs. the store to 'tick_next_period', neither
* by the compiler nor by the CPU.
*/
smp_store_release(&tick_next_period, nextp);
} else {
/*
- * A plain store is good enough on 32bit as the quick check
+ * A plain store is good enough on 32-bit, as the quick check
* above is protected by the sequence count.
*/
tick_next_period = nextp;
@@ -140,7 +138,7 @@ static void tick_do_update_jiffies64(ktime_t now)
/*
* Release the sequence count. calc_global_load() below is not
- * protected by it, but jiffies_lock needs to be held to prevent
+ * protected by it, but 'jiffies_lock' needs to be held to prevent
* concurrent invocations.
*/
write_seqcount_end(&jiffies_seq);
@@ -160,7 +158,8 @@ static ktime_t tick_init_jiffy_update(void)
raw_spin_lock(&jiffies_lock);
write_seqcount_begin(&jiffies_seq);
- /* Did we start the jiffies update yet ? */
+
+ /* Have we started the jiffies update yet ? */
if (last_jiffies_update == 0) {
u32 rem;
@@ -175,8 +174,10 @@ static ktime_t tick_init_jiffy_update(void)
last_jiffies_update = tick_next_period;
}
period = last_jiffies_update;
+
write_seqcount_end(&jiffies_seq);
raw_spin_unlock(&jiffies_lock);
+
return period;
}
@@ -192,10 +193,10 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
* concurrency: This happens only when the CPU in charge went
* into a long sleep. If two CPUs happen to assign themselves to
* this duty, then the jiffies update is still serialized by
- * jiffies_lock.
+ * 'jiffies_lock'.
*
* If nohz_full is enabled, this should not happen because the
- * tick_do_timer_cpu never relinquishes.
+ * 'tick_do_timer_cpu' CPU never relinquishes.
*/
if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
#ifdef CONFIG_NO_HZ_FULL
@@ -205,12 +206,12 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
}
#endif
- /* Check, if the jiffies need an update */
+ /* Check if jiffies need an update */
if (tick_do_timer_cpu == cpu)
tick_do_update_jiffies64(now);
/*
- * If jiffies update stalled for too long (timekeeper in stop_machine()
+ * If the jiffies update stalled for too long (timekeeper in stop_machine()
* or VMEXIT'ed for several msecs), force an update.
*/
if (ts->last_tick_jiffies != jiffies) {
@@ -234,10 +235,10 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
/*
* When we are idle and the tick is stopped, we have to touch
* the watchdog as we might not schedule for a really long
- * time. This happens on complete idle SMP systems while
+ * time. This happens on completely idle SMP systems while
* waiting on the login prompt. We also increment the "start of
* idle" jiffy stamp so the idle accounting adjustment we do
- * when we go busy again does not account too much ticks.
+ * when we go busy again does not account too many ticks.
*/
if (ts->tick_stopped) {
touch_softlockup_watchdog_sched();
@@ -362,7 +363,7 @@ static void tick_nohz_kick_task(struct task_struct *tsk)
/*
* If the task is not running, run_posix_cpu_timers()
- * has nothing to elapse, IPI can then be spared.
+ * has nothing to elapse, and an IPI can then be optimized out.
*
* activate_task() STORE p->tick_dep_mask
* STORE p->on_rq
@@ -425,7 +426,7 @@ static void tick_nohz_dep_set_all(atomic_t *dep,
/*
* Set a global tick dependency. Used by perf events that rely on freq and
- * by unstable clock.
+ * unstable clocks.
*/
void tick_nohz_dep_set(enum tick_dep_bits bit)
{
@@ -439,7 +440,7 @@ void tick_nohz_dep_clear(enum tick_dep_bits bit)
/*
* Set per-CPU tick dependency. Used by scheduler and perf events in order to
- * manage events throttling.
+ * manage event-throttling.
*/
void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
{
@@ -455,7 +456,7 @@ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
if (cpu == smp_processor_id()) {
tick_nohz_full_kick();
} else {
- /* Remote irq work not NMI-safe */
+ /* Remote IRQ work not NMI-safe */
if (!WARN_ON_ONCE(in_nmi()))
tick_nohz_full_kick_cpu(cpu);
}
@@ -473,7 +474,7 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
/*
- * Set a per-task tick dependency. RCU need this. Also posix CPU timers
+ * Set a per-task tick dependency. RCU needs this. Also posix CPU timers
* in order to elapse per task timers.
*/
void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
@@ -546,7 +547,7 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
{
/*
- * The tick_do_timer_cpu CPU handles housekeeping duty (unbound
+ * The 'tick_do_timer_cpu' CPU handles housekeeping duty (unbound
* timers, workqueues, timekeeping, ...) on behalf of full dynticks
* CPUs. It must remain online when nohz full is enabled.
*/
@@ -568,12 +569,12 @@ void __init tick_nohz_init(void)
return;
/*
- * Full dynticks uses irq work to drive the tick rescheduling on safe
- * locking contexts. But then we need irq work to raise its own
- * interrupts to avoid circular dependency on the tick
+ * Full dynticks uses IRQ work to drive the tick rescheduling on safe
+ * locking contexts. But then we need IRQ work to raise its own
+ * interrupts to avoid circular dependency on the tick.
*/
if (!arch_irq_work_has_interrupt()) {
- pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n");
+ pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support IRQ work self-IPIs\n");
cpumask_clear(tick_nohz_full_mask);
tick_nohz_full_running = false;
return;
@@ -643,7 +644,7 @@ bool tick_nohz_tick_stopped_cpu(int cpu)
* In case the sched_tick was stopped on this CPU, we have to check if jiffies
* must be updated. Otherwise an interrupt handler could use a stale jiffy
* value. We do this unconditionally on any CPU, as we don't know whether the
- * CPU, which has the update task assigned is in a long sleep.
+ * CPU, which has the update task assigned, is in a long sleep.
*/
static void tick_nohz_update_jiffies(ktime_t now)
{
@@ -726,7 +727,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
* counters if NULL.
*
* Return the cumulative idle time (since boot) for a given
- * CPU, in microseconds. Note this is partially broken due to
+ * CPU, in microseconds. Note that this is partially broken due to
* the counter of iowait tasks that can be remotely updated without
* any synchronization. Therefore it is possible to observe backward
* values within two consecutive reads.
@@ -787,7 +788,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
}
/*
- * Reset to make sure next tick stop doesn't get fooled by past
+ * Reset to make sure the next tick stop doesn't get fooled by past
* cached clock deadline.
*/
ts->next_tick = 0;
@@ -816,11 +817,11 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
/*
* Keep the periodic tick, when RCU, architecture or irq_work
* requests it.
- * Aside of that check whether the local timer softirq is
- * pending. If so its a bad idea to call get_next_timer_interrupt()
+ * Aside of that, check whether the local timer softirq is
+ * pending. If so, its a bad idea to call get_next_timer_interrupt(),
* because there is an already expired timer, so it will request
* immediate expiry, which rearms the hardware timer with a
- * minimal delta which brings us back to this place
+ * minimal delta, which brings us back to this place
* immediately. Lather, rinse and repeat...
*/
if (rcu_needs_cpu() || arch_needs_cpu() ||
@@ -861,7 +862,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
/*
* If this CPU is the one which had the do_timer() duty last, we limit
- * the sleep time to the timekeeping max_deferment value.
+ * the sleep time to the timekeeping 'max_deferment' value.
* Otherwise we can sleep as long as we want.
*/
delta = timekeeping_max_deferment();
@@ -895,8 +896,8 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
* If this CPU is the one which updates jiffies, then give up
* the assignment and let it be taken by the CPU which runs
* the tick timer next, which might be this CPU as well. If we
- * don't drop this here the jiffies might be stale and
- * do_timer() never invoked. Keep track of the fact that it
+ * don't drop this here, the jiffies might be stale and
+ * do_timer() never gets invoked. Keep track of the fact that it
* was the one which had the do_timer() duty last.
*/
if (cpu == tick_do_timer_cpu) {
@@ -906,7 +907,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
ts->do_timer_last = 0;
}
- /* Skip reprogram of event if its not changed */
+ /* Skip reprogram of event if it's not changed */
if (ts->tick_stopped && (expires == ts->next_tick)) {
/* Sanity check: make sure clockevent is actually programmed */
if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
@@ -919,11 +920,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
}
/*
- * nohz_stop_sched_tick can be called several times before
- * the nohz_restart_sched_tick is called. This happens when
+ * nohz_stop_sched_tick() can be called several times before
+ * nohz_restart_sched_tick() is called. This happens when
* interrupts arrive which do not cause a reschedule. In the
* first call we save the current tick time, so we can restart
- * the scheduler tick in nohz_restart_sched_tick.
+ * the scheduler tick in nohz_restart_sched_tick().
*/
if (!ts->tick_stopped) {
calc_load_nohz_start();
@@ -985,9 +986,8 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
calc_load_nohz_stop();
touch_softlockup_watchdog_sched();
- /*
- * Cancel the scheduled timer and restore the tick
- */
+
+ /* Cancel the scheduled timer and restore the tick: */
ts->tick_stopped = 0;
tick_nohz_restart(ts, now);
}
@@ -1019,11 +1019,11 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
/*
* A pending softirq outside an IRQ (or softirq disabled section) context
* should be waiting for ksoftirqd to handle it. Therefore we shouldn't
- * reach here due to the need_resched() early check in can_stop_idle_tick().
+ * reach this code due to the need_resched() early check in can_stop_idle_tick().
*
* However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the
* cpu_down() process, softirqs can still be raised while ksoftirqd is parked,
- * triggering the below since wakep_softirqd() is ignored.
+ * triggering the code below, since wakep_softirqd() is ignored.
*
*/
static bool report_idle_softirq(void)
@@ -1044,8 +1044,8 @@ static bool report_idle_softirq(void)
if (ratelimit >= 10)
return false;
- /* On RT, softirqs handling may be waiting on some lock */
- if (!local_bh_blocked())
+ /* On RT, softirq handling may be waiting on some lock */
+ if (local_bh_blocked())
return false;
pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n",
@@ -1061,8 +1061,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
* If this CPU is offline and it is the one which updates
* jiffies, then give up the assignment and let it be taken by
* the CPU which runs the tick timer next. If we don't drop
- * this here the jiffies might be stale and do_timer() never
- * invoked.
+ * this here, the jiffies might be stale and do_timer() never
+ * gets invoked.
*/
if (unlikely(!cpu_online(cpu))) {
if (cpu == tick_do_timer_cpu)
@@ -1175,12 +1175,23 @@ void tick_nohz_idle_enter(void)
}
/**
- * tick_nohz_irq_exit - update next tick event from interrupt exit
+ * tick_nohz_irq_exit - Notify the tick about IRQ exit
+ *
+ * A timer may have been added/modified/deleted either by the current IRQ,
+ * or by another place using this IRQ as a notification. This IRQ may have
+ * also updated the RCU callback list. These events may require a
+ * re-evaluation of the next tick. Depending on the context:
+ *
+ * 1) If the CPU is idle and no resched is pending, just proceed with idle
+ * time accounting. The next tick will be re-evaluated on the next idle
+ * loop iteration.
+ *
+ * 2) If the CPU is nohz_full:
*
- * When an interrupt fires while we are idle and it doesn't cause
- * a reschedule, it may still add, modify or delete a timer, enqueue
- * an RCU callback, etc...
- * So we need to re-calculate and reprogram the next tick event.
+ * 2.1) If there is any tick dependency, restart the tick if stopped.
+ *
+ * 2.2) If there is no tick dependency, (re-)evaluate the next tick and
+ * stop/update it accordingly.
*/
void tick_nohz_irq_exit(void)
{
@@ -1208,7 +1219,7 @@ bool tick_nohz_idle_got_tick(void)
/**
* tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer
- * or the tick, whatever that expires first. Note that, if the tick has been
+ * or the tick, whichever expires first. Note that, if the tick has been
* stopped, it returns the next hrtimer.
*
* Called from power state control code with interrupts disabled
@@ -1252,7 +1263,7 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
return *delta_next;
/*
- * If the next highres timer to expire is earlier than next_event, the
+ * If the next highres timer to expire is earlier than 'next_event', the
* idle governor needs to know that.
*/
next_event = min_t(u64, next_event,
@@ -1296,9 +1307,9 @@ static void tick_nohz_account_idle_time(struct tick_sched *ts,
if (vtime_accounting_enabled_this_cpu())
return;
/*
- * We stopped the tick in idle. Update process times would miss the
- * time we slept as update_process_times does only a 1 tick
- * accounting. Enforce that this is accounted to idle !
+ * We stopped the tick in idle. update_process_times() would miss the
+ * time we slept, as it does only a 1 tick accounting.
+ * Enforce that this is accounted to idle !
*/
ticks = jiffies - ts->idle_jiffies;
/*
@@ -1330,11 +1341,20 @@ static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now)
}
/**
- * tick_nohz_idle_exit - restart the idle tick from the idle task
+ * tick_nohz_idle_exit - Update the tick upon idle task exit
+ *
+ * When the idle task exits, update the tick depending on the
+ * following situations:
+ *
+ * 1) If the CPU is not in nohz_full mode (most cases), then
+ * restart the tick.
+ *
+ * 2) If the CPU is in nohz_full mode (corner case):
+ * 2.1) If the tick can be kept stopped (no tick dependencies)
+ * then re-evaluate the next tick and try to keep it stopped
+ * as long as possible.
+ * 2.2) If the tick has dependencies, restart the tick.
*
- * Restart the idle tick when the CPU is woken up from idle
- * This also exit the RCU extended quiescent state. The CPU
- * can use RCU again after this function is called.
*/
void tick_nohz_idle_exit(void)
{
@@ -1364,9 +1384,15 @@ void tick_nohz_idle_exit(void)
}
/*
- * The nohz low res interrupt handler
+ * In low-resolution mode, the tick handler must be implemented directly
+ * at the clockevent level. hrtimer can't be used instead, because its
+ * infrastructure actually relies on the tick itself as a backend in
+ * low-resolution mode (see hrtimer_run_queues()).
+ *
+ * This low-resolution handler still makes use of some hrtimer APIs meanwhile
+ * for convenience with expiration calculation and forwarding.
*/
-static void tick_nohz_handler(struct clock_event_device *dev)
+static void tick_nohz_lowres_handler(struct clock_event_device *dev)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
struct pt_regs *regs = get_irq_regs();
@@ -1377,18 +1403,16 @@ static void tick_nohz_handler(struct clock_event_device *dev)
tick_sched_do_timer(ts, now);
tick_sched_handle(ts, regs);
- if (unlikely(ts->tick_stopped)) {
- /*
- * The clockevent device is not reprogrammed, so change the
- * clock event device to ONESHOT_STOPPED to avoid spurious
- * interrupts on devices which might not be truly one shot.
- */
- tick_program_event(KTIME_MAX, 1);
- return;
+ /*
+ * In dynticks mode, tick reprogram is deferred:
+ * - to the idle task if in dynticks-idle
+ * - to IRQ exit if in full-dynticks.
+ */
+ if (likely(!ts->tick_stopped)) {
+ hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
+ tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
- hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
- tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
@@ -1402,7 +1426,7 @@ static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
}
/**
- * tick_nohz_switch_to_nohz - switch to nohz mode
+ * tick_nohz_switch_to_nohz - switch to NOHZ mode
*/
static void tick_nohz_switch_to_nohz(void)
{
@@ -1412,12 +1436,12 @@ static void tick_nohz_switch_to_nohz(void)
if (!tick_nohz_enabled)
return;
- if (tick_switch_to_oneshot(tick_nohz_handler))
+ if (tick_switch_to_oneshot(tick_nohz_lowres_handler))
return;
/*
- * Recycle the hrtimer in ts, so we can share the
- * hrtimer_forward with the highres code.
+ * Recycle the hrtimer in 'ts', so we can share the
+ * hrtimer_forward_now() function with the highres code.
*/
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
/* Get the next period */
@@ -1440,7 +1464,7 @@ static inline void tick_nohz_irq_enter(void)
if (ts->idle_active)
tick_nohz_stop_idle(ts, now);
/*
- * If all CPUs are idle. We may need to update a stale jiffies value.
+ * If all CPUs are idle we may need to update a stale jiffies value.
* Note nohz_full is a special case: a timekeeper is guaranteed to stay
* alive but it might be busy looping with interrupts disabled in some
* rare case (typically stop machine). So we must make sure we have a
@@ -1459,7 +1483,7 @@ static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { }
#endif /* CONFIG_NO_HZ_COMMON */
/*
- * Called from irq_enter to notify about the possible interruption of idle()
+ * Called from irq_enter() to notify about the possible interruption of idle()
*/
void tick_irq_enter(void)
{
@@ -1475,7 +1499,7 @@ void tick_irq_enter(void)
* We rearm the timer until we get disabled by the idle code.
* Called with interrupts disabled.
*/
-static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
+static enum hrtimer_restart tick_nohz_highres_handler(struct hrtimer *timer)
{
struct tick_sched *ts =
container_of(timer, struct tick_sched, sched_timer);
@@ -1485,15 +1509,19 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
tick_sched_do_timer(ts, now);
/*
- * Do not call, when we are not in irq context and have
- * no valid regs pointer
+ * Do not call when we are not in IRQ context and have
+ * no valid 'regs' pointer
*/
if (regs)
tick_sched_handle(ts, regs);
else
ts->next_tick = 0;
- /* No need to reprogram if we are in idle or full dynticks mode */
+ /*
+ * In dynticks mode, tick reprogram is deferred:
+ * - to the idle task if in dynticks-idle
+ * - to IRQ exit if in full-dynticks.
+ */
if (unlikely(ts->tick_stopped))
return HRTIMER_NORESTART;
@@ -1520,16 +1548,14 @@ void tick_setup_sched_timer(void)
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
ktime_t now = ktime_get();
- /*
- * Emulate tick processing via per-CPU hrtimers:
- */
+ /* Emulate tick processing via per-CPU hrtimers: */
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
- ts->sched_timer.function = tick_sched_timer;
+ ts->sched_timer.function = tick_nohz_highres_handler;
/* Get the next period (per-CPU) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
- /* Offset the tick to avert jiffies_lock contention. */
+ /* Offset the tick to avert 'jiffies_lock' contention. */
if (sched_skew_tick) {
u64 offset = TICK_NSEC >> 1;
do_div(offset, num_possible_cpus());
@@ -1579,10 +1605,10 @@ void tick_oneshot_notify(void)
}
/*
- * Check, if a change happened, which makes oneshot possible.
+ * Check if a change happened, which makes oneshot possible.
*
- * Called cyclic from the hrtimer softirq (driven by the timer
- * softirq) allow_nohz signals, that we can switch into low-res nohz
+ * Called cyclically from the hrtimer softirq (driven by the timer
+ * softirq). 'allow_nohz' signals that we can switch into low-res NOHZ
* mode, because high resolution timers are disabled (either compile
* or runtime). Called with interrupts disabled.
*/
diff --git a/kernel/time/time.c b/kernel/time/time.c
index f4198af60fee..642647f5046b 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -365,11 +365,14 @@ SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp)
}
#endif
-/*
- * Convert jiffies to milliseconds and back.
+/**
+ * jiffies_to_msecs - Convert jiffies to milliseconds
+ * @j: jiffies value
*
* Avoid unnecessary multiplications/divisions in the
- * two most common HZ cases:
+ * two most common HZ cases.
+ *
+ * Return: milliseconds value
*/
unsigned int jiffies_to_msecs(const unsigned long j)
{
@@ -388,6 +391,12 @@ unsigned int jiffies_to_msecs(const unsigned long j)
}
EXPORT_SYMBOL(jiffies_to_msecs);
+/**
+ * jiffies_to_usecs - Convert jiffies to microseconds
+ * @j: jiffies value
+ *
+ * Return: microseconds value
+ */
unsigned int jiffies_to_usecs(const unsigned long j)
{
/*
@@ -408,8 +417,15 @@ unsigned int jiffies_to_usecs(const unsigned long j)
}
EXPORT_SYMBOL(jiffies_to_usecs);
-/*
+/**
* mktime64 - Converts date to seconds.
+ * @year0: year to convert
+ * @mon0: month to convert
+ * @day: day to convert
+ * @hour: hour to convert
+ * @min: minute to convert
+ * @sec: second to convert
+ *
* Converts Gregorian date to seconds since 1970-01-01 00:00:00.
* Assumes input in normal date format, i.e. 1980-12-31 23:59:59
* => year=1980, mon=12, day=31, hour=23, min=59, sec=59.
@@ -427,6 +443,8 @@ EXPORT_SYMBOL(jiffies_to_usecs);
*
* An encoding of midnight at the end of the day as 24:00:00 - ie. midnight
* tomorrow - (allowable under ISO 8601) is supported.
+ *
+ * Return: seconds since the epoch time for the given input date
*/
time64_t mktime64(const unsigned int year0, const unsigned int mon0,
const unsigned int day, const unsigned int hour,
@@ -471,8 +489,7 @@ EXPORT_SYMBOL(ns_to_kernel_old_timeval);
* Set seconds and nanoseconds field of a timespec variable and
* normalize to the timespec storage format
*
- * Note: The tv_nsec part is always in the range of
- * 0 <= tv_nsec < NSEC_PER_SEC
+ * Note: The tv_nsec part is always in the range of 0 <= tv_nsec < NSEC_PER_SEC.
* For negative values only the tv_sec field is negative !
*/
void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec)
@@ -501,7 +518,7 @@ EXPORT_SYMBOL(set_normalized_timespec64);
* ns_to_timespec64 - Convert nanoseconds to timespec64
* @nsec: the nanoseconds value to be converted
*
- * Returns the timespec64 representation of the nsec parameter.
+ * Return: the timespec64 representation of the nsec parameter.
*/
struct timespec64 ns_to_timespec64(s64 nsec)
{
@@ -548,6 +565,8 @@ EXPORT_SYMBOL(ns_to_timespec64);
* runtime.
* The _msecs_to_jiffies helpers are the HZ dependent conversion
* routines found in include/linux/jiffies.h
+ *
+ * Return: jiffies value
*/
unsigned long __msecs_to_jiffies(const unsigned int m)
{
@@ -560,6 +579,12 @@ unsigned long __msecs_to_jiffies(const unsigned int m)
}
EXPORT_SYMBOL(__msecs_to_jiffies);
+/**
+ * __usecs_to_jiffies: - convert microseconds to jiffies
+ * @u: time in milliseconds
+ *
+ * Return: jiffies value
+ */
unsigned long __usecs_to_jiffies(const unsigned int u)
{
if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
@@ -568,7 +593,10 @@ unsigned long __usecs_to_jiffies(const unsigned int u)
}
EXPORT_SYMBOL(__usecs_to_jiffies);
-/*
+/**
+ * timespec64_to_jiffies - convert a timespec64 value to jiffies
+ * @value: pointer to &struct timespec64
+ *
* The TICK_NSEC - 1 rounds up the value to the next resolution. Note
* that a remainder subtract here would not do the right thing as the
* resolution values don't fall on second boundaries. I.e. the line:
@@ -582,8 +610,9 @@ EXPORT_SYMBOL(__usecs_to_jiffies);
*
* The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
* value to a scaled second value.
+ *
+ * Return: jiffies value
*/
-
unsigned long
timespec64_to_jiffies(const struct timespec64 *value)
{
@@ -601,6 +630,11 @@ timespec64_to_jiffies(const struct timespec64 *value)
}
EXPORT_SYMBOL(timespec64_to_jiffies);
+/**
+ * jiffies_to_timespec64 - convert jiffies value to &struct timespec64
+ * @jiffies: jiffies value
+ * @value: pointer to &struct timespec64
+ */
void
jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value)
{
@@ -618,6 +652,13 @@ EXPORT_SYMBOL(jiffies_to_timespec64);
/*
* Convert jiffies/jiffies_64 to clock_t and back.
*/
+
+/**
+ * jiffies_to_clock_t - Convert jiffies to clock_t
+ * @x: jiffies value
+ *
+ * Return: jiffies converted to clock_t (CLOCKS_PER_SEC)
+ */
clock_t jiffies_to_clock_t(unsigned long x)
{
#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
@@ -632,6 +673,12 @@ clock_t jiffies_to_clock_t(unsigned long x)
}
EXPORT_SYMBOL(jiffies_to_clock_t);
+/**
+ * clock_t_to_jiffies - Convert clock_t to jiffies
+ * @x: clock_t value
+ *
+ * Return: clock_t value converted to jiffies
+ */
unsigned long clock_t_to_jiffies(unsigned long x)
{
#if (HZ % USER_HZ)==0
@@ -649,6 +696,12 @@ unsigned long clock_t_to_jiffies(unsigned long x)
}
EXPORT_SYMBOL(clock_t_to_jiffies);
+/**
+ * jiffies_64_to_clock_t - Convert jiffies_64 to clock_t
+ * @x: jiffies_64 value
+ *
+ * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC)
+ */
u64 jiffies_64_to_clock_t(u64 x)
{
#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
@@ -671,6 +724,12 @@ u64 jiffies_64_to_clock_t(u64 x)
}
EXPORT_SYMBOL(jiffies_64_to_clock_t);
+/**
+ * nsec_to_clock_t - Convert nsec value to clock_t
+ * @x: nsec value
+ *
+ * Return: nsec value converted to 64-bit "clock_t" (CLOCKS_PER_SEC)
+ */
u64 nsec_to_clock_t(u64 x)
{
#if (NSEC_PER_SEC % USER_HZ) == 0
@@ -687,6 +746,12 @@ u64 nsec_to_clock_t(u64 x)
#endif
}
+/**
+ * jiffies64_to_nsecs - Convert jiffies64 to nanoseconds
+ * @j: jiffies64 value
+ *
+ * Return: nanoseconds value
+ */
u64 jiffies64_to_nsecs(u64 j)
{
#if !(NSEC_PER_SEC % HZ)
@@ -697,6 +762,12 @@ u64 jiffies64_to_nsecs(u64 j)
}
EXPORT_SYMBOL(jiffies64_to_nsecs);
+/**
+ * jiffies64_to_msecs - Convert jiffies64 to milliseconds
+ * @j: jiffies64 value
+ *
+ * Return: milliseconds value
+ */
u64 jiffies64_to_msecs(const u64 j)
{
#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
@@ -719,6 +790,8 @@ EXPORT_SYMBOL(jiffies64_to_msecs);
* note:
* NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
* ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ *
+ * Return: nsecs converted to jiffies64 value
*/
u64 nsecs_to_jiffies64(u64 n)
{
@@ -750,6 +823,8 @@ EXPORT_SYMBOL(nsecs_to_jiffies64);
* note:
* NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
* ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ *
+ * Return: nsecs converted to jiffies value
*/
unsigned long nsecs_to_jiffies(u64 n)
{
@@ -757,10 +832,16 @@ unsigned long nsecs_to_jiffies(u64 n)
}
EXPORT_SYMBOL_GPL(nsecs_to_jiffies);
-/*
- * Add two timespec64 values and do a safety check for overflow.
+/**
+ * timespec64_add_safe - Add two timespec64 values and do a safety check
+ * for overflow.
+ * @lhs: first (left) timespec64 to add
+ * @rhs: second (right) timespec64 to add
+ *
* It's assumed that both values are valid (>= 0).
* And, each timespec64 is in normalized form.
+ *
+ * Return: sum of @lhs + @rhs
*/
struct timespec64 timespec64_add_safe(const struct timespec64 lhs,
const struct timespec64 rhs)
@@ -778,6 +859,15 @@ struct timespec64 timespec64_add_safe(const struct timespec64 lhs,
return res;
}
+/**
+ * get_timespec64 - get user's time value into kernel space
+ * @ts: destination &struct timespec64
+ * @uts: user's time value as &struct __kernel_timespec
+ *
+ * Handles compat or 32-bit modes.
+ *
+ * Return: %0 on success or negative errno on error
+ */
int get_timespec64(struct timespec64 *ts,
const struct __kernel_timespec __user *uts)
{
@@ -801,6 +891,14 @@ int get_timespec64(struct timespec64 *ts,
}
EXPORT_SYMBOL_GPL(get_timespec64);
+/**
+ * put_timespec64 - convert timespec64 value to __kernel_timespec format and
+ * copy the latter to userspace
+ * @ts: input &struct timespec64
+ * @uts: user's &struct __kernel_timespec
+ *
+ * Return: %0 on success or negative errno on error
+ */
int put_timespec64(const struct timespec64 *ts,
struct __kernel_timespec __user *uts)
{
@@ -839,6 +937,15 @@ static int __put_old_timespec32(const struct timespec64 *ts64,
return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0;
}
+/**
+ * get_old_timespec32 - get user's old-format time value into kernel space
+ * @ts: destination &struct timespec64
+ * @uts: user's old-format time value (&struct old_timespec32)
+ *
+ * Handles X86_X32_ABI compatibility conversion.
+ *
+ * Return: %0 on success or negative errno on error
+ */
int get_old_timespec32(struct timespec64 *ts, const void __user *uts)
{
if (COMPAT_USE_64BIT_TIME)
@@ -848,6 +955,16 @@ int get_old_timespec32(struct timespec64 *ts, const void __user *uts)
}
EXPORT_SYMBOL_GPL(get_old_timespec32);
+/**
+ * put_old_timespec32 - convert timespec64 value to &struct old_timespec32 and
+ * copy the latter to userspace
+ * @ts: input &struct timespec64
+ * @uts: user's &struct old_timespec32
+ *
+ * Handles X86_X32_ABI compatibility conversion.
+ *
+ * Return: %0 on success or negative errno on error
+ */
int put_old_timespec32(const struct timespec64 *ts, void __user *uts)
{
if (COMPAT_USE_64BIT_TIME)
@@ -857,6 +974,13 @@ int put_old_timespec32(const struct timespec64 *ts, void __user *uts)
}
EXPORT_SYMBOL_GPL(put_old_timespec32);
+/**
+ * get_itimerspec64 - get user's &struct __kernel_itimerspec into kernel space
+ * @it: destination &struct itimerspec64
+ * @uit: user's &struct __kernel_itimerspec
+ *
+ * Return: %0 on success or negative errno on error
+ */
int get_itimerspec64(struct itimerspec64 *it,
const struct __kernel_itimerspec __user *uit)
{
@@ -872,6 +996,14 @@ int get_itimerspec64(struct itimerspec64 *it,
}
EXPORT_SYMBOL_GPL(get_itimerspec64);
+/**
+ * put_itimerspec64 - convert &struct itimerspec64 to __kernel_itimerspec format
+ * and copy the latter to userspace
+ * @it: input &struct itimerspec64
+ * @uit: user's &struct __kernel_itimerspec
+ *
+ * Return: %0 on success or negative errno on error
+ */
int put_itimerspec64(const struct itimerspec64 *it,
struct __kernel_itimerspec __user *uit)
{
@@ -887,6 +1019,13 @@ int put_itimerspec64(const struct itimerspec64 *it,
}
EXPORT_SYMBOL_GPL(put_itimerspec64);
+/**
+ * get_old_itimerspec32 - get user's &struct old_itimerspec32 into kernel space
+ * @its: destination &struct itimerspec64
+ * @uits: user's &struct old_itimerspec32
+ *
+ * Return: %0 on success or negative errno on error
+ */
int get_old_itimerspec32(struct itimerspec64 *its,
const struct old_itimerspec32 __user *uits)
{
@@ -898,6 +1037,14 @@ int get_old_itimerspec32(struct itimerspec64 *its,
}
EXPORT_SYMBOL_GPL(get_old_itimerspec32);
+/**
+ * put_old_itimerspec32 - convert &struct itimerspec64 to &struct
+ * old_itimerspec32 and copy the latter to userspace
+ * @its: input &struct itimerspec64
+ * @uits: user's &struct old_itimerspec32
+ *
+ * Return: %0 on success or negative errno on error
+ */
int put_old_itimerspec32(const struct itimerspec64 *its,
struct old_itimerspec32 __user *uits)
{
diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c
index 831e8e779ace..ca058c8af6ba 100644
--- a/kernel/time/time_test.c
+++ b/kernel/time/time_test.c
@@ -86,7 +86,7 @@ static void time64_to_tm_test_date_range(struct kunit *test)
}
static struct kunit_case time_test_cases[] = {
- KUNIT_CASE(time64_to_tm_test_date_range),
+ KUNIT_CASE_SLOW(time64_to_tm_test_date_range),
{}
};
diff --git a/kernel/torture.c b/kernel/torture.c
index 1a0519b836ac..c72ab2d251f4 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -37,6 +37,7 @@
#include <linux/ktime.h>
#include <asm/byteorder.h>
#include <linux/torture.h>
+#include <linux/sched/rt.h>
#include "rcu/rcu.h"
MODULE_LICENSE("GPL");
@@ -54,6 +55,9 @@ module_param(verbose_sleep_frequency, int, 0444);
static int verbose_sleep_duration = 1;
module_param(verbose_sleep_duration, int, 0444);
+static int random_shuffle;
+module_param(random_shuffle, int, 0444);
+
static char *torture_type;
static int verbose;
@@ -83,14 +87,15 @@ EXPORT_SYMBOL_GPL(verbose_torout_sleep);
* nanosecond random fuzz. This function and its friends desynchronize
* testing from the timer wheel.
*/
-int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_state *trsp)
+int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, const enum hrtimer_mode mode,
+ struct torture_random_state *trsp)
{
ktime_t hto = baset_ns;
if (trsp)
- hto += (torture_random(trsp) >> 3) % fuzzt_ns;
- set_current_state(TASK_UNINTERRUPTIBLE);
- return schedule_hrtimeout(&hto, HRTIMER_MODE_REL);
+ hto += torture_random(trsp) % fuzzt_ns;
+ set_current_state(TASK_IDLE);
+ return schedule_hrtimeout(&hto, mode);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_ns);
@@ -102,7 +107,7 @@ int torture_hrtimeout_us(u32 baset_us, u32 fuzzt_ns, struct torture_random_state
{
ktime_t baset_ns = baset_us * NSEC_PER_USEC;
- return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp);
+ return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_us);
@@ -119,7 +124,7 @@ int torture_hrtimeout_ms(u32 baset_ms, u32 fuzzt_us, struct torture_random_state
fuzzt_ns = (u32)~0U;
else
fuzzt_ns = fuzzt_us * NSEC_PER_USEC;
- return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp);
+ return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_ms);
@@ -132,7 +137,7 @@ int torture_hrtimeout_jiffies(u32 baset_j, struct torture_random_state *trsp)
{
ktime_t baset_ns = jiffies_to_nsecs(baset_j);
- return torture_hrtimeout_ns(baset_ns, jiffies_to_nsecs(1), trsp);
+ return torture_hrtimeout_ns(baset_ns, jiffies_to_nsecs(1), HRTIMER_MODE_REL, trsp);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_jiffies);
@@ -149,7 +154,7 @@ int torture_hrtimeout_s(u32 baset_s, u32 fuzzt_ms, struct torture_random_state *
fuzzt_ns = (u32)~0U;
else
fuzzt_ns = fuzzt_ms * NSEC_PER_MSEC;
- return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp);
+ return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_s);
@@ -350,22 +355,22 @@ torture_onoff(void *arg)
if (onoff_holdoff > 0) {
VERBOSE_TOROUT_STRING("torture_onoff begin holdoff");
- schedule_timeout_interruptible(onoff_holdoff);
+ torture_hrtimeout_jiffies(onoff_holdoff, &rand);
VERBOSE_TOROUT_STRING("torture_onoff end holdoff");
}
while (!torture_must_stop()) {
if (disable_onoff_at_boot && !rcu_inkernel_boot_has_ended()) {
- schedule_timeout_interruptible(HZ / 10);
+ torture_hrtimeout_jiffies(HZ / 10, &rand);
continue;
}
- cpu = (torture_random(&rand) >> 4) % (maxcpu + 1);
+ cpu = torture_random(&rand) % (maxcpu + 1);
if (!torture_offline(cpu,
&n_offline_attempts, &n_offline_successes,
&sum_offline, &min_offline, &max_offline))
torture_online(cpu,
&n_online_attempts, &n_online_successes,
&sum_online, &min_online, &max_online);
- schedule_timeout_interruptible(onoff_interval);
+ torture_hrtimeout_jiffies(onoff_interval, &rand);
}
stop:
@@ -516,7 +521,7 @@ static void torture_shuffle_task_unregister_all(void)
* A special case is when shuffle_idle_cpu = -1, in which case we allow
* the tasks to run on all CPUs.
*/
-static void torture_shuffle_tasks(void)
+static void torture_shuffle_tasks(struct torture_random_state *trp)
{
struct shuffle_task *stp;
@@ -537,8 +542,10 @@ static void torture_shuffle_tasks(void)
cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask);
mutex_lock(&shuffle_task_mutex);
- list_for_each_entry(stp, &shuffle_task_list, st_l)
- set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
+ list_for_each_entry(stp, &shuffle_task_list, st_l) {
+ if (!random_shuffle || torture_random(trp) & 0x1)
+ set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
+ }
mutex_unlock(&shuffle_task_mutex);
cpus_read_unlock();
@@ -550,10 +557,12 @@ static void torture_shuffle_tasks(void)
*/
static int torture_shuffle(void *arg)
{
+ DEFINE_TORTURE_RANDOM(rand);
+
VERBOSE_TOROUT_STRING("torture_shuffle task started");
do {
- schedule_timeout_interruptible(shuffle_interval);
- torture_shuffle_tasks();
+ torture_hrtimeout_jiffies(shuffle_interval, &rand);
+ torture_shuffle_tasks(&rand);
torture_shutdown_absorb("torture_shuffle");
} while (!torture_must_stop());
torture_kthread_stopping("torture_shuffle");
@@ -664,7 +673,7 @@ int torture_shutdown_init(int ssecs, void (*cleanup)(void))
if (ssecs > 0) {
shutdown_time = ktime_add(ktime_get(), ktime_set(ssecs, 0));
return torture_create_kthread(torture_shutdown, NULL,
- shutdown_task);
+ shutdown_task);
}
return 0;
}
@@ -711,7 +720,7 @@ static void torture_shutdown_cleanup(void)
* suddenly applied to or removed from the system.
*/
static struct task_struct *stutter_task;
-static int stutter_pause_test;
+static ktime_t stutter_till_abs_time;
static int stutter;
static int stutter_gap;
@@ -721,30 +730,16 @@ static int stutter_gap;
*/
bool stutter_wait(const char *title)
{
- unsigned int i = 0;
bool ret = false;
- int spt;
+ ktime_t till_ns;
cond_resched_tasks_rcu_qs();
- spt = READ_ONCE(stutter_pause_test);
- for (; spt; spt = READ_ONCE(stutter_pause_test)) {
- if (!ret) {
- sched_set_normal(current, MAX_NICE);
- ret = true;
- }
- if (spt == 1) {
- schedule_timeout_interruptible(1);
- } else if (spt == 2) {
- while (READ_ONCE(stutter_pause_test)) {
- if (!(i++ & 0xffff))
- torture_hrtimeout_us(10, 0, NULL);
- cond_resched();
- }
- } else {
- schedule_timeout_interruptible(round_jiffies_relative(HZ));
- }
- torture_shutdown_absorb(title);
+ till_ns = READ_ONCE(stutter_till_abs_time);
+ if (till_ns && ktime_before(ktime_get(), till_ns)) {
+ torture_hrtimeout_ns(till_ns, 0, HRTIMER_MODE_ABS, NULL);
+ ret = true;
}
+ torture_shutdown_absorb(title);
return ret;
}
EXPORT_SYMBOL_GPL(stutter_wait);
@@ -755,23 +750,16 @@ EXPORT_SYMBOL_GPL(stutter_wait);
*/
static int torture_stutter(void *arg)
{
- DEFINE_TORTURE_RANDOM(rand);
- int wtime;
+ ktime_t till_ns;
VERBOSE_TOROUT_STRING("torture_stutter task started");
do {
if (!torture_must_stop() && stutter > 1) {
- wtime = stutter;
- if (stutter > 2) {
- WRITE_ONCE(stutter_pause_test, 1);
- wtime = stutter - 3;
- torture_hrtimeout_jiffies(wtime, &rand);
- wtime = 2;
- }
- WRITE_ONCE(stutter_pause_test, 2);
- torture_hrtimeout_jiffies(wtime, NULL);
+ till_ns = ktime_add_ns(ktime_get(),
+ jiffies_to_nsecs(stutter));
+ WRITE_ONCE(stutter_till_abs_time, till_ns);
+ torture_hrtimeout_jiffies(stutter - 1, NULL);
}
- WRITE_ONCE(stutter_pause_test, 0);
if (!torture_must_stop())
torture_hrtimeout_jiffies(stutter_gap, NULL);
torture_shutdown_absorb("torture_stutter");
@@ -803,6 +791,13 @@ static void torture_stutter_cleanup(void)
stutter_task = NULL;
}
+static void
+torture_print_module_parms(void)
+{
+ pr_alert("torture module --- %s: disable_onoff_at_boot=%d ftrace_dump_at_shutdown=%d verbose_sleep_frequency=%d verbose_sleep_duration=%d random_shuffle=%d\n",
+ torture_type, disable_onoff_at_boot, ftrace_dump_at_shutdown, verbose_sleep_frequency, verbose_sleep_duration, random_shuffle);
+}
+
/*
* Initialize torture module. Please note that this is -not- invoked via
* the usual module_init() mechanism, but rather by an explicit call from
@@ -825,6 +820,7 @@ bool torture_init_begin(char *ttype, int v)
torture_type = ttype;
verbose = v;
fullstop = FULLSTOP_DONTSTOP;
+ torture_print_module_parms();
return true;
}
EXPORT_SYMBOL_GPL(torture_init_begin);
@@ -926,7 +922,7 @@ EXPORT_SYMBOL_GPL(torture_kthread_stopping);
* it starts, you will need to open-code your own.
*/
int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
- char *f, struct task_struct **tp)
+ char *f, struct task_struct **tp, void (*cbf)(struct task_struct *tp))
{
int ret = 0;
@@ -938,6 +934,10 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
*tp = NULL;
return ret;
}
+
+ if (cbf)
+ cbf(*tp);
+
wake_up_process(*tp); // Process is sleeping, so ordering provided.
torture_shuffle_task_register(*tp);
return ret;
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 64b61f67a403..057cd975d014 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -99,6 +99,7 @@ obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
endif
obj-$(CONFIG_DYNAMIC_EVENTS) += trace_dynevent.o
obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
+obj-$(CONFIG_PROBE_EVENTS_BTF_ARGS) += trace_btf.o
obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o
obj-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index bd1a42b23f3f..84e8a0f6e4e0 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -23,6 +23,7 @@
#include <linux/sort.h>
#include <linux/key.h>
#include <linux/verification.h>
+#include <linux/namei.h>
#include <net/bpf_sk_storage.h>
@@ -86,6 +87,9 @@ static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx);
static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx);
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
+
/**
* trace_call_bpf - invoke BPF program
* @call: tracepoint event
@@ -113,6 +117,9 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
* and don't send kprobe event into ring-buffer,
* so return zero here
*/
+ rcu_read_lock();
+ bpf_prog_inc_misses_counters(rcu_dereference(call->prog_array));
+ rcu_read_unlock();
ret = 0;
goto out;
}
@@ -223,17 +230,6 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = {
.arg3_type = ARG_ANYTHING,
};
-static __always_inline int
-bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
-{
- int ret;
-
- ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
- if (unlikely(ret < 0))
- memset(dst, 0, size);
- return ret;
-}
-
BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
const void *, unsafe_ptr)
{
@@ -1066,7 +1062,16 @@ static unsigned long get_entry_ip(unsigned long fentry_ip)
BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
{
- struct kprobe *kp = kprobe_running();
+ struct bpf_trace_run_ctx *run_ctx __maybe_unused;
+ struct kprobe *kp;
+
+#ifdef CONFIG_UPROBES
+ run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx);
+ if (run_ctx->is_uprobe)
+ return ((struct uprobe_dispatch_data *)current->utask->vaddr)->bp_addr;
+#endif
+
+ kp = kprobe_running();
if (!kp || !(kp->flags & KPROBE_FLAG_ON_FUNC_ENTRY))
return 0;
@@ -1105,6 +1110,30 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = {
.arg1_type = ARG_PTR_TO_CTX,
};
+BPF_CALL_1(bpf_get_func_ip_uprobe_multi, struct pt_regs *, regs)
+{
+ return bpf_uprobe_multi_entry_ip(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_func_ip_proto_uprobe_multi = {
+ .func = bpf_get_func_ip_uprobe_multi,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_attach_cookie_uprobe_multi, struct pt_regs *, regs)
+{
+ return bpf_uprobe_multi_cookie(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto_umulti = {
+ .func = bpf_get_attach_cookie_uprobe_multi,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx)
{
struct bpf_trace_run_ctx *run_ctx;
@@ -1223,9 +1252,7 @@ static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
};
#ifdef CONFIG_KEYS
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "kfuncs which will be used in BPF programs");
+__bpf_kfunc_start_defs();
/**
* bpf_lookup_user_key - lookup a key by its serial
@@ -1375,7 +1402,7 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
}
#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(key_sig_kfunc_set)
BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE)
@@ -1547,13 +1574,17 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_override_return_proto;
#endif
case BPF_FUNC_get_func_ip:
- return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
- &bpf_get_func_ip_proto_kprobe_multi :
- &bpf_get_func_ip_proto_kprobe;
+ if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
+ return &bpf_get_func_ip_proto_kprobe_multi;
+ if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+ return &bpf_get_func_ip_proto_uprobe_multi;
+ return &bpf_get_func_ip_proto_kprobe;
case BPF_FUNC_get_attach_cookie:
- return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
- &bpf_get_attach_cookie_proto_kmulti :
- &bpf_get_attach_cookie_proto_trace;
+ if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
+ return &bpf_get_attach_cookie_proto_kmulti;
+ if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+ return &bpf_get_attach_cookie_proto_umulti;
+ return &bpf_get_attach_cookie_proto_trace;
default:
return bpf_tracing_func_proto(func_id, prog);
}
@@ -2354,7 +2385,8 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
u32 *fd_type, const char **buf,
- u64 *probe_offset, u64 *probe_addr)
+ u64 *probe_offset, u64 *probe_addr,
+ unsigned long *missed)
{
bool is_tracepoint, is_syscall_tp;
struct bpf_prog *prog;
@@ -2376,22 +2408,26 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
if (is_tracepoint || is_syscall_tp) {
*buf = is_tracepoint ? event->tp_event->tp->name
: event->tp_event->name;
- *fd_type = BPF_FD_TYPE_TRACEPOINT;
- *probe_offset = 0x0;
- *probe_addr = 0x0;
+ /* We allow NULL pointer for tracepoint */
+ if (fd_type)
+ *fd_type = BPF_FD_TYPE_TRACEPOINT;
+ if (probe_offset)
+ *probe_offset = 0x0;
+ if (probe_addr)
+ *probe_addr = 0x0;
} else {
/* kprobe/uprobe */
err = -EOPNOTSUPP;
#ifdef CONFIG_KPROBE_EVENTS
if (flags & TRACE_EVENT_FL_KPROBE)
err = bpf_get_kprobe_info(event, fd_type, buf,
- probe_offset, probe_addr,
+ probe_offset, probe_addr, missed,
event->attr.type == PERF_TYPE_TRACEPOINT);
#endif
#ifdef CONFIG_UPROBE_EVENTS
if (flags & TRACE_EVENT_FL_UPROBE)
err = bpf_get_uprobe_info(event, fd_type, buf,
- probe_offset,
+ probe_offset, probe_addr,
event->attr.type == PERF_TYPE_TRACEPOINT);
#endif
}
@@ -2476,6 +2512,7 @@ struct bpf_kprobe_multi_link {
u32 cnt;
u32 mods_cnt;
struct module **mods;
+ u32 flags;
};
struct bpf_kprobe_multi_run_ctx {
@@ -2565,9 +2602,45 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
kfree(kmulti_link);
}
+static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
+ struct bpf_link_info *info)
+{
+ u64 __user *uaddrs = u64_to_user_ptr(info->kprobe_multi.addrs);
+ struct bpf_kprobe_multi_link *kmulti_link;
+ u32 ucount = info->kprobe_multi.count;
+ int err = 0, i;
+
+ if (!uaddrs ^ !ucount)
+ return -EINVAL;
+
+ kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+ info->kprobe_multi.count = kmulti_link->cnt;
+ info->kprobe_multi.flags = kmulti_link->flags;
+ info->kprobe_multi.missed = kmulti_link->fp.nmissed;
+
+ if (!uaddrs)
+ return 0;
+ if (ucount < kmulti_link->cnt)
+ err = -ENOSPC;
+ else
+ ucount = kmulti_link->cnt;
+
+ if (kallsyms_show_value(current_cred())) {
+ if (copy_to_user(uaddrs, kmulti_link->addrs, ucount * sizeof(u64)))
+ return -EFAULT;
+ } else {
+ for (i = 0; i < ucount; i++) {
+ if (put_user(0, uaddrs + i))
+ return -EFAULT;
+ }
+ }
+ return err;
+}
+
static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
.release = bpf_kprobe_multi_link_release,
.dealloc = bpf_kprobe_multi_link_dealloc,
+ .fill_link_info = bpf_kprobe_multi_link_fill_link_info,
};
static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv)
@@ -2640,6 +2713,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
int err;
if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
+ bpf_prog_inc_misses_counter(link->link.prog);
err = 0;
goto out;
}
@@ -2783,6 +2857,17 @@ static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u3
return arr.mods_cnt;
}
+static int addrs_check_error_injection_list(unsigned long *addrs, u32 cnt)
+{
+ u32 i;
+
+ for (i = 0; i < cnt; i++) {
+ if (!within_error_injection_list(addrs[i]))
+ return -EINVAL;
+ }
+ return 0;
+}
+
int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_kprobe_multi_link *link = NULL;
@@ -2860,6 +2945,11 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
goto error;
}
+ if (prog->kprobe_override && addrs_check_error_injection_list(addrs, cnt)) {
+ err = -EINVAL;
+ goto error;
+ }
+
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
err = -ENOMEM;
@@ -2881,6 +2971,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
link->addrs = addrs;
link->cookies = cookies;
link->cnt = cnt;
+ link->flags = flags;
if (cookies) {
/*
@@ -2931,3 +3022,303 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
return 0;
}
#endif
+
+#ifdef CONFIG_UPROBES
+struct bpf_uprobe_multi_link;
+
+struct bpf_uprobe {
+ struct bpf_uprobe_multi_link *link;
+ loff_t offset;
+ u64 cookie;
+ struct uprobe_consumer consumer;
+};
+
+struct bpf_uprobe_multi_link {
+ struct path path;
+ struct bpf_link link;
+ u32 cnt;
+ struct bpf_uprobe *uprobes;
+ struct task_struct *task;
+};
+
+struct bpf_uprobe_multi_run_ctx {
+ struct bpf_run_ctx run_ctx;
+ unsigned long entry_ip;
+ struct bpf_uprobe *uprobe;
+};
+
+static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes,
+ u32 cnt)
+{
+ u32 i;
+
+ for (i = 0; i < cnt; i++) {
+ uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset,
+ &uprobes[i].consumer);
+ }
+}
+
+static void bpf_uprobe_multi_link_release(struct bpf_link *link)
+{
+ struct bpf_uprobe_multi_link *umulti_link;
+
+ umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+ bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+}
+
+static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
+{
+ struct bpf_uprobe_multi_link *umulti_link;
+
+ umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+ if (umulti_link->task)
+ put_task_struct(umulti_link->task);
+ path_put(&umulti_link->path);
+ kvfree(umulti_link->uprobes);
+ kfree(umulti_link);
+}
+
+static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
+ .release = bpf_uprobe_multi_link_release,
+ .dealloc = bpf_uprobe_multi_link_dealloc,
+};
+
+static int uprobe_prog_run(struct bpf_uprobe *uprobe,
+ unsigned long entry_ip,
+ struct pt_regs *regs)
+{
+ struct bpf_uprobe_multi_link *link = uprobe->link;
+ struct bpf_uprobe_multi_run_ctx run_ctx = {
+ .entry_ip = entry_ip,
+ .uprobe = uprobe,
+ };
+ struct bpf_prog *prog = link->link.prog;
+ bool sleepable = prog->aux->sleepable;
+ struct bpf_run_ctx *old_run_ctx;
+ int err = 0;
+
+ if (link->task && current != link->task)
+ return 0;
+
+ if (sleepable)
+ rcu_read_lock_trace();
+ else
+ rcu_read_lock();
+
+ migrate_disable();
+
+ old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+ err = bpf_prog_run(link->link.prog, regs);
+ bpf_reset_run_ctx(old_run_ctx);
+
+ migrate_enable();
+
+ if (sleepable)
+ rcu_read_unlock_trace();
+ else
+ rcu_read_unlock();
+ return err;
+}
+
+static bool
+uprobe_multi_link_filter(struct uprobe_consumer *con, enum uprobe_filter_ctx ctx,
+ struct mm_struct *mm)
+{
+ struct bpf_uprobe *uprobe;
+
+ uprobe = container_of(con, struct bpf_uprobe, consumer);
+ return uprobe->link->task->mm == mm;
+}
+
+static int
+uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs)
+{
+ struct bpf_uprobe *uprobe;
+
+ uprobe = container_of(con, struct bpf_uprobe, consumer);
+ return uprobe_prog_run(uprobe, instruction_pointer(regs), regs);
+}
+
+static int
+uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs)
+{
+ struct bpf_uprobe *uprobe;
+
+ uprobe = container_of(con, struct bpf_uprobe, consumer);
+ return uprobe_prog_run(uprobe, func, regs);
+}
+
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+ struct bpf_uprobe_multi_run_ctx *run_ctx;
+
+ run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx);
+ return run_ctx->entry_ip;
+}
+
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+ struct bpf_uprobe_multi_run_ctx *run_ctx;
+
+ run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx);
+ return run_ctx->uprobe->cookie;
+}
+
+int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ struct bpf_uprobe_multi_link *link = NULL;
+ unsigned long __user *uref_ctr_offsets;
+ unsigned long *ref_ctr_offsets = NULL;
+ struct bpf_link_primer link_primer;
+ struct bpf_uprobe *uprobes = NULL;
+ struct task_struct *task = NULL;
+ unsigned long __user *uoffsets;
+ u64 __user *ucookies;
+ void __user *upath;
+ u32 flags, cnt, i;
+ struct path path;
+ char *name;
+ pid_t pid;
+ int err;
+
+ /* no support for 32bit archs yet */
+ if (sizeof(u64) != sizeof(void *))
+ return -EOPNOTSUPP;
+
+ if (prog->expected_attach_type != BPF_TRACE_UPROBE_MULTI)
+ return -EINVAL;
+
+ flags = attr->link_create.uprobe_multi.flags;
+ if (flags & ~BPF_F_UPROBE_MULTI_RETURN)
+ return -EINVAL;
+
+ /*
+ * path, offsets and cnt are mandatory,
+ * ref_ctr_offsets and cookies are optional
+ */
+ upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path);
+ uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets);
+ cnt = attr->link_create.uprobe_multi.cnt;
+
+ if (!upath || !uoffsets || !cnt)
+ return -EINVAL;
+
+ uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets);
+ ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies);
+
+ name = strndup_user(upath, PATH_MAX);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ return err;
+ }
+
+ err = kern_path(name, LOOKUP_FOLLOW, &path);
+ kfree(name);
+ if (err)
+ return err;
+
+ if (!d_is_reg(path.dentry)) {
+ err = -EBADF;
+ goto error_path_put;
+ }
+
+ pid = attr->link_create.uprobe_multi.pid;
+ if (pid) {
+ rcu_read_lock();
+ task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
+ rcu_read_unlock();
+ if (!task) {
+ err = -ESRCH;
+ goto error_path_put;
+ }
+ }
+
+ err = -ENOMEM;
+
+ link = kzalloc(sizeof(*link), GFP_KERNEL);
+ uprobes = kvcalloc(cnt, sizeof(*uprobes), GFP_KERNEL);
+
+ if (!uprobes || !link)
+ goto error_free;
+
+ if (uref_ctr_offsets) {
+ ref_ctr_offsets = kvcalloc(cnt, sizeof(*ref_ctr_offsets), GFP_KERNEL);
+ if (!ref_ctr_offsets)
+ goto error_free;
+ }
+
+ for (i = 0; i < cnt; i++) {
+ if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) {
+ err = -EFAULT;
+ goto error_free;
+ }
+ if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) {
+ err = -EFAULT;
+ goto error_free;
+ }
+ if (__get_user(uprobes[i].offset, uoffsets + i)) {
+ err = -EFAULT;
+ goto error_free;
+ }
+
+ uprobes[i].link = link;
+
+ if (flags & BPF_F_UPROBE_MULTI_RETURN)
+ uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler;
+ else
+ uprobes[i].consumer.handler = uprobe_multi_link_handler;
+
+ if (pid)
+ uprobes[i].consumer.filter = uprobe_multi_link_filter;
+ }
+
+ link->cnt = cnt;
+ link->uprobes = uprobes;
+ link->path = path;
+ link->task = task;
+
+ bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
+ &bpf_uprobe_multi_link_lops, prog);
+
+ for (i = 0; i < cnt; i++) {
+ err = uprobe_register_refctr(d_real_inode(link->path.dentry),
+ uprobes[i].offset,
+ ref_ctr_offsets ? ref_ctr_offsets[i] : 0,
+ &uprobes[i].consumer);
+ if (err) {
+ bpf_uprobe_unregister(&path, uprobes, i);
+ goto error_free;
+ }
+ }
+
+ err = bpf_link_prime(&link->link, &link_primer);
+ if (err)
+ goto error_free;
+
+ kvfree(ref_ctr_offsets);
+ return bpf_link_settle(&link_primer);
+
+error_free:
+ kvfree(ref_ctr_offsets);
+ kvfree(uprobes);
+ kfree(link);
+ if (task)
+ put_task_struct(task);
+error_path_put:
+ path_put(&path);
+ return err;
+}
+#else /* !CONFIG_UPROBES */
+int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ return -EOPNOTSUPP;
+}
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+ return 0;
+}
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+ return 0;
+}
+#endif /* CONFIG_UPROBES */
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 3b21f4063258..6cd2a4e3afb8 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -187,9 +187,9 @@ static void fprobe_init(struct fprobe *fp)
static int fprobe_init_rethook(struct fprobe *fp, int num)
{
- int i, size;
+ int size;
- if (num < 0)
+ if (num <= 0)
return -EINVAL;
if (!fp->exit_handler) {
@@ -202,29 +202,21 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
size = fp->nr_maxactive;
else
size = num * num_possible_cpus() * 2;
- if (size < 0)
- return -E2BIG;
-
- fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
- if (!fp->rethook)
- return -ENOMEM;
- for (i = 0; i < size; i++) {
- struct fprobe_rethook_node *node;
-
- node = kzalloc(sizeof(*node) + fp->entry_data_size, GFP_KERNEL);
- if (!node) {
- rethook_free(fp->rethook);
- fp->rethook = NULL;
- return -ENOMEM;
- }
- rethook_add_node(fp->rethook, &node->node);
- }
+ if (size <= 0)
+ return -EINVAL;
+
+ /* Initialize rethook */
+ fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler,
+ sizeof(struct fprobe_rethook_node), size);
+ if (IS_ERR(fp->rethook))
+ return PTR_ERR(fp->rethook);
+
return 0;
}
static void fprobe_fail_cleanup(struct fprobe *fp)
{
- if (fp->rethook) {
+ if (!IS_ERR_OR_NULL(fp->rethook)) {
/* Don't need to cleanup rethook->handler because this is not used. */
rethook_free(fp->rethook);
fp->rethook = NULL;
@@ -379,14 +371,14 @@ int unregister_fprobe(struct fprobe *fp)
if (!fprobe_is_registered(fp))
return -EINVAL;
- if (fp->rethook)
+ if (!IS_ERR_OR_NULL(fp->rethook))
rethook_stop(fp->rethook);
ret = unregister_ftrace_function(&fp->ops);
if (ret < 0)
return ret;
- if (fp->rethook)
+ if (!IS_ERR_OR_NULL(fp->rethook))
rethook_free(fp->rethook);
ftrace_free_filter(&fp->ops);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 05c0024815bf..8de8bec5f366 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6779,8 +6779,7 @@ void ftrace_release_mod(struct module *mod)
last_pg = &ftrace_pages_start;
for (pg = ftrace_pages_start; pg; pg = *last_pg) {
rec = &pg->records[0];
- if (within_module_core(rec->ip, mod) ||
- within_module_init(rec->ip, mod)) {
+ if (within_module(rec->ip, mod)) {
/*
* As core pages are first, the first
* page should never be a module page.
@@ -6852,8 +6851,7 @@ void ftrace_module_enable(struct module *mod)
* not part of this module, then skip this pg,
* which the "break" will do.
*/
- if (!within_module_core(rec->ip, mod) &&
- !within_module_init(rec->ip, mod))
+ if (!within_module(rec->ip, mod))
break;
/* Weak functions should still be ignored */
@@ -7142,9 +7140,7 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
struct dyn_ftrace key;
struct ftrace_mod_map *mod_map = NULL;
struct ftrace_init_func *func, *func_next;
- struct list_head clear_hash;
-
- INIT_LIST_HEAD(&clear_hash);
+ LIST_HEAD(clear_hash);
key.ip = start;
key.flags = end; /* overload flags, as it is unsigned long */
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 5eb9b598f4e9..fa03094e9e69 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -8,7 +8,6 @@
#include <linux/preempt.h>
#include <linux/rethook.h>
#include <linux/slab.h>
-#include <linux/sort.h>
/* Return hook list (shadow stack by list) */
@@ -36,21 +35,7 @@ void rethook_flush_task(struct task_struct *tk)
static void rethook_free_rcu(struct rcu_head *head)
{
struct rethook *rh = container_of(head, struct rethook, rcu);
- struct rethook_node *rhn;
- struct freelist_node *node;
- int count = 1;
-
- node = rh->pool.head;
- while (node) {
- rhn = container_of(node, struct rethook_node, freelist);
- node = node->next;
- kfree(rhn);
- count++;
- }
-
- /* The rh->ref is the number of pooled node + 1 */
- if (refcount_sub_and_test(count, &rh->ref))
- kfree(rh);
+ objpool_fini(&rh->pool);
}
/**
@@ -63,7 +48,7 @@ static void rethook_free_rcu(struct rcu_head *head)
*/
void rethook_stop(struct rethook *rh)
{
- WRITE_ONCE(rh->handler, NULL);
+ rcu_assign_pointer(rh->handler, NULL);
}
/**
@@ -78,59 +63,73 @@ void rethook_stop(struct rethook *rh)
*/
void rethook_free(struct rethook *rh)
{
- WRITE_ONCE(rh->handler, NULL);
+ rethook_stop(rh);
call_rcu(&rh->rcu, rethook_free_rcu);
}
+static int rethook_init_node(void *nod, void *context)
+{
+ struct rethook_node *node = nod;
+
+ node->rethook = context;
+ return 0;
+}
+
+static int rethook_fini_pool(struct objpool_head *head, void *context)
+{
+ kfree(context);
+ return 0;
+}
+
+static inline rethook_handler_t rethook_get_handler(struct rethook *rh)
+{
+ return (rethook_handler_t)rcu_dereference_check(rh->handler,
+ rcu_read_lock_any_held());
+}
+
/**
* rethook_alloc() - Allocate struct rethook.
* @data: a data to pass the @handler when hooking the return.
- * @handler: the return hook callback function.
+ * @handler: the return hook callback function, must NOT be NULL
+ * @size: node size: rethook node and additional data
+ * @num: number of rethook nodes to be preallocated
*
* Allocate and initialize a new rethook with @data and @handler.
- * Return NULL if memory allocation fails or @handler is NULL.
+ * Return pointer of new rethook, or error codes for failures.
+ *
* Note that @handler == NULL means this rethook is going to be freed.
*/
-struct rethook *rethook_alloc(void *data, rethook_handler_t handler)
+struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
+ int size, int num)
{
- struct rethook *rh = kzalloc(sizeof(struct rethook), GFP_KERNEL);
+ struct rethook *rh;
- if (!rh || !handler) {
- kfree(rh);
- return NULL;
- }
+ if (!handler || num <= 0 || size < sizeof(struct rethook_node))
+ return ERR_PTR(-EINVAL);
+
+ rh = kzalloc(sizeof(struct rethook), GFP_KERNEL);
+ if (!rh)
+ return ERR_PTR(-ENOMEM);
rh->data = data;
- rh->handler = handler;
- rh->pool.head = NULL;
- refcount_set(&rh->ref, 1);
+ rcu_assign_pointer(rh->handler, handler);
+ /* initialize the objpool for rethook nodes */
+ if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
+ rethook_init_node, rethook_fini_pool)) {
+ kfree(rh);
+ return ERR_PTR(-ENOMEM);
+ }
return rh;
}
-/**
- * rethook_add_node() - Add a new node to the rethook.
- * @rh: the struct rethook.
- * @node: the struct rethook_node to be added.
- *
- * Add @node to @rh. User must allocate @node (as a part of user's
- * data structure.) The @node fields are initialized in this function.
- */
-void rethook_add_node(struct rethook *rh, struct rethook_node *node)
-{
- node->rethook = rh;
- freelist_add(&node->freelist, &rh->pool);
- refcount_inc(&rh->ref);
-}
-
static void free_rethook_node_rcu(struct rcu_head *head)
{
struct rethook_node *node = container_of(head, struct rethook_node, rcu);
+ struct rethook *rh = node->rethook;
- if (refcount_dec_and_test(&node->rethook->ref))
- kfree(node->rethook);
- kfree(node);
+ objpool_drop(node, &rh->pool);
}
/**
@@ -142,10 +141,11 @@ static void free_rethook_node_rcu(struct rcu_head *head)
*/
void rethook_recycle(struct rethook_node *node)
{
- lockdep_assert_preemption_disabled();
+ rethook_handler_t handler;
- if (likely(READ_ONCE(node->rethook->handler)))
- freelist_add(&node->freelist, &node->rethook->pool);
+ handler = rethook_get_handler(node->rethook);
+ if (likely(handler))
+ objpool_push(node, &node->rethook->pool);
else
call_rcu(&node->rcu, free_rethook_node_rcu);
}
@@ -160,10 +160,7 @@ NOKPROBE_SYMBOL(rethook_recycle);
*/
struct rethook_node *rethook_try_get(struct rethook *rh)
{
- rethook_handler_t handler = READ_ONCE(rh->handler);
- struct freelist_node *fn;
-
- lockdep_assert_preemption_disabled();
+ rethook_handler_t handler = rethook_get_handler(rh);
/* Check whether @rh is going to be freed. */
if (unlikely(!handler))
@@ -178,11 +175,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
if (unlikely(!rcu_is_watching()))
return NULL;
- fn = freelist_try_get(&rh->pool);
- if (!fn)
- return NULL;
-
- return container_of(fn, struct rethook_node, freelist);
+ return (struct rethook_node *)objpool_pop(&rh->pool);
}
NOKPROBE_SYMBOL(rethook_try_get);
@@ -312,7 +305,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs,
rhn = container_of(first, struct rethook_node, llist);
if (WARN_ON_ONCE(rhn->frame != frame))
break;
- handler = READ_ONCE(rhn->rethook->handler);
+ handler = rethook_get_handler(rhn->rethook);
if (handler)
handler(rhn, rhn->rethook->data,
correct_ret_addr, regs);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 52dea5dd5362..83eab547f1d1 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage)
local_set(&bpage->commit, 0);
}
+static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
+{
+ return local_read(&bpage->page->commit);
+}
+
static void free_buffer_page(struct buffer_page *bpage)
{
free_page((unsigned long)bpage->page);
@@ -639,8 +644,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
*cnt = rb_time_cnt(top);
- /* If top and bottom counts don't match, this interrupted a write */
- if (*cnt != rb_time_cnt(bottom))
+ /* If top, msb or bottom counts don't match, this interrupted a write */
+ if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
return false;
/* The shift to msb will lose its cnt bits */
@@ -692,48 +697,7 @@ static void rb_time_set(rb_time_t *t, u64 val)
static inline bool
rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
{
- unsigned long ret;
-
- ret = local_cmpxchg(l, expect, set);
- return ret == expect;
-}
-
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
- unsigned long cnt, top, bottom, msb;
- unsigned long cnt2, top2, bottom2, msb2;
- u64 val;
-
- /* The cmpxchg always fails if it interrupted an update */
- if (!__rb_time_read(t, &val, &cnt2))
- return false;
-
- if (val != expect)
- return false;
-
- cnt = local_read(&t->cnt);
- if ((cnt & 3) != cnt2)
- return false;
-
- cnt2 = cnt + 1;
-
- rb_time_split(val, &top, &bottom, &msb);
- top = rb_time_val_cnt(top, cnt);
- bottom = rb_time_val_cnt(bottom, cnt);
-
- rb_time_split(set, &top2, &bottom2, &msb2);
- top2 = rb_time_val_cnt(top2, cnt2);
- bottom2 = rb_time_val_cnt(bottom2, cnt2);
-
- if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
- return false;
- if (!rb_time_read_cmpxchg(&t->msb, msb, msb2))
- return false;
- if (!rb_time_read_cmpxchg(&t->top, top, top2))
- return false;
- if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
- return false;
- return true;
+ return local_try_cmpxchg(l, &expect, set);
}
#else /* 64 bits */
@@ -749,13 +713,6 @@ static void rb_time_set(rb_time_t *t, u64 val)
{
local64_set(&t->time, val);
}
-
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
- u64 val;
- val = local64_cmpxchg(&t->time, expect, set);
- return val == expect;
-}
#endif
/*
@@ -1137,6 +1094,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
if (full) {
poll_wait(filp, &work->full_waiters, poll_table);
work->full_waiters_pending = true;
+ if (!cpu_buffer->shortest_full ||
+ cpu_buffer->shortest_full > full)
+ cpu_buffer->shortest_full = full;
} else {
poll_wait(filp, &work->waiters, poll_table);
work->waiters_pending = true;
@@ -1494,14 +1454,11 @@ static bool rb_head_page_replace(struct buffer_page *old,
{
unsigned long *ptr = (unsigned long *)&old->list.prev->next;
unsigned long val;
- unsigned long ret;
val = *ptr & ~RB_FLAG_MASK;
val |= RB_PAGE_HEAD;
- ret = cmpxchg(ptr, val, (unsigned long)&new->list);
-
- return ret == val;
+ return try_cmpxchg(ptr, &val, (unsigned long)&new->list);
}
/*
@@ -1787,6 +1744,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
free_buffer_page(bpage);
}
+ free_page((unsigned long)cpu_buffer->free_page);
+
kfree(cpu_buffer);
}
@@ -2011,7 +1970,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
* Increment overrun to account for the lost events.
*/
local_add(page_entries, &cpu_buffer->overrun);
- local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+ local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes);
local_inc(&cpu_buffer->pages_lost);
}
@@ -2056,7 +2015,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
retries = 10;
success = false;
while (retries--) {
- struct list_head *head_page, *prev_page, *r;
+ struct list_head *head_page, *prev_page;
struct list_head *last_page, *first_page;
struct list_head *head_page_with_bit;
struct buffer_page *hpage = rb_set_head_page(cpu_buffer);
@@ -2075,9 +2034,9 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
last_page->next = head_page_with_bit;
first_page->prev = prev_page;
- r = cmpxchg(&prev_page->next, head_page_with_bit, first_page);
-
- if (r == head_page_with_bit) {
+ /* caution: head_page_with_bit gets updated on cmpxchg failure */
+ if (try_cmpxchg(&prev_page->next,
+ &head_page_with_bit, first_page)) {
/*
* yay, we replaced the page pointer to our new list,
* now, we just have to update to head page's prev
@@ -2206,6 +2165,8 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
err = -ENOMEM;
goto out_err;
}
+
+ cond_resched();
}
cpus_read_lock();
@@ -2373,11 +2334,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->reader_page->read);
}
-static __always_inline unsigned rb_page_commit(struct buffer_page *bpage)
-{
- return local_read(&bpage->page->commit);
-}
-
static struct ring_buffer_event *
rb_iter_head_event(struct ring_buffer_iter *iter)
{
@@ -2396,6 +2352,11 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
*/
commit = rb_page_commit(iter_head_page);
smp_rmb();
+
+ /* An event needs to be at least 8 bytes in size */
+ if (iter->head > commit - 8)
+ goto reset;
+
event = __rb_page_index(iter_head_page, iter->head);
length = rb_event_length(event);
@@ -2405,7 +2366,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
*/
barrier();
- if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE)
+ if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
/* Writer corrupted the read? */
goto reset;
@@ -2518,7 +2479,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
* the counters.
*/
local_add(entries, &cpu_buffer->overrun);
- local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+ local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes);
local_inc(&cpu_buffer->pages_lost);
/*
@@ -2661,9 +2622,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
event = __rb_page_index(tail_page, tail);
- /* account for padding bytes */
- local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
-
/*
* Save the original length to the meta data.
* This will be used by the reader to add lost event
@@ -2677,7 +2635,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
* write counter enough to allow another writer to slip
* in on this page.
* We put in a discarded commit instead, to make sure
- * that this space is not used again.
+ * that this space is not used again, and this space will
+ * not be accounted into 'entries_bytes'.
*
* If we are less than the minimum size, we don't need to
* worry about it.
@@ -2702,6 +2661,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
/* time delta must be non zero */
event->time_delta = 1;
+ /* account for padding bytes */
+ local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+
/* Make sure the padding is visible before the tail_page->write update */
smp_wmb();
@@ -2978,35 +2940,13 @@ static unsigned rb_calculate_event_length(unsigned length)
return length;
}
-static u64 rb_time_delta(struct ring_buffer_event *event)
-{
- switch (event->type_len) {
- case RINGBUF_TYPE_PADDING:
- return 0;
-
- case RINGBUF_TYPE_TIME_EXTEND:
- return rb_event_time_stamp(event);
-
- case RINGBUF_TYPE_TIME_STAMP:
- return 0;
-
- case RINGBUF_TYPE_DATA:
- return event->time_delta;
- default:
- return 0;
- }
-}
-
static inline bool
rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
unsigned long new_index, old_index;
struct buffer_page *bpage;
- unsigned long index;
unsigned long addr;
- u64 write_stamp;
- u64 delta;
new_index = rb_event_index(event);
old_index = new_index + rb_event_ts_length(event);
@@ -3015,41 +2955,34 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
bpage = READ_ONCE(cpu_buffer->tail_page);
- delta = rb_time_delta(event);
-
- if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
- return false;
-
- /* Make sure the write stamp is read before testing the location */
- barrier();
-
+ /*
+ * Make sure the tail_page is still the same and
+ * the next write location is the end of this event
+ */
if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
unsigned long write_mask =
local_read(&bpage->write) & ~RB_WRITE_MASK;
unsigned long event_length = rb_event_length(event);
- /* Something came in, can't discard */
- if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
- write_stamp, write_stamp - delta))
- return false;
-
/*
- * It's possible that the event time delta is zero
- * (has the same time stamp as the previous event)
- * in which case write_stamp and before_stamp could
- * be the same. In such a case, force before_stamp
- * to be different than write_stamp. It doesn't
- * matter what it is, as long as its different.
+ * For the before_stamp to be different than the write_stamp
+ * to make sure that the next event adds an absolute
+ * value and does not rely on the saved write stamp, which
+ * is now going to be bogus.
+ *
+ * By setting the before_stamp to zero, the next event
+ * is not going to use the write_stamp and will instead
+ * create an absolute timestamp. This means there's no
+ * reason to update the wirte_stamp!
*/
- if (!delta)
- rb_time_set(&cpu_buffer->before_stamp, 0);
+ rb_time_set(&cpu_buffer->before_stamp, 0);
/*
* If an event were to come in now, it would see that the
* write_stamp and the before_stamp are different, and assume
* that this event just added itself before updating
* the write stamp. The interrupting event will fix the
- * write stamp for us, and use the before stamp as its delta.
+ * write stamp for us, and use an absolute timestamp.
*/
/*
@@ -3060,8 +2993,9 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
*/
old_index += write_mask;
new_index += write_mask;
- index = local_cmpxchg(&bpage->write, old_index, new_index);
- if (index == old_index) {
+
+ /* caution: old_index gets updated on cmpxchg failure */
+ if (local_try_cmpxchg(&bpage->write, &old_index, new_index)) {
/* update counters */
local_sub(event_length, &cpu_buffer->entries_bytes);
return true;
@@ -3485,7 +3419,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
return;
/*
- * If this interrupted another event,
+ * If this interrupted another event,
*/
if (atomic_inc_return(this_cpu_ptr(&checking)) != 1)
goto out;
@@ -3579,7 +3513,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
* absolute timestamp.
* Don't bother if this is the start of a new page (w == 0).
*/
- if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) {
+ if (!w) {
+ /* Use the sub-buffer timestamp */
+ info->delta = 0;
+ } else if (unlikely(!a_ok || !b_ok || info->before != info->after)) {
info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
info->length += RB_LEN_TIME_EXTEND;
} else {
@@ -3602,26 +3539,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
/* See if we shot pass the end of this buffer page */
if (unlikely(write > BUF_PAGE_SIZE)) {
- /* before and after may now different, fix it up*/
- b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- if (a_ok && b_ok && info->before != info->after)
- (void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
- info->before, info->after);
- if (a_ok && b_ok)
- check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
+ check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
return rb_move_tail(cpu_buffer, tail, info);
}
if (likely(tail == w)) {
- u64 save_before;
- bool s_ok;
-
/* Nothing interrupted us between A and C */
/*D*/ rb_time_set(&cpu_buffer->write_stamp, info->ts);
- barrier();
- /*E*/ s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before);
- RB_WARN_ON(cpu_buffer, !s_ok);
+ /*
+ * If something came in between C and D, the write stamp
+ * may now not be in sync. But that's fine as the before_stamp
+ * will be different and then next event will just be forced
+ * to use an absolute timestamp.
+ */
if (likely(!(info->add_timestamp &
(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
/* This did not interrupt any time update */
@@ -3629,41 +3559,40 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
else
/* Just use full timestamp for interrupting event */
info->delta = info->ts;
- barrier();
check_buffer(cpu_buffer, info, tail);
- if (unlikely(info->ts != save_before)) {
- /* SLOW PATH - Interrupted between C and E */
-
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- RB_WARN_ON(cpu_buffer, !a_ok);
-
- /* Write stamp must only go forward */
- if (save_before > info->after) {
- /*
- * We do not care about the result, only that
- * it gets updated atomically.
- */
- (void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
- info->after, save_before);
- }
- }
} else {
u64 ts;
/* SLOW PATH - Interrupted between A and C */
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- /* Was interrupted before here, write_stamp must be valid */
+
+ /* Save the old before_stamp */
+ a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
RB_WARN_ON(cpu_buffer, !a_ok);
+
+ /*
+ * Read a new timestamp and update the before_stamp to make
+ * the next event after this one force using an absolute
+ * timestamp. This is in case an interrupt were to come in
+ * between E and F.
+ */
ts = rb_time_stamp(cpu_buffer->buffer);
+ rb_time_set(&cpu_buffer->before_stamp, ts);
+
+ barrier();
+ /*E*/ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+ /* Was interrupted before here, write_stamp must be valid */
+ RB_WARN_ON(cpu_buffer, !a_ok);
barrier();
- /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
- info->after < ts &&
- rb_time_cmpxchg(&cpu_buffer->write_stamp,
- info->after, ts)) {
- /* Nothing came after this event between C and E */
+ /*F*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
+ info->after == info->before && info->after < ts) {
+ /*
+ * Nothing came after this event between C and F, it is
+ * safe to use info->after for the delta as it
+ * matched info->before and is still valid.
+ */
info->delta = ts - info->after;
} else {
/*
- * Interrupted between C and E:
+ * Interrupted between C and F:
* Lost the previous events time stamp. Just set the
* delta to zero, and this will be the same time as
* the event this event interrupted. And the events that
@@ -3714,6 +3643,12 @@ rb_reserve_next_event(struct trace_buffer *buffer,
int nr_loops = 0;
int add_ts_default;
+ /* ring buffer does cmpxchg, make sure it is safe in NMI context */
+ if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) &&
+ (unlikely(in_nmi()))) {
+ return NULL;
+ }
+
rb_start_commit(cpu_buffer);
/* The commit page can not change after this */
@@ -3737,6 +3672,8 @@ rb_reserve_next_event(struct trace_buffer *buffer,
if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
add_ts_default = RB_ADD_STAMP_ABSOLUTE;
info.length += RB_LEN_TIME_EXTEND;
+ if (info.length > BUF_MAX_DATA_SIZE)
+ goto out_fail;
} else {
add_ts_default = RB_ADD_STAMP_NONE;
}
@@ -4216,7 +4153,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu)
EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts);
/**
- * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer
+ * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer
* @buffer: The ring buffer
* @cpu: The per CPU buffer to read from.
*/
@@ -4724,6 +4661,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
length = rb_event_length(event);
cpu_buffer->reader_page->read += length;
+ cpu_buffer->read_bytes += length;
}
static void rb_advance_iter(struct ring_buffer_iter *iter)
@@ -5117,7 +5055,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
if (!iter)
return NULL;
- iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags);
+ /* Holds the entire event: data and meta data */
+ iter->event = kmalloc(BUF_PAGE_SIZE, flags);
if (!iter->event) {
kfree(iter);
return NULL;
@@ -5817,7 +5756,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
} else {
/* update the entry counter */
cpu_buffer->read += rb_page_entries(reader);
- cpu_buffer->read_bytes += BUF_PAGE_SIZE;
+ cpu_buffer->read_bytes += rb_page_commit(reader);
/* swap the pages */
rb_init_page(bpage);
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 8dfe85499d4a..354c2117be43 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -477,6 +477,17 @@ static int __init synth_event_gen_test_init(void)
ret = test_trace_synth_event();
WARN_ON(ret);
+
+ /* Disable when done */
+ trace_array_set_clr_event(gen_synth_test->tr,
+ "synthetic",
+ "gen_synth_test", false);
+ trace_array_set_clr_event(empty_synth_test->tr,
+ "synthetic",
+ "empty_synth_test", false);
+ trace_array_set_clr_event(create_synth_test->tr,
+ "synthetic",
+ "create_synth_test", false);
out:
return ret;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8e64aaad5361..199df497db07 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -54,12 +54,6 @@
#include "trace.h"
#include "trace_output.h"
-/*
- * On boot up, the ring buffer is set to the minimum size, so that
- * we do not waste memory on systems that are not using tracing.
- */
-bool ring_buffer_expanded;
-
#ifdef CONFIG_FTRACE_STARTUP_TEST
/*
* We need to change this state when a selftest is running.
@@ -202,7 +196,7 @@ static int __init set_cmdline_ftrace(char *str)
strscpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
default_bootup_tracer = bootup_tracer_buf;
/* We are using ftrace early, expand it */
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(NULL);
return 1;
}
__setup("ftrace=", set_cmdline_ftrace);
@@ -247,7 +241,7 @@ static int __init boot_alloc_snapshot(char *str)
} else {
allocate_snapshot = true;
/* We also need the main ring buffer expanded */
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(NULL);
}
return 1;
}
@@ -490,6 +484,13 @@ static struct trace_array global_trace = {
.trace_flags = TRACE_DEFAULT_FLAGS,
};
+void trace_set_ring_buffer_expanded(struct trace_array *tr)
+{
+ if (!tr)
+ tr = &global_trace;
+ tr->ring_buffer_expanded = true;
+}
+
LIST_HEAD(ftrace_trace_arrays);
int trace_array_get(struct trace_array *this_tr)
@@ -1730,15 +1731,15 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
{
int len;
- if (trace_seq_used(s) <= s->seq.readpos)
+ if (trace_seq_used(s) <= s->readpos)
return -EBUSY;
- len = trace_seq_used(s) - s->seq.readpos;
+ len = trace_seq_used(s) - s->readpos;
if (cnt > len)
cnt = len;
- memcpy(buf, s->buffer + s->seq.readpos, cnt);
+ memcpy(buf, s->buffer + s->readpos, cnt);
- s->seq.readpos += cnt;
+ s->readpos += cnt;
return cnt;
}
@@ -1772,7 +1773,7 @@ static void trace_create_maxlat_file(struct trace_array *tr,
init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq);
tr->d_max_latency = trace_create_file("tracing_max_latency",
TRACE_MODE_WRITE,
- d_tracer, &tr->max_latency,
+ d_tracer, tr,
&tracing_max_lat_fops);
}
@@ -1805,7 +1806,7 @@ void latency_fsnotify(struct trace_array *tr)
#define trace_create_maxlat_file(tr, d_tracer) \
trace_create_file("tracing_max_latency", TRACE_MODE_WRITE, \
- d_tracer, &tr->max_latency, &tracing_max_lat_fops)
+ d_tracer, tr, &tracing_max_lat_fops)
#endif
@@ -2012,7 +2013,7 @@ static int run_tracer_selftest(struct tracer *type)
#ifdef CONFIG_TRACER_MAX_TRACE
if (type->use_max_tr) {
/* If we expanded the buffers, make sure the max is expanded too */
- if (ring_buffer_expanded)
+ if (tr->ring_buffer_expanded)
ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size,
RING_BUFFER_ALL_CPUS);
tr->allocated_snapshot = true;
@@ -2038,7 +2039,7 @@ static int run_tracer_selftest(struct tracer *type)
tr->allocated_snapshot = false;
/* Shrink the max buffer again */
- if (ring_buffer_expanded)
+ if (tr->ring_buffer_expanded)
ring_buffer_resize(tr->max_buffer.buffer, 1,
RING_BUFFER_ALL_CPUS);
}
@@ -2359,13 +2360,7 @@ int is_tracing_stopped(void)
return global_trace.stop_count;
}
-/**
- * tracing_start - quick start of the tracer
- *
- * If tracing is enabled but was stopped by tracing_stop,
- * this will start the tracer back up.
- */
-void tracing_start(void)
+static void tracing_start_tr(struct trace_array *tr)
{
struct trace_buffer *buffer;
unsigned long flags;
@@ -2373,119 +2368,83 @@ void tracing_start(void)
if (tracing_disabled)
return;
- raw_spin_lock_irqsave(&global_trace.start_lock, flags);
- if (--global_trace.stop_count) {
- if (global_trace.stop_count < 0) {
+ raw_spin_lock_irqsave(&tr->start_lock, flags);
+ if (--tr->stop_count) {
+ if (WARN_ON_ONCE(tr->stop_count < 0)) {
/* Someone screwed up their debugging */
- WARN_ON_ONCE(1);
- global_trace.stop_count = 0;
+ tr->stop_count = 0;
}
goto out;
}
/* Prevent the buffers from switching */
- arch_spin_lock(&global_trace.max_lock);
+ arch_spin_lock(&tr->max_lock);
- buffer = global_trace.array_buffer.buffer;
+ buffer = tr->array_buffer.buffer;
if (buffer)
ring_buffer_record_enable(buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
- buffer = global_trace.max_buffer.buffer;
+ buffer = tr->max_buffer.buffer;
if (buffer)
ring_buffer_record_enable(buffer);
#endif
- arch_spin_unlock(&global_trace.max_lock);
-
- out:
- raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
-}
-
-static void tracing_start_tr(struct trace_array *tr)
-{
- struct trace_buffer *buffer;
- unsigned long flags;
-
- if (tracing_disabled)
- return;
-
- /* If global, we need to also start the max tracer */
- if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
- return tracing_start();
-
- raw_spin_lock_irqsave(&tr->start_lock, flags);
-
- if (--tr->stop_count) {
- if (tr->stop_count < 0) {
- /* Someone screwed up their debugging */
- WARN_ON_ONCE(1);
- tr->stop_count = 0;
- }
- goto out;
- }
-
- buffer = tr->array_buffer.buffer;
- if (buffer)
- ring_buffer_record_enable(buffer);
+ arch_spin_unlock(&tr->max_lock);
out:
raw_spin_unlock_irqrestore(&tr->start_lock, flags);
}
/**
- * tracing_stop - quick stop of the tracer
+ * tracing_start - quick start of the tracer
*
- * Light weight way to stop tracing. Use in conjunction with
- * tracing_start.
+ * If tracing is enabled but was stopped by tracing_stop,
+ * this will start the tracer back up.
*/
-void tracing_stop(void)
+void tracing_start(void)
+
+{
+ return tracing_start_tr(&global_trace);
+}
+
+static void tracing_stop_tr(struct trace_array *tr)
{
struct trace_buffer *buffer;
unsigned long flags;
- raw_spin_lock_irqsave(&global_trace.start_lock, flags);
- if (global_trace.stop_count++)
+ raw_spin_lock_irqsave(&tr->start_lock, flags);
+ if (tr->stop_count++)
goto out;
/* Prevent the buffers from switching */
- arch_spin_lock(&global_trace.max_lock);
+ arch_spin_lock(&tr->max_lock);
- buffer = global_trace.array_buffer.buffer;
+ buffer = tr->array_buffer.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
- buffer = global_trace.max_buffer.buffer;
+ buffer = tr->max_buffer.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
#endif
- arch_spin_unlock(&global_trace.max_lock);
+ arch_spin_unlock(&tr->max_lock);
out:
- raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+ raw_spin_unlock_irqrestore(&tr->start_lock, flags);
}
-static void tracing_stop_tr(struct trace_array *tr)
+/**
+ * tracing_stop - quick stop of the tracer
+ *
+ * Light weight way to stop tracing. Use in conjunction with
+ * tracing_start.
+ */
+void tracing_stop(void)
{
- struct trace_buffer *buffer;
- unsigned long flags;
-
- /* If global, we need to also stop the max tracer */
- if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
- return tracing_stop();
-
- raw_spin_lock_irqsave(&tr->start_lock, flags);
- if (tr->stop_count++)
- goto out;
-
- buffer = tr->array_buffer.buffer;
- if (buffer)
- ring_buffer_record_disable(buffer);
-
- out:
- raw_spin_unlock_irqrestore(&tr->start_lock, flags);
+ return tracing_stop_tr(&global_trace);
}
static int trace_save_cmdline(struct task_struct *tsk)
@@ -2769,8 +2728,11 @@ void trace_buffered_event_enable(void)
for_each_tracing_cpu(cpu) {
page = alloc_pages_node(cpu_to_node(cpu),
GFP_KERNEL | __GFP_NORETRY, 0);
- if (!page)
- goto failed;
+ /* This is just an optimization and can handle failures */
+ if (!page) {
+ pr_err("Failed to allocate event buffer\n");
+ break;
+ }
event = page_address(page);
memset(event, 0, sizeof(*event));
@@ -2784,10 +2746,6 @@ void trace_buffered_event_enable(void)
WARN_ON_ONCE(1);
preempt_enable();
}
-
- return;
- failed:
- trace_buffered_event_disable();
}
static void enable_trace_buffered_event(void *data)
@@ -2822,11 +2780,9 @@ void trace_buffered_event_disable(void)
if (--trace_buffered_event_ref)
return;
- preempt_disable();
/* For each CPU, set the buffer as used. */
- smp_call_function_many(tracing_buffer_mask,
- disable_trace_buffered_event, NULL, 1);
- preempt_enable();
+ on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event,
+ NULL, true);
/* Wait for all current users to finish */
synchronize_rcu();
@@ -2835,17 +2791,19 @@ void trace_buffered_event_disable(void)
free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
per_cpu(trace_buffered_event, cpu) = NULL;
}
+
/*
- * Make sure trace_buffered_event is NULL before clearing
- * trace_buffered_event_cnt.
+ * Wait for all CPUs that potentially started checking if they can use
+ * their event buffer only after the previous synchronize_rcu() call and
+ * they still read a valid pointer from trace_buffered_event. It must be
+ * ensured they don't see cleared trace_buffered_event_cnt else they
+ * could wrongly decide to use the pointed-to buffer which is now freed.
*/
- smp_wmb();
+ synchronize_rcu();
- preempt_disable();
- /* Do the work on each cpu */
- smp_call_function_many(tracing_buffer_mask,
- enable_trace_buffered_event, NULL, 1);
- preempt_enable();
+ /* For each CPU, relinquish the buffer */
+ on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL,
+ true);
}
static struct trace_buffer *temp_buffer;
@@ -3119,7 +3077,6 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
struct ftrace_stack *fstack;
struct stack_entry *entry;
int stackidx;
- void *ptr;
/*
* Add one, for this function and the call to save_stack_trace()
@@ -3157,32 +3114,16 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
nr_entries = stack_trace_save(fstack->calls, size, skip);
}
- size = nr_entries * sizeof(unsigned long);
event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
- (sizeof(*entry) - sizeof(entry->caller)) + size,
+ struct_size(entry, caller, nr_entries),
trace_ctx);
if (!event)
goto out;
- ptr = ring_buffer_event_data(event);
- entry = ptr;
-
- /*
- * For backward compatibility reasons, the entry->caller is an
- * array of 8 slots to store the stack. This is also exported
- * to user space. The amount allocated on the ring buffer actually
- * holds enough for the stack specified by nr_entries. This will
- * go into the location of entry->caller. Due to string fortifiers
- * checking the size of the destination of memcpy() it triggers
- * when it detects that size is greater than 8. To hide this from
- * the fortifiers, we use "ptr" and pointer arithmetic to assign caller.
- *
- * The below is really just:
- * memcpy(&entry->caller, fstack->calls, size);
- */
- ptr += offsetof(typeof(*entry), caller);
- memcpy(ptr, fstack->calls, size);
+ entry = ring_buffer_event_data(event);
entry->size = nr_entries;
+ memcpy(&entry->caller, fstack->calls,
+ flex_array_size(entry, caller, nr_entries));
if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
@@ -3420,7 +3361,7 @@ void trace_printk_init_buffers(void)
pr_warn("**********************************************************\n");
/* Expand the buffers to set size */
- tracing_update_buffers();
+ tracing_update_buffers(&global_trace);
buffers_allocated = 1;
@@ -3844,15 +3785,6 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
return false;
}
-static const char *show_buffer(struct trace_seq *s)
-{
- struct seq_buf *seq = &s->seq;
-
- seq_buf_terminate(seq);
-
- return seq->buffer;
-}
-
static DEFINE_STATIC_KEY_FALSE(trace_no_verify);
static int test_can_verify_check(const char *fmt, ...)
@@ -3992,7 +3924,7 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
*/
if (WARN_ONCE(!trace_safe_str(iter, str, star, len),
"fmt: '%s' current_buffer: '%s'",
- fmt, show_buffer(&iter->seq))) {
+ fmt, seq_buf_str(&iter->seq.seq))) {
int ret;
/* Try to safely read the string */
@@ -4206,18 +4138,12 @@ static void *s_start(struct seq_file *m, loff_t *pos)
loff_t l = 0;
int cpu;
- /*
- * copy the tracer to avoid using a global lock all around.
- * iter->trace is a copy of current_trace, the pointer to the
- * name may be used instead of a strcmp(), as iter->trace->name
- * will point to the same string as current_trace->name.
- */
mutex_lock(&trace_types_lock);
- if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) {
+ if (unlikely(tr->current_trace != iter->trace)) {
/* Close iter->trace before switching to the new current tracer */
if (iter->trace->close)
iter->trace->close(iter);
- *iter->trace = *tr->current_trace;
+ iter->trace = tr->current_trace;
/* Reopen the new current tracer */
if (iter->trace->open)
iter->trace->open(iter);
@@ -4796,7 +4722,11 @@ static int s_show(struct seq_file *m, void *v)
iter->leftover = ret;
} else {
- print_trace_line(iter);
+ ret = print_trace_line(iter);
+ if (ret == TRACE_TYPE_PARTIAL_LINE) {
+ iter->seq.full = 0;
+ trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n");
+ }
ret = trace_print_seq(m, &iter->seq);
/*
* If we overflow the seq_file buffer, then it will
@@ -4829,6 +4759,25 @@ static const struct seq_operations tracer_seq_ops = {
.show = s_show,
};
+/*
+ * Note, as iter itself can be allocated and freed in different
+ * ways, this function is only used to free its content, and not
+ * the iterator itself. The only requirement to all the allocations
+ * is that it must zero all fields (kzalloc), as freeing works with
+ * ethier allocated content or NULL.
+ */
+static void free_trace_iter_content(struct trace_iterator *iter)
+{
+ /* The fmt is either NULL, allocated or points to static_fmt_buf */
+ if (iter->fmt != static_fmt_buf)
+ kfree(iter->fmt);
+
+ kfree(iter->temp);
+ kfree(iter->buffer_iter);
+ mutex_destroy(&iter->mutex);
+ free_cpumask_var(iter->started);
+}
+
static struct trace_iterator *
__tracing_open(struct inode *inode, struct file *file, bool snapshot)
{
@@ -4870,16 +4819,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
iter->fmt = NULL;
iter->fmt_size = 0;
- /*
- * We make a copy of the current tracer to avoid concurrent
- * changes on it while we are reading.
- */
mutex_lock(&trace_types_lock);
- iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL);
- if (!iter->trace)
- goto fail;
-
- *iter->trace = *tr->current_trace;
+ iter->trace = tr->current_trace;
if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
goto fail;
@@ -4944,9 +4885,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
fail:
mutex_unlock(&trace_types_lock);
- kfree(iter->trace);
- kfree(iter->temp);
- kfree(iter->buffer_iter);
+ free_trace_iter_content(iter);
release:
seq_release_private(inode, file);
return ERR_PTR(-ENOMEM);
@@ -4987,6 +4926,54 @@ int tracing_open_generic_tr(struct inode *inode, struct file *filp)
return 0;
}
+/*
+ * The private pointer of the inode is the trace_event_file.
+ * Update the tr ref count associated to it.
+ */
+int tracing_open_file_tr(struct inode *inode, struct file *filp)
+{
+ struct trace_event_file *file = inode->i_private;
+ int ret;
+
+ ret = tracing_check_open_get_tr(file->tr);
+ if (ret)
+ return ret;
+
+ mutex_lock(&event_mutex);
+
+ /* Fail if the file is marked for removal */
+ if (file->flags & EVENT_FILE_FL_FREED) {
+ trace_array_put(file->tr);
+ ret = -ENODEV;
+ } else {
+ event_file_get(file);
+ }
+
+ mutex_unlock(&event_mutex);
+ if (ret)
+ return ret;
+
+ filp->private_data = inode->i_private;
+
+ return 0;
+}
+
+int tracing_release_file_tr(struct inode *inode, struct file *filp)
+{
+ struct trace_event_file *file = inode->i_private;
+
+ trace_array_put(file->tr);
+ event_file_put(file);
+
+ return 0;
+}
+
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp)
+{
+ tracing_release_file_tr(inode, filp);
+ return single_release(inode, filp);
+}
+
static int tracing_mark_open(struct inode *inode, struct file *filp)
{
stream_open(inode, filp);
@@ -5025,12 +5012,7 @@ static int tracing_release(struct inode *inode, struct file *file)
mutex_unlock(&trace_types_lock);
- mutex_destroy(&iter->mutex);
- free_cpumask_var(iter->started);
- kfree(iter->fmt);
- kfree(iter->temp);
- kfree(iter->trace);
- kfree(iter->buffer_iter);
+ free_trace_iter_content(iter);
seq_release_private(inode, file);
return 0;
@@ -5730,7 +5712,8 @@ static const char readme_msg[] =
"\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n"
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
- "\t $stack<index>, $stack, $retval, $comm, $arg<N>, <argname>\n"
+ "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
+ "\t <argname>[->field[->field|.field...]],\n"
#else
"\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
#endif
@@ -6318,6 +6301,15 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val)
per_cpu_ptr(buf->data, cpu)->entries = val;
}
+static void update_buffer_entries(struct array_buffer *buf, int cpu)
+{
+ if (cpu == RING_BUFFER_ALL_CPUS) {
+ set_buffer_entries(buf, ring_buffer_size(buf->buffer, 0));
+ } else {
+ per_cpu_ptr(buf->data, cpu)->entries = ring_buffer_size(buf->buffer, cpu);
+ }
+}
+
#ifdef CONFIG_TRACER_MAX_TRACE
/* resize @tr's buffer to the size of @size_tr's entries */
static int resize_buffer_duplicate_size(struct array_buffer *trace_buf,
@@ -6356,19 +6348,21 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
* we use the size that was given, and we can forget about
* expanding it later.
*/
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(tr);
/* May be called before buffers are initialized */
if (!tr->array_buffer.buffer)
return 0;
+ /* Do not allow tracing while resizing ring buffer */
+ tracing_stop_tr(tr);
+
ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu);
if (ret < 0)
- return ret;
+ goto out_start;
#ifdef CONFIG_TRACER_MAX_TRACE
- if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) ||
- !tr->current_trace->use_max_tr)
+ if (!tr->allocated_snapshot)
goto out;
ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
@@ -6393,22 +6387,17 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
WARN_ON(1);
tracing_disabled = 1;
}
- return ret;
+ goto out_start;
}
- if (cpu == RING_BUFFER_ALL_CPUS)
- set_buffer_entries(&tr->max_buffer, size);
- else
- per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size;
+ update_buffer_entries(&tr->max_buffer, cpu);
out:
#endif /* CONFIG_TRACER_MAX_TRACE */
- if (cpu == RING_BUFFER_ALL_CPUS)
- set_buffer_entries(&tr->array_buffer, size);
- else
- per_cpu_ptr(tr->array_buffer.data, cpu)->entries = size;
-
+ update_buffer_entries(&tr->array_buffer, cpu);
+ out_start:
+ tracing_start_tr(tr);
return ret;
}
@@ -6440,6 +6429,7 @@ out:
/**
* tracing_update_buffers - used by tracing facility to expand ring buffers
+ * @tr: The tracing instance
*
* To save on memory when the tracing is never used on a system with it
* configured in. The ring buffers are set to a minimum size. But once
@@ -6448,13 +6438,13 @@ out:
*
* This function is to be called when a tracer is about to be used.
*/
-int tracing_update_buffers(void)
+int tracing_update_buffers(struct trace_array *tr)
{
int ret = 0;
mutex_lock(&trace_types_lock);
- if (!ring_buffer_expanded)
- ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size,
+ if (!tr->ring_buffer_expanded)
+ ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
RING_BUFFER_ALL_CPUS);
mutex_unlock(&trace_types_lock);
@@ -6508,7 +6498,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
mutex_lock(&trace_types_lock);
- if (!ring_buffer_expanded) {
+ if (!tr->ring_buffer_expanded) {
ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
RING_BUFFER_ALL_CPUS);
if (ret < 0)
@@ -6706,14 +6696,18 @@ static ssize_t
tracing_max_lat_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- return tracing_nsecs_read(filp->private_data, ubuf, cnt, ppos);
+ struct trace_array *tr = filp->private_data;
+
+ return tracing_nsecs_read(&tr->max_latency, ubuf, cnt, ppos);
}
static ssize_t
tracing_max_lat_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- return tracing_nsecs_write(filp->private_data, ubuf, cnt, ppos);
+ struct trace_array *tr = filp->private_data;
+
+ return tracing_nsecs_write(&tr->max_latency, ubuf, cnt, ppos);
}
#endif
@@ -6825,10 +6819,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
close_pipe_on_cpu(tr, iter->cpu_file);
mutex_unlock(&trace_types_lock);
- free_cpumask_var(iter->started);
- kfree(iter->fmt);
- kfree(iter->temp);
- mutex_destroy(&iter->mutex);
+ free_trace_iter_content(iter);
kfree(iter);
trace_array_put(tr);
@@ -6993,7 +6984,7 @@ waitagain:
/* Now copy what we have to the user */
sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
- if (iter->seq.seq.readpos >= trace_seq_used(&iter->seq))
+ if (iter->seq.readpos >= trace_seq_used(&iter->seq))
trace_seq_init(&iter->seq);
/*
@@ -7179,7 +7170,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
}
if (buf_size_same) {
- if (!ring_buffer_expanded)
+ if (!tr->ring_buffer_expanded)
r = sprintf(buf, "%lu (expanded: %lu)\n",
size >> 10,
trace_buf_size >> 10);
@@ -7236,10 +7227,10 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf,
mutex_lock(&trace_types_lock);
for_each_tracing_cpu(cpu) {
size += per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10;
- if (!ring_buffer_expanded)
+ if (!tr->ring_buffer_expanded)
expanded_size += trace_buf_size >> 10;
}
- if (ring_buffer_expanded)
+ if (tr->ring_buffer_expanded)
r = sprintf(buf, "%lu\n", size);
else
r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size);
@@ -7618,6 +7609,11 @@ out:
return ret;
}
+static void tracing_swap_cpu_buffer(void *tr)
+{
+ update_max_tr_single((struct trace_array *)tr, current, smp_processor_id());
+}
+
static ssize_t
tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
@@ -7628,7 +7624,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
unsigned long val;
int ret;
- ret = tracing_update_buffers();
+ ret = tracing_update_buffers(tr);
if (ret < 0)
return ret;
@@ -7676,13 +7672,15 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
break;
- local_irq_disable();
/* Now, we're going to swap */
- if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
+ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
+ local_irq_disable();
update_max_tr(tr, current, smp_processor_id(), NULL);
- else
- update_max_tr_single(tr, current, iter->cpu_file);
- local_irq_enable();
+ local_irq_enable();
+ } else {
+ smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer,
+ (void *)tr, 1);
+ }
break;
default:
if (tr->allocated_snapshot) {
@@ -7763,18 +7761,20 @@ static const struct file_operations tracing_thresh_fops = {
#ifdef CONFIG_TRACER_MAX_TRACE
static const struct file_operations tracing_max_lat_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_generic_tr,
.read = tracing_max_lat_read,
.write = tracing_max_lat_write,
.llseek = generic_file_llseek,
+ .release = tracing_release_generic_tr,
};
#endif
static const struct file_operations set_tracer_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_generic_tr,
.read = tracing_set_trace_read,
.write = tracing_set_trace_write,
.llseek = generic_file_llseek,
+ .release = tracing_release_generic_tr,
};
static const struct file_operations tracing_pipe_fops = {
@@ -8967,12 +8967,33 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
return cnt;
}
+static int tracing_open_options(struct inode *inode, struct file *filp)
+{
+ struct trace_option_dentry *topt = inode->i_private;
+ int ret;
+
+ ret = tracing_check_open_get_tr(topt->tr);
+ if (ret)
+ return ret;
+
+ filp->private_data = inode->i_private;
+ return 0;
+}
+
+static int tracing_release_options(struct inode *inode, struct file *file)
+{
+ struct trace_option_dentry *topt = file->private_data;
+
+ trace_array_put(topt->tr);
+ return 0;
+}
static const struct file_operations trace_options_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_options,
.read = trace_options_read,
.write = trace_options_write,
.llseek = generic_file_llseek,
+ .release = tracing_release_options,
};
/*
@@ -9486,7 +9507,7 @@ static struct trace_array *trace_array_create(const char *name)
if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL))
goto out_free_tr;
- if (!alloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
goto out_free_tr;
tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
@@ -9507,6 +9528,9 @@ static struct trace_array *trace_array_create(const char *name)
if (allocate_trace_buffers(tr, trace_buf_size) < 0)
goto out_free_tr;
+ /* The ring buffer is defaultly expanded */
+ trace_set_ring_buffer_expanded(tr);
+
if (ftrace_allocate_ftrace_ops(tr) < 0)
goto out_free_tr;
@@ -9716,7 +9740,6 @@ static __init void create_trace_instances(struct dentry *d_tracer)
static void
init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
{
- struct trace_event_file *file;
int cpu;
trace_create_file("available_tracers", TRACE_MODE_READ, d_tracer,
@@ -9749,11 +9772,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
trace_create_file("trace_marker", 0220, d_tracer,
tr, &tracing_mark_fops);
- file = __find_event_file(tr, "ftrace", "print");
- if (file && file->dir)
- trace_create_file("trigger", TRACE_MODE_WRITE, file->dir,
- file, &event_trigger_fops);
- tr->trace_marker_file = file;
+ tr->trace_marker_file = __find_event_file(tr, "ftrace", "print");
trace_create_file("trace_marker_raw", 0220, d_tracer,
tr, &tracing_mark_raw_fops);
@@ -10401,7 +10420,7 @@ __init static int tracer_alloc_buffers(void)
trace_printk_init_buffers();
/* To save memory, keep the ring buffer size to its minimum */
- if (ring_buffer_expanded)
+ if (global_trace.ring_buffer_expanded)
ring_buf_size = trace_buf_size;
else
ring_buf_size = 1;
@@ -10431,7 +10450,7 @@ __init static int tracer_alloc_buffers(void)
if (trace_create_savedcmd() < 0)
goto out_free_temp_buffer;
- if (!alloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL))
goto out_free_savedcmd;
/* TODO: make the number of buffers hot pluggable with CPUS */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 73eaec158473..0489e72c8169 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -77,6 +77,16 @@ enum trace_type {
#undef __array
#define __array(type, item, size) type item[size];
+/*
+ * For backward compatibility, older user space expects to see the
+ * kernel_stack event with a fixed size caller field. But today the fix
+ * size is ignored by the kernel, and the real structure is dynamic.
+ * Expose to user space: "unsigned long caller[8];" but the real structure
+ * will be "unsigned long caller[] __counted_by(size)"
+ */
+#undef __stack_array
+#define __stack_array(type, item, size, field) type item[] __counted_by(field);
+
#undef __array_desc
#define __array_desc(type, container, item, size)
@@ -371,7 +381,7 @@ struct trace_array {
struct dentry *dir;
struct dentry *options;
struct dentry *percpu_dir;
- struct dentry *event_dir;
+ struct eventfs_inode *event_dir;
struct trace_options *topts;
struct list_head systems;
struct list_head events;
@@ -400,6 +410,11 @@ struct trace_array {
struct cond_snapshot *cond_snapshot;
#endif
struct trace_func_repeats __percpu *last_func_repeats;
+ /*
+ * On boot up, the ring buffer is set to the minimum size, so that
+ * we do not waste memory on systems that are not using tracing.
+ */
+ bool ring_buffer_expanded;
};
enum {
@@ -596,11 +611,13 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu)
int tracer_init(struct tracer *t, struct trace_array *tr);
int tracing_is_enabled(void);
void tracing_reset_online_cpus(struct array_buffer *buf);
-void tracing_reset_current(int cpu);
void tracing_reset_all_online_cpus(void);
void tracing_reset_all_online_cpus_unlocked(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
int tracing_open_generic_tr(struct inode *inode, struct file *filp);
+int tracing_open_file_tr(struct inode *inode, struct file *filp);
+int tracing_release_file_tr(struct inode *inode, struct file *filp);
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
bool tracing_is_disabled(void);
bool tracer_tracing_is_on(struct trace_array *tr);
void tracer_tracing_on(struct trace_array *tr);
@@ -697,7 +714,6 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos);
void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos);
int trace_pid_show(struct seq_file *m, void *v);
-void trace_free_pid_list(struct trace_pid_list *pid_list);
int trace_pid_write(struct trace_pid_list *filtered_pids,
struct trace_pid_list **new_pid_list,
const char __user *ubuf, size_t cnt);
@@ -751,7 +767,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
extern int DYN_FTRACE_TEST_NAME2(void);
-extern bool ring_buffer_expanded;
+extern void trace_set_ring_buffer_expanded(struct trace_array *tr);
extern bool tracing_selftest_disabled;
#ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -1295,7 +1311,7 @@ static inline void trace_branch_disable(void)
#endif /* CONFIG_BRANCH_TRACER */
/* set ring buffers to default size if not already done so */
-int tracing_update_buffers(void);
+int tracing_update_buffers(struct trace_array *tr);
union trace_synth_field {
u8 as_u8;
@@ -1334,7 +1350,7 @@ struct trace_subsystem_dir {
struct list_head list;
struct event_subsystem *subsystem;
struct trace_array *tr;
- struct dentry *entry;
+ struct eventfs_inode *ei;
int ref_count;
int nr_events;
};
@@ -1654,6 +1670,9 @@ extern void event_trigger_unregister(struct event_command *cmd_ops,
char *glob,
struct event_trigger_data *trigger_data);
+extern void event_file_get(struct trace_event_file *file);
+extern void event_file_put(struct trace_event_file *file);
+
/**
* struct event_trigger_ops - callbacks for trace event triggers
*
diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c
new file mode 100644
index 000000000000..ca224d53bfdc
--- /dev/null
+++ b/kernel/trace/trace_btf.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/btf.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "trace_btf.h"
+
+/*
+ * Find a function proto type by name, and return the btf_type with its btf
+ * in *@btf_p. Return NULL if not found.
+ * Note that caller has to call btf_put(*@btf_p) after using the btf_type.
+ */
+const struct btf_type *btf_find_func_proto(const char *func_name, struct btf **btf_p)
+{
+ const struct btf_type *t;
+ s32 id;
+
+ id = bpf_find_btf_id(func_name, BTF_KIND_FUNC, btf_p);
+ if (id < 0)
+ return NULL;
+
+ /* Get BTF_KIND_FUNC type */
+ t = btf_type_by_id(*btf_p, id);
+ if (!t || !btf_type_is_func(t))
+ goto err;
+
+ /* The type of BTF_KIND_FUNC is BTF_KIND_FUNC_PROTO */
+ t = btf_type_by_id(*btf_p, t->type);
+ if (!t || !btf_type_is_func_proto(t))
+ goto err;
+
+ return t;
+err:
+ btf_put(*btf_p);
+ return NULL;
+}
+
+/*
+ * Get function parameter with the number of parameters.
+ * This can return NULL if the function has no parameters.
+ * It can return -EINVAL if the @func_proto is not a function proto type.
+ */
+const struct btf_param *btf_get_func_param(const struct btf_type *func_proto, s32 *nr)
+{
+ if (!btf_type_is_func_proto(func_proto))
+ return ERR_PTR(-EINVAL);
+
+ *nr = btf_type_vlen(func_proto);
+ if (*nr > 0)
+ return (const struct btf_param *)(func_proto + 1);
+ else
+ return NULL;
+}
+
+#define BTF_ANON_STACK_MAX 16
+
+struct btf_anon_stack {
+ u32 tid;
+ u32 offset;
+};
+
+/*
+ * Find a member of data structure/union by name and return it.
+ * Return NULL if not found, or -EINVAL if parameter is invalid.
+ * If the member is an member of anonymous union/structure, the offset
+ * of that anonymous union/structure is stored into @anon_offset. Caller
+ * can calculate the correct offset from the root data structure by
+ * adding anon_offset to the member's offset.
+ */
+const struct btf_member *btf_find_struct_member(struct btf *btf,
+ const struct btf_type *type,
+ const char *member_name,
+ u32 *anon_offset)
+{
+ struct btf_anon_stack *anon_stack;
+ const struct btf_member *member;
+ u32 tid, cur_offset = 0;
+ const char *name;
+ int i, top = 0;
+
+ anon_stack = kcalloc(BTF_ANON_STACK_MAX, sizeof(*anon_stack), GFP_KERNEL);
+ if (!anon_stack)
+ return ERR_PTR(-ENOMEM);
+
+retry:
+ if (!btf_type_is_struct(type)) {
+ member = ERR_PTR(-EINVAL);
+ goto out;
+ }
+
+ for_each_member(i, type, member) {
+ if (!member->name_off) {
+ /* Anonymous union/struct: push it for later use */
+ type = btf_type_skip_modifiers(btf, member->type, &tid);
+ if (type && top < BTF_ANON_STACK_MAX) {
+ anon_stack[top].tid = tid;
+ anon_stack[top++].offset =
+ cur_offset + member->offset;
+ }
+ } else {
+ name = btf_name_by_offset(btf, member->name_off);
+ if (name && !strcmp(member_name, name)) {
+ if (anon_offset)
+ *anon_offset = cur_offset;
+ goto out;
+ }
+ }
+ }
+ if (top > 0) {
+ /* Pop from the anonymous stack and retry */
+ tid = anon_stack[--top].tid;
+ cur_offset = anon_stack[top].offset;
+ type = btf_type_by_id(btf, tid);
+ goto retry;
+ }
+ member = NULL;
+
+out:
+ kfree(anon_stack);
+ return member;
+}
+
diff --git a/kernel/trace/trace_btf.h b/kernel/trace/trace_btf.h
new file mode 100644
index 000000000000..4bc44bc261e6
--- /dev/null
+++ b/kernel/trace/trace_btf.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/btf.h>
+
+const struct btf_type *btf_find_func_proto(const char *func_name,
+ struct btf **btf_p);
+const struct btf_param *btf_get_func_param(const struct btf_type *func_proto,
+ s32 *nr);
+const struct btf_member *btf_find_struct_member(struct btf *btf,
+ const struct btf_type *type,
+ const char *member_name,
+ u32 *anon_offset);
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 340b2fa98218..c47422b20908 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -190,7 +190,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
F_STRUCT(
__field( int, size )
- __array( unsigned long, caller, FTRACE_STACK_ENTRIES )
+ __stack_array( unsigned long, caller, FTRACE_STACK_ENTRIES, size)
),
F_printk("\t=> %ps\n\t=> %ps\n\t=> %ps\n"
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index a0a704ba27db..03c851f57969 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -41,6 +41,10 @@ struct eprobe_data {
struct trace_eprobe *ep;
};
+
+#define for_each_trace_eprobe_tp(ep, _tp) \
+ list_for_each_entry(ep, trace_probe_probe_list(_tp), tp.list)
+
static int __trace_eprobe_create(int argc, const char *argv[]);
static void trace_event_probe_cleanup(struct trace_eprobe *ep)
@@ -640,7 +644,7 @@ static int disable_eprobe(struct trace_eprobe *ep,
static int enable_trace_eprobe(struct trace_event_call *call,
struct trace_event_file *file)
{
- struct trace_probe *pos, *tp;
+ struct trace_probe *tp;
struct trace_eprobe *ep;
bool enabled;
int ret = 0;
@@ -662,8 +666,7 @@ static int enable_trace_eprobe(struct trace_event_call *call,
if (enabled)
return 0;
- list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
- ep = container_of(pos, struct trace_eprobe, tp);
+ for_each_trace_eprobe_tp(ep, tp) {
ret = enable_eprobe(ep, file);
if (ret)
break;
@@ -680,8 +683,7 @@ static int enable_trace_eprobe(struct trace_event_call *call,
*/
WARN_ON_ONCE(ret != -ENOMEM);
- list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
- ep = container_of(pos, struct trace_eprobe, tp);
+ for_each_trace_eprobe_tp(ep, tp) {
disable_eprobe(ep, file->tr);
if (!--cnt)
break;
@@ -699,7 +701,7 @@ static int enable_trace_eprobe(struct trace_event_call *call,
static int disable_trace_eprobe(struct trace_event_call *call,
struct trace_event_file *file)
{
- struct trace_probe *pos, *tp;
+ struct trace_probe *tp;
struct trace_eprobe *ep;
tp = trace_probe_primary_from_call(call);
@@ -716,10 +718,8 @@ static int disable_trace_eprobe(struct trace_event_call *call,
trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
if (!trace_probe_is_enabled(tp)) {
- list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
- ep = container_of(pos, struct trace_eprobe, tp);
+ for_each_trace_eprobe_tp(ep, tp)
disable_eprobe(ep, file->tr);
- }
}
out:
@@ -788,12 +788,9 @@ find_and_get_event(const char *system, const char *event_name)
name = trace_event_name(tp_event);
if (!name || strcmp(event_name, name))
continue;
- if (!trace_event_try_get_ref(tp_event)) {
+ if (!trace_event_try_get_ref(tp_event))
return NULL;
- break;
- }
return tp_event;
- break;
}
return NULL;
}
@@ -807,13 +804,11 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[
int ret;
ret = traceprobe_parse_probe_arg(&ep->tp, i, argv[i], &ctx);
- if (ret)
- return ret;
-
/* Handle symbols "@" */
if (!ret)
ret = traceprobe_update_arg(&ep->tp.args[i]);
+ traceprobe_finish_parse(&ctx);
return ret;
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 578f1f7d49a6..f29e815ca5b2 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -984,32 +984,41 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
return;
if (!--dir->nr_events) {
- tracefs_remove(dir->entry);
+ eventfs_remove_dir(dir->ei);
list_del(&dir->list);
__put_system_dir(dir);
}
}
-static void remove_event_file_dir(struct trace_event_file *file)
+void event_file_get(struct trace_event_file *file)
{
- struct dentry *dir = file->dir;
- struct dentry *child;
+ atomic_inc(&file->ref);
+}
- if (dir) {
- spin_lock(&dir->d_lock); /* probably unneeded */
- list_for_each_entry(child, &dir->d_subdirs, d_child) {
- if (d_really_is_positive(child)) /* probably unneeded */
- d_inode(child)->i_private = NULL;
- }
- spin_unlock(&dir->d_lock);
+void event_file_put(struct trace_event_file *file)
+{
+ if (WARN_ON_ONCE(!atomic_read(&file->ref))) {
+ if (file->flags & EVENT_FILE_FL_FREED)
+ kmem_cache_free(file_cachep, file);
+ return;
+ }
- tracefs_remove(dir);
+ if (atomic_dec_and_test(&file->ref)) {
+ /* Count should only go to zero when it is freed */
+ if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED)))
+ return;
+ kmem_cache_free(file_cachep, file);
}
+}
+static void remove_event_file_dir(struct trace_event_file *file)
+{
+ eventfs_remove_dir(file->ei);
list_del(&file->list);
remove_subsystem(file->system);
free_event_filter(file->filter);
- kmem_cache_free(file_cachep, file);
+ file->flags |= EVENT_FILE_FL_FREED;
+ event_file_put(file);
}
/*
@@ -1179,7 +1188,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
if (!cnt)
return 0;
- ret = tracing_update_buffers();
+ ret = tracing_update_buffers(tr);
if (ret < 0)
return ret;
@@ -1382,7 +1391,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
flags = file->flags;
mutex_unlock(&event_mutex);
- if (!file)
+ if (!file || flags & EVENT_FILE_FL_FREED)
return -ENODEV;
if (flags & EVENT_FILE_FL_ENABLED &&
@@ -1410,18 +1419,20 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (ret)
return ret;
- ret = tracing_update_buffers();
- if (ret < 0)
- return ret;
-
switch (val) {
case 0:
case 1:
ret = -ENODEV;
mutex_lock(&event_mutex);
file = event_file_data(filp);
- if (likely(file))
+ if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) {
+ ret = tracing_update_buffers(file->tr);
+ if (ret < 0) {
+ mutex_unlock(&event_mutex);
+ return ret;
+ }
ret = ftrace_event_enable_disable(file, val);
+ }
mutex_unlock(&event_mutex);
break;
@@ -1495,7 +1506,7 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (ret)
return ret;
- ret = tracing_update_buffers();
+ ret = tracing_update_buffers(dir->tr);
if (ret < 0)
return ret;
@@ -1694,7 +1705,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
mutex_lock(&event_mutex);
file = event_file_data(filp);
- if (file)
+ if (file && !(file->flags & EVENT_FILE_FL_FREED))
print_event_filter(file, s);
mutex_unlock(&event_mutex);
@@ -1969,7 +1980,7 @@ event_pid_write(struct file *filp, const char __user *ubuf,
if (!cnt)
return 0;
- ret = tracing_update_buffers();
+ ret = tracing_update_buffers(tr);
if (ret < 0)
return ret;
@@ -2103,9 +2114,10 @@ static const struct file_operations ftrace_set_event_notrace_pid_fops = {
};
static const struct file_operations ftrace_enable_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_file_tr,
.read = event_enable_read,
.write = event_enable_write,
+ .release = tracing_release_file_tr,
.llseek = default_llseek,
};
@@ -2122,9 +2134,10 @@ static const struct file_operations ftrace_event_id_fops = {
};
static const struct file_operations ftrace_event_filter_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_file_tr,
.read = event_filter_read,
.write = event_filter_write,
+ .release = tracing_release_file_tr,
.llseek = default_llseek,
};
@@ -2291,13 +2304,40 @@ create_new_subsystem(const char *name)
return NULL;
}
-static struct dentry *
+static int system_callback(const char *name, umode_t *mode, void **data,
+ const struct file_operations **fops)
+{
+ if (strcmp(name, "filter") == 0)
+ *fops = &ftrace_subsystem_filter_fops;
+
+ else if (strcmp(name, "enable") == 0)
+ *fops = &ftrace_system_enable_fops;
+
+ else
+ return 0;
+
+ *mode = TRACE_MODE_WRITE;
+ return 1;
+}
+
+static struct eventfs_inode *
event_subsystem_dir(struct trace_array *tr, const char *name,
- struct trace_event_file *file, struct dentry *parent)
+ struct trace_event_file *file, struct eventfs_inode *parent)
{
struct event_subsystem *system, *iter;
struct trace_subsystem_dir *dir;
- struct dentry *entry;
+ struct eventfs_inode *ei;
+ int nr_entries;
+ static struct eventfs_entry system_entries[] = {
+ {
+ .name = "filter",
+ .callback = system_callback,
+ },
+ {
+ .name = "enable",
+ .callback = system_callback,
+ }
+ };
/* First see if we did not already create this dir */
list_for_each_entry(dir, &tr->systems, list) {
@@ -2305,7 +2345,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
if (strcmp(system->name, name) == 0) {
dir->nr_events++;
file->system = dir;
- return dir->entry;
+ return dir->ei;
}
}
@@ -2329,38 +2369,29 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
} else
__get_system(system);
- dir->entry = tracefs_create_dir(name, parent);
- if (!dir->entry) {
+ /* ftrace only has directories no files */
+ if (strcmp(name, "ftrace") == 0)
+ nr_entries = 0;
+ else
+ nr_entries = ARRAY_SIZE(system_entries);
+
+ ei = eventfs_create_dir(name, parent, system_entries, nr_entries, dir);
+ if (IS_ERR(ei)) {
pr_warn("Failed to create system directory %s\n", name);
__put_system(system);
goto out_free;
}
+ dir->ei = ei;
dir->tr = tr;
dir->ref_count = 1;
dir->nr_events = 1;
dir->subsystem = system;
file->system = dir;
- /* the ftrace system is special, do not create enable or filter files */
- if (strcmp(name, "ftrace") != 0) {
-
- entry = tracefs_create_file("filter", TRACE_MODE_WRITE,
- dir->entry, dir,
- &ftrace_subsystem_filter_fops);
- if (!entry) {
- kfree(system->filter);
- system->filter = NULL;
- pr_warn("Could not create tracefs '%s/filter' entry\n", name);
- }
-
- trace_create_file("enable", TRACE_MODE_WRITE, dir->entry, dir,
- &ftrace_system_enable_fops);
- }
-
list_add(&dir->list, &tr->systems);
- return dir->entry;
+ return dir->ei;
out_free:
kfree(dir);
@@ -2409,43 +2440,157 @@ event_define_fields(struct trace_event_call *call)
return ret;
}
+static int event_callback(const char *name, umode_t *mode, void **data,
+ const struct file_operations **fops)
+{
+ struct trace_event_file *file = *data;
+ struct trace_event_call *call = file->event_call;
+
+ if (strcmp(name, "format") == 0) {
+ *mode = TRACE_MODE_READ;
+ *fops = &ftrace_event_format_fops;
+ *data = call;
+ return 1;
+ }
+
+ /*
+ * Only event directories that can be enabled should have
+ * triggers or filters, with the exception of the "print"
+ * event that can have a "trigger" file.
+ */
+ if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
+ if (call->class->reg && strcmp(name, "enable") == 0) {
+ *mode = TRACE_MODE_WRITE;
+ *fops = &ftrace_enable_fops;
+ return 1;
+ }
+
+ if (strcmp(name, "filter") == 0) {
+ *mode = TRACE_MODE_WRITE;
+ *fops = &ftrace_event_filter_fops;
+ return 1;
+ }
+ }
+
+ if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) ||
+ strcmp(trace_event_name(call), "print") == 0) {
+ if (strcmp(name, "trigger") == 0) {
+ *mode = TRACE_MODE_WRITE;
+ *fops = &event_trigger_fops;
+ return 1;
+ }
+ }
+
+#ifdef CONFIG_PERF_EVENTS
+ if (call->event.type && call->class->reg &&
+ strcmp(name, "id") == 0) {
+ *mode = TRACE_MODE_READ;
+ *data = (void *)(long)call->event.type;
+ *fops = &ftrace_event_id_fops;
+ return 1;
+ }
+#endif
+
+#ifdef CONFIG_HIST_TRIGGERS
+ if (strcmp(name, "hist") == 0) {
+ *mode = TRACE_MODE_READ;
+ *fops = &event_hist_fops;
+ return 1;
+ }
+#endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+ if (strcmp(name, "hist_debug") == 0) {
+ *mode = TRACE_MODE_READ;
+ *fops = &event_hist_debug_fops;
+ return 1;
+ }
+#endif
+#ifdef CONFIG_TRACE_EVENT_INJECT
+ if (call->event.type && call->class->reg &&
+ strcmp(name, "inject") == 0) {
+ *mode = 0200;
+ *fops = &event_inject_fops;
+ return 1;
+ }
+#endif
+ return 0;
+}
+
static int
-event_create_dir(struct dentry *parent, struct trace_event_file *file)
+event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file)
{
struct trace_event_call *call = file->event_call;
struct trace_array *tr = file->tr;
- struct dentry *d_events;
+ struct eventfs_inode *e_events;
+ struct eventfs_inode *ei;
const char *name;
+ int nr_entries;
int ret;
+ static struct eventfs_entry event_entries[] = {
+ {
+ .name = "enable",
+ .callback = event_callback,
+ },
+ {
+ .name = "filter",
+ .callback = event_callback,
+ },
+ {
+ .name = "trigger",
+ .callback = event_callback,
+ },
+ {
+ .name = "format",
+ .callback = event_callback,
+ },
+#ifdef CONFIG_PERF_EVENTS
+ {
+ .name = "id",
+ .callback = event_callback,
+ },
+#endif
+#ifdef CONFIG_HIST_TRIGGERS
+ {
+ .name = "hist",
+ .callback = event_callback,
+ },
+#endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+ {
+ .name = "hist_debug",
+ .callback = event_callback,
+ },
+#endif
+#ifdef CONFIG_TRACE_EVENT_INJECT
+ {
+ .name = "inject",
+ .callback = event_callback,
+ },
+#endif
+ };
/*
* If the trace point header did not define TRACE_SYSTEM
- * then the system would be called "TRACE_SYSTEM".
+ * then the system would be called "TRACE_SYSTEM". This should
+ * never happen.
*/
- if (strcmp(call->class->system, TRACE_SYSTEM) != 0) {
- d_events = event_subsystem_dir(tr, call->class->system, file, parent);
- if (!d_events)
- return -ENOMEM;
- } else
- d_events = parent;
+ if (WARN_ON_ONCE(strcmp(call->class->system, TRACE_SYSTEM) == 0))
+ return -ENODEV;
+
+ e_events = event_subsystem_dir(tr, call->class->system, file, parent);
+ if (!e_events)
+ return -ENOMEM;
+
+ nr_entries = ARRAY_SIZE(event_entries);
name = trace_event_name(call);
- file->dir = tracefs_create_dir(name, d_events);
- if (!file->dir) {
+ ei = eventfs_create_dir(name, e_events, event_entries, nr_entries, file);
+ if (IS_ERR(ei)) {
pr_warn("Could not create tracefs '%s' directory\n", name);
return -1;
}
- if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
- trace_create_file("enable", TRACE_MODE_WRITE, file->dir, file,
- &ftrace_enable_fops);
-
-#ifdef CONFIG_PERF_EVENTS
- if (call->event.type && call->class->reg)
- trace_create_file("id", TRACE_MODE_READ, file->dir,
- (void *)(long)call->event.type,
- &ftrace_event_id_fops);
-#endif
+ file->ei = ei;
ret = event_define_fields(call);
if (ret < 0) {
@@ -2453,35 +2598,6 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
return ret;
}
- /*
- * Only event directories that can be enabled should have
- * triggers or filters.
- */
- if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
- trace_create_file("filter", TRACE_MODE_WRITE, file->dir,
- file, &ftrace_event_filter_fops);
-
- trace_create_file("trigger", TRACE_MODE_WRITE, file->dir,
- file, &event_trigger_fops);
- }
-
-#ifdef CONFIG_HIST_TRIGGERS
- trace_create_file("hist", TRACE_MODE_READ, file->dir, file,
- &event_hist_fops);
-#endif
-#ifdef CONFIG_HIST_TRIGGERS_DEBUG
- trace_create_file("hist_debug", TRACE_MODE_READ, file->dir, file,
- &event_hist_debug_fops);
-#endif
- trace_create_file("format", TRACE_MODE_READ, file->dir, call,
- &ftrace_event_format_fops);
-
-#ifdef CONFIG_TRACE_EVENT_INJECT
- if (call->event.type && call->class->reg)
- trace_create_file("inject", 0200, file->dir, file,
- &event_inject_fops);
-#endif
-
return 0;
}
@@ -2775,6 +2891,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
update_event_fields(call, map[i]);
}
}
+ cond_resched();
}
up_write(&trace_event_sem);
}
@@ -2807,6 +2924,7 @@ trace_create_new_event(struct trace_event_call *call,
atomic_set(&file->tm_ref, 0);
INIT_LIST_HEAD(&file->triggers);
list_add(&file->list, &tr->events);
+ event_file_get(file);
return file;
}
@@ -2828,7 +2946,7 @@ static __init int setup_trace_triggers(char *str)
int i;
strscpy(bootup_trigger_buf, str, COMMAND_LINE_SIZE);
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(NULL);
disable_tracing_selftest("running event triggers");
buf = bootup_trigger_buf;
@@ -3618,36 +3736,72 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
static __init int setup_trace_event(char *str)
{
strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(NULL);
disable_tracing_selftest("running event tracing");
return 1;
}
__setup("trace_event=", setup_trace_event);
+static int events_callback(const char *name, umode_t *mode, void **data,
+ const struct file_operations **fops)
+{
+ if (strcmp(name, "enable") == 0) {
+ *mode = TRACE_MODE_WRITE;
+ *fops = &ftrace_tr_enable_fops;
+ return 1;
+ }
+
+ if (strcmp(name, "header_page") == 0)
+ *data = ring_buffer_print_page_header;
+
+ else if (strcmp(name, "header_event") == 0)
+ *data = ring_buffer_print_entry_header;
+
+ else
+ return 0;
+
+ *mode = TRACE_MODE_READ;
+ *fops = &ftrace_show_header_fops;
+ return 1;
+}
+
/* Expects to have event_mutex held when called */
static int
create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
{
- struct dentry *d_events;
+ struct eventfs_inode *e_events;
struct dentry *entry;
+ int nr_entries;
+ static struct eventfs_entry events_entries[] = {
+ {
+ .name = "enable",
+ .callback = events_callback,
+ },
+ {
+ .name = "header_page",
+ .callback = events_callback,
+ },
+ {
+ .name = "header_event",
+ .callback = events_callback,
+ },
+ };
entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent,
tr, &ftrace_set_event_fops);
if (!entry)
return -ENOMEM;
- d_events = tracefs_create_dir("events", parent);
- if (!d_events) {
+ nr_entries = ARRAY_SIZE(events_entries);
+
+ e_events = eventfs_create_events_dir("events", parent, events_entries,
+ nr_entries, tr);
+ if (IS_ERR(e_events)) {
pr_warn("Could not create tracefs 'events' directory\n");
return -ENOMEM;
}
- entry = trace_create_file("enable", TRACE_MODE_WRITE, d_events,
- tr, &ftrace_tr_enable_fops);
- if (!entry)
- return -ENOMEM;
-
/* There are not as crucial, just warn if they are not created */
trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
@@ -3657,16 +3811,7 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
TRACE_MODE_WRITE, parent, tr,
&ftrace_set_event_notrace_pid_fops);
- /* ring buffer internal formats */
- trace_create_file("header_page", TRACE_MODE_READ, d_events,
- ring_buffer_print_page_header,
- &ftrace_show_header_fops);
-
- trace_create_file("header_event", TRACE_MODE_READ, d_events,
- ring_buffer_print_entry_header,
- &ftrace_show_header_fops);
-
- tr->event_dir = d_events;
+ tr->event_dir = e_events;
return 0;
}
@@ -3750,7 +3895,7 @@ int event_trace_del_tracer(struct trace_array *tr)
down_write(&trace_event_sem);
__trace_remove_event_dirs(tr);
- tracefs_remove(tr->event_dir);
+ eventfs_remove_events_dir(tr->event_dir);
up_write(&trace_event_sem);
tr->event_dir = NULL;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 1dad64267878..0c611b281a5b 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -46,15 +46,19 @@ static const char * ops[] = { OPS };
enum filter_pred_fn {
FILTER_PRED_FN_NOP,
FILTER_PRED_FN_64,
+ FILTER_PRED_FN_64_CPUMASK,
FILTER_PRED_FN_S64,
FILTER_PRED_FN_U64,
FILTER_PRED_FN_32,
+ FILTER_PRED_FN_32_CPUMASK,
FILTER_PRED_FN_S32,
FILTER_PRED_FN_U32,
FILTER_PRED_FN_16,
+ FILTER_PRED_FN_16_CPUMASK,
FILTER_PRED_FN_S16,
FILTER_PRED_FN_U16,
FILTER_PRED_FN_8,
+ FILTER_PRED_FN_8_CPUMASK,
FILTER_PRED_FN_S8,
FILTER_PRED_FN_U8,
FILTER_PRED_FN_COMM,
@@ -64,21 +68,25 @@ enum filter_pred_fn {
FILTER_PRED_FN_PCHAR_USER,
FILTER_PRED_FN_PCHAR,
FILTER_PRED_FN_CPU,
+ FILTER_PRED_FN_CPU_CPUMASK,
+ FILTER_PRED_FN_CPUMASK,
+ FILTER_PRED_FN_CPUMASK_CPU,
FILTER_PRED_FN_FUNCTION,
FILTER_PRED_FN_,
FILTER_PRED_TEST_VISITED,
};
struct filter_pred {
- enum filter_pred_fn fn_num;
- u64 val;
- u64 val2;
- struct regex regex;
+ struct regex *regex;
+ struct cpumask *mask;
unsigned short *ops;
struct ftrace_event_field *field;
- int offset;
+ u64 val;
+ u64 val2;
+ enum filter_pred_fn fn_num;
+ int offset;
int not;
- int op;
+ int op;
};
/*
@@ -94,6 +102,8 @@ struct filter_pred {
C(TOO_MANY_OPEN, "Too many '('"), \
C(TOO_MANY_CLOSE, "Too few '('"), \
C(MISSING_QUOTE, "Missing matching quote"), \
+ C(MISSING_BRACE_OPEN, "Missing '{'"), \
+ C(MISSING_BRACE_CLOSE, "Missing '}'"), \
C(OPERAND_TOO_LONG, "Operand too long"), \
C(EXPECT_STRING, "Expecting string field"), \
C(EXPECT_DIGIT, "Expecting numeric field"), \
@@ -103,6 +113,7 @@ struct filter_pred {
C(BAD_SUBSYS_FILTER, "Couldn't find or set field in one of a subsystem's events"), \
C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \
C(INVALID_FILTER, "Meaningless filter expression"), \
+ C(INVALID_CPULIST, "Invalid cpulist"), \
C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \
C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \
C(NO_FUNCTION, "Function not found"), \
@@ -186,6 +197,15 @@ enum {
PROCESS_OR = 4,
};
+static void free_predicate(struct filter_pred *pred)
+{
+ if (pred) {
+ kfree(pred->regex);
+ kfree(pred->mask);
+ kfree(pred);
+ }
+}
+
/*
* Without going into a formal proof, this explains the method that is used in
* parsing the logical expressions.
@@ -623,12 +643,64 @@ out_free:
kfree(inverts);
if (prog_stack) {
for (i = 0; prog_stack[i].pred; i++)
- kfree(prog_stack[i].pred);
+ free_predicate(prog_stack[i].pred);
kfree(prog_stack);
}
return ERR_PTR(ret);
}
+static inline int
+do_filter_cpumask(int op, const struct cpumask *mask, const struct cpumask *cmp)
+{
+ switch (op) {
+ case OP_EQ:
+ return cpumask_equal(mask, cmp);
+ case OP_NE:
+ return !cpumask_equal(mask, cmp);
+ case OP_BAND:
+ return cpumask_intersects(mask, cmp);
+ default:
+ return 0;
+ }
+}
+
+/* Optimisation of do_filter_cpumask() for scalar fields */
+static inline int
+do_filter_scalar_cpumask(int op, unsigned int cpu, const struct cpumask *mask)
+{
+ /*
+ * Per the weight-of-one cpumask optimisations, the mask passed in this
+ * function has a weight >= 2, so it is never equal to a single scalar.
+ */
+ switch (op) {
+ case OP_EQ:
+ return false;
+ case OP_NE:
+ return true;
+ case OP_BAND:
+ return cpumask_test_cpu(cpu, mask);
+ default:
+ return 0;
+ }
+}
+
+static inline int
+do_filter_cpumask_scalar(int op, const struct cpumask *mask, unsigned int cpu)
+{
+ switch (op) {
+ case OP_EQ:
+ return cpumask_test_cpu(cpu, mask) &&
+ cpumask_nth(1, mask) >= nr_cpu_ids;
+ case OP_NE:
+ return !cpumask_test_cpu(cpu, mask) ||
+ cpumask_nth(1, mask) < nr_cpu_ids;
+ case OP_BAND:
+ return cpumask_test_cpu(cpu, mask);
+ default:
+ return 0;
+ }
+}
+
enum pred_cmp_types {
PRED_CMP_TYPE_NOP,
PRED_CMP_TYPE_LT,
@@ -672,6 +744,18 @@ static int filter_pred_##type(struct filter_pred *pred, void *event) \
} \
}
+#define DEFINE_CPUMASK_COMPARISON_PRED(size) \
+static int filter_pred_##size##_cpumask(struct filter_pred *pred, void *event) \
+{ \
+ u##size *addr = (u##size *)(event + pred->offset); \
+ unsigned int cpu = *addr; \
+ \
+ if (cpu >= nr_cpu_ids) \
+ return 0; \
+ \
+ return do_filter_scalar_cpumask(pred->op, cpu, pred->mask); \
+}
+
#define DEFINE_EQUALITY_PRED(size) \
static int filter_pred_##size(struct filter_pred *pred, void *event) \
{ \
@@ -693,6 +777,11 @@ DEFINE_COMPARISON_PRED(u16);
DEFINE_COMPARISON_PRED(s8);
DEFINE_COMPARISON_PRED(u8);
+DEFINE_CPUMASK_COMPARISON_PRED(64);
+DEFINE_CPUMASK_COMPARISON_PRED(32);
+DEFINE_CPUMASK_COMPARISON_PRED(16);
+DEFINE_CPUMASK_COMPARISON_PRED(8);
+
DEFINE_EQUALITY_PRED(64);
DEFINE_EQUALITY_PRED(32);
DEFINE_EQUALITY_PRED(16);
@@ -750,7 +839,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event)
char *addr = (char *)(event + pred->offset);
int cmp, match;
- cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len);
+ cmp = pred->regex->match(addr, pred->regex, pred->regex->field_len);
match = cmp ^ pred->not;
@@ -763,7 +852,7 @@ static __always_inline int filter_pchar(struct filter_pred *pred, char *str)
int len;
len = strlen(str) + 1; /* including tailing '\0' */
- cmp = pred->regex.match(str, &pred->regex, len);
+ cmp = pred->regex->match(str, pred->regex, len);
match = cmp ^ pred->not;
@@ -813,7 +902,7 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event)
char *addr = (char *)(event + str_loc);
int cmp, match;
- cmp = pred->regex.match(addr, &pred->regex, str_len);
+ cmp = pred->regex->match(addr, pred->regex, str_len);
match = cmp ^ pred->not;
@@ -836,7 +925,7 @@ static int filter_pred_strrelloc(struct filter_pred *pred, void *event)
char *addr = (char *)(&item[1]) + str_loc;
int cmp, match;
- cmp = pred->regex.match(addr, &pred->regex, str_len);
+ cmp = pred->regex->match(addr, pred->regex, str_len);
match = cmp ^ pred->not;
@@ -869,12 +958,42 @@ static int filter_pred_cpu(struct filter_pred *pred, void *event)
}
}
+/* Filter predicate for current CPU vs user-provided cpumask */
+static int filter_pred_cpu_cpumask(struct filter_pred *pred, void *event)
+{
+ int cpu = raw_smp_processor_id();
+
+ return do_filter_scalar_cpumask(pred->op, cpu, pred->mask);
+}
+
+/* Filter predicate for cpumask field vs user-provided cpumask */
+static int filter_pred_cpumask(struct filter_pred *pred, void *event)
+{
+ u32 item = *(u32 *)(event + pred->offset);
+ int loc = item & 0xffff;
+ const struct cpumask *mask = (event + loc);
+ const struct cpumask *cmp = pred->mask;
+
+ return do_filter_cpumask(pred->op, mask, cmp);
+}
+
+/* Filter predicate for cpumask field vs user-provided scalar */
+static int filter_pred_cpumask_cpu(struct filter_pred *pred, void *event)
+{
+ u32 item = *(u32 *)(event + pred->offset);
+ int loc = item & 0xffff;
+ const struct cpumask *mask = (event + loc);
+ unsigned int cpu = pred->val;
+
+ return do_filter_cpumask_scalar(pred->op, mask, cpu);
+}
+
/* Filter predicate for COMM. */
static int filter_pred_comm(struct filter_pred *pred, void *event)
{
int cmp;
- cmp = pred->regex.match(current->comm, &pred->regex,
+ cmp = pred->regex->match(current->comm, pred->regex,
TASK_COMM_LEN);
return cmp ^ pred->not;
}
@@ -1004,7 +1123,7 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
static void filter_build_regex(struct filter_pred *pred)
{
- struct regex *r = &pred->regex;
+ struct regex *r = pred->regex;
char *search;
enum regex_type type = MATCH_FULL;
@@ -1169,7 +1288,7 @@ static void free_prog(struct event_filter *filter)
return;
for (i = 0; prog[i].pred; i++)
- kfree(prog[i].pred);
+ free_predicate(prog[i].pred);
kfree(prog);
}
@@ -1236,8 +1355,12 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
int filter_assign_type(const char *type)
{
- if (strstr(type, "__data_loc") && strstr(type, "char"))
- return FILTER_DYN_STRING;
+ if (strstr(type, "__data_loc")) {
+ if (strstr(type, "char"))
+ return FILTER_DYN_STRING;
+ if (strstr(type, "cpumask_t"))
+ return FILTER_CPUMASK;
+ }
if (strstr(type, "__rel_loc") && strstr(type, "char"))
return FILTER_RDYN_STRING;
@@ -1313,24 +1436,32 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event)
switch (pred->fn_num) {
case FILTER_PRED_FN_64:
return filter_pred_64(pred, event);
+ case FILTER_PRED_FN_64_CPUMASK:
+ return filter_pred_64_cpumask(pred, event);
case FILTER_PRED_FN_S64:
return filter_pred_s64(pred, event);
case FILTER_PRED_FN_U64:
return filter_pred_u64(pred, event);
case FILTER_PRED_FN_32:
return filter_pred_32(pred, event);
+ case FILTER_PRED_FN_32_CPUMASK:
+ return filter_pred_32_cpumask(pred, event);
case FILTER_PRED_FN_S32:
return filter_pred_s32(pred, event);
case FILTER_PRED_FN_U32:
return filter_pred_u32(pred, event);
case FILTER_PRED_FN_16:
return filter_pred_16(pred, event);
+ case FILTER_PRED_FN_16_CPUMASK:
+ return filter_pred_16_cpumask(pred, event);
case FILTER_PRED_FN_S16:
return filter_pred_s16(pred, event);
case FILTER_PRED_FN_U16:
return filter_pred_u16(pred, event);
case FILTER_PRED_FN_8:
return filter_pred_8(pred, event);
+ case FILTER_PRED_FN_8_CPUMASK:
+ return filter_pred_8_cpumask(pred, event);
case FILTER_PRED_FN_S8:
return filter_pred_s8(pred, event);
case FILTER_PRED_FN_U8:
@@ -1349,6 +1480,12 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event)
return filter_pred_pchar(pred, event);
case FILTER_PRED_FN_CPU:
return filter_pred_cpu(pred, event);
+ case FILTER_PRED_FN_CPU_CPUMASK:
+ return filter_pred_cpu_cpumask(pred, event);
+ case FILTER_PRED_FN_CPUMASK:
+ return filter_pred_cpumask(pred, event);
+ case FILTER_PRED_FN_CPUMASK_CPU:
+ return filter_pred_cpumask_cpu(pred, event);
case FILTER_PRED_FN_FUNCTION:
return filter_pred_function(pred, event);
case FILTER_PRED_TEST_VISITED:
@@ -1553,9 +1690,130 @@ static int parse_pred(const char *str, void *data,
goto err_free;
}
- pred->regex.len = len;
- strncpy(pred->regex.pattern, str + s, len);
- pred->regex.pattern[len] = 0;
+ pred->regex = kzalloc(sizeof(*pred->regex), GFP_KERNEL);
+ if (!pred->regex)
+ goto err_mem;
+ pred->regex->len = len;
+ strncpy(pred->regex->pattern, str + s, len);
+ pred->regex->pattern[len] = 0;
+
+ } else if (!strncmp(str + i, "CPUS", 4)) {
+ unsigned int maskstart;
+ bool single;
+ char *tmp;
+
+ switch (field->filter_type) {
+ case FILTER_CPUMASK:
+ case FILTER_CPU:
+ case FILTER_OTHER:
+ break;
+ default:
+ parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i);
+ goto err_free;
+ }
+
+ switch (op) {
+ case OP_EQ:
+ case OP_NE:
+ case OP_BAND:
+ break;
+ default:
+ parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i);
+ goto err_free;
+ }
+
+ /* Skip CPUS */
+ i += 4;
+ if (str[i++] != '{') {
+ parse_error(pe, FILT_ERR_MISSING_BRACE_OPEN, pos + i);
+ goto err_free;
+ }
+ maskstart = i;
+
+ /* Walk the cpulist until closing } */
+ for (; str[i] && str[i] != '}'; i++)
+ ;
+
+ if (str[i] != '}') {
+ parse_error(pe, FILT_ERR_MISSING_BRACE_CLOSE, pos + i);
+ goto err_free;
+ }
+
+ if (maskstart == i) {
+ parse_error(pe, FILT_ERR_INVALID_CPULIST, pos + i);
+ goto err_free;
+ }
+
+ /* Copy the cpulist between { and } */
+ tmp = kmalloc((i - maskstart) + 1, GFP_KERNEL);
+ if (!tmp)
+ goto err_mem;
+
+ strscpy(tmp, str + maskstart, (i - maskstart) + 1);
+ pred->mask = kzalloc(cpumask_size(), GFP_KERNEL);
+ if (!pred->mask) {
+ kfree(tmp);
+ goto err_mem;
+ }
+
+ /* Now parse it */
+ if (cpulist_parse(tmp, pred->mask)) {
+ kfree(tmp);
+ parse_error(pe, FILT_ERR_INVALID_CPULIST, pos + i);
+ goto err_free;
+ }
+ kfree(tmp);
+
+ /* Move along */
+ i++;
+
+ /*
+ * Optimisation: if the user-provided mask has a weight of one
+ * then we can treat it as a scalar input.
+ */
+ single = cpumask_weight(pred->mask) == 1;
+ if (single) {
+ pred->val = cpumask_first(pred->mask);
+ kfree(pred->mask);
+ pred->mask = NULL;
+ }
+
+ if (field->filter_type == FILTER_CPUMASK) {
+ pred->fn_num = single ?
+ FILTER_PRED_FN_CPUMASK_CPU :
+ FILTER_PRED_FN_CPUMASK;
+ } else if (field->filter_type == FILTER_CPU) {
+ if (single) {
+ if (pred->op == OP_BAND)
+ pred->op = OP_EQ;
+
+ pred->fn_num = FILTER_PRED_FN_CPU;
+ } else {
+ pred->fn_num = FILTER_PRED_FN_CPU_CPUMASK;
+ }
+ } else if (single) {
+ if (pred->op == OP_BAND)
+ pred->op = OP_EQ;
+
+ pred->fn_num = select_comparison_fn(pred->op, field->size, false);
+ if (pred->op == OP_NE)
+ pred->not = 1;
+ } else {
+ switch (field->size) {
+ case 8:
+ pred->fn_num = FILTER_PRED_FN_64_CPUMASK;
+ break;
+ case 4:
+ pred->fn_num = FILTER_PRED_FN_32_CPUMASK;
+ break;
+ case 2:
+ pred->fn_num = FILTER_PRED_FN_16_CPUMASK;
+ break;
+ case 1:
+ pred->fn_num = FILTER_PRED_FN_8_CPUMASK;
+ break;
+ }
+ }
/* This is either a string, or an integer */
} else if (str[i] == '\'' || str[i] == '"') {
@@ -1597,9 +1855,12 @@ static int parse_pred(const char *str, void *data,
goto err_free;
}
- pred->regex.len = len;
- strncpy(pred->regex.pattern, str + s, len);
- pred->regex.pattern[len] = 0;
+ pred->regex = kzalloc(sizeof(*pred->regex), GFP_KERNEL);
+ if (!pred->regex)
+ goto err_mem;
+ pred->regex->len = len;
+ strncpy(pred->regex->pattern, str + s, len);
+ pred->regex->pattern[len] = 0;
filter_build_regex(pred);
@@ -1608,7 +1869,7 @@ static int parse_pred(const char *str, void *data,
} else if (field->filter_type == FILTER_STATIC_STRING) {
pred->fn_num = FILTER_PRED_FN_STRING;
- pred->regex.field_len = field->size;
+ pred->regex->field_len = field->size;
} else if (field->filter_type == FILTER_DYN_STRING) {
pred->fn_num = FILTER_PRED_FN_STRLOC;
@@ -1691,10 +1952,10 @@ static int parse_pred(const char *str, void *data,
return i;
err_free:
- kfree(pred);
+ free_predicate(pred);
return -EINVAL;
err_mem:
- kfree(pred);
+ free_predicate(pred);
return -ENOMEM;
}
@@ -2088,6 +2349,9 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string)
struct event_filter *filter = NULL;
int err;
+ if (file->flags & EVENT_FILE_FL_FREED)
+ return -ENODEV;
+
if (!strcmp(strstrip(filter_string), "0")) {
filter_disable(file);
filter = event_filter(file);
@@ -2287,8 +2551,8 @@ static int ftrace_function_set_filter_pred(struct filter_pred *pred,
return ret;
return __ftrace_function_set_filter(pred->op == OP_EQ,
- pred->regex.pattern,
- pred->regex.len,
+ pred->regex->pattern,
+ pred->regex->len,
data);
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index d06938ae0717..5ecf3c8bde20 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -774,23 +774,16 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
{
const char *system = NULL, *name = NULL;
struct trace_event_call *call;
- int len;
if (!str)
return;
- /* sizeof() contains the nul byte */
- len = sizeof(HIST_PREFIX) + strlen(str);
kfree(last_cmd);
- last_cmd = kzalloc(len, GFP_KERNEL);
+
+ last_cmd = kasprintf(GFP_KERNEL, HIST_PREFIX "%s", str);
if (!last_cmd)
return;
- strcpy(last_cmd, HIST_PREFIX);
- /* Again, sizeof() contains the nul byte */
- len -= sizeof(HIST_PREFIX);
- strncat(last_cmd, str, len);
-
if (file) {
call = file->event_call;
system = call->class->system;
@@ -5630,10 +5623,12 @@ static int event_hist_open(struct inode *inode, struct file *file)
{
int ret;
- ret = security_locked_down(LOCKDOWN_TRACEFS);
+ ret = tracing_open_file_tr(inode, file);
if (ret)
return ret;
+ /* Clear private_data to avoid warning in single_open() */
+ file->private_data = NULL;
return single_open(file, hist_show, file);
}
@@ -5641,7 +5636,7 @@ const struct file_operations event_hist_fops = {
.open = event_hist_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = tracing_single_release_file_tr,
};
#ifdef CONFIG_HIST_TRIGGERS_DEBUG
@@ -5907,10 +5902,12 @@ static int event_hist_debug_open(struct inode *inode, struct file *file)
{
int ret;
- ret = security_locked_down(LOCKDOWN_TRACEFS);
+ ret = tracing_open_file_tr(inode, file);
if (ret)
return ret;
+ /* Clear private_data to avoid warning in single_open() */
+ file->private_data = NULL;
return single_open(file, hist_debug_show, file);
}
@@ -5918,7 +5915,7 @@ const struct file_operations event_hist_debug_fops = {
.open = event_hist_debug_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = tracing_single_release_file_tr,
};
#endif
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index abe805d471eb..8650562bdaa9 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -328,7 +328,8 @@ event_inject_read(struct file *file, char __user *buf, size_t size,
}
const struct file_operations event_inject_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_file_tr,
.read = event_inject_read,
.write = event_inject_write,
+ .release = tracing_release_file_tr,
};
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 9897d0bfcab7..e7af286af4f1 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -337,7 +337,7 @@ static void print_synth_event_num_val(struct trace_seq *s,
break;
default:
- trace_seq_printf(s, print_fmt, name, val, space);
+ trace_seq_printf(s, print_fmt, name, val->as_u64, space);
break;
}
}
@@ -452,7 +452,7 @@ static unsigned int trace_string(struct synth_trace_event *entry,
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
if ((unsigned long)str_val < TASK_SIZE)
- ret = strncpy_from_user_nofault(str_field, str_val, STR_VAR_LEN_MAX);
+ ret = strncpy_from_user_nofault(str_field, (const void __user *)str_val, STR_VAR_LEN_MAX);
else
#endif
ret = strncpy_from_kernel_nofault(str_field, str_val, STR_VAR_LEN_MAX);
@@ -1137,7 +1137,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_fields);
* @cmd: A pointer to the dynevent_cmd struct representing the new event
* @name: The name of the synthetic event
* @mod: The module creating the event, NULL if not created from a module
- * @args: Variable number of arg (pairs), one pair for each field
+ * @...: Variable number of arg (pairs), one pair for each field
*
* NOTE: Users normally won't want to call this function directly, but
* rather use the synth_event_gen_cmd_start() wrapper, which
@@ -1695,7 +1695,7 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state)
* synth_event_trace - Trace a synthetic event
* @file: The trace_event_file representing the synthetic event
* @n_vals: The number of values in vals
- * @args: Variable number of args containing the event values
+ * @...: Variable number of args containing the event values
*
* Trace a synthetic event using the values passed in the variable
* argument list.
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 33cb6af31f39..9365ce407426 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -50,18 +50,6 @@
#define EVENT_STATUS_OTHER BIT(7)
/*
- * User register flags are not allowed yet, keep them here until we are
- * ready to expose them out to the user ABI.
- */
-enum user_reg_flag {
- /* Event will not delete upon last reference closing */
- USER_EVENT_REG_PERSIST = 1U << 0,
-
- /* This value or above is currently non-ABI */
- USER_EVENT_REG_MAX = 1U << 1,
-};
-
-/*
* Stores the system name, tables, and locks for a group of events. This
* allows isolation for events by various means.
*/
@@ -127,8 +115,13 @@ struct user_event_enabler {
/* Bit 7 is for freeing status of enablement */
#define ENABLE_VAL_FREEING_BIT 7
-/* Only duplicate the bit value */
-#define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK
+/* Bit 8 is for marking 32-bit on 64-bit */
+#define ENABLE_VAL_32_ON_64_BIT 8
+
+#define ENABLE_VAL_COMPAT_MASK (1 << ENABLE_VAL_32_ON_64_BIT)
+
+/* Only duplicate the bit and compat values */
+#define ENABLE_VAL_DUP_MASK (ENABLE_VAL_BIT_MASK | ENABLE_VAL_COMPAT_MASK)
#define ENABLE_BITOPS(e) (&(e)->values)
@@ -174,6 +167,30 @@ struct user_event_validator {
int flags;
};
+static inline void align_addr_bit(unsigned long *addr, int *bit,
+ unsigned long *flags)
+{
+ if (IS_ALIGNED(*addr, sizeof(long))) {
+#ifdef __BIG_ENDIAN
+ /* 32 bit on BE 64 bit requires a 32 bit offset when aligned. */
+ if (test_bit(ENABLE_VAL_32_ON_64_BIT, flags))
+ *bit += 32;
+#endif
+ return;
+ }
+
+ *addr = ALIGN_DOWN(*addr, sizeof(long));
+
+ /*
+ * We only support 32 and 64 bit values. The only time we need
+ * to align is a 32 bit value on a 64 bit kernel, which on LE
+ * is always 32 bits, and on BE requires no change when unaligned.
+ */
+#ifdef __LITTLE_ENDIAN
+ *bit += 32;
+#endif
+}
+
typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
void *tpdata, bool *faulted);
@@ -191,6 +208,17 @@ static u32 user_event_key(char *name)
return jhash(name, strlen(name), 0);
}
+static bool user_event_capable(u16 reg_flags)
+{
+ /* Persistent events require CAP_PERFMON / CAP_SYS_ADMIN */
+ if (reg_flags & USER_EVENT_REG_PERSIST) {
+ if (!perfmon_capable())
+ return false;
+ }
+
+ return true;
+}
+
static struct user_event *user_event_get(struct user_event *user)
{
refcount_inc(&user->refcnt);
@@ -482,6 +510,7 @@ static int user_event_enabler_write(struct user_event_mm *mm,
unsigned long *ptr;
struct page *page;
void *kaddr;
+ int bit = ENABLE_BIT(enabler);
int ret;
lockdep_assert_held(&event_mutex);
@@ -497,6 +526,8 @@ static int user_event_enabler_write(struct user_event_mm *mm,
test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))))
return -EBUSY;
+ align_addr_bit(&uaddr, &bit, ENABLE_BITOPS(enabler));
+
ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT,
&page, NULL);
@@ -515,9 +546,9 @@ static int user_event_enabler_write(struct user_event_mm *mm,
/* Update bit atomically, user tracers must be atomic as well */
if (enabler->event && enabler->event->status)
- set_bit(ENABLE_BIT(enabler), ptr);
+ set_bit(bit, ptr);
else
- clear_bit(ENABLE_BIT(enabler), ptr);
+ clear_bit(bit, ptr);
kunmap_local(kaddr);
unpin_user_pages_dirty_lock(&page, 1, true);
@@ -849,6 +880,12 @@ static struct user_event_enabler
enabler->event = user;
enabler->addr = uaddr;
enabler->values = reg->enable_bit;
+
+#if BITS_PER_LONG >= 64
+ if (reg->enable_size == 4)
+ set_bit(ENABLE_VAL_32_ON_64_BIT, ENABLE_BITOPS(enabler));
+#endif
+
retry:
/* Prevents state changes from racing with new enablers */
mutex_lock(&event_mutex);
@@ -1328,14 +1365,14 @@ static int user_field_set_string(struct ftrace_event_field *field,
static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
{
- struct ftrace_event_field *field, *next;
+ struct ftrace_event_field *field;
struct list_head *head = &user->fields;
int pos = 0, depth = 0;
const char *str_func;
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
- list_for_each_entry_safe_reverse(field, next, head, link) {
+ list_for_each_entry_reverse(field, head, link) {
if (depth != 0)
pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
@@ -1347,7 +1384,7 @@ static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
- list_for_each_entry_safe_reverse(field, next, head, link) {
+ list_for_each_entry_reverse(field, head, link) {
if (user_field_is_dyn_string(field->type, &str_func))
pos += snprintf(buf + pos, LEN_OR_ZERO,
", %s(%s)", str_func, field->name);
@@ -1732,7 +1769,7 @@ static int user_event_create(const char *raw_command)
static int user_event_show(struct seq_file *m, struct dyn_event *ev)
{
struct user_event *user = container_of(ev, struct user_event, devent);
- struct ftrace_event_field *field, *next;
+ struct ftrace_event_field *field;
struct list_head *head;
int depth = 0;
@@ -1740,7 +1777,7 @@ static int user_event_show(struct seq_file *m, struct dyn_event *ev)
head = trace_get_fields(&user->call);
- list_for_each_entry_safe_reverse(field, next, head, link) {
+ list_for_each_entry_reverse(field, head, link) {
if (depth == 0)
seq_puts(m, " ");
else
@@ -1773,6 +1810,9 @@ static int user_event_free(struct dyn_event *ev)
if (!user_event_last_ref(user))
return -EBUSY;
+ if (!user_event_capable(user->reg_flags))
+ return -EPERM;
+
return destroy_user_event(user);
}
@@ -1816,13 +1856,14 @@ out:
static bool user_fields_match(struct user_event *user, int argc,
const char **argv)
{
- struct ftrace_event_field *field, *next;
+ struct ftrace_event_field *field;
struct list_head *head = &user->fields;
int i = 0;
- list_for_each_entry_safe_reverse(field, next, head, link)
+ list_for_each_entry_reverse(field, head, link) {
if (!user_field_match(field, argc, argv, &i))
return false;
+ }
if (i != argc)
return false;
@@ -1887,10 +1928,13 @@ static int user_event_parse(struct user_event_group *group, char *name,
int argc = 0;
char **argv;
- /* User register flags are not ready yet */
- if (reg_flags != 0 || flags != NULL)
+ /* Currently don't support any text based flags */
+ if (flags != NULL)
return -EINVAL;
+ if (!user_event_capable(reg_flags))
+ return -EPERM;
+
/* Prevent dyn_event from racing */
mutex_lock(&event_mutex);
user = find_user_event(group, name, &key);
@@ -2023,6 +2067,9 @@ static int delete_user_event(struct user_event_group *group, char *name)
if (!user_event_last_ref(user))
return -EBUSY;
+ if (!user_event_capable(user->reg_flags))
+ return -EPERM;
+
return destroy_user_event(user);
}
@@ -2376,7 +2423,8 @@ static long user_unreg_get(struct user_unreg __user *ureg,
}
static int user_event_mm_clear_bit(struct user_event_mm *user_mm,
- unsigned long uaddr, unsigned char bit)
+ unsigned long uaddr, unsigned char bit,
+ unsigned long flags)
{
struct user_event_enabler enabler;
int result;
@@ -2384,7 +2432,7 @@ static int user_event_mm_clear_bit(struct user_event_mm *user_mm,
memset(&enabler, 0, sizeof(enabler));
enabler.addr = uaddr;
- enabler.values = bit;
+ enabler.values = bit | flags;
retry:
/* Prevents state changes from racing with new enablers */
mutex_lock(&event_mutex);
@@ -2414,6 +2462,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
struct user_event_mm *mm = current->user_event_mm;
struct user_event_enabler *enabler, *next;
struct user_unreg reg;
+ unsigned long flags;
long ret;
ret = user_unreg_get(ureg, &reg);
@@ -2424,6 +2473,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
if (!mm)
return -ENOENT;
+ flags = 0;
ret = -ENOENT;
/*
@@ -2440,6 +2490,9 @@ static long user_events_ioctl_unreg(unsigned long uarg)
ENABLE_BIT(enabler) == reg.disable_bit) {
set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler));
+ /* We must keep compat flags for the clear */
+ flags |= enabler->values & ENABLE_VAL_COMPAT_MASK;
+
if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)))
user_event_enabler_destroy(enabler, true);
@@ -2453,7 +2506,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
/* Ensure bit is now cleared for user, regardless of event status */
if (!ret)
ret = user_event_mm_clear_bit(mm, reg.disable_addr,
- reg.disable_bit);
+ reg.disable_bit, flags);
return ret;
}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 58f3946081e2..1698fc22afa0 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -51,6 +51,9 @@ static int ftrace_event_register(struct trace_event_call *call,
#undef __array
#define __array(type, item, size) type item[size];
+#undef __stack_array
+#define __stack_array(type, item, size, field) __array(type, item, size)
+
#undef __array_desc
#define __array_desc(type, container, item, size) type item[size];
@@ -114,6 +117,9 @@ static void __always_unused ____ftrace_check_##name(void) \
is_signed_type(_type), .filter_type = FILTER_OTHER, \
.len = _len },
+#undef __stack_array
+#define __stack_array(_type, _item, _len, _field) __array(_type, _item, _len)
+
#undef __array_desc
#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len)
@@ -149,6 +155,9 @@ static struct trace_event_fields ftrace_event_fields_##name[] = { \
#undef __array
#define __array(type, item, len)
+#undef __stack_array
+#define __stack_array(type, item, len, field)
+
#undef __array_desc
#define __array_desc(type, container, item, len)
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index dfe2e546acdc..7d2ddbcfa377 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -898,6 +898,47 @@ static struct tracepoint *find_tracepoint(const char *tp_name)
return data.tpoint;
}
+static int parse_symbol_and_return(int argc, const char *argv[],
+ char **symbol, bool *is_return,
+ bool is_tracepoint)
+{
+ char *tmp = strchr(argv[1], '%');
+ int i;
+
+ if (tmp) {
+ int len = tmp - argv[1];
+
+ if (!is_tracepoint && !strcmp(tmp, "%return")) {
+ *is_return = true;
+ } else {
+ trace_probe_log_err(len, BAD_ADDR_SUFFIX);
+ return -EINVAL;
+ }
+ *symbol = kmemdup_nul(argv[1], len, GFP_KERNEL);
+ } else
+ *symbol = kstrdup(argv[1], GFP_KERNEL);
+ if (!*symbol)
+ return -ENOMEM;
+
+ if (*is_return)
+ return 0;
+
+ /* If there is $retval, this should be a return fprobe. */
+ for (i = 2; i < argc; i++) {
+ tmp = strstr(argv[i], "$retval");
+ if (tmp && !isalnum(tmp[7]) && tmp[7] != '_') {
+ if (is_tracepoint) {
+ trace_probe_log_set_index(i);
+ trace_probe_log_err(tmp - argv[i], RETVAL_ON_PROBE);
+ return -EINVAL;
+ }
+ *is_return = true;
+ break;
+ }
+ }
+ return 0;
+}
+
static int __trace_fprobe_create(int argc, const char *argv[])
{
/*
@@ -927,7 +968,7 @@ static int __trace_fprobe_create(int argc, const char *argv[])
struct trace_fprobe *tf = NULL;
int i, len, new_argc = 0, ret = 0;
bool is_return = false;
- char *symbol = NULL, *tmp = NULL;
+ char *symbol = NULL;
const char *event = NULL, *group = FPROBE_EVENT_SYSTEM;
const char **new_argv = NULL;
int maxactive = 0;
@@ -983,20 +1024,10 @@ static int __trace_fprobe_create(int argc, const char *argv[])
trace_probe_log_set_index(1);
/* a symbol(or tracepoint) must be specified */
- symbol = kstrdup(argv[1], GFP_KERNEL);
- if (!symbol)
- return -ENOMEM;
+ ret = parse_symbol_and_return(argc, argv, &symbol, &is_return, is_tracepoint);
+ if (ret < 0)
+ goto parse_error;
- tmp = strchr(symbol, '%');
- if (tmp) {
- if (!is_tracepoint && !strcmp(tmp, "%return")) {
- *tmp = '\0';
- is_return = true;
- } else {
- trace_probe_log_err(tmp - symbol, BAD_ADDR_SUFFIX);
- goto parse_error;
- }
- }
if (!is_return && maxactive) {
trace_probe_log_set_index(0);
trace_probe_log_err(1, BAD_MAXACT_TYPE);
@@ -1096,6 +1127,7 @@ static int __trace_fprobe_create(int argc, const char *argv[])
}
out:
+ traceprobe_finish_parse(&ctx);
trace_probe_log_clear();
kfree(new_argv);
kfree(symbol);
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 2f37a6e68aa9..b791524a6536 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -635,7 +635,7 @@ static int s_mode_show(struct seq_file *s, void *v)
else
seq_printf(s, "%s", thread_mode_str[mode]);
- if (mode != MODE_MAX)
+ if (mode < MODE_MAX - 1) /* if mode is any but last */
seq_puts(s, " ");
return 0;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 23dba01831f7..52f8b537dd0a 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -705,6 +705,41 @@ static struct notifier_block trace_kprobe_module_nb = {
.priority = 1 /* Invoked after kprobe module callback */
};
+static int count_symbols(void *data, unsigned long unused)
+{
+ unsigned int *count = data;
+
+ (*count)++;
+
+ return 0;
+}
+
+struct sym_count_ctx {
+ unsigned int count;
+ const char *name;
+};
+
+static int count_mod_symbols(void *data, const char *name, unsigned long unused)
+{
+ struct sym_count_ctx *ctx = data;
+
+ if (strcmp(name, ctx->name) == 0)
+ ctx->count++;
+
+ return 0;
+}
+
+static unsigned int number_of_same_symbols(char *func_name)
+{
+ struct sym_count_ctx ctx = { .count = 0, .name = func_name };
+
+ kallsyms_on_each_match_symbol(count_symbols, func_name, &ctx.count);
+
+ module_kallsyms_on_each_symbol(NULL, count_mod_symbols, &ctx);
+
+ return ctx.count;
+}
+
static int __trace_kprobe_create(int argc, const char *argv[])
{
/*
@@ -836,6 +871,31 @@ static int __trace_kprobe_create(int argc, const char *argv[])
}
}
+ if (symbol && !strchr(symbol, ':')) {
+ unsigned int count;
+
+ count = number_of_same_symbols(symbol);
+ if (count > 1) {
+ /*
+ * Users should use ADDR to remove the ambiguity of
+ * using KSYM only.
+ */
+ trace_probe_log_err(0, NON_UNIQ_SYMBOL);
+ ret = -EADDRNOTAVAIL;
+
+ goto error;
+ } else if (count == 0) {
+ /*
+ * We can return ENOENT earlier than when register the
+ * kprobe.
+ */
+ trace_probe_log_err(0, BAD_PROBE_ADDR);
+ ret = -ENOENT;
+
+ goto error;
+ }
+ }
+
trace_probe_log_set_index(0);
if (event) {
ret = traceprobe_parse_event_name(&event, &group, gbuf,
@@ -907,6 +967,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
}
out:
+ traceprobe_finish_parse(&ctx);
trace_probe_log_clear();
kfree(new_argv);
kfree(symbol);
@@ -959,10 +1020,10 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init);
/**
* __kprobe_event_gen_cmd_start - Generate a kprobe event command from arg list
* @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @kretprobe: Is this a return probe?
* @name: The name of the kprobe event
* @loc: The location of the kprobe event
- * @kretprobe: Is this a return probe?
- * @args: Variable number of arg (pairs), one pair for each field
+ * @...: Variable number of arg (pairs), one pair for each field
*
* NOTE: Users normally won't want to call this function directly, but
* rather use the kprobe_event_gen_cmd_start() wrapper, which automatically
@@ -1035,7 +1096,7 @@ EXPORT_SYMBOL_GPL(__kprobe_event_gen_cmd_start);
/**
* __kprobe_event_add_fields - Add probe fields to a kprobe command from arg list
* @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @args: Variable number of arg (pairs), one pair for each field
+ * @...: Variable number of arg (pairs), one pair for each field
*
* NOTE: Users normally won't want to call this function directly, but
* rather use the kprobe_event_add_fields() wrapper, which
@@ -1188,6 +1249,12 @@ static const struct file_operations kprobe_events_ops = {
.write = probes_write,
};
+static unsigned long trace_kprobe_missed(struct trace_kprobe *tk)
+{
+ return trace_kprobe_is_return(tk) ?
+ tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed;
+}
+
/* Probes profiling interfaces */
static int probes_profile_seq_show(struct seq_file *m, void *v)
{
@@ -1199,8 +1266,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
return 0;
tk = to_trace_kprobe(ev);
- nmissed = trace_kprobe_is_return(tk) ?
- tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed;
+ nmissed = trace_kprobe_missed(tk);
seq_printf(m, " %-44s %15lu %15lu\n",
trace_probe_name(&tk->tp),
trace_kprobe_nhit(tk),
@@ -1546,7 +1612,8 @@ NOKPROBE_SYMBOL(kretprobe_perf_func);
int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
const char **symbol, u64 *probe_offset,
- u64 *probe_addr, bool perf_type_tracepoint)
+ u64 *probe_addr, unsigned long *missed,
+ bool perf_type_tracepoint)
{
const char *pevent = trace_event_name(event->tp_event);
const char *group = event->tp_event->class->system;
@@ -1561,15 +1628,12 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
*fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE
: BPF_FD_TYPE_KPROBE;
- if (tk->symbol) {
- *symbol = tk->symbol;
- *probe_offset = tk->rp.kp.offset;
- *probe_addr = 0;
- } else {
- *symbol = NULL;
- *probe_offset = 0;
- *probe_addr = (unsigned long)tk->rp.kp.addr;
- }
+ *probe_offset = tk->rp.kp.offset;
+ *probe_addr = kallsyms_show_value(current_cred()) ?
+ (unsigned long)tk->rp.kp.addr : 0;
+ *symbol = tk->symbol;
+ if (missed)
+ *missed = trace_kprobe_missed(tk);
return 0;
}
#endif /* CONFIG_PERF_EVENTS */
@@ -1699,6 +1763,7 @@ static int unregister_kprobe_event(struct trace_kprobe *tk)
}
#ifdef CONFIG_PERF_EVENTS
+
/* create a trace_kprobe, but don't add it to global lists */
struct trace_event_call *
create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
@@ -1709,6 +1774,24 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
int ret;
char *event;
+ if (func) {
+ unsigned int count;
+
+ count = number_of_same_symbols(func);
+ if (count > 1)
+ /*
+ * Users should use addr to remove the ambiguity of
+ * using func only.
+ */
+ return ERR_PTR(-EADDRNOTAVAIL);
+ else if (count == 0)
+ /*
+ * We can return ENOENT earlier than when register the
+ * kprobe.
+ */
+ return ERR_PTR(-ENOENT);
+ }
+
/*
* local trace_kprobes are not added to dyn_event, so they are never
* searched in find_trace_kprobe(). Therefore, there is no concern of
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index db575094c498..3e7fa44dc2b2 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -404,7 +404,7 @@ static int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
vmstart = vma->vm_start;
}
if (file) {
- ret = trace_seq_path(s, &file->f_path);
+ ret = trace_seq_path(s, file_user_path(file));
if (ret)
trace_seq_printf(s, "[+0x%lx]",
ip - vmstart);
@@ -1587,11 +1587,12 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
{
struct print_entry *field;
struct trace_seq *s = &iter->seq;
+ int max = iter->ent_size - offsetof(struct print_entry, buf);
trace_assign_type(field, iter->ent);
seq_print_ip_sym(s, field->ip, flags);
- trace_seq_printf(s, ": %s", field->buf);
+ trace_seq_printf(s, ": %.*s", max, field->buf);
return trace_handle_return(s);
}
@@ -1600,10 +1601,11 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct print_entry *field;
+ int max = iter->ent_size - offsetof(struct print_entry, buf);
trace_assign_type(field, iter->ent);
- trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
+ trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf);
return trace_handle_return(&iter->seq);
}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index c68a72707852..4dc74d73fc1d 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -12,6 +12,7 @@
#define pr_fmt(fmt) "trace_probe: " fmt
#include <linux/bpf.h>
+#include "trace_btf.h"
#include "trace_probe.h"
@@ -304,31 +305,90 @@ static int parse_trace_event_arg(char *arg, struct fetch_insn *code,
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
-static struct btf *traceprobe_get_btf(void)
+static u32 btf_type_int(const struct btf_type *t)
{
- struct btf *btf = bpf_get_btf_vmlinux();
+ return *(u32 *)(t + 1);
+}
- if (IS_ERR_OR_NULL(btf))
- return NULL;
+static bool btf_type_is_char_ptr(struct btf *btf, const struct btf_type *type)
+{
+ const struct btf_type *real_type;
+ u32 intdata;
+ s32 tid;
+
+ real_type = btf_type_skip_modifiers(btf, type->type, &tid);
+ if (!real_type)
+ return false;
+
+ if (BTF_INFO_KIND(real_type->info) != BTF_KIND_INT)
+ return false;
- return btf;
+ intdata = btf_type_int(real_type);
+ return !(BTF_INT_ENCODING(intdata) & BTF_INT_SIGNED)
+ && BTF_INT_BITS(intdata) == 8;
}
-static u32 btf_type_int(const struct btf_type *t)
+static bool btf_type_is_char_array(struct btf *btf, const struct btf_type *type)
{
- return *(u32 *)(t + 1);
+ const struct btf_type *real_type;
+ const struct btf_array *array;
+ u32 intdata;
+ s32 tid;
+
+ if (BTF_INFO_KIND(type->info) != BTF_KIND_ARRAY)
+ return false;
+
+ array = (const struct btf_array *)(type + 1);
+
+ real_type = btf_type_skip_modifiers(btf, array->type, &tid);
+
+ intdata = btf_type_int(real_type);
+ return !(BTF_INT_ENCODING(intdata) & BTF_INT_SIGNED)
+ && BTF_INT_BITS(intdata) == 8;
}
-static const char *type_from_btf_id(struct btf *btf, s32 id)
+static int check_prepare_btf_string_fetch(char *typename,
+ struct fetch_insn **pcode,
+ struct traceprobe_parse_context *ctx)
+{
+ struct btf *btf = ctx->btf;
+
+ if (!btf || !ctx->last_type)
+ return 0;
+
+ /* char [] does not need any change. */
+ if (btf_type_is_char_array(btf, ctx->last_type))
+ return 0;
+
+ /* char * requires dereference the pointer. */
+ if (btf_type_is_char_ptr(btf, ctx->last_type)) {
+ struct fetch_insn *code = *pcode + 1;
+
+ if (code->op == FETCH_OP_END) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -E2BIG;
+ }
+ if (typename[0] == 'u')
+ code->op = FETCH_OP_UDEREF;
+ else
+ code->op = FETCH_OP_DEREF;
+ code->offset = 0;
+ *pcode = code;
+ return 0;
+ }
+ /* Other types are not available for string */
+ trace_probe_log_err(ctx->offset, BAD_TYPE4STR);
+ return -EINVAL;
+}
+
+static const char *fetch_type_from_btf_type(struct btf *btf,
+ const struct btf_type *type,
+ struct traceprobe_parse_context *ctx)
{
- const struct btf_type *t;
u32 intdata;
- s32 tid;
/* TODO: const char * could be converted as a string */
- t = btf_type_skip_modifiers(btf, id, &tid);
-
- switch (BTF_INFO_KIND(t->info)) {
+ switch (BTF_INFO_KIND(type->info)) {
case BTF_KIND_ENUM:
/* enum is "int", so convert to "s32" */
return "s32";
@@ -341,7 +401,7 @@ static const char *type_from_btf_id(struct btf *btf, s32 id)
else
return "x32";
case BTF_KIND_INT:
- intdata = btf_type_int(t);
+ intdata = btf_type_int(type);
if (BTF_INT_ENCODING(intdata) & BTF_INT_SIGNED) {
switch (BTF_INT_BITS(intdata)) {
case 8:
@@ -364,6 +424,10 @@ static const char *type_from_btf_id(struct btf *btf, s32 id)
case 64:
return "u64";
}
+ /* bitfield, size is encoded in the type */
+ ctx->last_bitsize = BTF_INT_BITS(intdata);
+ ctx->last_bitoffs += BTF_INT_OFFSET(intdata);
+ return "u64";
}
}
/* TODO: support other types */
@@ -371,88 +435,223 @@ static const char *type_from_btf_id(struct btf *btf, s32 id)
return NULL;
}
-static const struct btf_type *find_btf_func_proto(const char *funcname)
+static int query_btf_context(struct traceprobe_parse_context *ctx)
{
- struct btf *btf = traceprobe_get_btf();
- const struct btf_type *t;
- s32 id;
+ const struct btf_param *param;
+ const struct btf_type *type;
+ struct btf *btf;
+ s32 nr;
- if (!btf || !funcname)
- return ERR_PTR(-EINVAL);
+ if (ctx->btf)
+ return 0;
+
+ if (!ctx->funcname)
+ return -EINVAL;
+
+ type = btf_find_func_proto(ctx->funcname, &btf);
+ if (!type)
+ return -ENOENT;
- id = btf_find_by_name_kind(btf, funcname, BTF_KIND_FUNC);
- if (id <= 0)
- return ERR_PTR(-ENOENT);
+ ctx->btf = btf;
+ ctx->proto = type;
+
+ /* ctx->params is optional, since func(void) will not have params. */
+ nr = 0;
+ param = btf_get_func_param(type, &nr);
+ if (!IS_ERR_OR_NULL(param)) {
+ /* Hide the first 'data' argument of tracepoint */
+ if (ctx->flags & TPARG_FL_TPOINT) {
+ nr--;
+ param++;
+ }
+ }
- /* Get BTF_KIND_FUNC type */
- t = btf_type_by_id(btf, id);
- if (!t || !btf_type_is_func(t))
- return ERR_PTR(-ENOENT);
+ if (nr > 0) {
+ ctx->nr_params = nr;
+ ctx->params = param;
+ } else {
+ ctx->nr_params = 0;
+ ctx->params = NULL;
+ }
- /* The type of BTF_KIND_FUNC is BTF_KIND_FUNC_PROTO */
- t = btf_type_by_id(btf, t->type);
- if (!t || !btf_type_is_func_proto(t))
- return ERR_PTR(-ENOENT);
+ return 0;
+}
- return t;
+static void clear_btf_context(struct traceprobe_parse_context *ctx)
+{
+ if (ctx->btf) {
+ btf_put(ctx->btf);
+ ctx->btf = NULL;
+ ctx->proto = NULL;
+ ctx->params = NULL;
+ ctx->nr_params = 0;
+ }
}
-static const struct btf_param *find_btf_func_param(const char *funcname, s32 *nr,
- bool tracepoint)
+/* Return 1 if the field separater is arrow operator ('->') */
+static int split_next_field(char *varname, char **next_field,
+ struct traceprobe_parse_context *ctx)
{
- const struct btf_param *param;
- const struct btf_type *t;
+ char *field;
+ int ret = 0;
+
+ field = strpbrk(varname, ".-");
+ if (field) {
+ if (field[0] == '-' && field[1] == '>') {
+ field[0] = '\0';
+ field += 2;
+ ret = 1;
+ } else if (field[0] == '.') {
+ field[0] = '\0';
+ field += 1;
+ } else {
+ trace_probe_log_err(ctx->offset + field - varname, BAD_HYPHEN);
+ return -EINVAL;
+ }
+ *next_field = field;
+ }
- if (!funcname || !nr)
- return ERR_PTR(-EINVAL);
+ return ret;
+}
- t = find_btf_func_proto(funcname);
- if (IS_ERR(t))
- return (const struct btf_param *)t;
+/*
+ * Parse the field of data structure. The @type must be a pointer type
+ * pointing the target data structure type.
+ */
+static int parse_btf_field(char *fieldname, const struct btf_type *type,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx)
+{
+ struct fetch_insn *code = *pcode;
+ const struct btf_member *field;
+ u32 bitoffs, anon_offs;
+ char *next;
+ int is_ptr;
+ s32 tid;
- *nr = btf_type_vlen(t);
- param = (const struct btf_param *)(t + 1);
+ do {
+ /* Outer loop for solving arrow operator ('->') */
+ if (BTF_INFO_KIND(type->info) != BTF_KIND_PTR) {
+ trace_probe_log_err(ctx->offset, NO_PTR_STRCT);
+ return -EINVAL;
+ }
+ /* Convert a struct pointer type to a struct type */
+ type = btf_type_skip_modifiers(ctx->btf, type->type, &tid);
+ if (!type) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return -EINVAL;
+ }
- /* Hide the first 'data' argument of tracepoint */
- if (tracepoint) {
- (*nr)--;
- param++;
- }
+ bitoffs = 0;
+ do {
+ /* Inner loop for solving dot operator ('.') */
+ next = NULL;
+ is_ptr = split_next_field(fieldname, &next, ctx);
+ if (is_ptr < 0)
+ return is_ptr;
+
+ anon_offs = 0;
+ field = btf_find_struct_member(ctx->btf, type, fieldname,
+ &anon_offs);
+ if (!field) {
+ trace_probe_log_err(ctx->offset, NO_BTF_FIELD);
+ return -ENOENT;
+ }
+ /* Add anonymous structure/union offset */
+ bitoffs += anon_offs;
+
+ /* Accumulate the bit-offsets of the dot-connected fields */
+ if (btf_type_kflag(type)) {
+ bitoffs += BTF_MEMBER_BIT_OFFSET(field->offset);
+ ctx->last_bitsize = BTF_MEMBER_BITFIELD_SIZE(field->offset);
+ } else {
+ bitoffs += field->offset;
+ ctx->last_bitsize = 0;
+ }
- if (*nr > 0)
- return param;
- else
- return NULL;
+ type = btf_type_skip_modifiers(ctx->btf, field->type, &tid);
+ if (!type) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return -EINVAL;
+ }
+
+ ctx->offset += next - fieldname;
+ fieldname = next;
+ } while (!is_ptr && fieldname);
+
+ if (++code == end) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -EINVAL;
+ }
+ code->op = FETCH_OP_DEREF; /* TODO: user deref support */
+ code->offset = bitoffs / 8;
+ *pcode = code;
+
+ ctx->last_bitoffs = bitoffs % 8;
+ ctx->last_type = type;
+ } while (fieldname);
+
+ return 0;
}
-static int parse_btf_arg(const char *varname, struct fetch_insn *code,
+static int parse_btf_arg(char *varname,
+ struct fetch_insn **pcode, struct fetch_insn *end,
struct traceprobe_parse_context *ctx)
{
- struct btf *btf = traceprobe_get_btf();
+ struct fetch_insn *code = *pcode;
const struct btf_param *params;
- int i;
+ const struct btf_type *type;
+ char *field = NULL;
+ int i, is_ptr, ret;
+ u32 tid;
+
+ if (WARN_ON_ONCE(!ctx->funcname))
+ return -EINVAL;
- if (!btf) {
- trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
+ is_ptr = split_next_field(varname, &field, ctx);
+ if (is_ptr < 0)
+ return is_ptr;
+ if (!is_ptr && field) {
+ /* dot-connected field on an argument is not supported. */
+ trace_probe_log_err(ctx->offset + field - varname,
+ NOSUP_DAT_ARG);
return -EOPNOTSUPP;
}
- if (WARN_ON_ONCE(!ctx->funcname))
- return -EINVAL;
+ if (ctx->flags & TPARG_FL_RETURN) {
+ if (strcmp(varname, "$retval") != 0) {
+ trace_probe_log_err(ctx->offset, NO_BTFARG);
+ return -ENOENT;
+ }
+ code->op = FETCH_OP_RETVAL;
+ /* Check whether the function return type is not void */
+ if (query_btf_context(ctx) == 0) {
+ if (ctx->proto->type == 0) {
+ trace_probe_log_err(ctx->offset, NO_RETVAL);
+ return -ENOENT;
+ }
+ tid = ctx->proto->type;
+ goto found;
+ }
+ if (field) {
+ trace_probe_log_err(ctx->offset + field - varname,
+ NO_BTF_ENTRY);
+ return -ENOENT;
+ }
+ return 0;
+ }
- if (!ctx->params) {
- params = find_btf_func_param(ctx->funcname, &ctx->nr_params,
- ctx->flags & TPARG_FL_TPOINT);
- if (IS_ERR_OR_NULL(params)) {
+ if (!ctx->btf) {
+ ret = query_btf_context(ctx);
+ if (ret < 0 || ctx->nr_params == 0) {
trace_probe_log_err(ctx->offset, NO_BTF_ENTRY);
return PTR_ERR(params);
}
- ctx->params = params;
- } else
- params = ctx->params;
+ }
+ params = ctx->params;
for (i = 0; i < ctx->nr_params; i++) {
- const char *name = btf_name_by_offset(btf, params[i].name_off);
+ const char *name = btf_name_by_offset(ctx->btf, params[i].name_off);
if (name && !strcmp(name, varname)) {
code->op = FETCH_OP_ARG;
@@ -460,91 +659,114 @@ static int parse_btf_arg(const char *varname, struct fetch_insn *code,
code->param = i + 1;
else
code->param = i;
- return 0;
+ tid = params[i].type;
+ goto found;
}
}
trace_probe_log_err(ctx->offset, NO_BTFARG);
return -ENOENT;
-}
-
-static const struct fetch_type *parse_btf_arg_type(int arg_idx,
- struct traceprobe_parse_context *ctx)
-{
- struct btf *btf = traceprobe_get_btf();
- const char *typestr = NULL;
- if (btf && ctx->params) {
- if (ctx->flags & TPARG_FL_TPOINT)
- arg_idx--;
- typestr = type_from_btf_id(btf, ctx->params[arg_idx].type);
+found:
+ type = btf_type_skip_modifiers(ctx->btf, tid, &tid);
+ if (!type) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return -EINVAL;
}
-
- return find_fetch_type(typestr, ctx->flags);
+ /* Initialize the last type information */
+ ctx->last_type = type;
+ ctx->last_bitoffs = 0;
+ ctx->last_bitsize = 0;
+ if (field) {
+ ctx->offset += field - varname;
+ return parse_btf_field(field, type, pcode, end, ctx);
+ }
+ return 0;
}
-static const struct fetch_type *parse_btf_retval_type(
+static const struct fetch_type *find_fetch_type_from_btf_type(
struct traceprobe_parse_context *ctx)
{
- struct btf *btf = traceprobe_get_btf();
+ struct btf *btf = ctx->btf;
const char *typestr = NULL;
- const struct btf_type *t;
- if (btf && ctx->funcname) {
- t = find_btf_func_proto(ctx->funcname);
- if (!IS_ERR(t))
- typestr = type_from_btf_id(btf, t->type);
- }
+ if (btf && ctx->last_type)
+ typestr = fetch_type_from_btf_type(btf, ctx->last_type, ctx);
return find_fetch_type(typestr, ctx->flags);
}
-static bool is_btf_retval_void(const char *funcname)
+static int parse_btf_bitfield(struct fetch_insn **pcode,
+ struct traceprobe_parse_context *ctx)
{
- const struct btf_type *t;
+ struct fetch_insn *code = *pcode;
- t = find_btf_func_proto(funcname);
- if (IS_ERR(t))
- return false;
+ if ((ctx->last_bitsize % 8 == 0) && ctx->last_bitoffs == 0)
+ return 0;
+
+ code++;
+ if (code->op != FETCH_OP_NOP) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -EINVAL;
+ }
+ *pcode = code;
- return t->type == 0;
+ code->op = FETCH_OP_MOD_BF;
+ code->lshift = 64 - (ctx->last_bitsize + ctx->last_bitoffs);
+ code->rshift = 64 - ctx->last_bitsize;
+ code->basesize = 64 / 8;
+ return 0;
}
+
#else
-static struct btf *traceprobe_get_btf(void)
+static void clear_btf_context(struct traceprobe_parse_context *ctx)
{
- return NULL;
+ ctx->btf = NULL;
}
-static const struct btf_param *find_btf_func_param(const char *funcname, s32 *nr,
- bool tracepoint)
+static int query_btf_context(struct traceprobe_parse_context *ctx)
{
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
}
-static int parse_btf_arg(const char *varname, struct fetch_insn *code,
+static int parse_btf_arg(char *varname,
+ struct fetch_insn **pcode, struct fetch_insn *end,
struct traceprobe_parse_context *ctx)
{
trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
return -EOPNOTSUPP;
}
-#define parse_btf_arg_type(idx, ctx) \
- find_fetch_type(NULL, ctx->flags)
+static int parse_btf_bitfield(struct fetch_insn **pcode,
+ struct traceprobe_parse_context *ctx)
+{
+ trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
+ return -EOPNOTSUPP;
+}
-#define parse_btf_retval_type(ctx) \
+#define find_fetch_type_from_btf_type(ctx) \
find_fetch_type(NULL, ctx->flags)
-#define is_btf_retval_void(funcname) (false)
+static int check_prepare_btf_string_fetch(char *typename,
+ struct fetch_insn **pcode,
+ struct traceprobe_parse_context *ctx)
+{
+ return 0;
+}
#endif
#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
-static int parse_probe_vars(char *arg, const struct fetch_type *t,
- struct fetch_insn *code,
+/* Parse $vars. @orig_arg points '$', which syncs to @ctx->offset */
+static int parse_probe_vars(char *orig_arg, const struct fetch_type *t,
+ struct fetch_insn **pcode,
+ struct fetch_insn *end,
struct traceprobe_parse_context *ctx)
{
- unsigned long param;
+ struct fetch_insn *code = *pcode;
int err = TP_ERR_BAD_VAR;
+ char *arg = orig_arg + 1;
+ unsigned long param;
int ret = 0;
int len;
@@ -563,18 +785,17 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
goto inval;
}
- if (strcmp(arg, "retval") == 0) {
- if (ctx->flags & TPARG_FL_RETURN) {
- if ((ctx->flags & TPARG_FL_KERNEL) &&
- is_btf_retval_void(ctx->funcname)) {
- err = TP_ERR_NO_RETVAL;
- goto inval;
- }
+ if (str_has_prefix(arg, "retval")) {
+ if (!(ctx->flags & TPARG_FL_RETURN)) {
+ err = TP_ERR_RETVAL_ON_PROBE;
+ goto inval;
+ }
+ if (!(ctx->flags & TPARG_FL_KERNEL) ||
+ !IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS)) {
code->op = FETCH_OP_RETVAL;
return 0;
}
- err = TP_ERR_RETVAL_ON_PROBE;
- goto inval;
+ return parse_btf_arg(orig_arg, pcode, end, ctx);
}
len = str_has_prefix(arg, "stack");
@@ -676,7 +897,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
switch (arg[0]) {
case '$':
- ret = parse_probe_vars(arg + 1, type, code, ctx);
+ ret = parse_probe_vars(arg, type, pcode, end, ctx);
break;
case '%': /* named register */
@@ -795,6 +1016,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
code->op = deref;
code->offset = offset;
+ /* Reset the last type if used */
+ ctx->last_type = NULL;
}
break;
case '\\': /* Immediate value */
@@ -818,7 +1041,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
return -EINVAL;
}
- ret = parse_btf_arg(arg, code, ctx);
+ ret = parse_btf_arg(arg, pcode, end, ctx);
break;
}
}
@@ -964,17 +1187,22 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
goto out;
code[FETCH_INSN_MAX - 1].op = FETCH_OP_END;
+ ctx->last_type = NULL;
ret = parse_probe_arg(arg, parg->type, &code, &code[FETCH_INSN_MAX - 1],
ctx);
if (ret)
goto fail;
/* Update storing type if BTF is available */
- if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) && !t) {
- if (code->op == FETCH_OP_ARG)
- parg->type = parse_btf_arg_type(code->param, ctx);
- else if (code->op == FETCH_OP_RETVAL)
- parg->type = parse_btf_retval_type(ctx);
+ if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) &&
+ ctx->last_type) {
+ if (!t) {
+ parg->type = find_fetch_type_from_btf_type(ctx);
+ } else if (strstr(t, "string")) {
+ ret = check_prepare_btf_string_fetch(t, &code, ctx);
+ if (ret)
+ goto fail;
+ }
}
ret = -EINVAL;
@@ -1048,6 +1276,11 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
trace_probe_log_err(ctx->offset + t - arg, BAD_BITFIELD);
goto fail;
}
+ } else if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) &&
+ ctx->last_type) {
+ ret = parse_btf_bitfield(&code, ctx);
+ if (ret)
+ goto fail;
}
ret = -EINVAL;
/* Loop(Array) operation */
@@ -1231,7 +1464,6 @@ static int sprint_nth_btf_arg(int idx, const char *type,
char *buf, int bufsize,
struct traceprobe_parse_context *ctx)
{
- struct btf *btf = traceprobe_get_btf();
const char *name;
int ret;
@@ -1239,7 +1471,7 @@ static int sprint_nth_btf_arg(int idx, const char *type,
trace_probe_log_err(0, NO_BTFARG);
return -ENOENT;
}
- name = btf_name_by_offset(btf, ctx->params[idx].name_off);
+ name = btf_name_by_offset(ctx->btf, ctx->params[idx].name_off);
if (!name) {
trace_probe_log_err(0, NO_BTF_ENTRY);
return -ENOENT;
@@ -1260,7 +1492,6 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[],
const struct btf_param *params = NULL;
int i, j, n, used, ret, args_idx = -1;
const char **new_argv = NULL;
- int nr_params;
ret = argv_has_var_arg(argc, argv, &args_idx, ctx);
if (ret < 0)
@@ -1271,9 +1502,8 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[],
return NULL;
}
- params = find_btf_func_param(ctx->funcname, &nr_params,
- ctx->flags & TPARG_FL_TPOINT);
- if (IS_ERR_OR_NULL(params)) {
+ ret = query_btf_context(ctx);
+ if (ret < 0 || ctx->nr_params == 0) {
if (args_idx != -1) {
/* $arg* requires BTF info */
trace_probe_log_err(0, NOSUP_BTFARG);
@@ -1282,8 +1512,6 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[],
*new_argc = argc;
return NULL;
}
- ctx->params = params;
- ctx->nr_params = nr_params;
if (args_idx >= 0)
*new_argc = argc + ctx->nr_params - 1;
@@ -1298,7 +1526,7 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[],
for (i = 0, j = 0; i < argc; i++) {
trace_probe_log_set_index(i + 2);
if (i == args_idx) {
- for (n = 0; n < nr_params; n++) {
+ for (n = 0; n < ctx->nr_params; n++) {
ret = sprint_nth_btf_arg(n, "", buf + used,
bufsize - used, ctx);
if (ret < 0)
@@ -1337,6 +1565,11 @@ error:
return ERR_PTR(ret);
}
+void traceprobe_finish_parse(struct traceprobe_parse_context *ctx)
+{
+ clear_btf_context(ctx);
+}
+
int traceprobe_update_arg(struct probe_arg *arg)
{
struct fetch_insn *code = arg->code;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 01ea148723de..850d9ecb6765 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -383,9 +383,15 @@ static inline bool tparg_is_function_entry(unsigned int flags)
struct traceprobe_parse_context {
struct trace_event_call *event;
- const struct btf_param *params;
- s32 nr_params;
- const char *funcname;
+ /* BTF related parameters */
+ const char *funcname; /* Function name in BTF */
+ const struct btf_type *proto; /* Prototype of the function */
+ const struct btf_param *params; /* Parameter of the function */
+ s32 nr_params; /* The number of the parameters */
+ struct btf *btf; /* The BTF to be used */
+ const struct btf_type *last_type; /* Saved type */
+ u32 last_bitoffs; /* Saved bitoffs */
+ u32 last_bitsize; /* Saved bitsize */
unsigned int flags;
int offset;
};
@@ -400,6 +406,12 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[],
extern int traceprobe_update_arg(struct probe_arg *arg);
extern void traceprobe_free_probe_arg(struct probe_arg *arg);
+/*
+ * If either traceprobe_parse_probe_arg() or traceprobe_expand_meta_args() is called,
+ * this MUST be called for clean up the context and return a resource.
+ */
+void traceprobe_finish_parse(struct traceprobe_parse_context *ctx);
+
extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
char *buf, int offset);
@@ -438,6 +450,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(BAD_MAXACT, "Invalid maxactive number"), \
C(MAXACT_TOO_BIG, "Maxactive is too big"), \
C(BAD_PROBE_ADDR, "Invalid probed address or symbol"), \
+ C(NON_UNIQ_SYMBOL, "The symbol is not unique"), \
C(BAD_RETPROBE, "Retprobe address must be an function entry"), \
C(NO_TRACEPOINT, "Tracepoint is not found"), \
C(BAD_ADDR_SUFFIX, "Invalid probed address suffix"), \
@@ -495,7 +508,14 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(BAD_VAR_ARGS, "$arg* must be an independent parameter without name etc."),\
C(NOFENTRY_ARGS, "$arg* can be used only on function entry"), \
C(DOUBLE_ARGS, "$arg* can be used only once in the parameters"), \
- C(ARGS_2LONG, "$arg* failed because the argument list is too long"),
+ C(ARGS_2LONG, "$arg* failed because the argument list is too long"), \
+ C(ARGIDX_2BIG, "$argN index is too big"), \
+ C(NO_PTR_STRCT, "This is not a pointer to union/structure."), \
+ C(NOSUP_DAT_ARG, "Non pointer structure/union argument is not supported."),\
+ C(BAD_HYPHEN, "Failed to parse single hyphen. Forgot '>'?"), \
+ C(NO_BTF_FIELD, "This field is not found."), \
+ C(BAD_BTF_TID, "Failed to get BTF type info."),\
+ C(BAD_TYPE4STR, "This type does not fit for string."),
#undef C
#define C(a, b) TP_ERR_##a
@@ -519,3 +539,8 @@ void __trace_probe_log_err(int offset, int err);
#define trace_probe_log_err(offs, err) \
__trace_probe_log_err(offs, TP_ERR_##err)
+
+struct uprobe_dispatch_data {
+ struct trace_uprobe *tu;
+ unsigned long bp_addr;
+};
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index bac06ee3b98b..7be97229ddf8 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -370,8 +370,12 @@ EXPORT_SYMBOL_GPL(trace_seq_path);
*/
int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt)
{
+ int ret;
__trace_seq_init(s);
- return seq_buf_to_user(&s->seq, ubuf, cnt);
+ ret = seq_buf_to_user(&s->seq, ubuf, s->readpos, cnt);
+ if (ret > 0)
+ s->readpos += ret;
+ return ret;
}
EXPORT_SYMBOL_GPL(trace_seq_to_user);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 942ddbdace4a..9c581d6da843 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -555,12 +555,15 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
struct syscall_trace_enter *rec)
{
struct syscall_tp_t {
- unsigned long long regs;
- unsigned long syscall_nr;
+ struct trace_entry ent;
+ int syscall_nr;
unsigned long args[SYSCALL_DEFINE_MAXARGS];
- } param;
+ } __aligned(8) param;
int i;
+ BUILD_BUG_ON(sizeof(param.ent) < sizeof(void *));
+
+ /* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
*(struct pt_regs **)&param = regs;
param.syscall_nr = rec->nr;
for (i = 0; i < sys_data->nb_args; i++)
@@ -657,11 +660,12 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
struct syscall_trace_exit *rec)
{
struct syscall_tp_t {
- unsigned long long regs;
- unsigned long syscall_nr;
+ struct trace_entry ent;
+ int syscall_nr;
unsigned long ret;
- } param;
+ } __aligned(8) param;
+ /* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
*(struct pt_regs **)&param = regs;
param.syscall_nr = rec->nr;
param.ret = rec->ret;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 688bf579f2f1..99c051de412a 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -88,11 +88,6 @@ static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev)
static int register_uprobe_event(struct trace_uprobe *tu);
static int unregister_uprobe_event(struct trace_uprobe *tu);
-struct uprobe_dispatch_data {
- struct trace_uprobe *tu;
- unsigned long bp_addr;
-};
-
static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
static int uretprobe_dispatcher(struct uprobe_consumer *con,
unsigned long func, struct pt_regs *regs);
@@ -693,6 +688,7 @@ static int __trace_uprobe_create(int argc, const char **argv)
trace_probe_log_set_index(i + 2);
ret = traceprobe_parse_probe_arg(&tu->tp, i, argv[i], &ctx);
+ traceprobe_finish_parse(&ctx);
if (ret)
goto error;
}
@@ -1352,7 +1348,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
if (bpf_prog_array_valid(call)) {
u32 ret;
- ret = bpf_prog_run_array_sleepable(call->prog_array, regs, bpf_prog_run);
+ ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run);
if (!ret)
return;
}
@@ -1418,7 +1414,7 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
const char **filename, u64 *probe_offset,
- bool perf_type_tracepoint)
+ u64 *probe_addr, bool perf_type_tracepoint)
{
const char *pevent = trace_event_name(event->tp_event);
const char *group = event->tp_event->class->system;
@@ -1435,6 +1431,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
: BPF_FD_TYPE_UPROBE;
*filename = tu->filename;
*probe_offset = tu->offset;
+ *probe_addr = 0;
return 0;
}
#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/ucount.c b/kernel/ucount.c
index ee8e57fd6f90..4aa6166cb856 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -104,7 +104,8 @@ bool setup_userns_sysctls(struct user_namespace *ns)
for (i = 0; i < UCOUNT_COUNTS; i++) {
tbl[i].data = &ns->ucount_max[i];
}
- ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl);
+ ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl,
+ ARRAY_SIZE(user_table));
}
if (!ns->sysctls) {
kfree(tbl);
@@ -364,7 +365,7 @@ static __init int user_namespace_sysctl_init(void)
* default set so that registrations in the child sets work
* properly.
*/
- user_header = register_sysctl("user", empty);
+ user_header = register_sysctl_sz("user", empty, 0);
kmemleak_ignore(user_header);
BUG_ON(!user_header);
BUG_ON(!setup_userns_sysctls(&init_user_ns));
diff --git a/kernel/up.c b/kernel/up.c
index a38b8b095251..df50828cc2f0 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -25,7 +25,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
}
EXPORT_SYMBOL(smp_call_function_single);
-int smp_call_function_single_async(int cpu, struct __call_single_data *csd)
+int smp_call_function_single_async(int cpu, call_single_data_t *csd)
{
unsigned long flags;
diff --git a/kernel/user.c b/kernel/user.c
index d667debeafd6..03cedc366dc9 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -18,8 +18,18 @@
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
+#include <linux/binfmts.h>
#include <linux/proc_ns.h>
+#if IS_ENABLED(CONFIG_BINFMT_MISC)
+struct binfmt_misc init_binfmt_misc = {
+ .entries = LIST_HEAD_INIT(init_binfmt_misc.entries),
+ .enabled = true,
+ .entries_lock = __RW_LOCK_UNLOCKED(init_binfmt_misc.entries_lock),
+};
+EXPORT_SYMBOL_GPL(init_binfmt_misc);
+#endif
+
/*
* userns count is 1 for root user, 1 for init_uts_ns,
* and 1 for... ?
@@ -67,6 +77,9 @@ struct user_namespace init_user_ns = {
.keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list),
.keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem),
#endif
+#if IS_ENABLED(CONFIG_BINFMT_MISC)
+ .binfmt_misc = &init_binfmt_misc,
+#endif
};
EXPORT_SYMBOL_GPL(init_user_ns);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 1d8e47bed3f1..eabe8bcc7042 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -22,7 +22,7 @@
#include <linux/bsearch.h>
#include <linux/sort.h>
-static struct kmem_cache *user_ns_cachep __read_mostly;
+static struct kmem_cache *user_ns_cachep __ro_after_init;
static DEFINE_MUTEX(userns_state_mutex);
static bool new_idmap_permitted(const struct file *file,
@@ -213,6 +213,9 @@ static void free_user_ns(struct work_struct *work)
kfree(ns->projid_map.forward);
kfree(ns->projid_map.reverse);
}
+#if IS_ENABLED(CONFIG_BINFMT_MISC)
+ kfree(ns->binfmt_misc);
+#endif
retire_userns_sysctls(ns);
key_free_user_ns(ns);
ns_free_inum(&ns->ns);
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index d0b6b390ee42..778b4056700f 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -331,7 +331,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe,
filter.__reserved != 0)
return -EINVAL;
- tf = memdup_user(_filter->filters, filter.nr_filters * sizeof(*tf));
+ tf = memdup_array_user(_filter->filters, filter.nr_filters, sizeof(*tf));
if (IS_ERR(tf))
return PTR_ERR(tf);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index be38276a365f..5cd6d4e26915 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -151,9 +151,6 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
*/
if (is_hardlockup(cpu)) {
unsigned int this_cpu = smp_processor_id();
- struct cpumask backtrace_mask;
-
- cpumask_copy(&backtrace_mask, cpu_online_mask);
/* Only print hardlockups once. */
if (per_cpu(watchdog_hardlockup_warned, cpu))
@@ -167,10 +164,8 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
show_regs(regs);
else
dump_stack();
- cpumask_clear_cpu(cpu, &backtrace_mask);
} else {
- if (trigger_single_cpu_backtrace(cpu))
- cpumask_clear_cpu(cpu, &backtrace_mask);
+ trigger_single_cpu_backtrace(cpu);
}
/*
@@ -179,7 +174,7 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
*/
if (sysctl_hardlockup_all_cpu_backtrace &&
!test_and_set_bit(0, &watchdog_hardlockup_all_cpu_dumped))
- trigger_cpumask_backtrace(&backtrace_mask);
+ trigger_allbutcpu_cpu_backtrace(cpu);
if (hardlockup_panic)
nmi_panic(regs, "Hard LOCKUP");
@@ -288,6 +283,13 @@ static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static unsigned long soft_lockup_nmi_warn;
+static int __init softlockup_panic_setup(char *str)
+{
+ softlockup_panic = simple_strtoul(str, NULL, 0);
+ return 1;
+}
+__setup("softlockup_panic=", softlockup_panic_setup);
+
static int __init nowatchdog_setup(char *str)
{
watchdog_user_enabled = 0;
@@ -523,7 +525,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
dump_stack();
if (softlockup_all_cpu_backtrace) {
- trigger_allbutself_cpu_backtrace();
+ trigger_allbutcpu_cpu_backtrace(smp_processor_id());
clear_bit_unlock(0, &soft_lockup_nmi_warn);
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 800b4208dba9..2989b57e154a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -122,11 +122,6 @@ enum {
*
* L: pool->lock protected. Access with pool->lock held.
*
- * X: During normal operation, modification requires pool->lock and should
- * be done only from local cpu. Either disabling preemption on local
- * cpu or grabbing pool->lock is enough for read access. If
- * POOL_DISASSOCIATED is set, it's identical to L.
- *
* K: Only modified by worker while holding pool->lock. Can be safely read by
* self, while holding pool->lock or from IRQ context if %current is the
* kworker.
@@ -160,7 +155,7 @@ struct worker_pool {
int cpu; /* I: the associated cpu */
int node; /* I: the associated node ID */
int id; /* I: pool ID */
- unsigned int flags; /* X: flags */
+ unsigned int flags; /* L: flags */
unsigned long watchdog_ts; /* L: watchdog timestamp */
bool cpu_stall; /* WD: stalled cpu bound pool */
@@ -216,6 +211,7 @@ enum pool_workqueue_stats {
PWQ_STAT_CPU_TIME, /* total CPU time consumed */
PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */
PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */
+ PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */
PWQ_STAT_MAYDAY, /* maydays to rescuer */
PWQ_STAT_RESCUED, /* linked work items executed by rescuer */
@@ -262,12 +258,12 @@ struct pool_workqueue {
u64 stats[PWQ_NR_STATS];
/*
- * Release of unbound pwq is punted to system_wq. See put_pwq()
- * and pwq_unbound_release_workfn() for details. pool_workqueue
- * itself is also RCU protected so that the first pwq can be
- * determined without grabbing wq->mutex.
+ * Release of unbound pwq is punted to a kthread_worker. See put_pwq()
+ * and pwq_release_workfn() for details. pool_workqueue itself is also
+ * RCU protected so that the first pwq can be determined without
+ * grabbing wq->mutex.
*/
- struct work_struct unbound_release_work;
+ struct kthread_work release_work;
struct rcu_head rcu;
} __aligned(1 << WORK_STRUCT_FLAG_BITS);
@@ -326,14 +322,33 @@ struct workqueue_struct {
/* hot fields used during command issue, aligned to cacheline */
unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */
- struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */
- struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */
+ struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */
};
static struct kmem_cache *pwq_cache;
-static cpumask_var_t *wq_numa_possible_cpumask;
- /* possible CPUs of each node */
+/*
+ * Each pod type describes how CPUs should be grouped for unbound workqueues.
+ * See the comment above workqueue_attrs->affn_scope.
+ */
+struct wq_pod_type {
+ int nr_pods; /* number of pods */
+ cpumask_var_t *pod_cpus; /* pod -> cpus */
+ int *pod_node; /* pod -> node */
+ int *cpu_pod; /* cpu -> pod */
+};
+
+static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES];
+static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE;
+
+static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = {
+ [WQ_AFFN_DFL] = "default",
+ [WQ_AFFN_CPU] = "cpu",
+ [WQ_AFFN_SMT] = "smt",
+ [WQ_AFFN_CACHE] = "cache",
+ [WQ_AFFN_NUMA] = "numa",
+ [WQ_AFFN_SYSTEM] = "system",
+};
/*
* Per-cpu work items which run for longer than the following threshold are
@@ -345,19 +360,14 @@ static cpumask_var_t *wq_numa_possible_cpumask;
static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX;
module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644);
-static bool wq_disable_numa;
-module_param_named(disable_numa, wq_disable_numa, bool, 0444);
-
/* see the comment above the definition of WQ_POWER_EFFICIENT */
static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
module_param_named(power_efficient, wq_power_efficient, bool, 0444);
static bool wq_online; /* can kworkers be created yet? */
-static bool wq_numa_enabled; /* unbound NUMA affinity enabled */
-
-/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
-static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
+/* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */
+static struct workqueue_attrs *wq_update_pod_attrs_buf;
static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */
static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */
@@ -371,6 +381,9 @@ static bool workqueue_freezing; /* PL: have wqs started freezing? */
/* PL&A: allowable cpus for unbound wqs and work items */
static cpumask_var_t wq_unbound_cpumask;
+/* for further constrain wq_unbound_cpumask by cmdline parameter*/
+static struct cpumask wq_cmdline_cpumask __initdata;
+
/* CPU where unbound work was last round robin scheduled from this CPU */
static DEFINE_PER_CPU(int, wq_rr_cpu_last);
@@ -400,19 +413,26 @@ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
/* I: attributes used when instantiating ordered pools on demand */
static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
-struct workqueue_struct *system_wq __read_mostly;
+/*
+ * I: kthread_worker to release pwq's. pwq release needs to be bounced to a
+ * process context while holding a pool lock. Bounce to a dedicated kthread
+ * worker to avoid A-A deadlocks.
+ */
+static struct kthread_worker *pwq_release_worker __ro_after_init;
+
+struct workqueue_struct *system_wq __ro_after_init;
EXPORT_SYMBOL(system_wq);
-struct workqueue_struct *system_highpri_wq __read_mostly;
+struct workqueue_struct *system_highpri_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_highpri_wq);
-struct workqueue_struct *system_long_wq __read_mostly;
+struct workqueue_struct *system_long_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_long_wq);
-struct workqueue_struct *system_unbound_wq __read_mostly;
+struct workqueue_struct *system_unbound_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_unbound_wq);
-struct workqueue_struct *system_freezable_wq __read_mostly;
+struct workqueue_struct *system_freezable_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_freezable_wq);
-struct workqueue_struct *system_power_efficient_wq __read_mostly;
+struct workqueue_struct *system_power_efficient_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_power_efficient_wq);
-struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly;
+struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
static int worker_thread(void *__worker);
@@ -606,35 +626,6 @@ static int worker_pool_assign_id(struct worker_pool *pool)
return ret;
}
-/**
- * unbound_pwq_by_node - return the unbound pool_workqueue for the given node
- * @wq: the target workqueue
- * @node: the node ID
- *
- * This must be called with any of wq_pool_mutex, wq->mutex or RCU
- * read locked.
- * If the pwq needs to be used beyond the locking in effect, the caller is
- * responsible for guaranteeing that the pwq stays online.
- *
- * Return: The unbound pool_workqueue for @node.
- */
-static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
- int node)
-{
- assert_rcu_or_wq_mutex_or_pool_mutex(wq);
-
- /*
- * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
- * delayed item is pending. The plan is to keep CPU -> NODE
- * mapping valid and stable across CPU on/offlines. Once that
- * happens, this workaround can be removed.
- */
- if (unlikely(node == NUMA_NO_NODE))
- return wq->dfl_pwq;
-
- return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
-}
-
static unsigned int work_color_to_flags(int color)
{
return color << WORK_STRUCT_COLOR_SHIFT;
@@ -825,11 +816,6 @@ static bool work_is_canceling(struct work_struct *work)
* they're being called with pool->lock held.
*/
-static bool __need_more_worker(struct worker_pool *pool)
-{
- return !pool->nr_running;
-}
-
/*
* Need to wake up a worker? Called from anything but currently
* running workers.
@@ -840,7 +826,7 @@ static bool __need_more_worker(struct worker_pool *pool)
*/
static bool need_more_worker(struct worker_pool *pool)
{
- return !list_empty(&pool->worklist) && __need_more_worker(pool);
+ return !list_empty(&pool->worklist) && !pool->nr_running;
}
/* Can I start working? Called from busy but !running workers. */
@@ -871,51 +857,18 @@ static bool too_many_workers(struct worker_pool *pool)
return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy;
}
-/*
- * Wake up functions.
- */
-
-/* Return the first idle worker. Called with pool->lock held. */
-static struct worker *first_idle_worker(struct worker_pool *pool)
-{
- if (unlikely(list_empty(&pool->idle_list)))
- return NULL;
-
- return list_first_entry(&pool->idle_list, struct worker, entry);
-}
-
-/**
- * wake_up_worker - wake up an idle worker
- * @pool: worker pool to wake worker from
- *
- * Wake up the first idle worker of @pool.
- *
- * CONTEXT:
- * raw_spin_lock_irq(pool->lock).
- */
-static void wake_up_worker(struct worker_pool *pool)
-{
- struct worker *worker = first_idle_worker(pool);
-
- if (likely(worker))
- wake_up_process(worker->task);
-}
-
/**
* worker_set_flags - set worker flags and adjust nr_running accordingly
* @worker: self
* @flags: flags to set
*
* Set @flags in @worker->flags and adjust nr_running accordingly.
- *
- * CONTEXT:
- * raw_spin_lock_irq(pool->lock)
*/
static inline void worker_set_flags(struct worker *worker, unsigned int flags)
{
struct worker_pool *pool = worker->pool;
- WARN_ON_ONCE(worker->task != current);
+ lockdep_assert_held(&pool->lock);
/* If transitioning into NOT_RUNNING, adjust nr_running. */
if ((flags & WORKER_NOT_RUNNING) &&
@@ -932,16 +885,13 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags)
* @flags: flags to clear
*
* Clear @flags in @worker->flags and adjust nr_running accordingly.
- *
- * CONTEXT:
- * raw_spin_lock_irq(pool->lock)
*/
static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
{
struct worker_pool *pool = worker->pool;
unsigned int oflags = worker->flags;
- WARN_ON_ONCE(worker->task != current);
+ lockdep_assert_held(&pool->lock);
worker->flags &= ~flags;
@@ -955,6 +905,244 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
pool->nr_running++;
}
+/* Return the first idle worker. Called with pool->lock held. */
+static struct worker *first_idle_worker(struct worker_pool *pool)
+{
+ if (unlikely(list_empty(&pool->idle_list)))
+ return NULL;
+
+ return list_first_entry(&pool->idle_list, struct worker, entry);
+}
+
+/**
+ * worker_enter_idle - enter idle state
+ * @worker: worker which is entering idle state
+ *
+ * @worker is entering idle state. Update stats and idle timer if
+ * necessary.
+ *
+ * LOCKING:
+ * raw_spin_lock_irq(pool->lock).
+ */
+static void worker_enter_idle(struct worker *worker)
+{
+ struct worker_pool *pool = worker->pool;
+
+ if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) ||
+ WARN_ON_ONCE(!list_empty(&worker->entry) &&
+ (worker->hentry.next || worker->hentry.pprev)))
+ return;
+
+ /* can't use worker_set_flags(), also called from create_worker() */
+ worker->flags |= WORKER_IDLE;
+ pool->nr_idle++;
+ worker->last_active = jiffies;
+
+ /* idle_list is LIFO */
+ list_add(&worker->entry, &pool->idle_list);
+
+ if (too_many_workers(pool) && !timer_pending(&pool->idle_timer))
+ mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);
+
+ /* Sanity check nr_running. */
+ WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running);
+}
+
+/**
+ * worker_leave_idle - leave idle state
+ * @worker: worker which is leaving idle state
+ *
+ * @worker is leaving idle state. Update stats.
+ *
+ * LOCKING:
+ * raw_spin_lock_irq(pool->lock).
+ */
+static void worker_leave_idle(struct worker *worker)
+{
+ struct worker_pool *pool = worker->pool;
+
+ if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE)))
+ return;
+ worker_clr_flags(worker, WORKER_IDLE);
+ pool->nr_idle--;
+ list_del_init(&worker->entry);
+}
+
+/**
+ * find_worker_executing_work - find worker which is executing a work
+ * @pool: pool of interest
+ * @work: work to find worker for
+ *
+ * Find a worker which is executing @work on @pool by searching
+ * @pool->busy_hash which is keyed by the address of @work. For a worker
+ * to match, its current execution should match the address of @work and
+ * its work function. This is to avoid unwanted dependency between
+ * unrelated work executions through a work item being recycled while still
+ * being executed.
+ *
+ * This is a bit tricky. A work item may be freed once its execution
+ * starts and nothing prevents the freed area from being recycled for
+ * another work item. If the same work item address ends up being reused
+ * before the original execution finishes, workqueue will identify the
+ * recycled work item as currently executing and make it wait until the
+ * current execution finishes, introducing an unwanted dependency.
+ *
+ * This function checks the work item address and work function to avoid
+ * false positives. Note that this isn't complete as one may construct a
+ * work function which can introduce dependency onto itself through a
+ * recycled work item. Well, if somebody wants to shoot oneself in the
+ * foot that badly, there's only so much we can do, and if such deadlock
+ * actually occurs, it should be easy to locate the culprit work function.
+ *
+ * CONTEXT:
+ * raw_spin_lock_irq(pool->lock).
+ *
+ * Return:
+ * Pointer to worker which is executing @work if found, %NULL
+ * otherwise.
+ */
+static struct worker *find_worker_executing_work(struct worker_pool *pool,
+ struct work_struct *work)
+{
+ struct worker *worker;
+
+ hash_for_each_possible(pool->busy_hash, worker, hentry,
+ (unsigned long)work)
+ if (worker->current_work == work &&
+ worker->current_func == work->func)
+ return worker;
+
+ return NULL;
+}
+
+/**
+ * move_linked_works - move linked works to a list
+ * @work: start of series of works to be scheduled
+ * @head: target list to append @work to
+ * @nextp: out parameter for nested worklist walking
+ *
+ * Schedule linked works starting from @work to @head. Work series to be
+ * scheduled starts at @work and includes any consecutive work with
+ * WORK_STRUCT_LINKED set in its predecessor. See assign_work() for details on
+ * @nextp.
+ *
+ * CONTEXT:
+ * raw_spin_lock_irq(pool->lock).
+ */
+static void move_linked_works(struct work_struct *work, struct list_head *head,
+ struct work_struct **nextp)
+{
+ struct work_struct *n;
+
+ /*
+ * Linked worklist will always end before the end of the list,
+ * use NULL for list head.
+ */
+ list_for_each_entry_safe_from(work, n, NULL, entry) {
+ list_move_tail(&work->entry, head);
+ if (!(*work_data_bits(work) & WORK_STRUCT_LINKED))
+ break;
+ }
+
+ /*
+ * If we're already inside safe list traversal and have moved
+ * multiple works to the scheduled queue, the next position
+ * needs to be updated.
+ */
+ if (nextp)
+ *nextp = n;
+}
+
+/**
+ * assign_work - assign a work item and its linked work items to a worker
+ * @work: work to assign
+ * @worker: worker to assign to
+ * @nextp: out parameter for nested worklist walking
+ *
+ * Assign @work and its linked work items to @worker. If @work is already being
+ * executed by another worker in the same pool, it'll be punted there.
+ *
+ * If @nextp is not NULL, it's updated to point to the next work of the last
+ * scheduled work. This allows assign_work() to be nested inside
+ * list_for_each_entry_safe().
+ *
+ * Returns %true if @work was successfully assigned to @worker. %false if @work
+ * was punted to another worker already executing it.
+ */
+static bool assign_work(struct work_struct *work, struct worker *worker,
+ struct work_struct **nextp)
+{
+ struct worker_pool *pool = worker->pool;
+ struct worker *collision;
+
+ lockdep_assert_held(&pool->lock);
+
+ /*
+ * A single work shouldn't be executed concurrently by multiple workers.
+ * __queue_work() ensures that @work doesn't jump to a different pool
+ * while still running in the previous pool. Here, we should ensure that
+ * @work is not executed concurrently by multiple workers from the same
+ * pool. Check whether anyone is already processing the work. If so,
+ * defer the work to the currently executing one.
+ */
+ collision = find_worker_executing_work(pool, work);
+ if (unlikely(collision)) {
+ move_linked_works(work, &collision->scheduled, nextp);
+ return false;
+ }
+
+ move_linked_works(work, &worker->scheduled, nextp);
+ return true;
+}
+
+/**
+ * kick_pool - wake up an idle worker if necessary
+ * @pool: pool to kick
+ *
+ * @pool may have pending work items. Wake up worker if necessary. Returns
+ * whether a worker was woken up.
+ */
+static bool kick_pool(struct worker_pool *pool)
+{
+ struct worker *worker = first_idle_worker(pool);
+ struct task_struct *p;
+
+ lockdep_assert_held(&pool->lock);
+
+ if (!need_more_worker(pool) || !worker)
+ return false;
+
+ p = worker->task;
+
+#ifdef CONFIG_SMP
+ /*
+ * Idle @worker is about to execute @work and waking up provides an
+ * opportunity to migrate @worker at a lower cost by setting the task's
+ * wake_cpu field. Let's see if we want to move @worker to improve
+ * execution locality.
+ *
+ * We're waking the worker that went idle the latest and there's some
+ * chance that @worker is marked idle but hasn't gone off CPU yet. If
+ * so, setting the wake_cpu won't do anything. As this is a best-effort
+ * optimization and the race window is narrow, let's leave as-is for
+ * now. If this becomes pronounced, we can skip over workers which are
+ * still on cpu when picking an idle worker.
+ *
+ * If @pool has non-strict affinity, @worker might have ended up outside
+ * its affinity scope. Repatriate.
+ */
+ if (!pool->attrs->affn_strict &&
+ !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) {
+ struct work_struct *work = list_first_entry(&pool->worklist,
+ struct work_struct, entry);
+ p->wake_cpu = cpumask_any_distribute(pool->attrs->__pod_cpumask);
+ get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++;
+ }
+#endif
+ wake_up_process(p);
+ return true;
+}
+
#ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT
/*
@@ -1120,10 +1308,9 @@ void wq_worker_sleeping(struct task_struct *task)
}
pool->nr_running--;
- if (need_more_worker(pool)) {
+ if (kick_pool(pool))
worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++;
- wake_up_worker(pool);
- }
+
raw_spin_unlock_irq(&pool->lock);
}
@@ -1171,10 +1358,8 @@ void wq_worker_tick(struct task_struct *task)
wq_cpu_intensive_report(worker->current_func);
pwq->stats[PWQ_STAT_CPU_INTENSIVE]++;
- if (need_more_worker(pool)) {
+ if (kick_pool(pool))
pwq->stats[PWQ_STAT_CM_WAKEUP]++;
- wake_up_worker(pool);
- }
raw_spin_unlock(&pool->lock);
}
@@ -1211,94 +1396,6 @@ work_func_t wq_worker_last_func(struct task_struct *task)
}
/**
- * find_worker_executing_work - find worker which is executing a work
- * @pool: pool of interest
- * @work: work to find worker for
- *
- * Find a worker which is executing @work on @pool by searching
- * @pool->busy_hash which is keyed by the address of @work. For a worker
- * to match, its current execution should match the address of @work and
- * its work function. This is to avoid unwanted dependency between
- * unrelated work executions through a work item being recycled while still
- * being executed.
- *
- * This is a bit tricky. A work item may be freed once its execution
- * starts and nothing prevents the freed area from being recycled for
- * another work item. If the same work item address ends up being reused
- * before the original execution finishes, workqueue will identify the
- * recycled work item as currently executing and make it wait until the
- * current execution finishes, introducing an unwanted dependency.
- *
- * This function checks the work item address and work function to avoid
- * false positives. Note that this isn't complete as one may construct a
- * work function which can introduce dependency onto itself through a
- * recycled work item. Well, if somebody wants to shoot oneself in the
- * foot that badly, there's only so much we can do, and if such deadlock
- * actually occurs, it should be easy to locate the culprit work function.
- *
- * CONTEXT:
- * raw_spin_lock_irq(pool->lock).
- *
- * Return:
- * Pointer to worker which is executing @work if found, %NULL
- * otherwise.
- */
-static struct worker *find_worker_executing_work(struct worker_pool *pool,
- struct work_struct *work)
-{
- struct worker *worker;
-
- hash_for_each_possible(pool->busy_hash, worker, hentry,
- (unsigned long)work)
- if (worker->current_work == work &&
- worker->current_func == work->func)
- return worker;
-
- return NULL;
-}
-
-/**
- * move_linked_works - move linked works to a list
- * @work: start of series of works to be scheduled
- * @head: target list to append @work to
- * @nextp: out parameter for nested worklist walking
- *
- * Schedule linked works starting from @work to @head. Work series to
- * be scheduled starts at @work and includes any consecutive work with
- * WORK_STRUCT_LINKED set in its predecessor.
- *
- * If @nextp is not NULL, it's updated to point to the next work of
- * the last scheduled work. This allows move_linked_works() to be
- * nested inside outer list_for_each_entry_safe().
- *
- * CONTEXT:
- * raw_spin_lock_irq(pool->lock).
- */
-static void move_linked_works(struct work_struct *work, struct list_head *head,
- struct work_struct **nextp)
-{
- struct work_struct *n;
-
- /*
- * Linked worklist will always end before the end of the list,
- * use NULL for list head.
- */
- list_for_each_entry_safe_from(work, n, NULL, entry) {
- list_move_tail(&work->entry, head);
- if (!(*work_data_bits(work) & WORK_STRUCT_LINKED))
- break;
- }
-
- /*
- * If we're already inside safe list traversal and have moved
- * multiple works to the scheduled queue, the next position
- * needs to be updated.
- */
- if (nextp)
- *nextp = n;
-}
-
-/**
* get_pwq - get an extra reference on the specified pool_workqueue
* @pwq: pool_workqueue to get
*
@@ -1324,17 +1421,11 @@ static void put_pwq(struct pool_workqueue *pwq)
lockdep_assert_held(&pwq->pool->lock);
if (likely(--pwq->refcnt))
return;
- if (WARN_ON_ONCE(!(pwq->wq->flags & WQ_UNBOUND)))
- return;
/*
- * @pwq can't be released under pool->lock, bounce to
- * pwq_unbound_release_workfn(). This never recurses on the same
- * pool->lock as this path is taken only for unbound workqueues and
- * the release work item is scheduled on a per-cpu workqueue. To
- * avoid lockdep warning, unbound pool->locks are given lockdep
- * subclass of 1 in get_unbound_pool().
+ * @pwq can't be released under pool->lock, bounce to a dedicated
+ * kthread_worker to avoid A-A deadlocks.
*/
- schedule_work(&pwq->unbound_release_work);
+ kthread_queue_work(pwq_release_worker, &pwq->release_work);
}
/**
@@ -1550,7 +1641,7 @@ fail:
static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
struct list_head *head, unsigned int extra_flags)
{
- struct worker_pool *pool = pwq->pool;
+ debug_work_activate(work);
/* record the work call stack in order to print it in KASAN reports */
kasan_record_aux_stack_noalloc(work);
@@ -1559,9 +1650,6 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
set_work_pwq(work, pwq, extra_flags);
list_add_tail(&work->entry, head);
get_pwq(pwq);
-
- if (__need_more_worker(pool))
- wake_up_worker(pool);
}
/*
@@ -1596,9 +1684,6 @@ static int wq_select_unbound_cpu(int cpu)
pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n");
}
- if (cpumask_empty(wq_unbound_cpumask))
- return cpu;
-
new_cpu = __this_cpu_read(wq_rr_cpu_last);
new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
if (unlikely(new_cpu >= nr_cpu_ids)) {
@@ -1615,8 +1700,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
struct work_struct *work)
{
struct pool_workqueue *pwq;
- struct worker_pool *last_pool;
- struct list_head *worklist;
+ struct worker_pool *last_pool, *pool;
unsigned int work_flags;
unsigned int req_cpu = cpu;
@@ -1640,23 +1724,23 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
rcu_read_lock();
retry:
/* pwq which will be used unless @work is executing elsewhere */
- if (wq->flags & WQ_UNBOUND) {
- if (req_cpu == WORK_CPU_UNBOUND)
+ if (req_cpu == WORK_CPU_UNBOUND) {
+ if (wq->flags & WQ_UNBOUND)
cpu = wq_select_unbound_cpu(raw_smp_processor_id());
- pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
- } else {
- if (req_cpu == WORK_CPU_UNBOUND)
+ else
cpu = raw_smp_processor_id();
- pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
}
+ pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu));
+ pool = pwq->pool;
+
/*
* If @work was previously on a different pool, it might still be
* running there, in which case the work needs to be queued on that
* pool to guarantee non-reentrancy.
*/
last_pool = get_work_pool(work);
- if (last_pool && last_pool != pwq->pool) {
+ if (last_pool && last_pool != pool) {
struct worker *worker;
raw_spin_lock(&last_pool->lock);
@@ -1665,26 +1749,27 @@ retry:
if (worker && worker->current_pwq->wq == wq) {
pwq = worker->current_pwq;
+ pool = pwq->pool;
+ WARN_ON_ONCE(pool != last_pool);
} else {
/* meh... not running there, queue here */
raw_spin_unlock(&last_pool->lock);
- raw_spin_lock(&pwq->pool->lock);
+ raw_spin_lock(&pool->lock);
}
} else {
- raw_spin_lock(&pwq->pool->lock);
+ raw_spin_lock(&pool->lock);
}
/*
- * pwq is determined and locked. For unbound pools, we could have
- * raced with pwq release and it could already be dead. If its
- * refcnt is zero, repeat pwq selection. Note that pwqs never die
- * without another pwq replacing it in the numa_pwq_tbl or while
- * work items are executing on it, so the retrying is guaranteed to
- * make forward-progress.
+ * pwq is determined and locked. For unbound pools, we could have raced
+ * with pwq release and it could already be dead. If its refcnt is zero,
+ * repeat pwq selection. Note that unbound pwqs never die without
+ * another pwq replacing it in cpu_pwq or while work items are executing
+ * on it, so the retrying is guaranteed to make forward-progress.
*/
if (unlikely(!pwq->refcnt)) {
if (wq->flags & WQ_UNBOUND) {
- raw_spin_unlock(&pwq->pool->lock);
+ raw_spin_unlock(&pool->lock);
cpu_relax();
goto retry;
}
@@ -1703,21 +1788,20 @@ retry:
work_flags = work_color_to_flags(pwq->work_color);
if (likely(pwq->nr_active < pwq->max_active)) {
+ if (list_empty(&pool->worklist))
+ pool->watchdog_ts = jiffies;
+
trace_workqueue_activate_work(work);
pwq->nr_active++;
- worklist = &pwq->pool->worklist;
- if (list_empty(worklist))
- pwq->pool->watchdog_ts = jiffies;
+ insert_work(pwq, work, &pool->worklist, work_flags);
+ kick_pool(pool);
} else {
work_flags |= WORK_STRUCT_INACTIVE;
- worklist = &pwq->inactive_works;
+ insert_work(pwq, work, &pwq->inactive_works, work_flags);
}
- debug_work_activate(work);
- insert_work(pwq, work, worklist, work_flags);
-
out:
- raw_spin_unlock(&pwq->pool->lock);
+ raw_spin_unlock(&pool->lock);
rcu_read_unlock();
}
@@ -1754,7 +1838,7 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
EXPORT_SYMBOL(queue_work_on);
/**
- * workqueue_select_cpu_near - Select a CPU based on NUMA node
+ * select_numa_node_cpu - Select a CPU based on NUMA node
* @node: NUMA node ID that we want to select a CPU from
*
* This function will attempt to find a "random" cpu available on a given
@@ -1762,14 +1846,10 @@ EXPORT_SYMBOL(queue_work_on);
* WORK_CPU_UNBOUND indicating that we should just schedule to any
* available CPU if we need to schedule this work.
*/
-static int workqueue_select_cpu_near(int node)
+static int select_numa_node_cpu(int node)
{
int cpu;
- /* No point in doing this if NUMA isn't enabled for workqueues */
- if (!wq_numa_enabled)
- return WORK_CPU_UNBOUND;
-
/* Delay binding to CPU if node is not valid or online */
if (node < 0 || node >= MAX_NUMNODES || !node_online(node))
return WORK_CPU_UNBOUND;
@@ -1826,7 +1906,7 @@ bool queue_work_node(int node, struct workqueue_struct *wq,
local_irq_save(flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
- int cpu = workqueue_select_cpu_near(node);
+ int cpu = select_numa_node_cpu(node);
__queue_work(cpu, wq, work);
ret = true;
@@ -1981,60 +2061,6 @@ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork)
}
EXPORT_SYMBOL(queue_rcu_work);
-/**
- * worker_enter_idle - enter idle state
- * @worker: worker which is entering idle state
- *
- * @worker is entering idle state. Update stats and idle timer if
- * necessary.
- *
- * LOCKING:
- * raw_spin_lock_irq(pool->lock).
- */
-static void worker_enter_idle(struct worker *worker)
-{
- struct worker_pool *pool = worker->pool;
-
- if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) ||
- WARN_ON_ONCE(!list_empty(&worker->entry) &&
- (worker->hentry.next || worker->hentry.pprev)))
- return;
-
- /* can't use worker_set_flags(), also called from create_worker() */
- worker->flags |= WORKER_IDLE;
- pool->nr_idle++;
- worker->last_active = jiffies;
-
- /* idle_list is LIFO */
- list_add(&worker->entry, &pool->idle_list);
-
- if (too_many_workers(pool) && !timer_pending(&pool->idle_timer))
- mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);
-
- /* Sanity check nr_running. */
- WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running);
-}
-
-/**
- * worker_leave_idle - leave idle state
- * @worker: worker which is leaving idle state
- *
- * @worker is leaving idle state. Update stats.
- *
- * LOCKING:
- * raw_spin_lock_irq(pool->lock).
- */
-static void worker_leave_idle(struct worker *worker)
-{
- struct worker_pool *pool = worker->pool;
-
- if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE)))
- return;
- worker_clr_flags(worker, WORKER_IDLE);
- pool->nr_idle--;
- list_del_init(&worker->entry);
-}
-
static struct worker *alloc_worker(int node)
{
struct worker *worker;
@@ -2050,6 +2076,14 @@ static struct worker *alloc_worker(int node)
return worker;
}
+static cpumask_t *pool_allowed_cpus(struct worker_pool *pool)
+{
+ if (pool->cpu < 0 && pool->attrs->affn_strict)
+ return pool->attrs->__pod_cpumask;
+ else
+ return pool->attrs->cpumask;
+}
+
/**
* worker_attach_to_pool() - attach a worker to a pool
* @worker: worker to be attached
@@ -2075,7 +2109,7 @@ static void worker_attach_to_pool(struct worker *worker,
kthread_set_per_cpu(worker->task, pool->cpu);
if (worker->rescue_wq)
- set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
+ set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool));
list_add_tail(&worker->node, &pool->workers);
worker->pool = pool;
@@ -2129,7 +2163,7 @@ static struct worker *create_worker(struct worker_pool *pool)
{
struct worker *worker;
int id;
- char id_buf[16];
+ char id_buf[23];
/* ID is needed to determine kthread name */
id = ida_alloc(&pool->worker_ida, GFP_KERNEL);
@@ -2167,16 +2201,25 @@ static struct worker *create_worker(struct worker_pool *pool)
}
set_user_nice(worker->task, pool->attrs->nice);
- kthread_bind_mask(worker->task, pool->attrs->cpumask);
+ kthread_bind_mask(worker->task, pool_allowed_cpus(pool));
/* successful, attach the worker to the pool */
worker_attach_to_pool(worker, pool);
/* start the newly created worker */
raw_spin_lock_irq(&pool->lock);
+
worker->pool->nr_workers++;
worker_enter_idle(worker);
+ kick_pool(pool);
+
+ /*
+ * @worker is waiting on a completion in kthread() and will trigger hung
+ * check if not woken up soon. As kick_pool() might not have waken it
+ * up, wake it up explicitly once more.
+ */
wake_up_process(worker->task);
+
raw_spin_unlock_irq(&pool->lock);
return worker;
@@ -2304,9 +2347,8 @@ static void idle_worker_timeout(struct timer_list *t)
static void idle_cull_fn(struct work_struct *work)
{
struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work);
- struct list_head cull_list;
+ LIST_HEAD(cull_list);
- INIT_LIST_HEAD(&cull_list);
/*
* Grabbing wq_pool_attach_mutex here ensures an already-running worker
* cannot proceed beyong worker_detach_from_pool() in its self-destruct
@@ -2495,7 +2537,6 @@ __acquires(&pool->lock)
struct pool_workqueue *pwq = get_work_pwq(work);
struct worker_pool *pool = worker->pool;
unsigned long work_data;
- struct worker *collision;
#ifdef CONFIG_LOCKDEP
/*
* It is permissible to free the struct work_struct from
@@ -2512,18 +2553,6 @@ __acquires(&pool->lock)
WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) &&
raw_smp_processor_id() != pool->cpu);
- /*
- * A single work shouldn't be executed concurrently by
- * multiple workers on a single cpu. Check whether anyone is
- * already processing the work. If so, defer the work to the
- * currently executing one.
- */
- collision = find_worker_executing_work(pool, work);
- if (unlikely(collision)) {
- move_linked_works(work, &collision->scheduled, NULL);
- return;
- }
-
/* claim and dequeue */
debug_work_deactivate(work);
hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work);
@@ -2552,14 +2581,12 @@ __acquires(&pool->lock)
worker_set_flags(worker, WORKER_CPU_INTENSIVE);
/*
- * Wake up another worker if necessary. The condition is always
- * false for normal per-cpu workers since nr_running would always
- * be >= 1 at this point. This is used to chain execution of the
- * pending work items for WORKER_NOT_RUNNING workers such as the
- * UNBOUND and CPU_INTENSIVE ones.
+ * Kick @pool if necessary. It's always noop for per-cpu worker pools
+ * since nr_running would always be >= 1 at this point. This is used to
+ * chain execution of the pending work items for WORKER_NOT_RUNNING
+ * workers such as the UNBOUND and CPU_INTENSIVE ones.
*/
- if (need_more_worker(pool))
- wake_up_worker(pool);
+ kick_pool(pool);
/*
* Record the last pool and clear PENDING which should be the last
@@ -2569,6 +2596,7 @@ __acquires(&pool->lock)
*/
set_work_pool_and_clear_pending(work, pool->id);
+ pwq->stats[PWQ_STAT_STARTED]++;
raw_spin_unlock_irq(&pool->lock);
lock_map_acquire(&pwq->wq->lockdep_map);
@@ -2595,7 +2623,6 @@ __acquires(&pool->lock)
* workqueues), so hiding them isn't a problem.
*/
lockdep_invariant_state(true);
- pwq->stats[PWQ_STAT_STARTED]++;
trace_workqueue_execute_start(work);
worker->current_func(work);
/*
@@ -2661,9 +2688,15 @@ __acquires(&pool->lock)
*/
static void process_scheduled_works(struct worker *worker)
{
- while (!list_empty(&worker->scheduled)) {
- struct work_struct *work = list_first_entry(&worker->scheduled,
- struct work_struct, entry);
+ struct work_struct *work;
+ bool first = true;
+
+ while ((work = list_first_entry_or_null(&worker->scheduled,
+ struct work_struct, entry))) {
+ if (first) {
+ worker->pool->watchdog_ts = jiffies;
+ first = false;
+ }
process_one_work(worker, work);
}
}
@@ -2744,17 +2777,8 @@ recheck:
list_first_entry(&pool->worklist,
struct work_struct, entry);
- pool->watchdog_ts = jiffies;
-
- if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) {
- /* optimization path, not strictly necessary */
- process_one_work(worker, work);
- if (unlikely(!list_empty(&worker->scheduled)))
- process_scheduled_works(worker);
- } else {
- move_linked_works(work, &worker->scheduled, NULL);
+ if (assign_work(work, worker, NULL))
process_scheduled_works(worker);
- }
} while (keep_working(pool));
worker_set_flags(worker, WORKER_PREP);
@@ -2798,7 +2822,6 @@ static int rescuer_thread(void *__rescuer)
{
struct worker *rescuer = __rescuer;
struct workqueue_struct *wq = rescuer->rescue_wq;
- struct list_head *scheduled = &rescuer->scheduled;
bool should_stop;
set_user_nice(current, RESCUER_NICE_LEVEL);
@@ -2829,7 +2852,6 @@ repeat:
struct pool_workqueue, mayday_node);
struct worker_pool *pool = pwq->pool;
struct work_struct *work, *n;
- bool first = true;
__set_current_state(TASK_RUNNING);
list_del_init(&pwq->mayday_node);
@@ -2844,18 +2866,14 @@ repeat:
* Slurp in all works issued via this workqueue and
* process'em.
*/
- WARN_ON_ONCE(!list_empty(scheduled));
+ WARN_ON_ONCE(!list_empty(&rescuer->scheduled));
list_for_each_entry_safe(work, n, &pool->worklist, entry) {
- if (get_work_pwq(work) == pwq) {
- if (first)
- pool->watchdog_ts = jiffies;
- move_linked_works(work, scheduled, &n);
+ if (get_work_pwq(work) == pwq &&
+ assign_work(work, rescuer, &n))
pwq->stats[PWQ_STAT_RESCUED]++;
- }
- first = false;
}
- if (!list_empty(scheduled)) {
+ if (!list_empty(&rescuer->scheduled)) {
process_scheduled_works(rescuer);
/*
@@ -2888,12 +2906,10 @@ repeat:
put_pwq(pwq);
/*
- * Leave this pool. If need_more_worker() is %true, notify a
- * regular worker; otherwise, we end up with 0 concurrency
- * and stalling the execution.
+ * Leave this pool. Notify regular workers; otherwise, we end up
+ * with 0 concurrency and stalling the execution.
*/
- if (need_more_worker(pool))
- wake_up_worker(pool);
+ kick_pool(pool);
raw_spin_unlock_irq(&pool->lock);
@@ -3028,7 +3044,6 @@ static void insert_wq_barrier(struct pool_workqueue *pwq,
pwq->nr_in_flight[work_color]++;
work_flags |= work_color_to_flags(work_color);
- debug_work_activate(&barr->work);
insert_work(pwq, &barr->work, head, work_flags);
}
@@ -3691,6 +3706,7 @@ void free_workqueue_attrs(struct workqueue_attrs *attrs)
{
if (attrs) {
free_cpumask_var(attrs->cpumask);
+ free_cpumask_var(attrs->__pod_cpumask);
kfree(attrs);
}
}
@@ -3712,8 +3728,11 @@ struct workqueue_attrs *alloc_workqueue_attrs(void)
goto fail;
if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL))
goto fail;
+ if (!alloc_cpumask_var(&attrs->__pod_cpumask, GFP_KERNEL))
+ goto fail;
cpumask_copy(attrs->cpumask, cpu_possible_mask);
+ attrs->affn_scope = WQ_AFFN_DFL;
return attrs;
fail:
free_workqueue_attrs(attrs);
@@ -3725,12 +3744,26 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to,
{
to->nice = from->nice;
cpumask_copy(to->cpumask, from->cpumask);
+ cpumask_copy(to->__pod_cpumask, from->__pod_cpumask);
+ to->affn_strict = from->affn_strict;
+
/*
- * Unlike hash and equality test, this function doesn't ignore
- * ->no_numa as it is used for both pool and wq attrs. Instead,
- * get_unbound_pool() explicitly clears ->no_numa after copying.
+ * Unlike hash and equality test, copying shouldn't ignore wq-only
+ * fields as copying is used for both pool and wq attrs. Instead,
+ * get_unbound_pool() explicitly clears the fields.
*/
- to->no_numa = from->no_numa;
+ to->affn_scope = from->affn_scope;
+ to->ordered = from->ordered;
+}
+
+/*
+ * Some attrs fields are workqueue-only. Clear them for worker_pool's. See the
+ * comments in 'struct workqueue_attrs' definition.
+ */
+static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs)
+{
+ attrs->affn_scope = WQ_AFFN_NR_TYPES;
+ attrs->ordered = false;
}
/* hash value of the content of @attr */
@@ -3741,6 +3774,9 @@ static u32 wqattrs_hash(const struct workqueue_attrs *attrs)
hash = jhash_1word(attrs->nice, hash);
hash = jhash(cpumask_bits(attrs->cpumask),
BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash);
+ hash = jhash(cpumask_bits(attrs->__pod_cpumask),
+ BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash);
+ hash = jhash_1word(attrs->affn_strict, hash);
return hash;
}
@@ -3752,9 +3788,57 @@ static bool wqattrs_equal(const struct workqueue_attrs *a,
return false;
if (!cpumask_equal(a->cpumask, b->cpumask))
return false;
+ if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask))
+ return false;
+ if (a->affn_strict != b->affn_strict)
+ return false;
return true;
}
+/* Update @attrs with actually available CPUs */
+static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs,
+ const cpumask_t *unbound_cpumask)
+{
+ /*
+ * Calculate the effective CPU mask of @attrs given @unbound_cpumask. If
+ * @attrs->cpumask doesn't overlap with @unbound_cpumask, we fallback to
+ * @unbound_cpumask.
+ */
+ cpumask_and(attrs->cpumask, attrs->cpumask, unbound_cpumask);
+ if (unlikely(cpumask_empty(attrs->cpumask)))
+ cpumask_copy(attrs->cpumask, unbound_cpumask);
+}
+
+/* find wq_pod_type to use for @attrs */
+static const struct wq_pod_type *
+wqattrs_pod_type(const struct workqueue_attrs *attrs)
+{
+ enum wq_affn_scope scope;
+ struct wq_pod_type *pt;
+
+ /* to synchronize access to wq_affn_dfl */
+ lockdep_assert_held(&wq_pool_mutex);
+
+ if (attrs->affn_scope == WQ_AFFN_DFL)
+ scope = wq_affn_dfl;
+ else
+ scope = attrs->affn_scope;
+
+ pt = &wq_pod_types[scope];
+
+ if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) &&
+ likely(pt->nr_pods))
+ return pt;
+
+ /*
+ * Before workqueue_init_topology(), only SYSTEM is available which is
+ * initialized in workqueue_init_early().
+ */
+ pt = &wq_pod_types[WQ_AFFN_SYSTEM];
+ BUG_ON(!pt->nr_pods);
+ return pt;
+}
+
/**
* init_worker_pool - initialize a newly zalloc'd worker_pool
* @pool: worker_pool to initialize
@@ -3793,6 +3877,9 @@ static int init_worker_pool(struct worker_pool *pool)
pool->attrs = alloc_workqueue_attrs();
if (!pool->attrs)
return -ENOMEM;
+
+ wqattrs_clear_for_pool(pool->attrs);
+
return 0;
}
@@ -3840,12 +3927,8 @@ static void rcu_free_wq(struct rcu_head *rcu)
container_of(rcu, struct workqueue_struct, rcu);
wq_free_lockdep(wq);
-
- if (!(wq->flags & WQ_UNBOUND))
- free_percpu(wq->cpu_pwqs);
- else
- free_workqueue_attrs(wq->unbound_attrs);
-
+ free_percpu(wq->cpu_pwq);
+ free_workqueue_attrs(wq->unbound_attrs);
kfree(wq);
}
@@ -3872,10 +3955,8 @@ static void rcu_free_pool(struct rcu_head *rcu)
static void put_unbound_pool(struct worker_pool *pool)
{
DECLARE_COMPLETION_ONSTACK(detach_completion);
- struct list_head cull_list;
struct worker *worker;
-
- INIT_LIST_HEAD(&cull_list);
+ LIST_HEAD(cull_list);
lockdep_assert_held(&wq_pool_mutex);
@@ -3959,10 +4040,10 @@ static void put_unbound_pool(struct worker_pool *pool)
*/
static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
{
+ struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA];
u32 hash = wqattrs_hash(attrs);
struct worker_pool *pool;
- int node;
- int target_node = NUMA_NO_NODE;
+ int pod, node = NUMA_NO_NODE;
lockdep_assert_held(&wq_pool_mutex);
@@ -3974,31 +4055,22 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
}
}
- /* if cpumask is contained inside a NUMA node, we belong to that node */
- if (wq_numa_enabled) {
- for_each_node(node) {
- if (cpumask_subset(attrs->cpumask,
- wq_numa_possible_cpumask[node])) {
- target_node = node;
- break;
- }
+ /* If __pod_cpumask is contained inside a NUMA pod, that's our node */
+ for (pod = 0; pod < pt->nr_pods; pod++) {
+ if (cpumask_subset(attrs->__pod_cpumask, pt->pod_cpus[pod])) {
+ node = pt->pod_node[pod];
+ break;
}
}
/* nope, create a new one */
- pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_node);
+ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, node);
if (!pool || init_worker_pool(pool) < 0)
goto fail;
- lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */
+ pool->node = node;
copy_workqueue_attrs(pool->attrs, attrs);
- pool->node = target_node;
-
- /*
- * no_numa isn't a worker_pool attribute, always clear it. See
- * 'struct workqueue_attrs' comments for detail.
- */
- pool->attrs->no_numa = false;
+ wqattrs_clear_for_pool(pool->attrs);
if (worker_pool_assign_id(pool) < 0)
goto fail;
@@ -4024,34 +4096,33 @@ static void rcu_free_pwq(struct rcu_head *rcu)
}
/*
- * Scheduled on system_wq by put_pwq() when an unbound pwq hits zero refcnt
- * and needs to be destroyed.
+ * Scheduled on pwq_release_worker by put_pwq() when an unbound pwq hits zero
+ * refcnt and needs to be destroyed.
*/
-static void pwq_unbound_release_workfn(struct work_struct *work)
+static void pwq_release_workfn(struct kthread_work *work)
{
struct pool_workqueue *pwq = container_of(work, struct pool_workqueue,
- unbound_release_work);
+ release_work);
struct workqueue_struct *wq = pwq->wq;
struct worker_pool *pool = pwq->pool;
bool is_last = false;
/*
- * when @pwq is not linked, it doesn't hold any reference to the
+ * When @pwq is not linked, it doesn't hold any reference to the
* @wq, and @wq is invalid to access.
*/
if (!list_empty(&pwq->pwqs_node)) {
- if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
- return;
-
mutex_lock(&wq->mutex);
list_del_rcu(&pwq->pwqs_node);
is_last = list_empty(&wq->pwqs);
mutex_unlock(&wq->mutex);
}
- mutex_lock(&wq_pool_mutex);
- put_unbound_pool(pool);
- mutex_unlock(&wq_pool_mutex);
+ if (wq->flags & WQ_UNBOUND) {
+ mutex_lock(&wq_pool_mutex);
+ put_unbound_pool(pool);
+ mutex_unlock(&wq_pool_mutex);
+ }
call_rcu(&pwq->rcu, rcu_free_pwq);
@@ -4095,24 +4166,13 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
* is updated and visible.
*/
if (!freezable || !workqueue_freezing) {
- bool kick = false;
-
pwq->max_active = wq->saved_max_active;
while (!list_empty(&pwq->inactive_works) &&
- pwq->nr_active < pwq->max_active) {
+ pwq->nr_active < pwq->max_active)
pwq_activate_first_inactive(pwq);
- kick = true;
- }
- /*
- * Need to kick a worker after thawed or an unbound wq's
- * max_active is bumped. In realtime scenarios, always kicking a
- * worker will cause interference on the isolated cpu cores, so
- * let's kick iff work items were activated.
- */
- if (kick)
- wake_up_worker(pwq->pool);
+ kick_pool(pwq->pool);
} else {
pwq->max_active = 0;
}
@@ -4135,7 +4195,7 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
INIT_LIST_HEAD(&pwq->inactive_works);
INIT_LIST_HEAD(&pwq->pwqs_node);
INIT_LIST_HEAD(&pwq->mayday_node);
- INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn);
+ kthread_init_work(&pwq->release_work, pwq_release_workfn);
}
/* sync @pwq with the current state of its associated wq and link it */
@@ -4183,61 +4243,49 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq,
}
/**
- * wq_calc_node_cpumask - calculate a wq_attrs' cpumask for the specified node
+ * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod
* @attrs: the wq_attrs of the default pwq of the target workqueue
- * @node: the target NUMA node
+ * @cpu: the target CPU
* @cpu_going_down: if >= 0, the CPU to consider as offline
- * @cpumask: outarg, the resulting cpumask
- *
- * Calculate the cpumask a workqueue with @attrs should use on @node. If
- * @cpu_going_down is >= 0, that cpu is considered offline during
- * calculation. The result is stored in @cpumask.
*
- * If NUMA affinity is not enabled, @attrs->cpumask is always used. If
- * enabled and @node has online CPUs requested by @attrs, the returned
- * cpumask is the intersection of the possible CPUs of @node and
- * @attrs->cpumask.
+ * Calculate the cpumask a workqueue with @attrs should use on @pod. If
+ * @cpu_going_down is >= 0, that cpu is considered offline during calculation.
+ * The result is stored in @attrs->__pod_cpumask.
*
- * The caller is responsible for ensuring that the cpumask of @node stays
- * stable.
+ * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled
+ * and @pod has online CPUs requested by @attrs, the returned cpumask is the
+ * intersection of the possible CPUs of @pod and @attrs->cpumask.
*
- * Return: %true if the resulting @cpumask is different from @attrs->cpumask,
- * %false if equal.
+ * The caller is responsible for ensuring that the cpumask of @pod stays stable.
*/
-static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node,
- int cpu_going_down, cpumask_t *cpumask)
+static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu,
+ int cpu_going_down)
{
- if (!wq_numa_enabled || attrs->no_numa)
- goto use_dfl;
+ const struct wq_pod_type *pt = wqattrs_pod_type(attrs);
+ int pod = pt->cpu_pod[cpu];
- /* does @node have any online CPUs @attrs wants? */
- cpumask_and(cpumask, cpumask_of_node(node), attrs->cpumask);
+ /* does @pod have any online CPUs @attrs wants? */
+ cpumask_and(attrs->__pod_cpumask, pt->pod_cpus[pod], attrs->cpumask);
+ cpumask_and(attrs->__pod_cpumask, attrs->__pod_cpumask, cpu_online_mask);
if (cpu_going_down >= 0)
- cpumask_clear_cpu(cpu_going_down, cpumask);
+ cpumask_clear_cpu(cpu_going_down, attrs->__pod_cpumask);
- if (cpumask_empty(cpumask))
- goto use_dfl;
+ if (cpumask_empty(attrs->__pod_cpumask)) {
+ cpumask_copy(attrs->__pod_cpumask, attrs->cpumask);
+ return;
+ }
- /* yeap, return possible CPUs in @node that @attrs wants */
- cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]);
+ /* yeap, return possible CPUs in @pod that @attrs wants */
+ cpumask_and(attrs->__pod_cpumask, attrs->cpumask, pt->pod_cpus[pod]);
- if (cpumask_empty(cpumask)) {
+ if (cpumask_empty(attrs->__pod_cpumask))
pr_warn_once("WARNING: workqueue cpumask: online intersect > "
"possible intersect\n");
- return false;
- }
-
- return !cpumask_equal(cpumask, attrs->cpumask);
-
-use_dfl:
- cpumask_copy(cpumask, attrs->cpumask);
- return false;
}
-/* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */
-static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq,
- int node,
- struct pool_workqueue *pwq)
+/* install @pwq into @wq's cpu_pwq and return the old pwq */
+static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq,
+ int cpu, struct pool_workqueue *pwq)
{
struct pool_workqueue *old_pwq;
@@ -4247,8 +4295,8 @@ static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq,
/* link_pwq() can handle duplicate calls */
link_pwq(pwq);
- old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]);
- rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq);
+ old_pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu));
+ rcu_assign_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu), pwq);
return old_pwq;
}
@@ -4265,10 +4313,10 @@ struct apply_wqattrs_ctx {
static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx)
{
if (ctx) {
- int node;
+ int cpu;
- for_each_node(node)
- put_pwq_unlocked(ctx->pwq_tbl[node]);
+ for_each_possible_cpu(cpu)
+ put_pwq_unlocked(ctx->pwq_tbl[cpu]);
put_pwq_unlocked(ctx->dfl_pwq);
free_workqueue_attrs(ctx->attrs);
@@ -4284,76 +4332,64 @@ apply_wqattrs_prepare(struct workqueue_struct *wq,
const cpumask_var_t unbound_cpumask)
{
struct apply_wqattrs_ctx *ctx;
- struct workqueue_attrs *new_attrs, *tmp_attrs;
- int node;
+ struct workqueue_attrs *new_attrs;
+ int cpu;
lockdep_assert_held(&wq_pool_mutex);
- ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL);
+ if (WARN_ON(attrs->affn_scope < 0 ||
+ attrs->affn_scope >= WQ_AFFN_NR_TYPES))
+ return ERR_PTR(-EINVAL);
+
+ ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_cpu_ids), GFP_KERNEL);
new_attrs = alloc_workqueue_attrs();
- tmp_attrs = alloc_workqueue_attrs();
- if (!ctx || !new_attrs || !tmp_attrs)
+ if (!ctx || !new_attrs)
goto out_free;
/*
- * Calculate the attrs of the default pwq with unbound_cpumask
- * which is wq_unbound_cpumask or to set to wq_unbound_cpumask.
- * If the user configured cpumask doesn't overlap with the
- * wq_unbound_cpumask, we fallback to the wq_unbound_cpumask.
- */
- copy_workqueue_attrs(new_attrs, attrs);
- cpumask_and(new_attrs->cpumask, new_attrs->cpumask, unbound_cpumask);
- if (unlikely(cpumask_empty(new_attrs->cpumask)))
- cpumask_copy(new_attrs->cpumask, unbound_cpumask);
-
- /*
- * We may create multiple pwqs with differing cpumasks. Make a
- * copy of @new_attrs which will be modified and used to obtain
- * pools.
- */
- copy_workqueue_attrs(tmp_attrs, new_attrs);
-
- /*
* If something goes wrong during CPU up/down, we'll fall back to
* the default pwq covering whole @attrs->cpumask. Always create
* it even if we don't use it immediately.
*/
+ copy_workqueue_attrs(new_attrs, attrs);
+ wqattrs_actualize_cpumask(new_attrs, unbound_cpumask);
+ cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask);
ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs);
if (!ctx->dfl_pwq)
goto out_free;
- for_each_node(node) {
- if (wq_calc_node_cpumask(new_attrs, node, -1, tmp_attrs->cpumask)) {
- ctx->pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs);
- if (!ctx->pwq_tbl[node])
- goto out_free;
- } else {
+ for_each_possible_cpu(cpu) {
+ if (new_attrs->ordered) {
ctx->dfl_pwq->refcnt++;
- ctx->pwq_tbl[node] = ctx->dfl_pwq;
+ ctx->pwq_tbl[cpu] = ctx->dfl_pwq;
+ } else {
+ wq_calc_pod_cpumask(new_attrs, cpu, -1);
+ ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, new_attrs);
+ if (!ctx->pwq_tbl[cpu])
+ goto out_free;
}
}
/* save the user configured attrs and sanitize it. */
copy_workqueue_attrs(new_attrs, attrs);
cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask);
+ cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask);
ctx->attrs = new_attrs;
ctx->wq = wq;
- free_workqueue_attrs(tmp_attrs);
return ctx;
out_free:
- free_workqueue_attrs(tmp_attrs);
free_workqueue_attrs(new_attrs);
apply_wqattrs_cleanup(ctx);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
/* set attrs and install prepared pwqs, @ctx points to old pwqs on return */
static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
{
- int node;
+ int cpu;
/* all pwqs have been created successfully, let's install'em */
mutex_lock(&ctx->wq->mutex);
@@ -4361,9 +4397,9 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs);
/* save the previous pwq and install the new one */
- for_each_node(node)
- ctx->pwq_tbl[node] = numa_pwq_tbl_install(ctx->wq, node,
- ctx->pwq_tbl[node]);
+ for_each_possible_cpu(cpu)
+ ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu,
+ ctx->pwq_tbl[cpu]);
/* @dfl_pwq might not have been used, ensure it's linked */
link_pwq(ctx->dfl_pwq);
@@ -4403,8 +4439,8 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
}
ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask);
- if (!ctx)
- return -ENOMEM;
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
/* the ctx has been prepared successfully, let's commit it */
apply_wqattrs_commit(ctx);
@@ -4418,12 +4454,11 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
* @wq: the target workqueue
* @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs()
*
- * Apply @attrs to an unbound workqueue @wq. Unless disabled, on NUMA
- * machines, this function maps a separate pwq to each NUMA node with
- * possibles CPUs in @attrs->cpumask so that work items are affine to the
- * NUMA node it was issued on. Older pwqs are released as in-flight work
- * items finish. Note that a work item which repeatedly requeues itself
- * back-to-back will stay on its current pwq.
+ * Apply @attrs to an unbound workqueue @wq. Unless disabled, this function maps
+ * a separate pwq to each CPU pod with possibles CPUs in @attrs->cpumask so that
+ * work items are affine to the pod it was issued on. Older pwqs are released as
+ * in-flight work items finish. Note that a work item which repeatedly requeues
+ * itself back-to-back will stay on its current pwq.
*
* Performs GFP_KERNEL allocations.
*
@@ -4446,40 +4481,37 @@ int apply_workqueue_attrs(struct workqueue_struct *wq,
}
/**
- * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug
+ * wq_update_pod - update pod affinity of a wq for CPU hot[un]plug
* @wq: the target workqueue
- * @cpu: the CPU coming up or going down
+ * @cpu: the CPU to update pool association for
+ * @hotplug_cpu: the CPU coming up or going down
* @online: whether @cpu is coming up or going down
*
* This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and
- * %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update NUMA affinity of
+ * %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update pod affinity of
* @wq accordingly.
*
- * If NUMA affinity can't be adjusted due to memory allocation failure, it
- * falls back to @wq->dfl_pwq which may not be optimal but is always
- * correct.
- *
- * Note that when the last allowed CPU of a NUMA node goes offline for a
- * workqueue with a cpumask spanning multiple nodes, the workers which were
- * already executing the work items for the workqueue will lose their CPU
- * affinity and may execute on any CPU. This is similar to how per-cpu
- * workqueues behave on CPU_DOWN. If a workqueue user wants strict
- * affinity, it's the user's responsibility to flush the work item from
- * CPU_DOWN_PREPARE.
+ *
+ * If pod affinity can't be adjusted due to memory allocation failure, it falls
+ * back to @wq->dfl_pwq which may not be optimal but is always correct.
+ *
+ * Note that when the last allowed CPU of a pod goes offline for a workqueue
+ * with a cpumask spanning multiple pods, the workers which were already
+ * executing the work items for the workqueue will lose their CPU affinity and
+ * may execute on any CPU. This is similar to how per-cpu workqueues behave on
+ * CPU_DOWN. If a workqueue user wants strict affinity, it's the user's
+ * responsibility to flush the work item from CPU_DOWN_PREPARE.
*/
-static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
- bool online)
+static void wq_update_pod(struct workqueue_struct *wq, int cpu,
+ int hotplug_cpu, bool online)
{
- int node = cpu_to_node(cpu);
- int cpu_off = online ? -1 : cpu;
+ int off_cpu = online ? -1 : hotplug_cpu;
struct pool_workqueue *old_pwq = NULL, *pwq;
struct workqueue_attrs *target_attrs;
- cpumask_t *cpumask;
lockdep_assert_held(&wq_pool_mutex);
- if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND) ||
- wq->unbound_attrs->no_numa)
+ if (!(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->ordered)
return;
/*
@@ -4487,36 +4519,29 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
* Let's use a preallocated one. The following buf is protected by
* CPU hotplug exclusion.
*/
- target_attrs = wq_update_unbound_numa_attrs_buf;
- cpumask = target_attrs->cpumask;
+ target_attrs = wq_update_pod_attrs_buf;
copy_workqueue_attrs(target_attrs, wq->unbound_attrs);
- pwq = unbound_pwq_by_node(wq, node);
+ wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask);
- /*
- * Let's determine what needs to be done. If the target cpumask is
- * different from the default pwq's, we need to compare it to @pwq's
- * and create a new one if they don't match. If the target cpumask
- * equals the default pwq's, the default pwq should be used.
- */
- if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, cpu_off, cpumask)) {
- if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask))
- return;
- } else {
- goto use_dfl_pwq;
- }
+ /* nothing to do if the target cpumask matches the current pwq */
+ wq_calc_pod_cpumask(target_attrs, cpu, off_cpu);
+ pwq = rcu_dereference_protected(*per_cpu_ptr(wq->cpu_pwq, cpu),
+ lockdep_is_held(&wq_pool_mutex));
+ if (wqattrs_equal(target_attrs, pwq->pool->attrs))
+ return;
/* create a new pwq */
pwq = alloc_unbound_pwq(wq, target_attrs);
if (!pwq) {
- pr_warn("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
+ pr_warn("workqueue: allocation failed while updating CPU pod affinity of \"%s\"\n",
wq->name);
goto use_dfl_pwq;
}
/* Install the new pwq. */
mutex_lock(&wq->mutex);
- old_pwq = numa_pwq_tbl_install(wq, node, pwq);
+ old_pwq = install_unbound_pwq(wq, cpu, pwq);
goto out_unlock;
use_dfl_pwq:
@@ -4524,7 +4549,7 @@ use_dfl_pwq:
raw_spin_lock_irq(&wq->dfl_pwq->pool->lock);
get_pwq(wq->dfl_pwq);
raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock);
- old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq);
+ old_pwq = install_unbound_pwq(wq, cpu, wq->dfl_pwq);
out_unlock:
mutex_unlock(&wq->mutex);
put_pwq_unlocked(old_pwq);
@@ -4535,21 +4560,26 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
bool highpri = wq->flags & WQ_HIGHPRI;
int cpu, ret;
- if (!(wq->flags & WQ_UNBOUND)) {
- wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
- if (!wq->cpu_pwqs)
- return -ENOMEM;
+ wq->cpu_pwq = alloc_percpu(struct pool_workqueue *);
+ if (!wq->cpu_pwq)
+ goto enomem;
+ if (!(wq->flags & WQ_UNBOUND)) {
for_each_possible_cpu(cpu) {
- struct pool_workqueue *pwq =
- per_cpu_ptr(wq->cpu_pwqs, cpu);
- struct worker_pool *cpu_pools =
- per_cpu(cpu_worker_pools, cpu);
+ struct pool_workqueue **pwq_p =
+ per_cpu_ptr(wq->cpu_pwq, cpu);
+ struct worker_pool *pool =
+ &(per_cpu_ptr(cpu_worker_pools, cpu)[highpri]);
+
+ *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL,
+ pool->node);
+ if (!*pwq_p)
+ goto enomem;
- init_pwq(pwq, wq, &cpu_pools[highpri]);
+ init_pwq(*pwq_p, wq, pool);
mutex_lock(&wq->mutex);
- link_pwq(pwq);
+ link_pwq(*pwq_p);
mutex_unlock(&wq->mutex);
}
return 0;
@@ -4567,19 +4597,36 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
}
cpus_read_unlock();
+ /* for unbound pwq, flush the pwq_release_worker ensures that the
+ * pwq_release_workfn() completes before calling kfree(wq).
+ */
+ if (ret)
+ kthread_flush_worker(pwq_release_worker);
+
return ret;
+
+enomem:
+ if (wq->cpu_pwq) {
+ for_each_possible_cpu(cpu) {
+ struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu);
+
+ if (pwq)
+ kmem_cache_free(pwq_cache, pwq);
+ }
+ free_percpu(wq->cpu_pwq);
+ wq->cpu_pwq = NULL;
+ }
+ return -ENOMEM;
}
static int wq_clamp_max_active(int max_active, unsigned int flags,
const char *name)
{
- int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE;
-
- if (max_active < 1 || max_active > lim)
+ if (max_active < 1 || max_active > WQ_MAX_ACTIVE)
pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n",
- max_active, name, 1, lim);
+ max_active, name, 1, WQ_MAX_ACTIVE);
- return clamp_val(max_active, 1, lim);
+ return clamp_val(max_active, 1, WQ_MAX_ACTIVE);
}
/*
@@ -4602,7 +4649,7 @@ static int init_rescuer(struct workqueue_struct *wq)
}
rescuer->rescue_wq = wq;
- rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name);
+ rescuer->task = kthread_create(rescuer_thread, rescuer, "kworker/R-%s", wq->name);
if (IS_ERR(rescuer->task)) {
ret = PTR_ERR(rescuer->task);
pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe",
@@ -4623,17 +4670,15 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
unsigned int flags,
int max_active, ...)
{
- size_t tbl_size = 0;
va_list args;
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
/*
- * Unbound && max_active == 1 used to imply ordered, which is no
- * longer the case on NUMA machines due to per-node pools. While
+ * Unbound && max_active == 1 used to imply ordered, which is no longer
+ * the case on many machines due to per-pod pools. While
* alloc_ordered_workqueue() is the right way to create an ordered
- * workqueue, keep the previous behavior to avoid subtle breakages
- * on NUMA.
+ * workqueue, keep the previous behavior to avoid subtle breakages.
*/
if ((flags & WQ_UNBOUND) && max_active == 1)
flags |= __WQ_ORDERED;
@@ -4643,10 +4688,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
flags |= WQ_UNBOUND;
/* allocate wq and format name */
- if (flags & WQ_UNBOUND)
- tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]);
-
- wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL);
+ wq = kzalloc(sizeof(*wq), GFP_KERNEL);
if (!wq)
return NULL;
@@ -4741,7 +4783,7 @@ static bool pwq_busy(struct pool_workqueue *pwq)
void destroy_workqueue(struct workqueue_struct *wq)
{
struct pool_workqueue *pwq;
- int node;
+ int cpu;
/*
* Remove it from sysfs first so that sanity check failure doesn't
@@ -4800,33 +4842,23 @@ void destroy_workqueue(struct workqueue_struct *wq)
list_del_rcu(&wq->list);
mutex_unlock(&wq_pool_mutex);
- if (!(wq->flags & WQ_UNBOUND)) {
- wq_unregister_lockdep(wq);
- /*
- * The base ref is never dropped on per-cpu pwqs. Directly
- * schedule RCU free.
- */
- call_rcu(&wq->rcu, rcu_free_wq);
- } else {
- /*
- * We're the sole accessor of @wq at this point. Directly
- * access numa_pwq_tbl[] and dfl_pwq to put the base refs.
- * @wq will be freed when the last pwq is released.
- */
- for_each_node(node) {
- pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]);
- RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL);
- put_pwq_unlocked(pwq);
- }
+ /*
+ * We're the sole accessor of @wq. Directly access cpu_pwq and dfl_pwq
+ * to put the base refs. @wq will be auto-destroyed from the last
+ * pwq_put. RCU read lock prevents @wq from going away from under us.
+ */
+ rcu_read_lock();
- /*
- * Put dfl_pwq. @wq may be freed any time after dfl_pwq is
- * put. Don't access it afterwards.
- */
- pwq = wq->dfl_pwq;
- wq->dfl_pwq = NULL;
+ for_each_possible_cpu(cpu) {
+ pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu));
+ RCU_INIT_POINTER(*per_cpu_ptr(wq->cpu_pwq, cpu), NULL);
put_pwq_unlocked(pwq);
}
+
+ put_pwq_unlocked(wq->dfl_pwq);
+ wq->dfl_pwq = NULL;
+
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(destroy_workqueue);
@@ -4903,10 +4935,11 @@ bool current_is_workqueue_rescuer(void)
* unreliable and only useful as advisory hints or for debugging.
*
* If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU.
- * Note that both per-cpu and unbound workqueues may be associated with
- * multiple pool_workqueues which have separate congested states. A
- * workqueue being congested on one CPU doesn't mean the workqueue is also
- * contested on other CPUs / NUMA nodes.
+ *
+ * With the exception of ordered workqueues, all workqueues have per-cpu
+ * pool_workqueues, each with its own congested state. A workqueue being
+ * congested on one CPU doesn't mean that the workqueue is contested on any
+ * other CPUs.
*
* Return:
* %true if congested, %false otherwise.
@@ -4922,12 +4955,9 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
if (cpu == WORK_CPU_UNBOUND)
cpu = smp_processor_id();
- if (!(wq->flags & WQ_UNBOUND))
- pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
- else
- pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
-
+ pwq = *per_cpu_ptr(wq->cpu_pwq, cpu);
ret = !list_empty(&pwq->inactive_works);
+
preempt_enable();
rcu_read_unlock();
@@ -5402,7 +5432,7 @@ static void unbind_workers(int cpu)
* worker blocking could lead to lengthy stalls. Kick off
* unbound chain execution of currently pending work items.
*/
- wake_up_worker(pool);
+ kick_pool(pool);
raw_spin_unlock_irq(&pool->lock);
@@ -5435,7 +5465,7 @@ static void rebind_workers(struct worker_pool *pool)
for_each_pool_worker(worker, pool) {
kthread_set_per_cpu(worker->task, pool->cpu);
WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
- pool->attrs->cpumask) < 0);
+ pool_allowed_cpus(pool)) < 0);
}
raw_spin_lock_irq(&pool->lock);
@@ -5529,9 +5559,18 @@ int workqueue_online_cpu(unsigned int cpu)
mutex_unlock(&wq_pool_attach_mutex);
}
- /* update NUMA affinity of unbound workqueues */
- list_for_each_entry(wq, &workqueues, list)
- wq_update_unbound_numa(wq, cpu, true);
+ /* update pod affinity of unbound workqueues */
+ list_for_each_entry(wq, &workqueues, list) {
+ struct workqueue_attrs *attrs = wq->unbound_attrs;
+
+ if (attrs) {
+ const struct wq_pod_type *pt = wqattrs_pod_type(attrs);
+ int tcpu;
+
+ for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]])
+ wq_update_pod(wq, tcpu, cpu, true);
+ }
+ }
mutex_unlock(&wq_pool_mutex);
return 0;
@@ -5547,10 +5586,19 @@ int workqueue_offline_cpu(unsigned int cpu)
unbind_workers(cpu);
- /* update NUMA affinity of unbound workqueues */
+ /* update pod affinity of unbound workqueues */
mutex_lock(&wq_pool_mutex);
- list_for_each_entry(wq, &workqueues, list)
- wq_update_unbound_numa(wq, cpu, false);
+ list_for_each_entry(wq, &workqueues, list) {
+ struct workqueue_attrs *attrs = wq->unbound_attrs;
+
+ if (attrs) {
+ const struct wq_pod_type *pt = wqattrs_pod_type(attrs);
+ int tcpu;
+
+ for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]])
+ wq_update_pod(wq, tcpu, cpu, false);
+ }
+ }
mutex_unlock(&wq_pool_mutex);
return 0;
@@ -5571,50 +5619,54 @@ static void work_for_cpu_fn(struct work_struct *work)
}
/**
- * work_on_cpu - run a function in thread context on a particular cpu
+ * work_on_cpu_key - run a function in thread context on a particular cpu
* @cpu: the cpu to run on
* @fn: the function to run
* @arg: the function arg
+ * @key: The lock class key for lock debugging purposes
*
* It is up to the caller to ensure that the cpu doesn't go offline.
* The caller must not hold any locks which would prevent @fn from completing.
*
* Return: The value @fn returns.
*/
-long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
+long work_on_cpu_key(int cpu, long (*fn)(void *),
+ void *arg, struct lock_class_key *key)
{
struct work_for_cpu wfc = { .fn = fn, .arg = arg };
- INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
+ INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key);
schedule_work_on(cpu, &wfc.work);
flush_work(&wfc.work);
destroy_work_on_stack(&wfc.work);
return wfc.ret;
}
-EXPORT_SYMBOL_GPL(work_on_cpu);
+EXPORT_SYMBOL_GPL(work_on_cpu_key);
/**
- * work_on_cpu_safe - run a function in thread context on a particular cpu
+ * work_on_cpu_safe_key - run a function in thread context on a particular cpu
* @cpu: the cpu to run on
* @fn: the function to run
* @arg: the function argument
+ * @key: The lock class key for lock debugging purposes
*
* Disables CPU hotplug and calls work_on_cpu(). The caller must not hold
* any locks which would prevent @fn from completing.
*
* Return: The value @fn returns.
*/
-long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg)
+long work_on_cpu_safe_key(int cpu, long (*fn)(void *),
+ void *arg, struct lock_class_key *key)
{
long ret = -ENODEV;
cpus_read_lock();
if (cpu_online(cpu))
- ret = work_on_cpu(cpu, fn, arg);
+ ret = work_on_cpu_key(cpu, fn, arg, key);
cpus_read_unlock();
return ret;
}
-EXPORT_SYMBOL_GPL(work_on_cpu_safe);
+EXPORT_SYMBOL_GPL(work_on_cpu_safe_key);
#endif /* CONFIG_SMP */
#ifdef CONFIG_FREEZER
@@ -5741,13 +5793,17 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
list_for_each_entry(wq, &workqueues, list) {
if (!(wq->flags & WQ_UNBOUND))
continue;
+
/* creating multiple pwqs breaks ordering guarantee */
- if (wq->flags & __WQ_ORDERED)
- continue;
+ if (!list_empty(&wq->pwqs)) {
+ if (wq->flags & __WQ_ORDERED_EXPLICIT)
+ continue;
+ wq->flags &= ~__WQ_ORDERED;
+ }
ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask);
- if (!ctx) {
- ret = -ENOMEM;
+ if (IS_ERR(ctx)) {
+ ret = PTR_ERR(ctx);
break;
}
@@ -5805,21 +5861,72 @@ out_unlock:
return ret;
}
+static int parse_affn_scope(const char *val)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(wq_affn_names); i++) {
+ if (!strncasecmp(val, wq_affn_names[i], strlen(wq_affn_names[i])))
+ return i;
+ }
+ return -EINVAL;
+}
+
+static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp)
+{
+ struct workqueue_struct *wq;
+ int affn, cpu;
+
+ affn = parse_affn_scope(val);
+ if (affn < 0)
+ return affn;
+ if (affn == WQ_AFFN_DFL)
+ return -EINVAL;
+
+ cpus_read_lock();
+ mutex_lock(&wq_pool_mutex);
+
+ wq_affn_dfl = affn;
+
+ list_for_each_entry(wq, &workqueues, list) {
+ for_each_online_cpu(cpu) {
+ wq_update_pod(wq, cpu, cpu, true);
+ }
+ }
+
+ mutex_unlock(&wq_pool_mutex);
+ cpus_read_unlock();
+
+ return 0;
+}
+
+static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp)
+{
+ return scnprintf(buffer, PAGE_SIZE, "%s\n", wq_affn_names[wq_affn_dfl]);
+}
+
+static const struct kernel_param_ops wq_affn_dfl_ops = {
+ .set = wq_affn_dfl_set,
+ .get = wq_affn_dfl_get,
+};
+
+module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644);
+
#ifdef CONFIG_SYSFS
/*
* Workqueues with WQ_SYSFS flag set is visible to userland via
* /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the
* following attributes.
*
- * per_cpu RO bool : whether the workqueue is per-cpu or unbound
- * max_active RW int : maximum number of in-flight work items
+ * per_cpu RO bool : whether the workqueue is per-cpu or unbound
+ * max_active RW int : maximum number of in-flight work items
*
* Unbound workqueues have the following extra attributes.
*
- * pool_ids RO int : the associated pool IDs for each node
- * nice RW int : nice value of the workers
- * cpumask RW mask : bitmask of allowed CPUs for the workers
- * numa RW bool : whether enable NUMA affinity
+ * nice RW int : nice value of the workers
+ * cpumask RW mask : bitmask of allowed CPUs for the workers
+ * affinity_scope RW str : worker CPU affinity scope (cache, numa, none)
+ * affinity_strict RW bool : worker CPU affinity is strict
*/
struct wq_device {
struct workqueue_struct *wq;
@@ -5872,28 +5979,6 @@ static struct attribute *wq_sysfs_attrs[] = {
};
ATTRIBUTE_GROUPS(wq_sysfs);
-static ssize_t wq_pool_ids_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct workqueue_struct *wq = dev_to_wq(dev);
- const char *delim = "";
- int node, written = 0;
-
- cpus_read_lock();
- rcu_read_lock();
- for_each_node(node) {
- written += scnprintf(buf + written, PAGE_SIZE - written,
- "%s%d:%d", delim, node,
- unbound_pwq_by_node(wq, node)->pool->id);
- delim = " ";
- }
- written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
- rcu_read_unlock();
- cpus_read_unlock();
-
- return written;
-}
-
static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -5984,50 +6069,84 @@ out_unlock:
return ret ?: count;
}
-static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t wq_affn_scope_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
int written;
mutex_lock(&wq->mutex);
- written = scnprintf(buf, PAGE_SIZE, "%d\n",
- !wq->unbound_attrs->no_numa);
+ if (wq->unbound_attrs->affn_scope == WQ_AFFN_DFL)
+ written = scnprintf(buf, PAGE_SIZE, "%s (%s)\n",
+ wq_affn_names[WQ_AFFN_DFL],
+ wq_affn_names[wq_affn_dfl]);
+ else
+ written = scnprintf(buf, PAGE_SIZE, "%s\n",
+ wq_affn_names[wq->unbound_attrs->affn_scope]);
mutex_unlock(&wq->mutex);
return written;
}
-static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t wq_affn_scope_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct workqueue_struct *wq = dev_to_wq(dev);
struct workqueue_attrs *attrs;
- int v, ret = -ENOMEM;
+ int affn, ret = -ENOMEM;
- apply_wqattrs_lock();
+ affn = parse_affn_scope(buf);
+ if (affn < 0)
+ return affn;
+ apply_wqattrs_lock();
attrs = wq_sysfs_prep_attrs(wq);
- if (!attrs)
- goto out_unlock;
-
- ret = -EINVAL;
- if (sscanf(buf, "%d", &v) == 1) {
- attrs->no_numa = !v;
+ if (attrs) {
+ attrs->affn_scope = affn;
ret = apply_workqueue_attrs_locked(wq, attrs);
}
+ apply_wqattrs_unlock();
+ free_workqueue_attrs(attrs);
+ return ret ?: count;
+}
-out_unlock:
+static ssize_t wq_affinity_strict_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct workqueue_struct *wq = dev_to_wq(dev);
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n",
+ wq->unbound_attrs->affn_strict);
+}
+
+static ssize_t wq_affinity_strict_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct workqueue_struct *wq = dev_to_wq(dev);
+ struct workqueue_attrs *attrs;
+ int v, ret = -ENOMEM;
+
+ if (sscanf(buf, "%d", &v) != 1)
+ return -EINVAL;
+
+ apply_wqattrs_lock();
+ attrs = wq_sysfs_prep_attrs(wq);
+ if (attrs) {
+ attrs->affn_strict = (bool)v;
+ ret = apply_workqueue_attrs_locked(wq, attrs);
+ }
apply_wqattrs_unlock();
free_workqueue_attrs(attrs);
return ret ?: count;
}
static struct device_attribute wq_sysfs_unbound_attrs[] = {
- __ATTR(pool_ids, 0444, wq_pool_ids_show, NULL),
__ATTR(nice, 0644, wq_nice_show, wq_nice_store),
__ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store),
- __ATTR(numa, 0644, wq_numa_show, wq_numa_store),
+ __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store),
+ __ATTR(affinity_strict, 0644, wq_affinity_strict_show, wq_affinity_strict_store),
__ATTR_NULL,
};
@@ -6393,73 +6512,60 @@ static inline void wq_watchdog_init(void) { }
#endif /* CONFIG_WQ_WATCHDOG */
-static void __init wq_numa_init(void)
+static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask)
{
- cpumask_var_t *tbl;
- int node, cpu;
-
- if (num_possible_nodes() <= 1)
- return;
-
- if (wq_disable_numa) {
- pr_info("workqueue: NUMA affinity support disabled\n");
+ if (!cpumask_intersects(wq_unbound_cpumask, mask)) {
+ pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n",
+ cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask));
return;
}
- for_each_possible_cpu(cpu) {
- if (WARN_ON(cpu_to_node(cpu) == NUMA_NO_NODE)) {
- pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu);
- return;
- }
- }
-
- wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs();
- BUG_ON(!wq_update_unbound_numa_attrs_buf);
-
- /*
- * We want masks of possible CPUs of each node which isn't readily
- * available. Build one from cpu_to_node() which should have been
- * fully initialized by now.
- */
- tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL);
- BUG_ON(!tbl);
-
- for_each_node(node)
- BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
- node_online(node) ? node : NUMA_NO_NODE));
-
- for_each_possible_cpu(cpu) {
- node = cpu_to_node(cpu);
- cpumask_set_cpu(cpu, tbl[node]);
- }
-
- wq_numa_possible_cpumask = tbl;
- wq_numa_enabled = true;
+ cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask);
}
/**
* workqueue_init_early - early init for workqueue subsystem
*
- * This is the first half of two-staged workqueue subsystem initialization
- * and invoked as soon as the bare basics - memory allocation, cpumasks and
- * idr are up. It sets up all the data structures and system workqueues
- * and allows early boot code to create workqueues and queue/cancel work
- * items. Actual work item execution starts only after kthreads can be
- * created and scheduled right before early initcalls.
+ * This is the first step of three-staged workqueue subsystem initialization and
+ * invoked as soon as the bare basics - memory allocation, cpumasks and idr are
+ * up. It sets up all the data structures and system workqueues and allows early
+ * boot code to create workqueues and queue/cancel work items. Actual work item
+ * execution starts only after kthreads can be created and scheduled right
+ * before early initcalls.
*/
void __init workqueue_init_early(void)
{
+ struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM];
int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
int i, cpu;
BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
- cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ));
- cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN));
+ cpumask_copy(wq_unbound_cpumask, cpu_possible_mask);
+ restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ));
+ restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN));
+ if (!cpumask_empty(&wq_cmdline_cpumask))
+ restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
+ wq_update_pod_attrs_buf = alloc_workqueue_attrs();
+ BUG_ON(!wq_update_pod_attrs_buf);
+
+ /* initialize WQ_AFFN_SYSTEM pods */
+ pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL);
+ pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL);
+ pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL);
+ BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod);
+
+ BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE));
+
+ pt->nr_pods = 1;
+ cpumask_copy(pt->pod_cpus[0], cpu_possible_mask);
+ pt->pod_node[0] = NUMA_NO_NODE;
+ pt->cpu_pod[0] = 0;
+
/* initialize CPU pools */
for_each_possible_cpu(cpu) {
struct worker_pool *pool;
@@ -6469,7 +6575,9 @@ void __init workqueue_init_early(void)
BUG_ON(init_worker_pool(pool));
pool->cpu = cpu;
cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu));
+ cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu));
pool->attrs->nice = std_nice[i++];
+ pool->attrs->affn_strict = true;
pool->node = cpu_to_node(cpu);
/* alloc pool ID */
@@ -6490,11 +6598,10 @@ void __init workqueue_init_early(void)
/*
* An ordered wq should have only one pwq as ordering is
* guaranteed by max_active which is enforced by pwqs.
- * Turn off NUMA so that dfl_pwq is used for all nodes.
*/
BUG_ON(!(attrs = alloc_workqueue_attrs()));
attrs->nice = std_nice[i];
- attrs->no_numa = true;
+ attrs->ordered = true;
ordered_wq_attrs[i] = attrs;
}
@@ -6502,7 +6609,7 @@ void __init workqueue_init_early(void)
system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0);
system_long_wq = alloc_workqueue("events_long", 0, 0);
system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
- WQ_UNBOUND_MAX_ACTIVE);
+ WQ_MAX_ACTIVE);
system_freezable_wq = alloc_workqueue("events_freezable",
WQ_FREEZABLE, 0);
system_power_efficient_wq = alloc_workqueue("events_power_efficient",
@@ -6521,6 +6628,9 @@ static void __init wq_cpu_intensive_thresh_init(void)
unsigned long thresh;
unsigned long bogo;
+ pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release");
+ BUG_ON(IS_ERR(pwq_release_worker));
+
/* if the user set it to a specific value, keep it */
if (wq_cpu_intensive_thresh_us != ULONG_MAX)
return;
@@ -6555,11 +6665,11 @@ static void __init wq_cpu_intensive_thresh_init(void)
/**
* workqueue_init - bring workqueue subsystem fully online
*
- * This is the latter half of two-staged workqueue subsystem initialization
- * and invoked as soon as kthreads can be created and scheduled.
- * Workqueues have been created and work items queued on them, but there
- * are no kworkers executing the work items yet. Populate the worker pools
- * with the initial workers and enable future kworker creations.
+ * This is the second step of three-staged workqueue subsystem initialization
+ * and invoked as soon as kthreads can be created and scheduled. Workqueues have
+ * been created and work items queued on them, but there are no kworkers
+ * executing the work items yet. Populate the worker pools with the initial
+ * workers and enable future kworker creations.
*/
void __init workqueue_init(void)
{
@@ -6569,19 +6679,12 @@ void __init workqueue_init(void)
wq_cpu_intensive_thresh_init();
- /*
- * It'd be simpler to initialize NUMA in workqueue_init_early() but
- * CPU to node mapping may not be available that early on some
- * archs such as power and arm64. As per-cpu pools created
- * previously could be missing node hint and unbound pools NUMA
- * affinity, fix them up.
- *
- * Also, while iterating workqueues, create rescuers if requested.
- */
- wq_numa_init();
-
mutex_lock(&wq_pool_mutex);
+ /*
+ * Per-cpu pools created earlier could be missing node hint. Fix them
+ * up. Also, create a rescuer for workqueues that requested it.
+ */
for_each_possible_cpu(cpu) {
for_each_cpu_worker_pool(pool, cpu) {
pool->node = cpu_to_node(cpu);
@@ -6589,7 +6692,6 @@ void __init workqueue_init(void)
}
list_for_each_entry(wq, &workqueues, list) {
- wq_update_unbound_numa(wq, smp_processor_id(), true);
WARN(init_rescuer(wq),
"workqueue: failed to create early rescuer for %s",
wq->name);
@@ -6613,9 +6715,114 @@ void __init workqueue_init(void)
}
/*
- * Despite the naming, this is a no-op function which is here only for avoiding
- * link error. Since compile-time warning may fail to catch, we will need to
- * emit run-time warning from __flush_workqueue().
+ * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to
+ * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique
+ * and consecutive pod ID. The rest of @pt is initialized accordingly.
*/
-void __warn_flushing_systemwide_wq(void) { }
+static void __init init_pod_type(struct wq_pod_type *pt,
+ bool (*cpus_share_pod)(int, int))
+{
+ int cur, pre, cpu, pod;
+
+ pt->nr_pods = 0;
+
+ /* init @pt->cpu_pod[] according to @cpus_share_pod() */
+ pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL);
+ BUG_ON(!pt->cpu_pod);
+
+ for_each_possible_cpu(cur) {
+ for_each_possible_cpu(pre) {
+ if (pre >= cur) {
+ pt->cpu_pod[cur] = pt->nr_pods++;
+ break;
+ }
+ if (cpus_share_pod(cur, pre)) {
+ pt->cpu_pod[cur] = pt->cpu_pod[pre];
+ break;
+ }
+ }
+ }
+
+ /* init the rest to match @pt->cpu_pod[] */
+ pt->pod_cpus = kcalloc(pt->nr_pods, sizeof(pt->pod_cpus[0]), GFP_KERNEL);
+ pt->pod_node = kcalloc(pt->nr_pods, sizeof(pt->pod_node[0]), GFP_KERNEL);
+ BUG_ON(!pt->pod_cpus || !pt->pod_node);
+
+ for (pod = 0; pod < pt->nr_pods; pod++)
+ BUG_ON(!zalloc_cpumask_var(&pt->pod_cpus[pod], GFP_KERNEL));
+
+ for_each_possible_cpu(cpu) {
+ cpumask_set_cpu(cpu, pt->pod_cpus[pt->cpu_pod[cpu]]);
+ pt->pod_node[pt->cpu_pod[cpu]] = cpu_to_node(cpu);
+ }
+}
+
+static bool __init cpus_dont_share(int cpu0, int cpu1)
+{
+ return false;
+}
+
+static bool __init cpus_share_smt(int cpu0, int cpu1)
+{
+#ifdef CONFIG_SCHED_SMT
+ return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1));
+#else
+ return false;
+#endif
+}
+
+static bool __init cpus_share_numa(int cpu0, int cpu1)
+{
+ return cpu_to_node(cpu0) == cpu_to_node(cpu1);
+}
+
+/**
+ * workqueue_init_topology - initialize CPU pods for unbound workqueues
+ *
+ * This is the third step of there-staged workqueue subsystem initialization and
+ * invoked after SMP and topology information are fully initialized. It
+ * initializes the unbound CPU pods accordingly.
+ */
+void __init workqueue_init_topology(void)
+{
+ struct workqueue_struct *wq;
+ int cpu;
+
+ init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share);
+ init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt);
+ init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache);
+ init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa);
+
+ mutex_lock(&wq_pool_mutex);
+
+ /*
+ * Workqueues allocated earlier would have all CPUs sharing the default
+ * worker pool. Explicitly call wq_update_pod() on all workqueue and CPU
+ * combinations to apply per-pod sharing.
+ */
+ list_for_each_entry(wq, &workqueues, list) {
+ for_each_online_cpu(cpu) {
+ wq_update_pod(wq, cpu, cpu, true);
+ }
+ }
+
+ mutex_unlock(&wq_pool_mutex);
+}
+
+void __warn_flushing_systemwide_wq(void)
+{
+ pr_warn("WARNING: Flushing system-wide workqueues will be prohibited in near future.\n");
+ dump_stack();
+}
EXPORT_SYMBOL(__warn_flushing_systemwide_wq);
+
+static int __init workqueue_unbound_cpus_setup(char *str)
+{
+ if (cpulist_parse(str, &wq_cmdline_cpumask) < 0) {
+ cpumask_clear(&wq_cmdline_cpumask);
+ pr_warn("workqueue.unbound_cpus: incorrect CPU range, using default\n");
+ }
+
+ return 1;
+}
+__setup("workqueue.unbound_cpus=", workqueue_unbound_cpus_setup);
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 6b1d66e28269..f6275944ada7 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -48,7 +48,7 @@ struct worker {
/* A: runs through worker->node */
unsigned long last_active; /* K: last active timestamp */
- unsigned int flags; /* X: flags */
+ unsigned int flags; /* L: flags */
int id; /* I: worker id */
/*