summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.kexec4
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/async.c90
-rw-r--r--kernel/audit.c31
-rw-r--r--kernel/bpf/arraymap.c93
-rw-r--r--kernel/bpf/bpf_cgrp_storage.c6
-rw-r--r--kernel/bpf/bpf_lsm.c12
-rw-r--r--kernel/bpf/bpf_struct_ops.c35
-rw-r--r--kernel/bpf/btf.c300
-rw-r--r--kernel/bpf/core.c62
-rw-r--r--kernel/bpf/cpumask.c20
-rw-r--r--kernel/bpf/dispatcher.c7
-rw-r--r--kernel/bpf/hashtab.c13
-rw-r--r--kernel/bpf/helpers.c78
-rw-r--r--kernel/bpf/inode.c53
-rw-r--r--kernel/bpf/log.c504
-rw-r--r--kernel/bpf/lpm_trie.c3
-rw-r--r--kernel/bpf/map_in_map.c17
-rw-r--r--kernel/bpf/map_in_map.h2
-rw-r--r--kernel/bpf/memalloc.c200
-rw-r--r--kernel/bpf/stackmap.c11
-rw-r--r--kernel/bpf/syscall.c114
-rw-r--r--kernel/bpf/task_iter.c29
-rw-r--r--kernel/bpf/tnum.c13
-rw-r--r--kernel/bpf/trampoline.c101
-rw-r--r--kernel/bpf/verifier.c2586
-rw-r--r--kernel/cgroup/cgroup-internal.h4
-rw-r--r--kernel/cgroup/cgroup-v1.c34
-rw-r--r--kernel/cgroup/cgroup.c45
-rw-r--r--kernel/cgroup/cpuset.c297
-rw-r--r--kernel/cgroup/legacy_freezer.c8
-rw-r--r--kernel/cgroup/rstat.c150
-rw-r--r--kernel/cpu.c5
-rw-r--r--kernel/crash_core.c117
-rw-r--r--kernel/cred.c251
-rw-r--r--kernel/dma/coherent.c4
-rw-r--r--kernel/dma/debug.c2
-rw-r--r--kernel/dma/direct.c1
-rw-r--r--kernel/dma/pool.c6
-rw-r--r--kernel/dma/swiotlb.c94
-rw-r--r--kernel/entry/common.c108
-rw-r--r--kernel/events/core.c115
-rw-r--r--kernel/events/ring_buffer.c10
-rw-r--r--kernel/events/uprobes.c4
-rw-r--r--kernel/exit.c7
-rw-r--r--kernel/fork.c72
-rw-r--r--kernel/freezer.c3
-rw-r--r--kernel/futex/core.c1
-rw-r--r--kernel/futex/requeue.c1
-rw-r--r--kernel/futex/waitwake.c1
-rw-r--r--kernel/kexec_core.c22
-rw-r--r--kernel/kexec_file.c20
-rw-r--r--kernel/kprobes.c4
-rw-r--r--kernel/locking/locktorture.c18
-rw-r--r--kernel/locking/mutex.c5
-rw-r--r--kernel/locking/osq_lock.c37
-rw-r--r--kernel/locking/spinlock_debug.c1
-rw-r--r--kernel/module/dups.c2
-rw-r--r--kernel/module/main.c3
-rw-r--r--kernel/numa.c26
-rw-r--r--kernel/params.c52
-rw-r--r--kernel/pid.c2
-rw-r--r--kernel/pid_namespace.c1
-rw-r--r--kernel/power/hibernate.c10
-rw-r--r--kernel/power/main.c16
-rw-r--r--kernel/power/power.h2
-rw-r--r--kernel/power/snapshot.c16
-rw-r--r--kernel/power/swap.c41
-rw-r--r--kernel/ptrace.c141
-rw-r--r--kernel/rcu/Kconfig.debug25
-rw-r--r--kernel/rcu/rcu.h8
-rw-r--r--kernel/rcu/rcutorture.c16
-rw-r--r--kernel/rcu/srcutree.c24
-rw-r--r--kernel/rcu/tasks.h4
-rw-r--r--kernel/rcu/tree.c2
-rw-r--r--kernel/rcu/tree_stall.h11
-rw-r--r--kernel/rcu/update.c6
-rw-r--r--kernel/reboot.c51
-rw-r--r--kernel/relay.c162
-rw-r--r--kernel/resource.c61
-rw-r--r--kernel/sched/core.c141
-rw-r--r--kernel/sched/cpufreq_schedutil.c90
-rw-r--r--kernel/sched/deadline.c479
-rw-r--r--kernel/sched/debug.c18
-rw-r--r--kernel/sched/fair.c462
-rw-r--r--kernel/sched/features.h1
-rw-r--r--kernel/sched/idle.c30
-rw-r--r--kernel/sched/pelt.h4
-rw-r--r--kernel/sched/rt.c15
-rw-r--r--kernel/sched/sched.h146
-rw-r--r--kernel/sched/stop_task.c13
-rw-r--r--kernel/seccomp.c2
-rw-r--r--kernel/signal.c28
-rw-r--r--kernel/stacktrace.c2
-rw-r--r--kernel/sys_ni.c17
-rw-r--r--kernel/time/posix-stubs.c45
-rw-r--r--kernel/time/tick-internal.h3
-rw-r--r--kernel/time/tick-sched.c25
-rw-r--r--kernel/time/timer.c110
-rw-r--r--kernel/trace/bpf_trace.c180
-rw-r--r--kernel/trace/ftrace.c100
-rw-r--r--kernel/trace/rethook.c23
-rw-r--r--kernel/trace/ring_buffer.c209
-rw-r--r--kernel/trace/synth_event_gen_test.c11
-rw-r--r--kernel/trace/trace.c190
-rw-r--r--kernel/trace/trace.h1
-rw-r--r--kernel/trace/trace_events_hist.c12
-rw-r--r--kernel/trace/trace_events_synth.c4
-rw-r--r--kernel/trace/trace_events_user.c4
-rw-r--r--kernel/trace/trace_output.c6
-rw-r--r--kernel/trace/trace_uprobe.c2
-rw-r--r--kernel/user_namespace.c20
-rw-r--r--kernel/watch_queue.c2
-rw-r--r--kernel/watchdog.c40
-rw-r--r--kernel/workqueue.c187
115 files changed, 5099 insertions, 4037 deletions
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 7aff28ded2f4..946dffa048b7 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -36,6 +36,8 @@ config KEXEC
config KEXEC_FILE
bool "Enable kexec file based system call"
depends on ARCH_SUPPORTS_KEXEC_FILE
+ select CRYPTO
+ select CRYPTO_SHA256
select KEXEC_CORE
help
This is new version of kexec system call. This system call is
@@ -94,10 +96,8 @@ config KEXEC_JUMP
config CRASH_DUMP
bool "kernel crash dumps"
depends on ARCH_SUPPORTS_CRASH_DUMP
- depends on ARCH_SUPPORTS_KEXEC
select CRASH_CORE
select KEXEC_CORE
- select KEXEC
help
Generate crash dump after being started by kexec.
This should be normally only set in special crash dump kernels
diff --git a/kernel/Makefile b/kernel/Makefile
index 3947122d618b..ce105a5558fc 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -114,6 +114,7 @@ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o
obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o
obj-$(CONFIG_CFI_CLANG) += cfi.o
+obj-$(CONFIG_NUMA) += numa.o
obj-$(CONFIG_PERF_EVENTS) += events/
diff --git a/kernel/async.c b/kernel/async.c
index b2c4ba5686ee..97f224a5257b 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -46,11 +46,12 @@ asynchronous and synchronous parts of the kernel.
#include <linux/async.h>
#include <linux/atomic.h>
-#include <linux/ktime.h>
#include <linux/export.h>
-#include <linux/wait.h>
+#include <linux/ktime.h>
+#include <linux/pid.h>
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/wait.h>
#include <linux/workqueue.h>
#include "workqueue_internal.h"
@@ -145,6 +146,39 @@ static void async_run_entry_fn(struct work_struct *work)
wake_up(&async_done);
}
+static async_cookie_t __async_schedule_node_domain(async_func_t func,
+ void *data, int node,
+ struct async_domain *domain,
+ struct async_entry *entry)
+{
+ async_cookie_t newcookie;
+ unsigned long flags;
+
+ INIT_LIST_HEAD(&entry->domain_list);
+ INIT_LIST_HEAD(&entry->global_list);
+ INIT_WORK(&entry->work, async_run_entry_fn);
+ entry->func = func;
+ entry->data = data;
+ entry->domain = domain;
+
+ spin_lock_irqsave(&async_lock, flags);
+
+ /* allocate cookie and queue */
+ newcookie = entry->cookie = next_cookie++;
+
+ list_add_tail(&entry->domain_list, &domain->pending);
+ if (domain->registered)
+ list_add_tail(&entry->global_list, &async_global_pending);
+
+ atomic_inc(&entry_count);
+ spin_unlock_irqrestore(&async_lock, flags);
+
+ /* schedule for execution */
+ queue_work_node(node, system_unbound_wq, &entry->work);
+
+ return newcookie;
+}
+
/**
* async_schedule_node_domain - NUMA specific version of async_schedule_domain
* @func: function to execute asynchronously
@@ -186,29 +220,8 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data,
func(data, newcookie);
return newcookie;
}
- INIT_LIST_HEAD(&entry->domain_list);
- INIT_LIST_HEAD(&entry->global_list);
- INIT_WORK(&entry->work, async_run_entry_fn);
- entry->func = func;
- entry->data = data;
- entry->domain = domain;
-
- spin_lock_irqsave(&async_lock, flags);
-
- /* allocate cookie and queue */
- newcookie = entry->cookie = next_cookie++;
- list_add_tail(&entry->domain_list, &domain->pending);
- if (domain->registered)
- list_add_tail(&entry->global_list, &async_global_pending);
-
- atomic_inc(&entry_count);
- spin_unlock_irqrestore(&async_lock, flags);
-
- /* schedule for execution */
- queue_work_node(node, system_unbound_wq, &entry->work);
-
- return newcookie;
+ return __async_schedule_node_domain(func, data, node, domain, entry);
}
EXPORT_SYMBOL_GPL(async_schedule_node_domain);
@@ -232,6 +245,35 @@ async_cookie_t async_schedule_node(async_func_t func, void *data, int node)
EXPORT_SYMBOL_GPL(async_schedule_node);
/**
+ * async_schedule_dev_nocall - A simplified variant of async_schedule_dev()
+ * @func: function to execute asynchronously
+ * @dev: device argument to be passed to function
+ *
+ * @dev is used as both the argument for the function and to provide NUMA
+ * context for where to run the function.
+ *
+ * If the asynchronous execution of @func is scheduled successfully, return
+ * true. Otherwise, do nothing and return false, unlike async_schedule_dev()
+ * that will run the function synchronously then.
+ */
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev)
+{
+ struct async_entry *entry;
+
+ entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL);
+
+ /* Give up if there is no memory or too much work. */
+ if (!entry || atomic_read(&entry_count) > MAX_WORK) {
+ kfree(entry);
+ return false;
+ }
+
+ __async_schedule_node_domain(func, dev, dev_to_node(dev),
+ &async_dfl_domain, entry);
+ return true;
+}
+
+/**
* async_synchronize_full - synchronize all asynchronous function calls
*
* This function waits until all asynchronous function calls have been done.
diff --git a/kernel/audit.c b/kernel/audit.c
index 16205dd29843..9c8e5f732c4c 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -487,15 +487,19 @@ static void auditd_conn_free(struct rcu_head *rcu)
* @pid: auditd PID
* @portid: auditd netlink portid
* @net: auditd network namespace pointer
+ * @skb: the netlink command from the audit daemon
+ * @ack: netlink ack flag, cleared if ack'd here
*
* Description:
* This function will obtain and drop network namespace references as
* necessary. Returns zero on success, negative values on failure.
*/
-static int auditd_set(struct pid *pid, u32 portid, struct net *net)
+static int auditd_set(struct pid *pid, u32 portid, struct net *net,
+ struct sk_buff *skb, bool *ack)
{
unsigned long flags;
struct auditd_connection *ac_old, *ac_new;
+ struct nlmsghdr *nlh;
if (!pid || !net)
return -EINVAL;
@@ -507,6 +511,13 @@ static int auditd_set(struct pid *pid, u32 portid, struct net *net)
ac_new->portid = portid;
ac_new->net = get_net(net);
+ /* send the ack now to avoid a race with the queue backlog */
+ if (*ack) {
+ nlh = nlmsg_hdr(skb);
+ netlink_ack(skb, nlh, 0, NULL);
+ *ack = false;
+ }
+
spin_lock_irqsave(&auditd_conn_lock, flags);
ac_old = rcu_dereference_protected(auditd_conn,
lockdep_is_held(&auditd_conn_lock));
@@ -1200,7 +1211,8 @@ static int audit_replace(struct pid *pid)
return auditd_send_unicast_skb(skb);
}
-static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+ bool *ack)
{
u32 seq;
void *data;
@@ -1293,7 +1305,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
/* register a new auditd connection */
err = auditd_set(req_pid,
NETLINK_CB(skb).portid,
- sock_net(NETLINK_CB(skb).sk));
+ sock_net(NETLINK_CB(skb).sk),
+ skb, ack);
if (audit_enabled != AUDIT_OFF)
audit_log_config_change("audit_pid",
new_pid,
@@ -1538,9 +1551,10 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
* Parse the provided skb and deal with any messages that may be present,
* malformed skbs are discarded.
*/
-static void audit_receive(struct sk_buff *skb)
+static void audit_receive(struct sk_buff *skb)
{
struct nlmsghdr *nlh;
+ bool ack;
/*
* len MUST be signed for nlmsg_next to be able to dec it below 0
* if the nlmsg_len was not aligned
@@ -1553,9 +1567,12 @@ static void audit_receive(struct sk_buff *skb)
audit_ctl_lock();
while (nlmsg_ok(nlh, len)) {
- err = audit_receive_msg(skb, nlh);
- /* if err or if this message says it wants a response */
- if (err || (nlh->nlmsg_flags & NLM_F_ACK))
+ ack = nlh->nlmsg_flags & NLM_F_ACK;
+ err = audit_receive_msg(skb, nlh, &ack);
+
+ /* send an ack if the user asked for one and audit_receive_msg
+ * didn't already do it, or if there was an error. */
+ if (ack || err)
netlink_ack(skb, nlh, err, NULL);
nlh = nlmsg_next(nlh, &len);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..0bdbbbeab155 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -867,11 +867,11 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
}
if (old_ptr)
- map->ops->map_fd_put_ptr(old_ptr);
+ map->ops->map_fd_put_ptr(map, old_ptr, true);
return 0;
}
-static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
void *old_ptr;
@@ -890,13 +890,18 @@ static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
}
if (old_ptr) {
- map->ops->map_fd_put_ptr(old_ptr);
+ map->ops->map_fd_put_ptr(map, old_ptr, need_defer);
return 0;
} else {
return -ENOENT;
}
}
+static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+ return __fd_array_map_delete_elem(map, key, true);
+}
+
static void *prog_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file, int fd)
{
@@ -913,8 +918,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map,
return prog;
}
-static void prog_fd_array_put_ptr(void *ptr)
+static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
{
+ /* bpf_prog is freed after one RCU or tasks trace grace period */
bpf_prog_put(ptr);
}
@@ -924,13 +930,13 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
}
/* decrement refcnt of all bpf_progs that are stored in this map */
-static void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
for (i = 0; i < array->map.max_entries; i++)
- fd_array_map_delete_elem(map, &i);
+ __fd_array_map_delete_elem(map, &i, need_defer);
}
static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -1012,11 +1018,16 @@ 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 +1036,7 @@ 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 +1055,10 @@ 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 +1068,7 @@ 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);
}
}
}
@@ -1109,7 +1077,7 @@ static void prog_array_map_clear_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_array_aux,
work)->map;
- bpf_fd_array_map_clear(map);
+ bpf_fd_array_map_clear(map, true);
bpf_map_put(map);
}
@@ -1189,7 +1157,7 @@ static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
{
struct bpf_event_entry *ee;
- ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
+ ee = kzalloc(sizeof(*ee), GFP_KERNEL);
if (ee) {
ee->event = perf_file->private_data;
ee->perf_file = perf_file;
@@ -1239,8 +1207,9 @@ err_out:
return ee;
}
-static void perf_event_fd_array_put_ptr(void *ptr)
+static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
{
+ /* bpf_perf_event is freed after one RCU grace period */
bpf_event_entry_free_rcu(ptr);
}
@@ -1258,7 +1227,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
for (i = 0; i < array->map.max_entries; i++) {
ee = READ_ONCE(array->ptrs[i]);
if (ee && ee->map_file == map_file)
- fd_array_map_delete_elem(map, &i);
+ __fd_array_map_delete_elem(map, &i, true);
}
rcu_read_unlock();
}
@@ -1266,7 +1235,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
static void perf_event_fd_array_map_free(struct bpf_map *map)
{
if (map->map_flags & BPF_F_PRESERVE_ELEMS)
- bpf_fd_array_map_clear(map);
+ bpf_fd_array_map_clear(map, false);
fd_array_map_free(map);
}
@@ -1294,7 +1263,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
return cgroup_get_from_fd(fd);
}
-static void cgroup_fd_array_put_ptr(void *ptr)
+static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
{
/* cgroup_put free cgrp after a rcu grace period */
cgroup_put(ptr);
@@ -1302,7 +1271,7 @@ static void cgroup_fd_array_put_ptr(void *ptr)
static void cgroup_fd_array_free(struct bpf_map *map)
{
- bpf_fd_array_map_clear(map);
+ bpf_fd_array_map_clear(map, false);
fd_array_map_free(map);
}
@@ -1347,7 +1316,7 @@ static void array_of_map_free(struct bpf_map *map)
* is protected by fdget/fdput.
*/
bpf_map_meta_free(map->inner_map_meta);
- bpf_fd_array_map_clear(map);
+ bpf_fd_array_map_clear(map, false);
fd_array_map_free(map);
}
diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c
index d44fe8dd9732..28efd0a3f220 100644
--- a/kernel/bpf/bpf_cgrp_storage.c
+++ b/kernel/bpf/bpf_cgrp_storage.c
@@ -82,7 +82,7 @@ static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key)
int fd;
fd = *(int *)key;
- cgroup = cgroup_get_from_fd(fd);
+ cgroup = cgroup_v1v2_get_from_fd(fd);
if (IS_ERR(cgroup))
return ERR_CAST(cgroup);
@@ -101,7 +101,7 @@ static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key,
int fd;
fd = *(int *)key;
- cgroup = cgroup_get_from_fd(fd);
+ cgroup = cgroup_v1v2_get_from_fd(fd);
if (IS_ERR(cgroup))
return PTR_ERR(cgroup);
@@ -131,7 +131,7 @@ static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key)
int err, fd;
fd = *(int *)key;
- cgroup = cgroup_get_from_fd(fd);
+ cgroup = cgroup_v1v2_get_from_fd(fd);
if (IS_ERR(cgroup))
return PTR_ERR(cgroup);
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index e14c822f8911..e8e910395bf6 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -298,6 +298,18 @@ BTF_ID(func, bpf_lsm_kernel_module_request)
BTF_ID(func, bpf_lsm_kernel_read_file)
BTF_ID(func, bpf_lsm_kernfs_init_security)
+#ifdef CONFIG_SECURITY_PATH
+BTF_ID(func, bpf_lsm_path_unlink)
+BTF_ID(func, bpf_lsm_path_mkdir)
+BTF_ID(func, bpf_lsm_path_rmdir)
+BTF_ID(func, bpf_lsm_path_truncate)
+BTF_ID(func, bpf_lsm_path_symlink)
+BTF_ID(func, bpf_lsm_path_link)
+BTF_ID(func, bpf_lsm_path_rename)
+BTF_ID(func, bpf_lsm_path_chmod)
+BTF_ID(func, bpf_lsm_path_chown)
+#endif /* CONFIG_SECURITY_PATH */
+
#ifdef CONFIG_KEYS
BTF_ID(func, bpf_lsm_key_free)
#endif /* CONFIG_KEYS */
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index db6176fb64dc..02068bd0e4d9 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -352,18 +352,24 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = {
int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
struct bpf_tramp_link *link,
const struct btf_func_model *model,
- void *image, void *image_end)
+ void *stub_func, void *image, void *image_end)
{
- u32 flags;
+ u32 flags = BPF_TRAMP_F_INDIRECT;
+ int size;
tlinks[BPF_TRAMP_FENTRY].links[0] = link;
tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
- /* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
- * and it must be used alone.
- */
- flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
+
+ if (model->ret_size > 0)
+ flags |= BPF_TRAMP_F_RET_FENTRY_RET;
+
+ size = arch_bpf_trampoline_size(model, flags, tlinks, NULL);
+ if (size < 0)
+ return size;
+ if (size > (unsigned long)image_end - (unsigned long)image)
+ return -E2BIG;
return arch_prepare_bpf_trampoline(NULL, image, image_end,
- model, flags, tlinks, NULL);
+ model, flags, tlinks, stub_func);
}
static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
@@ -497,11 +503,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
err = bpf_struct_ops_prepare_trampoline(tlinks, link,
&st_ops->func_models[i],
+ *(void **)(st_ops->cfi_stubs + moff),
image, image_end);
if (err < 0)
goto reset_unlock;
- *(void **)(kdata + moff) = image;
+ *(void **)(kdata + moff) = image + cfi_get_offset();
image += err;
/* put prog_id to udata */
@@ -515,7 +522,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
if (err)
goto reset_unlock;
}
- set_memory_rox((long)st_map->image, 1);
+ arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE);
/* Let bpf_link handle registration & unregistration.
*
* Pair with smp_load_acquire() during lookup_elem().
@@ -524,7 +531,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
goto unlock;
}
- set_memory_rox((long)st_map->image, 1);
+ arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE);
err = st_ops->reg(kdata);
if (likely(!err)) {
/* This refcnt increment on the map here after
@@ -547,8 +554,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
* there was a race in registering the struct_ops (under the same name) to
* a sub-system through different struct_ops's maps.
*/
- set_memory_nx((long)st_map->image, 1);
- set_memory_rw((long)st_map->image, 1);
+ arch_unprotect_bpf_trampoline(st_map->image, PAGE_SIZE);
reset_unlock:
bpf_struct_ops_map_put_progs(st_map);
@@ -616,7 +622,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map)
bpf_struct_ops_map_put_progs(st_map);
bpf_map_area_free(st_map->links);
if (st_map->image) {
- bpf_jit_free_exec(st_map->image);
+ arch_free_bpf_trampoline(st_map->image, PAGE_SIZE);
bpf_jit_uncharge_modmem(PAGE_SIZE);
}
bpf_map_area_free(st_map->uvalue);
@@ -691,7 +697,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
return ERR_PTR(ret);
}
- st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
+ st_map->image = arch_alloc_bpf_trampoline(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
@@ -711,7 +717,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
}
mutex_init(&st_map->lock);
- set_vm_flush_reset_perms(st_map->image);
bpf_map_init_from_attr(map, attr);
return map;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 15d71d2986d3..51e8b4bee0c8 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3840,9 +3840,6 @@ end:
return ERR_PTR(ret);
}
-#define GRAPH_ROOT_MASK (BPF_LIST_HEAD | BPF_RB_ROOT)
-#define GRAPH_NODE_MASK (BPF_LIST_NODE | BPF_RB_NODE)
-
int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
{
int i;
@@ -3855,13 +3852,13 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
* Hence we only need to ensure that bpf_{list_head,rb_root} ownership
* does not form cycles.
*/
- if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & GRAPH_ROOT_MASK))
+ if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_GRAPH_ROOT))
return 0;
for (i = 0; i < rec->cnt; i++) {
struct btf_struct_meta *meta;
u32 btf_id;
- if (!(rec->fields[i].type & GRAPH_ROOT_MASK))
+ if (!(rec->fields[i].type & BPF_GRAPH_ROOT))
continue;
btf_id = rec->fields[i].graph_root.value_btf_id;
meta = btf_find_struct_meta(btf, btf_id);
@@ -3873,7 +3870,7 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
* to check ownership cycle for a type unless it's also a
* node type.
*/
- if (!(rec->field_mask & GRAPH_NODE_MASK))
+ if (!(rec->field_mask & BPF_GRAPH_NODE))
continue;
/* We need to ensure ownership acyclicity among all types. The
@@ -3909,7 +3906,7 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
* - A is both an root and node.
* - B is only an node.
*/
- if (meta->record->field_mask & GRAPH_ROOT_MASK)
+ if (meta->record->field_mask & BPF_GRAPH_ROOT)
return -ELOOP;
}
return 0;
@@ -6768,222 +6765,64 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr
return btf_check_func_type_match(log, btf1, t1, btf2, t2);
}
-static int btf_check_func_arg_match(struct bpf_verifier_env *env,
- const struct btf *btf, u32 func_id,
- struct bpf_reg_state *regs,
- bool ptr_to_mem_ok,
- bool processing_call)
+static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t)
{
- enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
- struct bpf_verifier_log *log = &env->log;
- const char *func_name, *ref_tname;
- const struct btf_type *t, *ref_t;
- const struct btf_param *args;
- u32 i, nargs, ref_id;
- int ret;
-
- t = btf_type_by_id(btf, func_id);
- if (!t || !btf_type_is_func(t)) {
- /* These checks were already done by the verifier while loading
- * struct bpf_func_info or in add_kfunc_call().
- */
- bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n",
- func_id);
- return -EFAULT;
- }
- func_name = btf_name_by_offset(btf, t->name_off);
-
- t = btf_type_by_id(btf, t->type);
- if (!t || !btf_type_is_func_proto(t)) {
- bpf_log(log, "Invalid BTF of func %s\n", func_name);
- return -EFAULT;
- }
- args = (const struct btf_param *)(t + 1);
- nargs = btf_type_vlen(t);
- if (nargs > MAX_BPF_FUNC_REG_ARGS) {
- bpf_log(log, "Function %s has %d > %d args\n", func_name, nargs,
- MAX_BPF_FUNC_REG_ARGS);
- return -EINVAL;
- }
-
- /* check that BTF function arguments match actual types that the
- * verifier sees.
- */
- for (i = 0; i < nargs; i++) {
- enum bpf_arg_type arg_type = ARG_DONTCARE;
- u32 regno = i + 1;
- struct bpf_reg_state *reg = &regs[regno];
-
- t = btf_type_skip_modifiers(btf, args[i].type, NULL);
- if (btf_type_is_scalar(t)) {
- if (reg->type == SCALAR_VALUE)
- continue;
- bpf_log(log, "R%d is not a scalar\n", regno);
- return -EINVAL;
- }
-
- if (!btf_type_is_ptr(t)) {
- bpf_log(log, "Unrecognized arg#%d type %s\n",
- i, btf_type_str(t));
- return -EINVAL;
- }
-
- ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
- ref_tname = btf_name_by_offset(btf, ref_t->name_off);
-
- ret = check_func_arg_reg_off(env, reg, regno, arg_type);
- if (ret < 0)
- return ret;
+ const char *name;
- if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
- /* If function expects ctx type in BTF check that caller
- * is passing PTR_TO_CTX.
- */
- if (reg->type != PTR_TO_CTX) {
- bpf_log(log,
- "arg#%d expected pointer to ctx, but got %s\n",
- i, btf_type_str(t));
- return -EINVAL;
- }
- } else if (ptr_to_mem_ok && processing_call) {
- const struct btf_type *resolve_ret;
- u32 type_size;
+ t = btf_type_by_id(btf, t->type); /* skip PTR */
- resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
- if (IS_ERR(resolve_ret)) {
- bpf_log(log,
- "arg#%d reference type('%s %s') size cannot be determined: %ld\n",
- i, btf_type_str(ref_t), ref_tname,
- PTR_ERR(resolve_ret));
- return -EINVAL;
- }
+ while (btf_type_is_modifier(t))
+ t = btf_type_by_id(btf, t->type);
- if (check_mem_reg(env, reg, regno, type_size))
- return -EINVAL;
- } else {
- bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i,
- func_name, func_id);
- return -EINVAL;
- }
+ /* allow either struct or struct forward declaration */
+ if (btf_type_is_struct(t) ||
+ (btf_type_is_fwd(t) && btf_type_kflag(t) == 0)) {
+ name = btf_str_by_offset(btf, t->name_off);
+ return name && strcmp(name, "bpf_dynptr") == 0;
}
- return 0;
-}
-
-/* Compare BTF of a function declaration with given bpf_reg_state.
- * Returns:
- * EFAULT - there is a verifier bug. Abort verification.
- * EINVAL - there is a type mismatch or BTF is not available.
- * 0 - BTF matches with what bpf_reg_state expects.
- * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
- */
-int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
- struct bpf_reg_state *regs)
-{
- struct bpf_prog *prog = env->prog;
- struct btf *btf = prog->aux->btf;
- bool is_global;
- u32 btf_id;
- int err;
-
- if (!prog->aux->func_info)
- return -EINVAL;
-
- btf_id = prog->aux->func_info[subprog].type_id;
- if (!btf_id)
- return -EFAULT;
-
- if (prog->aux->func_info_aux[subprog].unreliable)
- return -EINVAL;
-
- is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
- err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false);
-
- /* Compiler optimizations can remove arguments from static functions
- * or mismatched type can be passed into a global function.
- * In such cases mark the function as unreliable from BTF point of view.
- */
- if (err)
- prog->aux->func_info_aux[subprog].unreliable = true;
- return err;
-}
-
-/* Compare BTF of a function call with given bpf_reg_state.
- * Returns:
- * EFAULT - there is a verifier bug. Abort verification.
- * EINVAL - there is a type mismatch or BTF is not available.
- * 0 - BTF matches with what bpf_reg_state expects.
- * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
- *
- * NOTE: the code is duplicated from btf_check_subprog_arg_match()
- * because btf_check_func_arg_match() is still doing both. Once that
- * function is split in 2, we can call from here btf_check_subprog_arg_match()
- * first, and then treat the calling part in a new code path.
- */
-int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
- struct bpf_reg_state *regs)
-{
- struct bpf_prog *prog = env->prog;
- struct btf *btf = prog->aux->btf;
- bool is_global;
- u32 btf_id;
- int err;
-
- if (!prog->aux->func_info)
- return -EINVAL;
-
- btf_id = prog->aux->func_info[subprog].type_id;
- if (!btf_id)
- return -EFAULT;
-
- if (prog->aux->func_info_aux[subprog].unreliable)
- return -EINVAL;
-
- is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
- err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true);
-
- /* Compiler optimizations can remove arguments from static functions
- * or mismatched type can be passed into a global function.
- * In such cases mark the function as unreliable from BTF point of view.
- */
- if (err)
- prog->aux->func_info_aux[subprog].unreliable = true;
- return err;
+ return false;
}
-/* Convert BTF of a function into bpf_reg_state if possible
+/* Process BTF of a function to produce high-level expectation of function
+ * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information
+ * is cached in subprog info for reuse.
* Returns:
* EFAULT - there is a verifier bug. Abort verification.
* EINVAL - cannot convert BTF.
- * 0 - Successfully converted BTF into bpf_reg_state
- * (either PTR_TO_CTX or SCALAR_VALUE).
+ * 0 - Successfully processed BTF and constructed argument expectations.
*/
-int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
- struct bpf_reg_state *regs, bool is_ex_cb)
+int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
{
+ bool is_global = subprog_aux(env, subprog)->linkage == BTF_FUNC_GLOBAL;
+ struct bpf_subprog_info *sub = subprog_info(env, subprog);
struct bpf_verifier_log *log = &env->log;
struct bpf_prog *prog = env->prog;
enum bpf_prog_type prog_type = prog->type;
struct btf *btf = prog->aux->btf;
const struct btf_param *args;
- const struct btf_type *t, *ref_t;
+ const struct btf_type *t, *ref_t, *fn_t;
u32 i, nargs, btf_id;
const char *tname;
- if (!prog->aux->func_info ||
- prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) {
+ if (sub->args_cached)
+ return 0;
+
+ if (!prog->aux->func_info) {
bpf_log(log, "Verifier bug\n");
return -EFAULT;
}
btf_id = prog->aux->func_info[subprog].type_id;
if (!btf_id) {
+ if (!is_global) /* not fatal for static funcs */
+ return -EINVAL;
bpf_log(log, "Global functions need valid BTF\n");
return -EFAULT;
}
- t = btf_type_by_id(btf, btf_id);
- if (!t || !btf_type_is_func(t)) {
+ fn_t = btf_type_by_id(btf, btf_id);
+ if (!fn_t || !btf_type_is_func(fn_t)) {
/* These checks were already done by the verifier while loading
* struct bpf_func_info
*/
@@ -6991,11 +6830,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
subprog);
return -EFAULT;
}
- tname = btf_name_by_offset(btf, t->name_off);
-
- if (log->level & BPF_LOG_LEVEL)
- bpf_log(log, "Validating %s() func#%d...\n",
- tname, subprog);
+ tname = btf_name_by_offset(btf, fn_t->name_off);
if (prog->aux->func_info_aux[subprog].unreliable) {
bpf_log(log, "Verifier bug in function %s()\n", tname);
@@ -7004,7 +6839,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
if (prog_type == BPF_PROG_TYPE_EXT)
prog_type = prog->aux->dst_prog->type;
- t = btf_type_by_id(btf, t->type);
+ t = btf_type_by_id(btf, fn_t->type);
if (!t || !btf_type_is_func_proto(t)) {
bpf_log(log, "Invalid type of function %s()\n", tname);
return -EFAULT;
@@ -7030,24 +6865,54 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
* Only PTR_TO_CTX and SCALAR are supported atm.
*/
for (i = 0; i < nargs; i++) {
- struct bpf_reg_state *reg = &regs[i + 1];
+ bool is_nonnull = false;
+ const char *tag;
t = btf_type_by_id(btf, args[i].type);
+
+ tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:");
+ if (IS_ERR(tag) && PTR_ERR(tag) == -ENOENT) {
+ tag = NULL;
+ } else if (IS_ERR(tag)) {
+ bpf_log(log, "arg#%d type's tag fetching failure: %ld\n", i, PTR_ERR(tag));
+ return PTR_ERR(tag);
+ }
+ /* 'arg:<tag>' decl_tag takes precedence over derivation of
+ * register type from BTF type itself
+ */
+ if (tag) {
+ /* disallow arg tags in static subprogs */
+ if (!is_global) {
+ bpf_log(log, "arg#%d type tag is not supported in static functions\n", i);
+ return -EOPNOTSUPP;
+ }
+ if (strcmp(tag, "ctx") == 0) {
+ sub->args[i].arg_type = ARG_PTR_TO_CTX;
+ continue;
+ }
+ if (strcmp(tag, "nonnull") == 0)
+ is_nonnull = true;
+ }
+
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
if (btf_type_is_int(t) || btf_is_any_enum(t)) {
- reg->type = SCALAR_VALUE;
+ sub->args[i].arg_type = ARG_ANYTHING;
continue;
}
- if (btf_type_is_ptr(t)) {
- if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
- reg->type = PTR_TO_CTX;
- continue;
- }
+ if (btf_type_is_ptr(t) && btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
+ sub->args[i].arg_type = ARG_PTR_TO_CTX;
+ continue;
+ }
+ if (btf_type_is_ptr(t) && btf_is_dynptr_ptr(btf, t)) {
+ sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY;
+ continue;
+ }
+ if (is_global && btf_type_is_ptr(t)) {
+ u32 mem_size;
t = btf_type_skip_modifiers(btf, t->type, NULL);
-
- ref_t = btf_resolve_size(btf, t, &reg->mem_size);
+ ref_t = btf_resolve_size(btf, t, &mem_size);
if (IS_ERR(ref_t)) {
bpf_log(log,
"arg#%d reference type('%s %s') size cannot be determined: %ld\n",
@@ -7056,23 +6921,22 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
return -EINVAL;
}
- reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
- reg->id = ++env->id_gen;
-
+ sub->args[i].arg_type = is_nonnull ? ARG_PTR_TO_MEM : ARG_PTR_TO_MEM_OR_NULL;
+ sub->args[i].mem_size = mem_size;
continue;
}
+ if (is_nonnull) {
+ bpf_log(log, "arg#%d marked as non-null, but is not a pointer type\n", i);
+ return -EINVAL;
+ }
bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n",
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;
- }
+
+ sub->arg_cnt = nargs;
+ sub->args_cached = true;
+
return 0;
}
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index cd3afe57ece3..ea6843be2616 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -121,6 +121,9 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
#endif
INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+#ifdef CONFIG_FINEIBT
+ INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode);
+#endif
mutex_init(&fp->aux->used_maps_mutex);
mutex_init(&fp->aux->dst_mutex);
@@ -371,14 +374,18 @@ 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;
- if (insn->code == (BPF_JMP32 | BPF_JA))
+ if (insn->code == (BPF_JMP32 | BPF_JA)) {
off = insn->imm;
- else
+ 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;
@@ -683,6 +690,23 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp)
fp->aux->ksym.prog = true;
bpf_ksym_add(&fp->aux->ksym);
+
+#ifdef CONFIG_FINEIBT
+ /*
+ * When FineIBT, code in the __cfi_foo() symbols can get executed
+ * and hence unwinder needs help.
+ */
+ if (cfi_mode != CFI_FINEIBT)
+ return;
+
+ snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN,
+ "__cfi_%s", fp->aux->ksym.name);
+
+ fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16;
+ fp->aux->ksym_prefix.end = (unsigned long) fp->bpf_func;
+
+ bpf_ksym_add(&fp->aux->ksym_prefix);
+#endif
}
void bpf_prog_kallsyms_del(struct bpf_prog *fp)
@@ -691,6 +715,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp)
return;
bpf_ksym_del(&fp->aux->ksym);
+#ifdef CONFIG_FINEIBT
+ if (cfi_mode != CFI_FINEIBT)
+ return;
+ bpf_ksym_del(&fp->aux->ksym_prefix);
+#endif
}
static struct bpf_ksym *bpf_ksym_find(unsigned long addr)
@@ -928,20 +957,20 @@ out:
return ptr;
}
-void bpf_prog_pack_free(struct bpf_binary_header *hdr)
+void bpf_prog_pack_free(void *ptr, u32 size)
{
struct bpf_prog_pack *pack = NULL, *tmp;
unsigned int nbits;
unsigned long pos;
mutex_lock(&pack_mutex);
- if (hdr->size > BPF_PROG_PACK_SIZE) {
- bpf_jit_free_exec(hdr);
+ if (size > BPF_PROG_PACK_SIZE) {
+ bpf_jit_free_exec(ptr);
goto out;
}
list_for_each_entry(tmp, &pack_list, list) {
- if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) {
+ if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) {
pack = tmp;
break;
}
@@ -950,10 +979,10 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
if (WARN_ONCE(!pack, "bpf_prog_pack bug\n"))
goto out;
- nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size);
- pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
+ nbits = BPF_PROG_SIZE_TO_NBITS(size);
+ pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
- WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size),
+ WARN_ONCE(bpf_arch_text_invalidate(ptr, size),
"bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n");
bitmap_clear(pack->bitmap, pos, nbits);
@@ -1100,8 +1129,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
*rw_header = kvmalloc(size, GFP_KERNEL);
if (!*rw_header) {
- bpf_arch_text_copy(&ro_header->size, &size, sizeof(size));
- bpf_prog_pack_free(ro_header);
+ bpf_prog_pack_free(ro_header, size);
bpf_jit_uncharge_modmem(size);
return NULL;
}
@@ -1132,7 +1160,7 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog,
kvfree(rw_header);
if (IS_ERR(ptr)) {
- bpf_prog_pack_free(ro_header);
+ bpf_prog_pack_free(ro_header, ro_header->size);
return PTR_ERR(ptr);
}
return 0;
@@ -1153,7 +1181,7 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
{
u32 size = ro_header->size;
- bpf_prog_pack_free(ro_header);
+ bpf_prog_pack_free(ro_header, size);
kvfree(rw_header);
bpf_jit_uncharge_modmem(size);
}
@@ -2664,12 +2692,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux,
struct bpf_map **used_maps, u32 len)
{
struct bpf_map *map;
+ bool sleepable;
u32 i;
+ sleepable = aux->sleepable;
for (i = 0; i < len; i++) {
map = used_maps[i];
if (map->ops->map_poke_untrack)
map->ops->map_poke_untrack(map, aux);
+ if (sleepable)
+ atomic64_dec(&map->sleepable_refcnt);
bpf_map_put(map);
}
}
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index e01c741e54e7..2e73533a3811 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -96,6 +96,12 @@ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask)
migrate_enable();
}
+__bpf_kfunc void bpf_cpumask_release_dtor(void *cpumask)
+{
+ bpf_cpumask_release(cpumask);
+}
+CFI_NOSEAL(bpf_cpumask_release_dtor);
+
/**
* bpf_cpumask_first() - Get the index of the first nonzero bit in the cpumask.
* @cpumask: The cpumask being queried.
@@ -405,6 +411,17 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
return cpumask_any_and_distribute(src1, src2);
}
+/**
+ * bpf_cpumask_weight() - Return the number of bits in @cpumask.
+ * @cpumask: The cpumask being queried.
+ *
+ * Count the number of set bits in the given cpumask.
+ */
+__bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask)
+{
+ return cpumask_weight(cpumask);
+}
+
__bpf_kfunc_end_defs();
BTF_SET8_START(cpumask_kfunc_btf_ids)
@@ -432,6 +449,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_full, KF_RCU)
BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU)
BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU)
BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU)
+BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU)
BTF_SET8_END(cpumask_kfunc_btf_ids)
static const struct btf_kfunc_id_set cpumask_kfunc_set = {
@@ -441,7 +459,7 @@ static const struct btf_kfunc_id_set cpumask_kfunc_set = {
BTF_ID_LIST(cpumask_dtor_ids)
BTF_ID(struct, bpf_cpumask)
-BTF_ID(func, bpf_cpumask_release)
+BTF_ID(func, bpf_cpumask_release_dtor)
static int __init cpumask_kfunc_init(void)
{
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index fa3e9225aedc..70fb82bf1637 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -150,14 +150,11 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
goto out;
d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE);
if (!d->rw_image) {
- u32 size = PAGE_SIZE;
-
- bpf_arch_text_copy(d->image, &size, sizeof(size));
- bpf_prog_pack_free((struct bpf_binary_header *)d->image);
+ bpf_prog_pack_free(d->image, PAGE_SIZE);
d->image = NULL;
goto out;
}
- bpf_image_ksym_add(d->image, &d->ksym);
+ bpf_image_ksym_add(d->image, PAGE_SIZE, &d->ksym);
}
prev_num_progs = d->num_progs;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fd8d4b0addfc..03a6a2500b6a 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -7,6 +7,7 @@
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
+#include <linux/rcupdate_wait.h>
#include <linux/random.h>
#include <uapi/linux/btf.h>
#include <linux/rcupdate_trace.h>
@@ -897,7 +898,7 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
if (map->ops->map_fd_put_ptr) {
ptr = fd_htab_map_get_ptr(map, l);
- map->ops->map_fd_put_ptr(ptr);
+ map->ops->map_fd_put_ptr(map, ptr, true);
}
}
@@ -2484,7 +2485,7 @@ static void fd_htab_map_free(struct bpf_map *map)
hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
void *ptr = fd_htab_map_get_ptr(map, l);
- map->ops->map_fd_put_ptr(ptr);
+ map->ops->map_fd_put_ptr(map, ptr, false);
}
}
@@ -2523,9 +2524,15 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
if (IS_ERR(ptr))
return PTR_ERR(ptr);
+ /* The htab bucket lock is always held during update operations in fd
+ * htab map, and the following rcu_read_lock() is only used to avoid
+ * the WARN_ON_ONCE in htab_map_update_elem().
+ */
+ rcu_read_lock();
ret = htab_map_update_elem(map, key, &ptr, map_flags);
+ rcu_read_unlock();
if (ret)
- map->ops->map_fd_put_ptr(ptr);
+ map->ops->map_fd_put_ptr(map, ptr, false);
return ret;
}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 56b0c1f678ee..be72824f32b2 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -32,12 +32,13 @@
*
* Different map implementations will rely on rcu in map methods
* lookup/update/delete, therefore eBPF programs must run under rcu lock
- * if program is allowed to access maps, so check rcu_read_lock_held in
- * all three functions.
+ * if program is allowed to access maps, so check rcu_read_lock_held() or
+ * rcu_read_lock_trace_held() in all three functions.
*/
BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
{
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
return (unsigned long) map->ops->map_lookup_elem(map, key);
}
@@ -53,7 +54,8 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = {
BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
void *, value, u64, flags)
{
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
return map->ops->map_update_elem(map, key, value, flags);
}
@@ -70,7 +72,8 @@ const struct bpf_func_proto bpf_map_update_elem_proto = {
BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
{
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
return map->ops->map_delete_elem(map, key);
}
@@ -1937,10 +1940,7 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool 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_mem_free_rcu(ma, p);
}
__bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
@@ -2150,6 +2150,12 @@ __bpf_kfunc void bpf_task_release(struct task_struct *p)
put_task_struct_rcu_user(p);
}
+__bpf_kfunc void bpf_task_release_dtor(void *p)
+{
+ put_task_struct_rcu_user(p);
+}
+CFI_NOSEAL(bpf_task_release_dtor);
+
#ifdef CONFIG_CGROUPS
/**
* bpf_cgroup_acquire - Acquire a reference to a cgroup. A cgroup acquired by
@@ -2174,6 +2180,12 @@ __bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp)
cgroup_put(cgrp);
}
+__bpf_kfunc void bpf_cgroup_release_dtor(void *cgrp)
+{
+ cgroup_put(cgrp);
+}
+CFI_NOSEAL(bpf_cgroup_release_dtor);
+
/**
* bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor
* array. A cgroup returned by this kfunc which is not subsequently stored in a
@@ -2231,6 +2243,25 @@ __bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task,
rcu_read_unlock();
return ret;
}
+
+/**
+ * bpf_task_get_cgroup1 - Acquires the associated cgroup of a task within a
+ * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its
+ * hierarchy ID.
+ * @task: The target task
+ * @hierarchy_id: The ID of a cgroup1 hierarchy
+ *
+ * On success, the cgroup is returen. On failure, NULL is returned.
+ */
+__bpf_kfunc struct cgroup *
+bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id)
+{
+ struct cgroup *cgrp = task_get_cgroup1(task, hierarchy_id);
+
+ if (IS_ERR(cgrp))
+ return NULL;
+ return cgrp;
+}
#endif /* CONFIG_CGROUPS */
/**
@@ -2506,7 +2537,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
* 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);
+ ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp, 0, 0);
WARN(1, "A call to BPF exception callback should never return\n");
}
@@ -2520,7 +2551,7 @@ 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_refcount_acquire_impl, KF_ACQUIRE | KF_RET_NULL | KF_RCU)
BTF_ID_FLAGS(func, bpf_list_push_front_impl)
BTF_ID_FLAGS(func, bpf_list_push_back_impl)
BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL)
@@ -2537,6 +2568,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU)
+BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
#endif
BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_throw)
@@ -2550,10 +2582,10 @@ static const struct btf_kfunc_id_set generic_kfunc_set = {
BTF_ID_LIST(generic_dtor_ids)
BTF_ID(struct, task_struct)
-BTF_ID(func, bpf_task_release)
+BTF_ID(func, bpf_task_release_dtor)
#ifdef CONFIG_CGROUPS
BTF_ID(struct, cgroup)
-BTF_ID(func, bpf_cgroup_release)
+BTF_ID(func, bpf_cgroup_release_dtor)
#endif
BTF_SET8_START(common_btf_ids)
@@ -2610,6 +2642,7 @@ static int __init kfunc_init(void)
ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set);
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &generic_kfunc_set);
+ ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &generic_kfunc_set);
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &generic_kfunc_set);
ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors,
ARRAY_SIZE(generic_dtors),
@@ -2618,3 +2651,22 @@ static int __init kfunc_init(void)
}
late_initcall(kfunc_init);
+
+/* Get a pointer to dynptr data up to len bytes for read only access. If
+ * the dynptr doesn't have continuous data up to len bytes, return NULL.
+ */
+const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len)
+{
+ return bpf_dynptr_slice(ptr, 0, NULL, len);
+}
+
+/* Get a pointer to dynptr data up to len bytes for read write access. If
+ * the dynptr doesn't have continuous data up to len bytes, or the dynptr
+ * is read only, return NULL.
+ */
+void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len)
+{
+ if (__bpf_dynptr_is_rdonly(ptr))
+ return NULL;
+ return (void *)__bpf_dynptr_data(ptr, len);
+}
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 1aafb2ff2e95..41e0a55c35f5 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -599,8 +599,15 @@ EXPORT_SYMBOL(bpf_prog_get_type_path);
*/
static int bpf_show_options(struct seq_file *m, struct dentry *root)
{
- umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
-
+ struct inode *inode = d_inode(root);
+ umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX;
+
+ if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID))
+ seq_printf(m, ",uid=%u",
+ from_kuid_munged(&init_user_ns, inode->i_uid));
+ if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID))
+ seq_printf(m, ",gid=%u",
+ from_kgid_munged(&init_user_ns, inode->i_gid));
if (mode != S_IRWXUGO)
seq_printf(m, ",mode=%o", mode);
return 0;
@@ -625,15 +632,21 @@ static const struct super_operations bpf_super_ops = {
};
enum {
+ OPT_UID,
+ OPT_GID,
OPT_MODE,
};
static const struct fs_parameter_spec bpf_fs_parameters[] = {
+ fsparam_u32 ("uid", OPT_UID),
+ fsparam_u32 ("gid", OPT_GID),
fsparam_u32oct ("mode", OPT_MODE),
{}
};
struct bpf_mount_opts {
+ kuid_t uid;
+ kgid_t gid;
umode_t mode;
};
@@ -641,6 +654,8 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct bpf_mount_opts *opts = fc->fs_private;
struct fs_parse_result result;
+ kuid_t uid;
+ kgid_t gid;
int opt;
opt = fs_parse(fc, bpf_fs_parameters, param, &result);
@@ -662,12 +677,42 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
}
switch (opt) {
+ case OPT_UID:
+ uid = make_kuid(current_user_ns(), result.uint_32);
+ if (!uid_valid(uid))
+ goto bad_value;
+
+ /*
+ * The requested uid must be representable in the
+ * filesystem's idmapping.
+ */
+ if (!kuid_has_mapping(fc->user_ns, uid))
+ goto bad_value;
+
+ opts->uid = uid;
+ break;
+ case OPT_GID:
+ gid = make_kgid(current_user_ns(), result.uint_32);
+ if (!gid_valid(gid))
+ goto bad_value;
+
+ /*
+ * The requested gid must be representable in the
+ * filesystem's idmapping.
+ */
+ if (!kgid_has_mapping(fc->user_ns, gid))
+ goto bad_value;
+
+ opts->gid = gid;
+ break;
case OPT_MODE:
opts->mode = result.uint_32 & S_IALLUGO;
break;
}
return 0;
+bad_value:
+ return invalfc(fc, "Bad value for '%s'", param->key);
}
struct bpf_preload_ops *bpf_preload_ops;
@@ -750,6 +795,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
sb->s_op = &bpf_super_ops;
inode = sb->s_root->d_inode;
+ inode->i_uid = opts->uid;
+ inode->i_gid = opts->gid;
inode->i_op = &bpf_dir_iops;
inode->i_mode &= ~S_IALLUGO;
populate_bpffs(sb->s_root);
@@ -785,6 +832,8 @@ static int bpf_init_fs_context(struct fs_context *fc)
return -ENOMEM;
opts->mode = S_IRWXUGO;
+ opts->uid = current_fsuid();
+ opts->gid = current_fsgid();
fc->fs_private = opts;
fc->ops = &bpf_context_ops;
diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index 850494423530..594a234f122b 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -10,6 +10,8 @@
#include <linux/bpf_verifier.h>
#include <linux/math64.h>
+#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args)
+
static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log)
{
/* ubuf and len_total should both be specified (or not) together */
@@ -325,3 +327,505 @@ __printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
va_end(args);
}
EXPORT_SYMBOL_GPL(bpf_log);
+
+static const struct bpf_line_info *
+find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+{
+ const struct bpf_line_info *linfo;
+ const struct bpf_prog *prog;
+ u32 i, nr_linfo;
+
+ prog = env->prog;
+ nr_linfo = prog->aux->nr_linfo;
+
+ if (!nr_linfo || insn_off >= prog->len)
+ return NULL;
+
+ linfo = prog->aux->linfo;
+ for (i = 1; i < nr_linfo; i++)
+ if (insn_off < linfo[i].insn_off)
+ break;
+
+ return &linfo[i - 1];
+}
+
+static const char *ltrim(const char *s)
+{
+ while (isspace(*s))
+ s++;
+
+ return s;
+}
+
+__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env,
+ u32 insn_off,
+ const char *prefix_fmt, ...)
+{
+ const struct bpf_line_info *linfo;
+
+ if (!bpf_verifier_log_needed(&env->log))
+ return;
+
+ linfo = find_linfo(env, insn_off);
+ if (!linfo || linfo == env->prev_linfo)
+ return;
+
+ if (prefix_fmt) {
+ va_list args;
+
+ va_start(args, prefix_fmt);
+ bpf_verifier_vlog(&env->log, prefix_fmt, args);
+ va_end(args);
+ }
+
+ verbose(env, "%s\n",
+ ltrim(btf_name_by_offset(env->prog->aux->btf,
+ linfo->line_off)));
+
+ env->prev_linfo = linfo;
+}
+
+static const char *btf_type_name(const struct btf *btf, u32 id)
+{
+ return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
+}
+
+/* string representation of 'enum bpf_reg_type'
+ *
+ * Note that reg_type_str() can not appear more than once in a single verbose()
+ * statement.
+ */
+const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type)
+{
+ char postfix[16] = {0}, prefix[64] = {0};
+ static const char * const str[] = {
+ [NOT_INIT] = "?",
+ [SCALAR_VALUE] = "scalar",
+ [PTR_TO_CTX] = "ctx",
+ [CONST_PTR_TO_MAP] = "map_ptr",
+ [PTR_TO_MAP_VALUE] = "map_value",
+ [PTR_TO_STACK] = "fp",
+ [PTR_TO_PACKET] = "pkt",
+ [PTR_TO_PACKET_META] = "pkt_meta",
+ [PTR_TO_PACKET_END] = "pkt_end",
+ [PTR_TO_FLOW_KEYS] = "flow_keys",
+ [PTR_TO_SOCKET] = "sock",
+ [PTR_TO_SOCK_COMMON] = "sock_common",
+ [PTR_TO_TCP_SOCK] = "tcp_sock",
+ [PTR_TO_TP_BUFFER] = "tp_buffer",
+ [PTR_TO_XDP_SOCK] = "xdp_sock",
+ [PTR_TO_BTF_ID] = "ptr_",
+ [PTR_TO_MEM] = "mem",
+ [PTR_TO_BUF] = "buf",
+ [PTR_TO_FUNC] = "func",
+ [PTR_TO_MAP_KEY] = "map_key",
+ [CONST_PTR_TO_DYNPTR] = "dynptr_ptr",
+ };
+
+ if (type & PTR_MAYBE_NULL) {
+ if (base_type(type) == PTR_TO_BTF_ID)
+ strncpy(postfix, "or_null_", 16);
+ else
+ strncpy(postfix, "_or_null", 16);
+ }
+
+ snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s",
+ type & MEM_RDONLY ? "rdonly_" : "",
+ type & MEM_RINGBUF ? "ringbuf_" : "",
+ type & MEM_USER ? "user_" : "",
+ type & MEM_PERCPU ? "percpu_" : "",
+ type & MEM_RCU ? "rcu_" : "",
+ type & PTR_UNTRUSTED ? "untrusted_" : "",
+ type & PTR_TRUSTED ? "trusted_" : ""
+ );
+
+ snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
+ prefix, str[base_type(type)], postfix);
+ return env->tmp_str_buf;
+}
+
+const char *dynptr_type_str(enum bpf_dynptr_type type)
+{
+ switch (type) {
+ case BPF_DYNPTR_TYPE_LOCAL:
+ return "local";
+ case BPF_DYNPTR_TYPE_RINGBUF:
+ return "ringbuf";
+ case BPF_DYNPTR_TYPE_SKB:
+ return "skb";
+ case BPF_DYNPTR_TYPE_XDP:
+ return "xdp";
+ case BPF_DYNPTR_TYPE_INVALID:
+ return "<invalid>";
+ default:
+ WARN_ONCE(1, "unknown dynptr type %d\n", type);
+ return "<unknown>";
+ }
+}
+
+const char *iter_type_str(const struct btf *btf, u32 btf_id)
+{
+ if (!btf || btf_id == 0)
+ return "<invalid>";
+
+ /* we already validated that type is valid and has conforming name */
+ return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1;
+}
+
+const char *iter_state_str(enum bpf_iter_state state)
+{
+ switch (state) {
+ case BPF_ITER_STATE_ACTIVE:
+ return "active";
+ case BPF_ITER_STATE_DRAINED:
+ return "drained";
+ case BPF_ITER_STATE_INVALID:
+ return "<invalid>";
+ default:
+ WARN_ONCE(1, "unknown iter state %d\n", state);
+ return "<unknown>";
+ }
+}
+
+static char slot_type_char[] = {
+ [STACK_INVALID] = '?',
+ [STACK_SPILL] = 'r',
+ [STACK_MISC] = 'm',
+ [STACK_ZERO] = '0',
+ [STACK_DYNPTR] = 'd',
+ [STACK_ITER] = 'i',
+};
+
+static void print_liveness(struct bpf_verifier_env *env,
+ enum bpf_reg_liveness live)
+{
+ if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
+ verbose(env, "_");
+ if (live & REG_LIVE_READ)
+ verbose(env, "r");
+ if (live & REG_LIVE_WRITTEN)
+ verbose(env, "w");
+ if (live & REG_LIVE_DONE)
+ verbose(env, "D");
+}
+
+#define UNUM_MAX_DECIMAL U16_MAX
+#define SNUM_MAX_DECIMAL S16_MAX
+#define SNUM_MIN_DECIMAL S16_MIN
+
+static bool is_unum_decimal(u64 num)
+{
+ return num <= UNUM_MAX_DECIMAL;
+}
+
+static bool is_snum_decimal(s64 num)
+{
+ return num >= SNUM_MIN_DECIMAL && num <= SNUM_MAX_DECIMAL;
+}
+
+static void verbose_unum(struct bpf_verifier_env *env, u64 num)
+{
+ if (is_unum_decimal(num))
+ verbose(env, "%llu", num);
+ else
+ verbose(env, "%#llx", num);
+}
+
+static void verbose_snum(struct bpf_verifier_env *env, s64 num)
+{
+ if (is_snum_decimal(num))
+ verbose(env, "%lld", num);
+ else
+ verbose(env, "%#llx", num);
+}
+
+int tnum_strn(char *str, size_t size, struct tnum a)
+{
+ /* print as a constant, if tnum is fully known */
+ if (a.mask == 0) {
+ if (is_unum_decimal(a.value))
+ return snprintf(str, size, "%llu", a.value);
+ else
+ return snprintf(str, size, "%#llx", a.value);
+ }
+ return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask);
+}
+EXPORT_SYMBOL_GPL(tnum_strn);
+
+static void print_scalar_ranges(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ const char **sep)
+{
+ /* For signed ranges, we want to unify 64-bit and 32-bit values in the
+ * output as much as possible, but there is a bit of a complication.
+ * If we choose to print values as decimals, this is natural to do,
+ * because negative 64-bit and 32-bit values >= -S32_MIN have the same
+ * representation due to sign extension. But if we choose to print
+ * them in hex format (see is_snum_decimal()), then sign extension is
+ * misleading.
+ * E.g., smin=-2 and smin32=-2 are exactly the same in decimal, but in
+ * hex they will be smin=0xfffffffffffffffe and smin32=0xfffffffe, two
+ * very different numbers.
+ * So we avoid sign extension if we choose to print values in hex.
+ */
+ 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",
+ is_snum_decimal((s64)reg->s32_min_value)
+ ? (s64)reg->s32_min_value
+ : (u32)reg->s32_min_value, reg->s32_min_value == S32_MIN},
+ {"smax32",
+ is_snum_decimal((s64)reg->s32_max_value)
+ ? (s64)reg->s32_max_value
+ : (u32)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);
+ }
+
+ if (m1->name[0] == 's')
+ verbose_snum(env, m1->val);
+ else
+ verbose_unum(env, m1->val);
+ }
+}
+
+static bool type_is_map_ptr(enum bpf_reg_type t) {
+ switch (base_type(t)) {
+ case CONST_PTR_TO_MAP:
+ case PTR_TO_MAP_KEY:
+ case PTR_TO_MAP_VALUE:
+ return true;
+ default:
+ return false;
+ }
+}
+
+/*
+ * _a stands for append, was shortened to avoid multiline statements below.
+ * This macro is used to output a comma separated list of attributes.
+ */
+#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; })
+
+static void print_reg_state(struct bpf_verifier_env *env,
+ const struct bpf_func_state *state,
+ const struct bpf_reg_state *reg)
+{
+ enum bpf_reg_type t;
+ const char *sep = "";
+
+ t = reg->type;
+ if (t == SCALAR_VALUE && reg->precise)
+ verbose(env, "P");
+ if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) {
+ /* reg->off should be 0 for SCALAR_VALUE */
+ verbose_snum(env, reg->var_off.value + reg->off);
+ return;
+ }
+
+ verbose(env, "%s", reg_type_str(env, t));
+ if (t == PTR_TO_STACK) {
+ if (state->frameno != reg->frameno)
+ verbose(env, "[%d]", reg->frameno);
+ if (tnum_is_const(reg->var_off)) {
+ verbose_snum(env, reg->var_off.value + reg->off);
+ return;
+ }
+ }
+ if (base_type(t) == PTR_TO_BTF_ID)
+ verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id));
+ verbose(env, "(");
+ if (reg->id)
+ verbose_a("id=%d", reg->id);
+ if (reg->ref_obj_id)
+ verbose_a("ref_obj_id=%d", reg->ref_obj_id);
+ if (type_is_non_owning_ref(reg->type))
+ verbose_a("%s", "non_own_ref");
+ if (type_is_map_ptr(t)) {
+ if (reg->map_ptr->name[0])
+ verbose_a("map=%s", reg->map_ptr->name);
+ verbose_a("ks=%d,vs=%d",
+ reg->map_ptr->key_size,
+ reg->map_ptr->value_size);
+ }
+ if (t != SCALAR_VALUE && reg->off) {
+ verbose_a("off=");
+ verbose_snum(env, reg->off);
+ }
+ if (type_is_pkt_pointer(t)) {
+ verbose_a("r=");
+ verbose_unum(env, reg->range);
+ }
+ if (base_type(t) == PTR_TO_MEM) {
+ verbose_a("sz=");
+ verbose_unum(env, reg->mem_size);
+ }
+ if (t == CONST_PTR_TO_DYNPTR)
+ verbose_a("type=%s", dynptr_type_str(reg->dynptr.type));
+ if (tnum_is_const(reg->var_off)) {
+ /* a pointer register with fixed offset */
+ if (reg->var_off.value) {
+ verbose_a("imm=");
+ verbose_snum(env, reg->var_off.value);
+ }
+ } else {
+ 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);
+ }
+ }
+ verbose(env, ")");
+}
+
+void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state,
+ bool print_all)
+{
+ const struct bpf_reg_state *reg;
+ int i;
+
+ if (state->frameno)
+ verbose(env, " frame%d:", state->frameno);
+ for (i = 0; i < MAX_BPF_REG; i++) {
+ reg = &state->regs[i];
+ if (reg->type == NOT_INIT)
+ continue;
+ if (!print_all && !reg_scratched(env, i))
+ continue;
+ verbose(env, " R%d", i);
+ print_liveness(env, reg->live);
+ verbose(env, "=");
+ print_reg_state(env, state, reg);
+ }
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ char types_buf[BPF_REG_SIZE + 1];
+ const char *sep = "";
+ bool valid = false;
+ u8 slot_type;
+ int j;
+
+ if (!print_all && !stack_slot_scratched(env, i))
+ continue;
+
+ for (j = 0; j < BPF_REG_SIZE; j++) {
+ slot_type = state->stack[i].slot_type[j];
+ if (slot_type != STACK_INVALID)
+ valid = true;
+ types_buf[j] = slot_type_char[slot_type];
+ }
+ types_buf[BPF_REG_SIZE] = 0;
+ if (!valid)
+ continue;
+
+ reg = &state->stack[i].spilled_ptr;
+ switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) {
+ case STACK_SPILL:
+ /* print MISC/ZERO/INVALID slots above subreg spill */
+ for (j = 0; j < BPF_REG_SIZE; j++)
+ if (state->stack[i].slot_type[j] == STACK_SPILL)
+ break;
+ types_buf[j] = '\0';
+
+ verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+ print_liveness(env, reg->live);
+ verbose(env, "=%s", types_buf);
+ print_reg_state(env, state, reg);
+ break;
+ case STACK_DYNPTR:
+ /* skip to main dynptr slot */
+ i += BPF_DYNPTR_NR_SLOTS - 1;
+ reg = &state->stack[i].spilled_ptr;
+
+ verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+ print_liveness(env, reg->live);
+ verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type));
+ if (reg->id)
+ verbose_a("id=%d", reg->id);
+ if (reg->ref_obj_id)
+ verbose_a("ref_id=%d", reg->ref_obj_id);
+ if (reg->dynptr_id)
+ verbose_a("dynptr_id=%d", reg->dynptr_id);
+ verbose(env, ")");
+ break;
+ case STACK_ITER:
+ /* only main slot has ref_obj_id set; skip others */
+ if (!reg->ref_obj_id)
+ continue;
+
+ verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+ print_liveness(env, reg->live);
+ verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)",
+ iter_type_str(reg->iter.btf, reg->iter.btf_id),
+ reg->ref_obj_id, iter_state_str(reg->iter.state),
+ reg->iter.depth);
+ break;
+ case STACK_MISC:
+ case STACK_ZERO:
+ default:
+ verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+ print_liveness(env, reg->live);
+ verbose(env, "=%s", types_buf);
+ break;
+ }
+ }
+ if (state->acquired_refs && state->refs[0].id) {
+ verbose(env, " refs=%d", state->refs[0].id);
+ for (i = 1; i < state->acquired_refs; i++)
+ if (state->refs[i].id)
+ verbose(env, ",%d", state->refs[i].id);
+ }
+ if (state->in_callback_fn)
+ verbose(env, " cb");
+ if (state->in_async_callback_fn)
+ verbose(env, " async_cb");
+ verbose(env, "\n");
+ if (!print_all)
+ mark_verifier_state_clean(env);
+}
+
+static inline u32 vlog_alignment(u32 pos)
+{
+ return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
+ BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+}
+
+void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state)
+{
+ if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) {
+ /* remove new line character */
+ bpf_vlog_reset(&env->log, env->prev_log_pos - 1);
+ verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' ');
+ } else {
+ verbose(env, "%d:", env->insn_idx);
+ }
+ print_verifier_state(env, state, false);
+}
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 17c7e7782a1f..b32be680da6c 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -231,6 +231,9 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)
struct lpm_trie_node *node, *found = NULL;
struct bpf_lpm_trie_key *key = _key;
+ if (key->prefixlen > trie->max_prefixlen)
+ return NULL;
+
/* Start walking the trie from the root node ... */
for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held());
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index cd5eafaba97e..8ef269e66ba5 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -127,12 +127,21 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map,
return inner_map;
}
-void bpf_map_fd_put_ptr(void *ptr)
+void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
{
- /* ptr->ops->map_free() has to go through one
- * rcu grace period by itself.
+ struct bpf_map *inner_map = ptr;
+
+ /* Defer the freeing of inner map according to the sleepable attribute
+ * of bpf program which owns the outer map, so unnecessary waiting for
+ * RCU tasks trace grace period can be avoided.
*/
- bpf_map_put(ptr);
+ if (need_defer) {
+ if (atomic64_read(&map->sleepable_refcnt))
+ WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true);
+ else
+ WRITE_ONCE(inner_map->free_after_rcu_gp, true);
+ }
+ bpf_map_put(inner_map);
}
u32 bpf_map_fd_sys_lookup_elem(void *ptr)
diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h
index bcb7534afb3c..7d61602354de 100644
--- a/kernel/bpf/map_in_map.h
+++ b/kernel/bpf/map_in_map.h
@@ -13,7 +13,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd);
void bpf_map_meta_free(struct bpf_map *map_meta);
void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file,
int ufd);
-void bpf_map_fd_put_ptr(void *ptr);
+void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer);
u32 bpf_map_fd_sys_lookup_elem(void *ptr);
#endif
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 63b909d277d4..550f02e2cb13 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -121,6 +121,8 @@ struct bpf_mem_caches {
struct bpf_mem_cache cache[NUM_CACHES];
};
+static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+
static struct llist_node notrace *__llist_del_first(struct llist_head *head)
{
struct llist_node *entry, *next;
@@ -462,11 +464,17 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
* consume ~ 11 Kbyte per cpu.
* Typical case will be between 11K and 116K closer to 11K.
* bpf progs can and should share bpf_mem_cache when possible.
+ *
+ * Percpu allocation is typically rare. To avoid potential unnecessary large
+ * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1.
*/
static void init_refill_work(struct bpf_mem_cache *c)
{
init_irq_work(&c->refill_work, bpf_mem_refill);
- if (c->unit_size <= 256) {
+ if (c->percpu_size) {
+ c->low_watermark = 1;
+ c->high_watermark = 3;
+ } else if (c->unit_size <= 256) {
c->low_watermark = 32;
c->high_watermark = 96;
} else {
@@ -483,32 +491,16 @@ static void init_refill_work(struct bpf_mem_cache *c)
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), false);
-}
-
-static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
-{
- struct llist_node *first;
- unsigned int obj_size;
+ int cnt = 1;
- 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;
+ /* To avoid consuming memory, for non-percpu allocation, assume that
+ * 1st run of bpf prog won't be doing more than 4 map_update_elem from
+ * irq disabled region if unit size is less than or equal to 256.
+ * For all other cases, let us just do one allocation.
+ */
+ if (!c->percpu_size && c->unit_size <= 256)
+ cnt = 4;
+ alloc_bulk(c, cnt, cpu_to_node(cpu), false);
}
/* When size != 0 bpf_mem_cache for each cpu.
@@ -520,11 +512,13 @@ static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
*/
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;
+
+ if (percpu && size == 0)
+ return -EINVAL;
/* room for llist_node and per-cpu pointer */
if (percpu)
@@ -544,6 +538,8 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
if (memcg_bpf_enabled())
objcg = get_obj_cgroup_from_current();
#endif
+ ma->objcg = objcg;
+
for_each_possible_cpu(cpu) {
c = per_cpu_ptr(pc, cpu);
c->unit_size = unit_size;
@@ -560,10 +556,10 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
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
+ ma->objcg = objcg;
for_each_possible_cpu(cpu) {
cc = per_cpu_ptr(pcc, cpu);
for (i = 0; i < NUM_CACHES; i++) {
@@ -574,28 +570,62 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
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;
- /* 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;
+ return 0;
+}
+
+int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg)
+{
+ struct bpf_mem_caches __percpu *pcc;
+
+ pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL);
+ if (!pcc)
+ return -ENOMEM;
+
+ ma->caches = pcc;
+ ma->objcg = objcg;
+ ma->percpu = true;
+ return 0;
+}
+
+int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size)
+{
+ struct bpf_mem_caches *cc, __percpu *pcc;
+ int cpu, i, unit_size, percpu_size;
+ struct obj_cgroup *objcg;
+ struct bpf_mem_cache *c;
+
+ i = bpf_mem_cache_idx(size);
+ if (i < 0)
+ return -EINVAL;
+
+ /* room for llist_node and per-cpu pointer */
+ percpu_size = LLIST_NODE_SZ + sizeof(void *);
+
+ unit_size = sizes[i];
+ objcg = ma->objcg;
+ pcc = ma->caches;
+
+ for_each_possible_cpu(cpu) {
+ cc = per_cpu_ptr(pcc, cpu);
+ c = &cc->cache[i];
+ if (c->unit_size)
+ break;
+
+ 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);
+ }
+
+ return 0;
}
static void drain_mem_cache(struct bpf_mem_cache *c)
@@ -729,9 +759,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
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 */
- if (c->objcg)
- obj_cgroup_put(c->objcg);
+ if (ma->objcg)
+ obj_cgroup_put(ma->objcg);
destroy_mem_alloc(ma, rcu_in_progress);
}
if (ma->caches) {
@@ -747,8 +776,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
}
}
- if (c->objcg)
- obj_cgroup_put(c->objcg);
+ if (ma->objcg)
+ obj_cgroup_put(ma->objcg);
destroy_mem_alloc(ma, rcu_in_progress);
}
}
@@ -869,9 +898,11 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
void *ret;
if (!size)
- return ZERO_SIZE_PTR;
+ return NULL;
- idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ);
+ if (!ma->percpu)
+ size += LLIST_NODE_SZ;
+ idx = bpf_mem_cache_idx(size);
if (idx < 0)
return NULL;
@@ -879,26 +910,17 @@ 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)
{
+ struct bpf_mem_cache *c;
int idx;
if (!ptr)
return;
- idx = bpf_mem_free_idx(ptr, ma->percpu);
- if (idx < 0)
+ c = *(void **)(ptr - LLIST_NODE_SZ);
+ idx = bpf_mem_cache_idx(c->unit_size);
+ if (WARN_ON_ONCE(idx < 0))
return;
unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
@@ -906,13 +928,15 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
{
+ struct bpf_mem_cache *c;
int idx;
if (!ptr)
return;
- idx = bpf_mem_free_idx(ptr, ma->percpu);
- if (idx < 0)
+ c = *(void **)(ptr - LLIST_NODE_SZ);
+ idx = bpf_mem_cache_idx(c->unit_size);
+ if (WARN_ON_ONCE(idx < 0))
return;
unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr);
@@ -978,47 +1002,11 @@ 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/stackmap.c b/kernel/bpf/stackmap.c
index d6b277482085..dff7ba539701 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -388,6 +388,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
{
u32 trace_nr, copy_len, elem_size, num_elem, max_depth;
bool user_build_id = flags & BPF_F_USER_BUILD_ID;
+ bool crosstask = task && task != current;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
bool user = flags & BPF_F_USER_STACK;
struct perf_callchain_entry *trace;
@@ -410,6 +411,14 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
if (task && user && !user_mode(regs))
goto err_fault;
+ /* get_perf_callchain does not support crosstask user stack walking
+ * but returns an empty stack instead of NULL.
+ */
+ if (crosstask && user) {
+ err = -EOPNOTSUPP;
+ goto clear;
+ }
+
num_elem = size / elem_size;
max_depth = num_elem + skip;
if (sysctl_perf_event_max_stack < max_depth)
@@ -421,7 +430,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
trace = get_callchain_entry_for_task(task, max_depth);
else
trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
- false, false);
+ crosstask, false);
if (unlikely(!trace))
goto err_fault;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0ed286b8a0f0..a1f18681721c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -142,9 +142,13 @@ static u32 bpf_map_value_size(const struct bpf_map *map)
static void maybe_wait_bpf_programs(struct bpf_map *map)
{
- /* Wait for any running BPF programs to complete so that
- * userspace, when we return to it, knows that all programs
- * that could be running use the new map value.
+ /* Wait for any running non-sleepable BPF programs to complete so that
+ * userspace, when we return to it, knows that all non-sleepable
+ * programs that could be running use the new map value. For sleepable
+ * BPF programs, synchronize_rcu_tasks_trace() should be used to wait
+ * for the completions of these programs, but considering the waiting
+ * time can be very long and userspace may think it will hang forever,
+ * so don't handle sleepable BPF programs now.
*/
if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
@@ -180,15 +184,11 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
err = bpf_percpu_cgroup_storage_update(map, key, value,
flags);
} else if (IS_FD_ARRAY(map)) {
- rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, map_file, key, value,
flags);
- rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
- rcu_read_lock();
err = bpf_fd_htab_map_update_elem(map, map_file, key, value,
flags);
- rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
/* rcu_read_lock() is not needed */
err = bpf_fd_reuseport_array_update_elem(map, key, value,
@@ -203,7 +203,6 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
rcu_read_unlock();
}
bpf_enable_instrumentation();
- maybe_wait_bpf_programs(map);
return err;
}
@@ -264,7 +263,6 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
}
bpf_enable_instrumentation();
- maybe_wait_bpf_programs(map);
return err;
}
@@ -694,6 +692,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
struct btf_record *rec = map->record;
+ struct btf *btf = map->btf;
security_bpf_map_free(map);
bpf_map_release_memcg(map);
@@ -709,6 +708,10 @@ static void bpf_map_free_deferred(struct work_struct *work)
* template bpf_map struct used during verification.
*/
btf_record_free(rec);
+ /* Delay freeing of btf for maps, as map_free callback may need
+ * struct_meta info which will be freed with btf_put().
+ */
+ btf_put(btf);
}
static void bpf_map_put_uref(struct bpf_map *map)
@@ -719,6 +722,28 @@ static void bpf_map_put_uref(struct bpf_map *map)
}
}
+static void bpf_map_free_in_work(struct bpf_map *map)
+{
+ INIT_WORK(&map->work, bpf_map_free_deferred);
+ /* Avoid spawning kworkers, since they all might contend
+ * for the same mutex like slab_mutex.
+ */
+ queue_work(system_unbound_wq, &map->work);
+}
+
+static void bpf_map_free_rcu_gp(struct rcu_head *rcu)
+{
+ bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu));
+}
+
+static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu)
+{
+ if (rcu_trace_implies_rcu_gp())
+ bpf_map_free_rcu_gp(rcu);
+ else
+ call_rcu(rcu, bpf_map_free_rcu_gp);
+}
+
/* decrement map refcnt and schedule it for freeing via workqueue
* (underlying map implementation ops->map_free() might sleep)
*/
@@ -727,12 +752,14 @@ void bpf_map_put(struct bpf_map *map)
if (atomic64_dec_and_test(&map->refcnt)) {
/* bpf_map_free_id() must be called first */
bpf_map_free_id(map);
- btf_put(map->btf);
- INIT_WORK(&map->work, bpf_map_free_deferred);
- /* Avoid spawning kworkers, since they all might contend
- * for the same mutex like slab_mutex.
- */
- queue_work(system_unbound_wq, &map->work);
+
+ WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt));
+ if (READ_ONCE(map->free_after_mult_rcu_gp))
+ call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp);
+ else if (READ_ONCE(map->free_after_rcu_gp))
+ call_rcu(&map->rcu, bpf_map_free_rcu_gp);
+ else
+ bpf_map_free_in_work(map);
}
}
EXPORT_SYMBOL_GPL(bpf_map_put);
@@ -1524,6 +1551,8 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
}
err = bpf_map_update_value(map, f.file, key, value, attr->flags);
+ if (!err)
+ maybe_wait_bpf_programs(map);
kvfree(value);
free_key:
@@ -1579,7 +1608,8 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr)
err = map->ops->map_delete_elem(map, key);
rcu_read_unlock();
bpf_enable_instrumentation();
- maybe_wait_bpf_programs(map);
+ if (!err)
+ maybe_wait_bpf_programs(map);
out:
kvfree(key);
err_put:
@@ -1676,6 +1706,9 @@ int generic_map_delete_batch(struct bpf_map *map,
if (!max_count)
return 0;
+ if (put_user(0, &uattr->batch.count))
+ return -EFAULT;
+
key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
if (!key)
return -ENOMEM;
@@ -1705,7 +1738,6 @@ int generic_map_delete_batch(struct bpf_map *map,
kvfree(key);
- maybe_wait_bpf_programs(map);
return err;
}
@@ -1733,6 +1765,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
if (!max_count)
return 0;
+ if (put_user(0, &uattr->batch.count))
+ return -EFAULT;
+
key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
if (!key)
return -ENOMEM;
@@ -1763,6 +1798,7 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
kvfree(value);
kvfree(key);
+
return err;
}
@@ -2573,7 +2609,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
BPF_F_SLEEPABLE |
BPF_F_TEST_RND_HI32 |
BPF_F_XDP_HAS_FRAGS |
- BPF_F_XDP_DEV_BOUND_ONLY))
+ BPF_F_XDP_DEV_BOUND_ONLY |
+ BPF_F_TEST_REG_INVARIANTS))
return -EINVAL;
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
@@ -2701,6 +2738,22 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
goto free_prog_sec;
}
+ /*
+ * Bookkeeping for managing the program attachment chain.
+ *
+ * It might be tempting to set attach_tracing_prog flag at the attachment
+ * time, but this will not prevent from loading bunch of tracing prog
+ * first, then attach them one to another.
+ *
+ * The flag attach_tracing_prog is set for the whole program lifecycle, and
+ * doesn't have to be cleared in bpf_tracing_link_release, since tracing
+ * programs cannot change attachment target.
+ */
+ if (type == BPF_PROG_TYPE_TRACING && dst_prog &&
+ dst_prog->type == BPF_PROG_TYPE_TRACING) {
+ prog->aux->attach_tracing_prog = true;
+ }
+
/* find program type: socket_filter vs tracing_filter */
err = find_prog_type(type, prog);
if (err < 0)
@@ -3134,7 +3187,12 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
}
if (tgt_prog_fd) {
- /* For now we only allow new targets for BPF_PROG_TYPE_EXT */
+ /*
+ * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this
+ * part would be changed to implement the same for
+ * BPF_PROG_TYPE_TRACING, do not forget to update the way how
+ * attach_tracing_prog flag is set.
+ */
if (prog->type != BPF_PROG_TYPE_EXT) {
err = -EINVAL;
goto out_put_prog;
@@ -3179,6 +3237,10 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
*
* - if prog->aux->dst_trampoline and tgt_prog is NULL, the program
* was detached and is going for re-attachment.
+ *
+ * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf
+ * are NULL, then program was already attached and user did not provide
+ * tgt_prog_fd so we have no way to find out or create trampoline
*/
if (!prog->aux->dst_trampoline && !tgt_prog) {
/*
@@ -3192,6 +3254,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
err = -EINVAL;
goto out_unlock;
}
+ /* We can allow re-attach only if we have valid attach_btf. */
+ if (!prog->aux->attach_btf) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
btf_id = prog->aux->attach_btf_id;
key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id);
}
@@ -4919,8 +4986,10 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
else
BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr);
err_put:
- if (has_write)
+ if (has_write) {
+ maybe_wait_bpf_programs(map);
bpf_map_write_active_dec(map);
+ }
fdput(f);
return err;
}
@@ -5322,6 +5391,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr)
goto out_unlock;
}
+ /* The bpf program will not access the bpf map, but for the sake of
+ * simplicity, increase sleepable_refcnt for sleepable program as well.
+ */
+ if (prog->aux->sleepable)
+ atomic64_inc(&map->sleepable_refcnt);
memcpy(used_maps_new, used_maps_old,
sizeof(used_maps_old[0]) * prog->aux->used_map_cnt);
used_maps_new[prog->aux->used_map_cnt] = map;
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 26082b97894d..e5c3500443c6 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -70,15 +70,13 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm
return NULL;
retry:
- task = next_thread(task);
+ task = __next_thread(task);
+ if (!task)
+ return NULL;
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.
- */
- return NULL;
- }
+ if (!next_tid)
+ goto retry;
if (skip_if_dup_files && task->files == task->group_leader->files)
goto retry;
@@ -980,7 +978,6 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
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:
@@ -1017,20 +1014,16 @@ __bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it)
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
+ kit->pos = __next_thread(kit->pos);
+ if (kit->pos || flags == BPF_TASK_ITER_PROC_THREADS)
return pos;
get_next_task:
- kit->pos = next_task(kit->pos);
- kit->task = kit->pos;
- if (kit->pos == &init_task)
+ kit->task = next_task(kit->task);
+ if (kit->task == &init_task)
kit->pos = NULL;
+ else
+ kit->pos = kit->task;
return pos;
}
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 3d7127f439a1..9dbc31b25e3d 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -172,12 +172,6 @@ bool tnum_in(struct tnum a, struct tnum b)
return a.value == b.value;
}
-int tnum_strn(char *str, size_t size, struct tnum a)
-{
- return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask);
-}
-EXPORT_SYMBOL_GPL(tnum_strn);
-
int tnum_sbin(char *str, size_t size, struct tnum a)
{
size_t n;
@@ -208,7 +202,12 @@ struct tnum tnum_clear_subreg(struct tnum a)
return tnum_lshift(tnum_rshift(a, 32), 32);
}
+struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg)
+{
+ return tnum_or(tnum_clear_subreg(reg), tnum_subreg(subreg));
+}
+
struct tnum tnum_const_subreg(struct tnum a, u32 value)
{
- return tnum_or(tnum_clear_subreg(a), tnum_const(value));
+ return tnum_with_subreg(a, tnum_const(value));
}
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index e97aeda3a86b..d382f5ebe06c 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -115,10 +115,10 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
(ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC);
}
-void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym)
+void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym)
{
ksym->start = (unsigned long) data;
- ksym->end = ksym->start + PAGE_SIZE;
+ ksym->end = ksym->start + size;
bpf_ksym_add(ksym);
perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
PAGE_SIZE, false, ksym->name);
@@ -254,8 +254,8 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a
static void bpf_tramp_image_free(struct bpf_tramp_image *im)
{
bpf_image_ksym_del(&im->ksym);
- bpf_jit_free_exec(im->image);
- bpf_jit_uncharge_modmem(PAGE_SIZE);
+ arch_free_bpf_trampoline(im->image, im->size);
+ bpf_jit_uncharge_modmem(im->size);
percpu_ref_exit(&im->pcref);
kfree_rcu(im, rcu);
}
@@ -349,7 +349,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im)
call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
}
-static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
+static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size)
{
struct bpf_tramp_image *im;
struct bpf_ksym *ksym;
@@ -360,15 +360,15 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
if (!im)
goto out;
- err = bpf_jit_charge_modmem(PAGE_SIZE);
+ err = bpf_jit_charge_modmem(size);
if (err)
goto out_free_im;
+ im->size = size;
err = -ENOMEM;
- im->image = image = bpf_jit_alloc_exec(PAGE_SIZE);
+ im->image = image = arch_alloc_bpf_trampoline(size);
if (!image)
goto out_uncharge;
- set_vm_flush_reset_perms(image);
err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL);
if (err)
@@ -377,13 +377,13 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
ksym = &im->ksym;
INIT_LIST_HEAD_RCU(&ksym->lnode);
snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key);
- bpf_image_ksym_add(image, ksym);
+ bpf_image_ksym_add(image, size, ksym);
return im;
out_free_image:
- bpf_jit_free_exec(im->image);
+ arch_free_bpf_trampoline(im->image, im->size);
out_uncharge:
- bpf_jit_uncharge_modmem(PAGE_SIZE);
+ bpf_jit_uncharge_modmem(size);
out_free_im:
kfree(im);
out:
@@ -396,7 +396,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
struct bpf_tramp_links *tlinks;
u32 orig_flags = tr->flags;
bool ip_arg = false;
- int err, total;
+ int err, total, size;
tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg);
if (IS_ERR(tlinks))
@@ -409,12 +409,6 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
goto out;
}
- im = bpf_tramp_image_alloc(tr->key);
- if (IS_ERR(im)) {
- err = PTR_ERR(im);
- goto out;
- }
-
/* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */
tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX);
@@ -438,13 +432,31 @@ again:
tr->flags |= BPF_TRAMP_F_ORIG_STACK;
#endif
- err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
+ size = arch_bpf_trampoline_size(&tr->func.model, tr->flags,
+ tlinks, tr->func.addr);
+ if (size < 0) {
+ err = size;
+ goto out;
+ }
+
+ if (size > PAGE_SIZE) {
+ err = -E2BIG;
+ goto out;
+ }
+
+ im = bpf_tramp_image_alloc(tr->key, size);
+ if (IS_ERR(im)) {
+ err = PTR_ERR(im);
+ goto out;
+ }
+
+ err = arch_prepare_bpf_trampoline(im, im->image, im->image + size,
&tr->func.model, tr->flags, tlinks,
tr->func.addr);
if (err < 0)
goto out_free;
- set_memory_rox((long)im->image, 1);
+ arch_protect_bpf_trampoline(im->image, im->size);
WARN_ON(tr->cur_image && total == 0);
if (tr->cur_image)
@@ -464,9 +476,8 @@ again:
tr->fops->func = NULL;
tr->fops->trampoline = 0;
- /* reset im->image memory attr for arch_prepare_bpf_trampoline */
- set_memory_nx((long)im->image, 1);
- set_memory_rw((long)im->image, 1);
+ /* free im memory and reallocate later */
+ bpf_tramp_image_free(im);
goto again;
}
#endif
@@ -1032,10 +1043,50 @@ bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog)
}
int __weak
-arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
+arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_tramp_links *tlinks,
- void *orig_call)
+ void *func_addr)
+{
+ return -ENOTSUPP;
+}
+
+void * __weak arch_alloc_bpf_trampoline(unsigned int size)
+{
+ void *image;
+
+ if (WARN_ON_ONCE(size > PAGE_SIZE))
+ return NULL;
+ image = bpf_jit_alloc_exec(PAGE_SIZE);
+ if (image)
+ set_vm_flush_reset_perms(image);
+ return image;
+}
+
+void __weak arch_free_bpf_trampoline(void *image, unsigned int size)
+{
+ WARN_ON_ONCE(size > PAGE_SIZE);
+ /* bpf_jit_free_exec doesn't need "size", but
+ * bpf_prog_pack_free() needs it.
+ */
+ bpf_jit_free_exec(image);
+}
+
+void __weak arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+ WARN_ON_ONCE(size > PAGE_SIZE);
+ set_memory_rox((long)image, 1);
+}
+
+void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+{
+ WARN_ON_ONCE(size > PAGE_SIZE);
+ set_memory_nx((long)image, 1);
+ set_memory_rw((long)image, 1);
+}
+
+int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+ struct bpf_tramp_links *tlinks, void *func_addr)
{
return -ENOTSUPP;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index af2819d5c8ee..adbf330d364b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -195,6 +195,8 @@ struct bpf_verifier_stack_elem {
POISON_POINTER_DELTA))
#define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
+#define BPF_GLOBAL_PERCPU_MA_MAX_SIZE 512
+
static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx);
static int release_reference(struct bpf_verifier_env *env, int ref_obj_id);
static void invalidate_non_owning_refs(struct bpf_verifier_env *env);
@@ -339,30 +341,14 @@ 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)
+static const char *btf_type_name(const struct btf *btf, u32 id)
{
- const struct bpf_line_info *linfo;
- const struct bpf_prog *prog;
- u32 i, nr_linfo;
-
- prog = env->prog;
- nr_linfo = prog->aux->nr_linfo;
-
- if (!nr_linfo || insn_off >= prog->len)
- return NULL;
-
- linfo = prog->aux->linfo;
- for (i = 1; i < nr_linfo; i++)
- if (insn_off < linfo[i].insn_off)
- break;
-
- return &linfo[i - 1];
+ return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
}
+static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
+
__printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
{
struct bpf_verifier_env *env = private_data;
@@ -376,73 +362,25 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
va_end(args);
}
-static const char *ltrim(const char *s)
-{
- while (isspace(*s))
- s++;
-
- return s;
-}
-
-__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
- u32 insn_off,
- const char *prefix_fmt, ...)
-{
- const struct bpf_line_info *linfo;
-
- if (!bpf_verifier_log_needed(&env->log))
- return;
-
- linfo = find_linfo(env, insn_off);
- if (!linfo || linfo == env->prev_linfo)
- return;
-
- if (prefix_fmt) {
- va_list args;
-
- va_start(args, prefix_fmt);
- bpf_verifier_vlog(&env->log, prefix_fmt, args);
- va_end(args);
- }
-
- verbose(env, "%s\n",
- ltrim(btf_name_by_offset(env->prog->aux->btf,
- linfo->line_off)));
-
- env->prev_linfo = linfo;
-}
-
static void verbose_invalid_scalar(struct bpf_verifier_env *env,
struct bpf_reg_state *reg,
- struct tnum *range, const char *ctx,
+ struct bpf_retval_range range, const char *ctx,
const char *reg_name)
{
- char tn_buf[48];
+ bool unknown = true;
- verbose(env, "At %s the register %s ", ctx, reg_name);
- if (!tnum_is_unknown(reg->var_off)) {
- tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "has value %s", tn_buf);
- } else {
- verbose(env, "has unknown scalar value");
+ verbose(env, "%s the register %s has", ctx, reg_name);
+ if (reg->smin_value > S64_MIN) {
+ verbose(env, " smin=%lld", reg->smin_value);
+ unknown = false;
}
- tnum_strn(tn_buf, sizeof(tn_buf), *range);
- verbose(env, " should have been in %s\n", tn_buf);
-}
-
-static bool type_is_pkt_pointer(enum bpf_reg_type type)
-{
- type = base_type(type);
- return type == PTR_TO_PACKET ||
- type == PTR_TO_PACKET_META;
-}
-
-static bool type_is_sk_pointer(enum bpf_reg_type type)
-{
- return type == PTR_TO_SOCKET ||
- type == PTR_TO_SOCK_COMMON ||
- type == PTR_TO_TCP_SOCK ||
- type == PTR_TO_XDP_SOCK;
+ if (reg->smax_value < S64_MAX) {
+ verbose(env, " smax=%lld", reg->smax_value);
+ unknown = false;
+ }
+ if (unknown)
+ verbose(env, " unknown scalar value");
+ verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval);
}
static bool type_may_be_null(u32 type)
@@ -468,16 +406,6 @@ static bool reg_not_null(const struct bpf_reg_state *reg)
type == PTR_TO_MEM;
}
-static bool type_is_ptr_alloc_obj(u32 type)
-{
- return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC;
-}
-
-static bool type_is_non_owning_ref(u32 type)
-{
- return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF;
-}
-
static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
{
struct btf_record *rec = NULL;
@@ -500,6 +428,31 @@ static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog)
return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL;
}
+static const char *subprog_name(const struct bpf_verifier_env *env, int subprog)
+{
+ struct bpf_func_info *info;
+
+ if (!env->prog->aux->func_info)
+ return "";
+
+ info = &env->prog->aux->func_info[subprog];
+ return btf_type_name(env->prog->aux->btf, info->type_id);
+}
+
+static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog)
+{
+ struct bpf_subprog_info *info = subprog_info(env, subprog);
+
+ info->is_cb = true;
+ info->is_async_cb = true;
+ info->is_exception_cb = true;
+}
+
+static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog)
+{
+ return subprog_info(env, subprog)->is_exception_cb;
+}
+
static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
{
return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK);
@@ -605,83 +558,6 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn)
insn->imm == BPF_CMPXCHG;
}
-/* string representation of 'enum bpf_reg_type'
- *
- * Note that reg_type_str() can not appear more than once in a single verbose()
- * statement.
- */
-static const char *reg_type_str(struct bpf_verifier_env *env,
- enum bpf_reg_type type)
-{
- char postfix[16] = {0}, prefix[64] = {0};
- static const char * const str[] = {
- [NOT_INIT] = "?",
- [SCALAR_VALUE] = "scalar",
- [PTR_TO_CTX] = "ctx",
- [CONST_PTR_TO_MAP] = "map_ptr",
- [PTR_TO_MAP_VALUE] = "map_value",
- [PTR_TO_STACK] = "fp",
- [PTR_TO_PACKET] = "pkt",
- [PTR_TO_PACKET_META] = "pkt_meta",
- [PTR_TO_PACKET_END] = "pkt_end",
- [PTR_TO_FLOW_KEYS] = "flow_keys",
- [PTR_TO_SOCKET] = "sock",
- [PTR_TO_SOCK_COMMON] = "sock_common",
- [PTR_TO_TCP_SOCK] = "tcp_sock",
- [PTR_TO_TP_BUFFER] = "tp_buffer",
- [PTR_TO_XDP_SOCK] = "xdp_sock",
- [PTR_TO_BTF_ID] = "ptr_",
- [PTR_TO_MEM] = "mem",
- [PTR_TO_BUF] = "buf",
- [PTR_TO_FUNC] = "func",
- [PTR_TO_MAP_KEY] = "map_key",
- [CONST_PTR_TO_DYNPTR] = "dynptr_ptr",
- };
-
- if (type & PTR_MAYBE_NULL) {
- if (base_type(type) == PTR_TO_BTF_ID)
- strncpy(postfix, "or_null_", 16);
- else
- strncpy(postfix, "_or_null", 16);
- }
-
- snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s",
- type & MEM_RDONLY ? "rdonly_" : "",
- type & MEM_RINGBUF ? "ringbuf_" : "",
- type & MEM_USER ? "user_" : "",
- type & MEM_PERCPU ? "percpu_" : "",
- type & MEM_RCU ? "rcu_" : "",
- type & PTR_UNTRUSTED ? "untrusted_" : "",
- type & PTR_TRUSTED ? "trusted_" : ""
- );
-
- snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
- prefix, str[base_type(type)], postfix);
- return env->tmp_str_buf;
-}
-
-static char slot_type_char[] = {
- [STACK_INVALID] = '?',
- [STACK_SPILL] = 'r',
- [STACK_MISC] = 'm',
- [STACK_ZERO] = '0',
- [STACK_DYNPTR] = 'd',
- [STACK_ITER] = 'i',
-};
-
-static void print_liveness(struct bpf_verifier_env *env,
- enum bpf_reg_liveness live)
-{
- if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
- verbose(env, "_");
- if (live & REG_LIVE_READ)
- verbose(env, "r");
- if (live & REG_LIVE_WRITTEN)
- verbose(env, "w");
- if (live & REG_LIVE_DONE)
- verbose(env, "D");
-}
-
static int __get_spi(s32 off)
{
return (-off - 1) / BPF_REG_SIZE;
@@ -746,92 +622,6 @@ static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
return stack_slot_obj_get_spi(env, reg, "iter", nr_slots);
}
-static const char *btf_type_name(const struct btf *btf, u32 id)
-{
- return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
-}
-
-static const char *dynptr_type_str(enum bpf_dynptr_type type)
-{
- switch (type) {
- case BPF_DYNPTR_TYPE_LOCAL:
- return "local";
- case BPF_DYNPTR_TYPE_RINGBUF:
- return "ringbuf";
- case BPF_DYNPTR_TYPE_SKB:
- return "skb";
- case BPF_DYNPTR_TYPE_XDP:
- return "xdp";
- case BPF_DYNPTR_TYPE_INVALID:
- return "<invalid>";
- default:
- WARN_ONCE(1, "unknown dynptr type %d\n", type);
- return "<unknown>";
- }
-}
-
-static const char *iter_type_str(const struct btf *btf, u32 btf_id)
-{
- if (!btf || btf_id == 0)
- return "<invalid>";
-
- /* we already validated that type is valid and has conforming name */
- return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1;
-}
-
-static const char *iter_state_str(enum bpf_iter_state state)
-{
- switch (state) {
- case BPF_ITER_STATE_ACTIVE:
- return "active";
- case BPF_ITER_STATE_DRAINED:
- return "drained";
- case BPF_ITER_STATE_INVALID:
- return "<invalid>";
- default:
- WARN_ONCE(1, "unknown iter state %d\n", state);
- return "<unknown>";
- }
-}
-
-static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
-{
- env->scratched_regs |= 1U << regno;
-}
-
-static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
-{
- env->scratched_stack_slots |= 1ULL << spi;
-}
-
-static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
-{
- return (env->scratched_regs >> regno) & 1;
-}
-
-static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
-{
- return (env->scratched_stack_slots >> regno) & 1;
-}
-
-static bool verifier_state_scratched(const struct bpf_verifier_env *env)
-{
- return env->scratched_regs || env->scratched_stack_slots;
-}
-
-static void mark_verifier_state_clean(struct bpf_verifier_env *env)
-{
- env->scratched_regs = 0U;
- env->scratched_stack_slots = 0ULL;
-}
-
-/* Used for printing the entire verifier state. */
-static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
-{
- env->scratched_regs = ~0U;
- env->scratched_stack_slots = ~0ULL;
-}
-
static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
{
switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
@@ -1365,230 +1155,25 @@ static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack)
stack->spilled_ptr.type == SCALAR_VALUE;
}
-static void scrub_spilled_slot(u8 *stype)
-{
- if (*stype != STACK_INVALID)
- *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)
-{
- const struct bpf_reg_state *reg;
- enum bpf_reg_type t;
- int i;
-
- if (state->frameno)
- verbose(env, " frame%d:", state->frameno);
- for (i = 0; i < MAX_BPF_REG; i++) {
- reg = &state->regs[i];
- t = reg->type;
- if (t == NOT_INIT)
- continue;
- if (!print_all && !reg_scratched(env, i))
- continue;
- verbose(env, " R%d", i);
- print_liveness(env, reg->live);
- verbose(env, "=");
- if (t == SCALAR_VALUE && reg->precise)
- verbose(env, "P");
- if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
- tnum_is_const(reg->var_off)) {
- /* reg->off should be 0 for SCALAR_VALUE */
- verbose(env, "%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
- verbose(env, "%lld", reg->var_off.value + reg->off);
- } else {
- const char *sep = "";
-
- verbose(env, "%s", reg_type_str(env, t));
- if (base_type(t) == PTR_TO_BTF_ID)
- verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id));
- verbose(env, "(");
-/*
- * _a stands for append, was shortened to avoid multiline statements below.
- * This macro is used to output a comma separated list of attributes.
+/* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which
+ * case they are equivalent, or it's STACK_ZERO, in which case we preserve
+ * more precise STACK_ZERO.
+ * Note, in uprivileged mode leaving STACK_INVALID is wrong, so we take
+ * env->allow_ptr_leaks into account and force STACK_MISC, if necessary.
*/
-#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, __VA_ARGS__); sep = ","; })
-
- if (reg->id)
- verbose_a("id=%d", reg->id);
- if (reg->ref_obj_id)
- verbose_a("ref_obj_id=%d", reg->ref_obj_id);
- if (type_is_non_owning_ref(reg->type))
- verbose_a("%s", "non_own_ref");
- if (t != SCALAR_VALUE)
- verbose_a("off=%d", reg->off);
- if (type_is_pkt_pointer(t))
- verbose_a("r=%d", reg->range);
- else if (base_type(t) == CONST_PTR_TO_MAP ||
- base_type(t) == PTR_TO_MAP_KEY ||
- base_type(t) == PTR_TO_MAP_VALUE)
- verbose_a("ks=%d,vs=%d",
- reg->map_ptr->key_size,
- reg->map_ptr->value_size);
- if (tnum_is_const(reg->var_off)) {
- /* Typically an immediate SCALAR_VALUE, but
- * could be a pointer whose offset is too big
- * for reg->off
- */
- verbose_a("imm=%llx", reg->var_off.value);
- } else {
- 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);
- }
- }
-#undef verbose_a
-
- verbose(env, ")");
- }
- }
- for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
- char types_buf[BPF_REG_SIZE + 1];
- bool valid = false;
- int j;
-
- for (j = 0; j < BPF_REG_SIZE; j++) {
- if (state->stack[i].slot_type[j] != STACK_INVALID)
- valid = true;
- types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
- }
- types_buf[BPF_REG_SIZE] = 0;
- if (!valid)
- continue;
- if (!print_all && !stack_slot_scratched(env, i))
- continue;
- switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) {
- case STACK_SPILL:
- reg = &state->stack[i].spilled_ptr;
- t = reg->type;
-
- verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
- print_liveness(env, reg->live);
- verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
- if (t == SCALAR_VALUE && reg->precise)
- verbose(env, "P");
- if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
- verbose(env, "%lld", reg->var_off.value + reg->off);
- break;
- case STACK_DYNPTR:
- i += BPF_DYNPTR_NR_SLOTS - 1;
- reg = &state->stack[i].spilled_ptr;
-
- verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
- print_liveness(env, reg->live);
- verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type));
- if (reg->ref_obj_id)
- verbose(env, "(ref_id=%d)", reg->ref_obj_id);
- break;
- case STACK_ITER:
- /* only main slot has ref_obj_id set; skip others */
- reg = &state->stack[i].spilled_ptr;
- if (!reg->ref_obj_id)
- continue;
-
- verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
- print_liveness(env, reg->live);
- verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)",
- iter_type_str(reg->iter.btf, reg->iter.btf_id),
- reg->ref_obj_id, iter_state_str(reg->iter.state),
- reg->iter.depth);
- break;
- case STACK_MISC:
- case STACK_ZERO:
- default:
- reg = &state->stack[i].spilled_ptr;
-
- for (j = 0; j < BPF_REG_SIZE; j++)
- types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
- types_buf[BPF_REG_SIZE] = 0;
-
- verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
- print_liveness(env, reg->live);
- verbose(env, "=%s", types_buf);
- break;
- }
- }
- if (state->acquired_refs && state->refs[0].id) {
- verbose(env, " refs=%d", state->refs[0].id);
- for (i = 1; i < state->acquired_refs; i++)
- if (state->refs[i].id)
- verbose(env, ",%d", state->refs[i].id);
- }
- if (state->in_callback_fn)
- verbose(env, " cb");
- if (state->in_async_callback_fn)
- verbose(env, " async_cb");
- verbose(env, "\n");
- if (!print_all)
- mark_verifier_state_clean(env);
-}
-
-static inline u32 vlog_alignment(u32 pos)
+static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype)
{
- return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
- BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+ if (*stype == STACK_ZERO)
+ return;
+ if (env->allow_ptr_leaks && *stype == STACK_INVALID)
+ return;
+ *stype = STACK_MISC;
}
-static void print_insn_state(struct bpf_verifier_env *env,
- const struct bpf_func_state *state)
+static void scrub_spilled_slot(u8 *stype)
{
- if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) {
- /* remove new line character */
- bpf_vlog_reset(&env->log, env->prev_log_pos - 1);
- verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' ');
- } else {
- verbose(env, "%d:", env->insn_idx);
- }
- print_verifier_state(env, state, false);
+ if (*stype != STACK_INVALID)
+ *stype = STACK_MISC;
}
/* copy array src of length n * size bytes to dst. dst is reallocated if it's too
@@ -1685,9 +1270,16 @@ static int resize_reference_state(struct bpf_func_state *state, size_t n)
return 0;
}
-static int grow_stack_state(struct bpf_func_state *state, int size)
+/* Possibly update state->allocated_stack to be at least size bytes. Also
+ * possibly update the function's high-water mark in its bpf_subprog_info.
+ */
+static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size)
{
- size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE;
+ size_t old_n = state->allocated_stack / BPF_REG_SIZE, n;
+
+ /* The stack size is always a multiple of BPF_REG_SIZE. */
+ size = round_up(size, BPF_REG_SIZE);
+ n = size / BPF_REG_SIZE;
if (old_n >= n)
return 0;
@@ -1697,6 +1289,11 @@ static int grow_stack_state(struct bpf_func_state *state, int size)
return -ENOMEM;
state->allocated_stack = size;
+
+ /* update known max for given subprogram */
+ if (env->subprog_info[state->subprogno].stack_depth < size)
+ env->subprog_info[state->subprogno].stack_depth = size;
+
return 0;
}
@@ -1796,8 +1393,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
int i, err;
dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
- src->jmp_history_cnt, sizeof(struct bpf_idx_pair),
- GFP_USER);
+ src->jmp_history_cnt, sizeof(*dst_state->jmp_history),
+ GFP_USER);
if (!dst_state->jmp_history)
return -ENOMEM;
dst_state->jmp_history_cnt = src->jmp_history_cnt;
@@ -2172,10 +1769,14 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg)
__mark_reg_known(reg, 0);
}
-static void __mark_reg_const_zero(struct bpf_reg_state *reg)
+static void __mark_reg_const_zero(const struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
__mark_reg_known(reg, 0);
reg->type = SCALAR_VALUE;
+ /* all scalars are assumed imprecise initially (unless unprivileged,
+ * in which case everything is forced to be precise)
+ */
+ reg->precise = !env->bpf_capable;
}
static void mark_reg_known_zero(struct bpf_verifier_env *env,
@@ -2341,69 +1942,214 @@ static void __update_reg_bounds(struct bpf_reg_state *reg)
/* Uses signed min/max values to inform unsigned, and vice-versa */
static void __reg32_deduce_bounds(struct bpf_reg_state *reg)
{
- /* Learn sign from signed bounds.
- * If we cannot cross the sign boundary, then signed and unsigned bounds
- * are the same, so combine. This works even in the negative case, e.g.
- * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
+ /* If upper 32 bits of u64/s64 range don't change, we can use lower 32
+ * bits to improve our u32/s32 boundaries.
+ *
+ * E.g., the case where we have upper 32 bits as zero ([10, 20] in
+ * u64) is pretty trivial, it's obvious that in u32 we'll also have
+ * [10, 20] range. But this property holds for any 64-bit range as
+ * long as upper 32 bits in that entire range of values stay the same.
+ *
+ * E.g., u64 range [0x10000000A, 0x10000000F] ([4294967306, 4294967311]
+ * in decimal) has the same upper 32 bits throughout all the values in
+ * that range. As such, lower 32 bits form a valid [0xA, 0xF] ([10, 15])
+ * range.
+ *
+ * Note also, that [0xA, 0xF] is a valid range both in u32 and in s32,
+ * following the rules outlined below about u64/s64 correspondence
+ * (which equally applies to u32 vs s32 correspondence). In general it
+ * depends on actual hexadecimal values of 32-bit range. They can form
+ * only valid u32, or only valid s32 ranges in some cases.
+ *
+ * So we use all these insights to derive bounds for subregisters here.
*/
- if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) {
- reg->s32_min_value = reg->u32_min_value =
- max_t(u32, reg->s32_min_value, reg->u32_min_value);
- reg->s32_max_value = reg->u32_max_value =
- min_t(u32, reg->s32_max_value, reg->u32_max_value);
- return;
+ if ((reg->umin_value >> 32) == (reg->umax_value >> 32)) {
+ /* u64 to u32 casting preserves validity of low 32 bits as
+ * a range, if upper 32 bits are the same
+ */
+ reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->umin_value);
+ reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->umax_value);
+
+ if ((s32)reg->umin_value <= (s32)reg->umax_value) {
+ reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value);
+ reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value);
+ }
+ }
+ if ((reg->smin_value >> 32) == (reg->smax_value >> 32)) {
+ /* low 32 bits should form a proper u32 range */
+ if ((u32)reg->smin_value <= (u32)reg->smax_value) {
+ reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->smin_value);
+ reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->smax_value);
+ }
+ /* low 32 bits should form a proper s32 range */
+ if ((s32)reg->smin_value <= (s32)reg->smax_value) {
+ reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value);
+ reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value);
+ }
+ }
+ /* Special case where upper bits form a small sequence of two
+ * sequential numbers (in 32-bit unsigned space, so 0xffffffff to
+ * 0x00000000 is also valid), while lower bits form a proper s32 range
+ * going from negative numbers to positive numbers. E.g., let's say we
+ * have s64 range [-1, 1] ([0xffffffffffffffff, 0x0000000000000001]).
+ * Possible s64 values are {-1, 0, 1} ({0xffffffffffffffff,
+ * 0x0000000000000000, 0x00000000000001}). Ignoring upper 32 bits,
+ * we still get a valid s32 range [-1, 1] ([0xffffffff, 0x00000001]).
+ * Note that it doesn't have to be 0xffffffff going to 0x00000000 in
+ * upper 32 bits. As a random example, s64 range
+ * [0xfffffff0fffffff0; 0xfffffff100000010], forms a valid s32 range
+ * [-16, 16] ([0xfffffff0; 0x00000010]) in its 32 bit subregister.
+ */
+ if ((u32)(reg->umin_value >> 32) + 1 == (u32)(reg->umax_value >> 32) &&
+ (s32)reg->umin_value < 0 && (s32)reg->umax_value >= 0) {
+ reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value);
+ reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value);
+ }
+ if ((u32)(reg->smin_value >> 32) + 1 == (u32)(reg->smax_value >> 32) &&
+ (s32)reg->smin_value < 0 && (s32)reg->smax_value >= 0) {
+ reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value);
+ reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value);
+ }
+ /* if u32 range forms a valid s32 range (due to matching sign bit),
+ * try to learn from that
+ */
+ if ((s32)reg->u32_min_value <= (s32)reg->u32_max_value) {
+ reg->s32_min_value = max_t(s32, reg->s32_min_value, reg->u32_min_value);
+ reg->s32_max_value = min_t(s32, reg->s32_max_value, reg->u32_max_value);
}
- /* Learn sign from unsigned bounds. Signed bounds cross the sign
- * boundary, so we must be careful.
+ /* If we cannot cross the sign boundary, then signed and unsigned bounds
+ * are the same, so combine. This works even in the negative case, e.g.
+ * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
*/
- if ((s32)reg->u32_max_value >= 0) {
- /* Positive. We can't learn anything from the smin, but smax
- * is positive, hence safe.
- */
- reg->s32_min_value = reg->u32_min_value;
- reg->s32_max_value = reg->u32_max_value =
- min_t(u32, reg->s32_max_value, reg->u32_max_value);
- } else if ((s32)reg->u32_min_value < 0) {
- /* Negative. We can't learn anything from the smax, but smin
- * is negative, hence safe.
- */
- reg->s32_min_value = reg->u32_min_value =
- max_t(u32, reg->s32_min_value, reg->u32_min_value);
- reg->s32_max_value = reg->u32_max_value;
+ if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) {
+ reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value);
+ reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value);
}
}
static void __reg64_deduce_bounds(struct bpf_reg_state *reg)
{
- /* Learn sign from signed bounds.
- * If we cannot cross the sign boundary, then signed and unsigned bounds
+ /* If u64 range forms a valid s64 range (due to matching sign bit),
+ * try to learn from that. Let's do a bit of ASCII art to see when
+ * this is happening. Let's take u64 range first:
+ *
+ * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX
+ * |-------------------------------|--------------------------------|
+ *
+ * Valid u64 range is formed when umin and umax are anywhere in the
+ * range [0, U64_MAX], and umin <= umax. u64 case is simple and
+ * straightforward. Let's see how s64 range maps onto the same range
+ * of values, annotated below the line for comparison:
+ *
+ * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX
+ * |-------------------------------|--------------------------------|
+ * 0 S64_MAX S64_MIN -1
+ *
+ * So s64 values basically start in the middle and they are logically
+ * contiguous to the right of it, wrapping around from -1 to 0, and
+ * then finishing as S64_MAX (0x7fffffffffffffff) right before
+ * S64_MIN. We can try drawing the continuity of u64 vs s64 values
+ * more visually as mapped to sign-agnostic range of hex values.
+ *
+ * u64 start u64 end
+ * _______________________________________________________________
+ * / \
+ * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX
+ * |-------------------------------|--------------------------------|
+ * 0 S64_MAX S64_MIN -1
+ * / \
+ * >------------------------------ ------------------------------->
+ * s64 continues... s64 end s64 start s64 "midpoint"
+ *
+ * What this means is that, in general, we can't always derive
+ * something new about u64 from any random s64 range, and vice versa.
+ *
+ * But we can do that in two particular cases. One is when entire
+ * u64/s64 range is *entirely* contained within left half of the above
+ * diagram or when it is *entirely* contained in the right half. I.e.:
+ *
+ * |-------------------------------|--------------------------------|
+ * ^ ^ ^ ^
+ * A B C D
+ *
+ * [A, B] and [C, D] are contained entirely in their respective halves
+ * and form valid contiguous ranges as both u64 and s64 values. [A, B]
+ * will be non-negative both as u64 and s64 (and in fact it will be
+ * identical ranges no matter the signedness). [C, D] treated as s64
+ * will be a range of negative values, while in u64 it will be
+ * non-negative range of values larger than 0x8000000000000000.
+ *
+ * Now, any other range here can't be represented in both u64 and s64
+ * simultaneously. E.g., [A, C], [A, D], [B, C], [B, D] are valid
+ * contiguous u64 ranges, but they are discontinuous in s64. [B, C]
+ * in s64 would be properly presented as [S64_MIN, C] and [B, S64_MAX],
+ * for example. Similarly, valid s64 range [D, A] (going from negative
+ * to positive values), would be two separate [D, U64_MAX] and [0, A]
+ * ranges as u64. Currently reg_state can't represent two segments per
+ * numeric domain, so in such situations we can only derive maximal
+ * possible range ([0, U64_MAX] for u64, and [S64_MIN, S64_MAX] for s64).
+ *
+ * So we use these facts to derive umin/umax from smin/smax and vice
+ * versa only if they stay within the same "half". This is equivalent
+ * to checking sign bit: lower half will have sign bit as zero, upper
+ * half have sign bit 1. Below in code we simplify this by just
+ * casting umin/umax as smin/smax and checking if they form valid
+ * range, and vice versa. Those are equivalent checks.
+ */
+ if ((s64)reg->umin_value <= (s64)reg->umax_value) {
+ reg->smin_value = max_t(s64, reg->smin_value, reg->umin_value);
+ reg->smax_value = min_t(s64, reg->smax_value, reg->umax_value);
+ }
+ /* If we cannot cross the sign boundary, then signed and unsigned bounds
* are the same, so combine. This works even in the negative case, e.g.
* -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
*/
- if (reg->smin_value >= 0 || reg->smax_value < 0) {
- reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
- reg->umin_value);
- reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
- reg->umax_value);
- return;
+ if ((u64)reg->smin_value <= (u64)reg->smax_value) {
+ reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value);
+ reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value);
}
- /* Learn sign from unsigned bounds. Signed bounds cross the sign
- * boundary, so we must be careful.
+}
+
+static void __reg_deduce_mixed_bounds(struct bpf_reg_state *reg)
+{
+ /* Try to tighten 64-bit bounds from 32-bit knowledge, using 32-bit
+ * values on both sides of 64-bit range in hope to have tigher range.
+ * E.g., if r1 is [0x1'00000000, 0x3'80000000], and we learn from
+ * 32-bit signed > 0 operation that s32 bounds are now [1; 0x7fffffff].
+ * With this, we can substitute 1 as low 32-bits of _low_ 64-bit bound
+ * (0x100000000 -> 0x100000001) and 0x7fffffff as low 32-bits of
+ * _high_ 64-bit bound (0x380000000 -> 0x37fffffff) and arrive at a
+ * better overall bounds for r1 as [0x1'000000001; 0x3'7fffffff].
+ * We just need to make sure that derived bounds we are intersecting
+ * with are well-formed ranges in respecitve s64 or u64 domain, just
+ * like we do with similar kinds of 32-to-64 or 64-to-32 adjustments.
*/
- if ((s64)reg->umax_value >= 0) {
- /* Positive. We can't learn anything from the smin, but smax
- * is positive, hence safe.
- */
- reg->smin_value = reg->umin_value;
- reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
- reg->umax_value);
- } else if ((s64)reg->umin_value < 0) {
- /* Negative. We can't learn anything from the smax, but smin
- * is negative, hence safe.
- */
- reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
- reg->umin_value);
- reg->smax_value = reg->umax_value;
+ __u64 new_umin, new_umax;
+ __s64 new_smin, new_smax;
+
+ /* u32 -> u64 tightening, it's always well-formed */
+ new_umin = (reg->umin_value & ~0xffffffffULL) | reg->u32_min_value;
+ new_umax = (reg->umax_value & ~0xffffffffULL) | reg->u32_max_value;
+ reg->umin_value = max_t(u64, reg->umin_value, new_umin);
+ reg->umax_value = min_t(u64, reg->umax_value, new_umax);
+ /* u32 -> s64 tightening, u32 range embedded into s64 preserves range validity */
+ new_smin = (reg->smin_value & ~0xffffffffULL) | reg->u32_min_value;
+ new_smax = (reg->smax_value & ~0xffffffffULL) | reg->u32_max_value;
+ reg->smin_value = max_t(s64, reg->smin_value, new_smin);
+ reg->smax_value = min_t(s64, reg->smax_value, new_smax);
+
+ /* if s32 can be treated as valid u32 range, we can use it as well */
+ if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) {
+ /* s32 -> u64 tightening */
+ new_umin = (reg->umin_value & ~0xffffffffULL) | (u32)reg->s32_min_value;
+ new_umax = (reg->umax_value & ~0xffffffffULL) | (u32)reg->s32_max_value;
+ reg->umin_value = max_t(u64, reg->umin_value, new_umin);
+ reg->umax_value = min_t(u64, reg->umax_value, new_umax);
+ /* s32 -> s64 tightening */
+ new_smin = (reg->smin_value & ~0xffffffffULL) | (u32)reg->s32_min_value;
+ new_smax = (reg->smax_value & ~0xffffffffULL) | (u32)reg->s32_max_value;
+ reg->smin_value = max_t(s64, reg->smin_value, new_smin);
+ reg->smax_value = min_t(s64, reg->smax_value, new_smax);
}
}
@@ -2411,6 +2157,7 @@ static void __reg_deduce_bounds(struct bpf_reg_state *reg)
{
__reg32_deduce_bounds(reg);
__reg64_deduce_bounds(reg);
+ __reg_deduce_mixed_bounds(reg);
}
/* Attempts to improve var_off based on unsigned min/max information */
@@ -2432,6 +2179,7 @@ static void reg_bounds_sync(struct bpf_reg_state *reg)
__update_reg_bounds(reg);
/* We might have learned something about the sign bit. */
__reg_deduce_bounds(reg);
+ __reg_deduce_bounds(reg);
/* We might have learned some bits from the bounds. */
__reg_bound_offset(reg);
/* Intersecting with the old var_off might have improved our bounds
@@ -2441,6 +2189,56 @@ static void reg_bounds_sync(struct bpf_reg_state *reg)
__update_reg_bounds(reg);
}
+static int reg_bounds_sanity_check(struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg, const char *ctx)
+{
+ const char *msg;
+
+ if (reg->umin_value > reg->umax_value ||
+ reg->smin_value > reg->smax_value ||
+ reg->u32_min_value > reg->u32_max_value ||
+ reg->s32_min_value > reg->s32_max_value) {
+ msg = "range bounds violation";
+ goto out;
+ }
+
+ if (tnum_is_const(reg->var_off)) {
+ u64 uval = reg->var_off.value;
+ s64 sval = (s64)uval;
+
+ if (reg->umin_value != uval || reg->umax_value != uval ||
+ reg->smin_value != sval || reg->smax_value != sval) {
+ msg = "const tnum out of sync with range bounds";
+ goto out;
+ }
+ }
+
+ if (tnum_subreg_is_const(reg->var_off)) {
+ u32 uval32 = tnum_subreg(reg->var_off).value;
+ s32 sval32 = (s32)uval32;
+
+ if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 ||
+ reg->s32_min_value != sval32 || reg->s32_max_value != sval32) {
+ msg = "const subreg tnum out of sync with range bounds";
+ goto out;
+ }
+ }
+
+ return 0;
+out:
+ verbose(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] "
+ "s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n",
+ ctx, msg, reg->umin_value, reg->umax_value,
+ reg->smin_value, reg->smax_value,
+ reg->u32_min_value, reg->u32_max_value,
+ reg->s32_min_value, reg->s32_max_value,
+ reg->var_off.value, reg->var_off.mask);
+ if (env->test_reg_invariants)
+ return -EFAULT;
+ __mark_reg_unbounded(reg);
+ return 0;
+}
+
static bool __reg32_bound_s64(s32 a)
{
return a >= 0 && a <= S32_MAX;
@@ -2465,51 +2263,6 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
}
}
-static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
-{
- /* special case when 64-bit register has upper 32-bit register
- * zeroed. Typically happens after zext or <<32, >>32 sequence
- * allowing us to use 32-bit bounds directly,
- */
- if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) {
- __reg_assign_32_into_64(reg);
- } else {
- /* Otherwise the best we can do is push lower 32bit known and
- * unknown bits into register (var_off set from jmp logic)
- * then learn as much as possible from the 64-bit tnum
- * known and unknown bits. The previous smin/smax bounds are
- * invalid here because of jmp32 compare so mark them unknown
- * so they do not impact tnum bounds calculation.
- */
- __mark_reg64_unbounded(reg);
- }
- reg_bounds_sync(reg);
-}
-
-static bool __reg64_bound_s32(s64 a)
-{
- return a >= S32_MIN && a <= S32_MAX;
-}
-
-static bool __reg64_bound_u32(u64 a)
-{
- return a >= U32_MIN && a <= U32_MAX;
-}
-
-static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
-{
- __mark_reg32_unbounded(reg);
- if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) {
- reg->s32_min_value = (s32)reg->smin_value;
- reg->s32_max_value = (s32)reg->smax_value;
- }
- if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) {
- reg->u32_min_value = (u32)reg->umin_value;
- reg->u32_max_value = (u32)reg->umax_value;
- }
- reg_bounds_sync(reg);
-}
-
/* Mark a register as having a completely unknown (scalar) value. */
static void __mark_reg_unknown(const struct bpf_verifier_env *env,
struct bpf_reg_state *reg)
@@ -2597,6 +2350,11 @@ static void init_reg_state(struct bpf_verifier_env *env,
regs[BPF_REG_FP].frameno = state->frameno;
}
+static struct bpf_retval_range retval_range(s32 minval, s32 maxval)
+{
+ return (struct bpf_retval_range){ minval, maxval };
+}
+
#define BPF_MAIN_FUNC (-1)
static void init_func_state(struct bpf_verifier_env *env,
struct bpf_func_state *state,
@@ -2605,7 +2363,7 @@ static void init_func_state(struct bpf_verifier_env *env,
state->callsite = callsite;
state->frameno = frameno;
state->subprogno = subprogno;
- state->callback_ret_range = tnum_range(0, 0);
+ state->callback_ret_range = retval_range(0, 0);
init_reg_state(env, state);
mark_verifier_state_scratched(env);
}
@@ -3149,6 +2907,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
if (env->subprog_info[i].start != ex_cb_insn)
continue;
env->exception_callback_subprog = i;
+ mark_subprog_exc_cb(env, i);
break;
}
}
@@ -3505,6 +3264,21 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
return __check_reg_arg(env, state->regs, regno, t);
}
+static int insn_stack_access_flags(int frameno, int spi)
+{
+ return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno;
+}
+
+static int insn_stack_access_spi(int insn_flags)
+{
+ return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK;
+}
+
+static int insn_stack_access_frameno(int insn_flags)
+{
+ return insn_flags & INSN_F_FRAMENO_MASK;
+}
+
static void mark_jmp_point(struct bpf_verifier_env *env, int idx)
{
env->insn_aux_data[idx].jmp_point = true;
@@ -3516,28 +3290,51 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx)
}
/* for any branch, call, exit record the history of jmps in the given state */
-static int push_jmp_history(struct bpf_verifier_env *env,
- struct bpf_verifier_state *cur)
+static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
+ int insn_flags)
{
u32 cnt = cur->jmp_history_cnt;
- struct bpf_idx_pair *p;
+ struct bpf_jmp_history_entry *p;
size_t alloc_size;
- if (!is_jmp_point(env, env->insn_idx))
+ /* combine instruction flags if we already recorded this instruction */
+ if (env->cur_hist_ent) {
+ /* atomic instructions push insn_flags twice, for READ and
+ * WRITE sides, but they should agree on stack slot
+ */
+ WARN_ONCE((env->cur_hist_ent->flags & insn_flags) &&
+ (env->cur_hist_ent->flags & insn_flags) != insn_flags,
+ "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n",
+ env->insn_idx, env->cur_hist_ent->flags, insn_flags);
+ env->cur_hist_ent->flags |= insn_flags;
return 0;
+ }
cnt++;
alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p)));
p = krealloc(cur->jmp_history, alloc_size, GFP_USER);
if (!p)
return -ENOMEM;
- p[cnt - 1].idx = env->insn_idx;
- p[cnt - 1].prev_idx = env->prev_insn_idx;
cur->jmp_history = p;
+
+ p = &cur->jmp_history[cnt - 1];
+ p->idx = env->insn_idx;
+ p->prev_idx = env->prev_insn_idx;
+ p->flags = insn_flags;
cur->jmp_history_cnt = cnt;
+ env->cur_hist_ent = p;
+
return 0;
}
+static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st,
+ u32 hist_end, int insn_idx)
+{
+ if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx)
+ return &st->jmp_history[hist_end - 1];
+ return NULL;
+}
+
/* 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.
@@ -3664,16 +3461,6 @@ static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u3
bt->stack_masks[frame] &= ~(1ull << slot);
}
-static inline void bt_set_slot(struct backtrack_state *bt, u32 slot)
-{
- bt_set_frame_slot(bt, bt->frame, slot);
-}
-
-static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot)
-{
- bt_clear_frame_slot(bt, bt->frame, slot);
-}
-
static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame)
{
return bt->reg_masks[frame];
@@ -3699,9 +3486,9 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
return bt->reg_masks[bt->frame] & (1 << reg);
}
-static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot)
+static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot)
{
- return bt->stack_masks[bt->frame] & (1ull << slot);
+ return bt->stack_masks[frame] & (1ull << slot);
}
/* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */
@@ -3755,7 +3542,7 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
* - *was* processed previously during backtracking.
*/
static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
- struct backtrack_state *bt)
+ struct bpf_jmp_history_entry *hist, struct backtrack_state *bt)
{
const struct bpf_insn_cbs cbs = {
.cb_call = disasm_kfunc_name,
@@ -3768,7 +3555,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
u8 mode = BPF_MODE(insn->code);
u32 dreg = insn->dst_reg;
u32 sreg = insn->src_reg;
- u32 spi, i;
+ u32 spi, i, fr;
if (insn->code == 0)
return 0;
@@ -3829,20 +3616,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
* by 'precise' mark in corresponding register of this state.
* No further tracking necessary.
*/
- if (insn->src_reg != BPF_REG_FP)
+ if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
return 0;
-
/* dreg = *(u64 *)[fp - off] was a fill from the stack.
* that [fp - off] slot contains scalar that needs to be
* tracked with precision
*/
- spi = (-insn->off - 1) / BPF_REG_SIZE;
- if (spi >= 64) {
- verbose(env, "BUG spi %d\n", spi);
- WARN_ONCE(1, "verifier backtracking bug");
- return -EFAULT;
- }
- bt_set_slot(bt, spi);
+ spi = insn_stack_access_spi(hist->flags);
+ fr = insn_stack_access_frameno(hist->flags);
+ bt_set_frame_slot(bt, fr, spi);
} else if (class == BPF_STX || class == BPF_ST) {
if (bt_is_reg_set(bt, dreg))
/* stx & st shouldn't be using _scalar_ dst_reg
@@ -3851,17 +3633,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
*/
return -ENOTSUPP;
/* scalars can only be spilled into stack */
- if (insn->dst_reg != BPF_REG_FP)
+ if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
return 0;
- spi = (-insn->off - 1) / BPF_REG_SIZE;
- if (spi >= 64) {
- verbose(env, "BUG spi %d\n", spi);
- WARN_ONCE(1, "verifier backtracking bug");
- return -EFAULT;
- }
- if (!bt_is_slot_set(bt, spi))
+ spi = insn_stack_access_spi(hist->flags);
+ fr = insn_stack_access_frameno(hist->flags);
+ if (!bt_is_frame_slot_set(bt, fr, spi))
return 0;
- bt_clear_slot(bt, spi);
+ bt_clear_frame_slot(bt, fr, spi);
if (class == BPF_STX)
bt_set_reg(bt, sreg);
} else if (class == BPF_JMP || class == BPF_JMP32) {
@@ -3905,10 +3683,14 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
- /* we don't track register spills perfectly,
- * so fallback to force-precise instead of failing */
- if (bt_stack_mask(bt) != 0)
- return -ENOTSUPP;
+ /* we are now tracking register spills correctly,
+ * so any instance of leftover slots is a bug
+ */
+ if (bt_stack_mask(bt) != 0) {
+ verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
+ WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)");
+ return -EFAULT;
+ }
/* propagate r1-r5 to the caller */
for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
if (bt_is_reg_set(bt, i)) {
@@ -3933,8 +3715,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
- if (bt_stack_mask(bt) != 0)
- return -ENOTSUPP;
+ if (bt_stack_mask(bt) != 0) {
+ verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
+ WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)");
+ return -EFAULT;
+ }
/* clear r1-r5 in callback subprog's mask */
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
bt_clear_reg(bt, i);
@@ -4371,6 +4156,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
for (;;) {
DECLARE_BITMAP(mask, 64);
u32 history = st->jmp_history_cnt;
+ struct bpf_jmp_history_entry *hist;
if (env->log.level & BPF_LOG_LEVEL2) {
verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
@@ -4434,7 +4220,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
err = 0;
skip_first = false;
} else {
- err = backtrack_insn(env, i, subseq_idx, bt);
+ hist = get_jmp_hist_entry(st, history, i);
+ err = backtrack_insn(env, i, subseq_idx, hist, bt);
}
if (err == -ENOTSUPP) {
mark_all_scalars_precise(env, env->cur_state);
@@ -4487,22 +4274,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
for_each_set_bit(i, mask, 64) {
if (i >= func->allocated_stack / BPF_REG_SIZE) {
- /* the sequence of instructions:
- * 2: (bf) r3 = r10
- * 3: (7b) *(u64 *)(r3 -8) = r0
- * 4: (79) r4 = *(u64 *)(r10 -8)
- * doesn't contain jmps. It's backtracked
- * as a single block.
- * During backtracking insn 3 is not recognized as
- * stack access, so at the end of backtracking
- * stack slot fp-8 is still marked in stack_mask.
- * However the parent state may not have accessed
- * fp-8 and it's "unallocated" stack space.
- * In such case fallback to conservative.
- */
- mark_all_scalars_precise(env, env->cur_state);
- bt_reset(bt);
- return 0;
+ verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n",
+ i, func->allocated_stack / BPF_REG_SIZE);
+ WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)");
+ return -EFAULT;
}
if (!is_spilled_scalar_reg(&func->stack[i])) {
@@ -4592,9 +4367,17 @@ static bool register_is_null(struct bpf_reg_state *reg)
return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
}
-static bool register_is_const(struct bpf_reg_state *reg)
+/* check if register is a constant scalar value */
+static bool is_reg_const(struct bpf_reg_state *reg, bool subreg32)
{
- return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
+ return reg->type == SCALAR_VALUE &&
+ tnum_is_const(subreg32 ? tnum_subreg(reg->var_off) : reg->var_off);
+}
+
+/* assuming is_reg_const() is true, return constant value of a register */
+static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32)
+{
+ return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value;
}
static bool __is_scalar_unbounded(struct bpf_reg_state *reg)
@@ -4631,7 +4414,8 @@ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_
dst->live = live;
}
-static void save_register_state(struct bpf_func_state *state,
+static void save_register_state(struct bpf_verifier_env *env,
+ struct bpf_func_state *state,
int spi, struct bpf_reg_state *reg,
int size)
{
@@ -4646,7 +4430,7 @@ static void save_register_state(struct bpf_func_state *state,
/* size < 8 bytes spill */
for (; i; i--)
- scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]);
+ mark_stack_slot_misc(env, &state->stack[spi].slot_type[i - 1]);
}
static bool is_bpf_st_mem(struct bpf_insn *insn)
@@ -4667,16 +4451,13 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
struct bpf_reg_state *reg = NULL;
- u32 dst_reg = insn->dst_reg;
+ int insn_flags = insn_stack_access_flags(state->frameno, spi);
- err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE));
- if (err)
- return err;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
* so it's aligned access and [off, off + size) are within stack limits
*/
if (!env->allow_ptr_leaks &&
- state->stack[spi].slot_type[0] == STACK_SPILL &&
+ is_spilled_reg(&state->stack[spi]) &&
size != BPF_REG_SIZE) {
verbose(env, "attempt to corrupt spilled pointer on stack\n");
return -EACCES;
@@ -4706,20 +4487,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
return err;
mark_stack_slot_scratched(env, spi);
- if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
- !register_is_null(reg) && env->bpf_capable) {
- if (dst_reg != BPF_REG_FP) {
- /* The backtracking logic can only recognize explicit
- * stack slot address like [fp - 8]. Other spill of
- * scalar via different register has to be conservative.
- * Backtrack from here and mark all registers as precise
- * that contributed into 'reg' being a constant.
- */
- err = mark_chain_precision(env, value_regno);
- if (err)
- return err;
- }
- save_register_state(state, spi, reg, size);
+ if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && env->bpf_capable) {
+ save_register_state(env, state, spi, reg, size);
/* Break the relation on a narrowing spill. */
if (fls64(reg->umax_value) > BITS_PER_BYTE * size)
state->stack[spi].spilled_ptr.id = 0;
@@ -4729,7 +4498,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
__mark_reg_known(&fake_reg, insn->imm);
fake_reg.type = SCALAR_VALUE;
- save_register_state(state, spi, &fake_reg, size);
+ save_register_state(env, state, spi, &fake_reg, size);
} else if (reg && is_spillable_regtype(reg->type)) {
/* register containing pointer is being spilled into stack */
if (size != BPF_REG_SIZE) {
@@ -4741,7 +4510,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
- save_register_state(state, spi, reg, size);
+ save_register_state(env, state, spi, reg, size);
} else {
u8 type = STACK_MISC;
@@ -4766,7 +4535,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
/* when we zero initialize stack slots mark them as such */
if ((reg && register_is_null(reg)) ||
(!reg && is_bpf_st_mem(insn) && insn->imm == 0)) {
- /* backtracking doesn't work for STACK_ZERO yet. */
+ /* STACK_ZERO case happened because register spill
+ * wasn't properly aligned at the stack slot boundary,
+ * so it's not a register spill anymore; force
+ * originating register to be precise to make
+ * STACK_ZERO correct for subsequent states
+ */
err = mark_chain_precision(env, value_regno);
if (err)
return err;
@@ -4775,9 +4549,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
/* Mark slots affected by this stack write. */
for (i = 0; i < size; i++)
- state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
- type;
+ state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type;
+ insn_flags = 0; /* not a register spill */
}
+
+ if (insn_flags)
+ return push_jmp_history(env, env->cur_state, insn_flags);
return 0;
}
@@ -4827,10 +4604,6 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
(!value_reg && is_bpf_st_mem(insn) && insn->imm == 0))
writing_zero = true;
- err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE));
- if (err)
- return err;
-
for (i = min_off; i < max_off; i++) {
int spi;
@@ -4929,21 +4702,10 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env,
zeros++;
}
if (zeros == max_off - min_off) {
- /* any access_size read into register is zero extended,
- * so the whole register == const_zero
+ /* Any access_size read into register is zero extended,
+ * so the whole register == const_zero.
*/
- __mark_reg_const_zero(&state->regs[dst_regno]);
- /* backtracking doesn't support STACK_ZERO yet,
- * so mark it precise here, so that later
- * backtracking can stop here.
- * Backtracking may not need this if this register
- * doesn't participate in pointer adjustment.
- * Forward propagation of precise flag is not
- * necessary either. This mark is only to stop
- * backtracking. Any register that contributed
- * to const 0 was marked precise before spill.
- */
- state->regs[dst_regno].precise = true;
+ __mark_reg_const_zero(env, &state->regs[dst_regno]);
} else {
/* have read misc data from the stack */
mark_reg_unknown(env, state->regs, dst_regno);
@@ -4970,6 +4732,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
struct bpf_reg_state *reg;
u8 *stype, type;
+ int insn_flags = insn_stack_access_flags(reg_state->frameno, spi);
stype = reg_state->stack[spi].slot_type;
reg = &reg_state->stack[spi].spilled_ptr;
@@ -5002,25 +4765,42 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
copy_register_state(&state->regs[dst_regno], reg);
state->regs[dst_regno].subreg_def = subreg_def;
} else {
+ int spill_cnt = 0, zero_cnt = 0;
+
for (i = 0; i < size; i++) {
type = stype[(slot - i) % BPF_REG_SIZE];
- if (type == STACK_SPILL)
+ if (type == STACK_SPILL) {
+ spill_cnt++;
continue;
+ }
if (type == STACK_MISC)
continue;
+ if (type == STACK_ZERO) {
+ zero_cnt++;
+ continue;
+ }
if (type == STACK_INVALID && env->allow_uninit_stack)
continue;
verbose(env, "invalid read from stack off %d+%d size %d\n",
off, i, size);
return -EACCES;
}
- mark_reg_unknown(env, state->regs, dst_regno);
+
+ if (spill_cnt == size &&
+ tnum_is_const(reg->var_off) && reg->var_off.value == 0) {
+ __mark_reg_const_zero(env, &state->regs[dst_regno]);
+ /* this IS register fill, so keep insn_flags */
+ } else if (zero_cnt == size) {
+ /* similarly to mark_reg_stack_read(), preserve zeroes */
+ __mark_reg_const_zero(env, &state->regs[dst_regno]);
+ insn_flags = 0; /* not restoring original register state */
+ } else {
+ mark_reg_unknown(env, state->regs, dst_regno);
+ insn_flags = 0; /* not restoring original register state */
+ }
}
state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
- return 0;
- }
-
- if (dst_regno >= 0) {
+ } else if (dst_regno >= 0) {
/* restore register state from stack */
copy_register_state(&state->regs[dst_regno], reg);
/* mark reg as written since spilled pointer state likely
@@ -5056,7 +4836,10 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
if (dst_regno >= 0)
mark_reg_stack_read(env, reg_state, off, off + size, dst_regno);
+ insn_flags = 0; /* we are not restoring spilled register */
}
+ if (insn_flags)
+ return push_jmp_history(env, env->cur_state, insn_flags);
return 0;
}
@@ -5346,8 +5129,8 @@ static int __check_ptr_off_reg(struct bpf_verifier_env *env,
return 0;
}
-int check_ptr_off_reg(struct bpf_verifier_env *env,
- const struct bpf_reg_state *reg, int regno)
+static int check_ptr_off_reg(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno)
{
return __check_ptr_off_reg(env, reg, regno, false);
}
@@ -5451,10 +5234,23 @@ BTF_SET_END(rcu_protected_types)
static bool rcu_protected_object(const struct btf *btf, u32 btf_id)
{
if (!btf_is_kernel(btf))
- return false;
+ return true;
return btf_id_set_contains(&rcu_protected_types, btf_id);
}
+static struct btf_record *kptr_pointee_btf_record(struct btf_field *kptr_field)
+{
+ struct btf_struct_meta *meta;
+
+ if (btf_is_kernel(kptr_field->kptr.btf))
+ return NULL;
+
+ meta = btf_find_struct_meta(kptr_field->kptr.btf,
+ kptr_field->kptr.btf_id);
+
+ return meta ? meta->record : NULL;
+}
+
static bool rcu_safe_kptr(const struct btf_field *field)
{
const struct btf_field_kptr *kptr = &field->kptr;
@@ -5465,12 +5261,25 @@ static bool rcu_safe_kptr(const struct btf_field *field)
static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field)
{
+ struct btf_record *rec;
+ u32 ret;
+
+ ret = PTR_MAYBE_NULL;
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;
+ ret |= MEM_RCU;
+ if (kptr_field->type == BPF_KPTR_PERCPU)
+ ret |= MEM_PERCPU;
+ else if (!btf_is_kernel(kptr_field->kptr.btf))
+ ret |= MEM_ALLOC;
+
+ rec = kptr_pointee_btf_record(kptr_field);
+ if (rec && btf_record_has_field(rec, BPF_GRAPH_NODE))
+ ret |= NON_OWN_REF;
+ } else {
+ ret |= PTR_UNTRUSTED;
}
- return PTR_MAYBE_NULL | PTR_UNTRUSTED;
+
+ return ret;
}
static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
@@ -5959,20 +5768,6 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
strict);
}
-static int update_stack_depth(struct bpf_verifier_env *env,
- const struct bpf_func_state *func,
- int off)
-{
- u16 stack = env->subprog_info[func->subprogno].stack_depth;
-
- if (stack >= -off)
- return 0;
-
- /* update known max for given subprogram */
- env->subprog_info[func->subprogno].stack_depth = -off;
- return 0;
-}
-
/* starting from main bpf function walk all instructions of the function
* and recursively walk all callees that given function can call.
* Ignore jump and exit insns.
@@ -6244,9 +6039,10 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
* values are also truncated so we push 64-bit bounds into
* 32-bit bounds. Above were truncated < 32-bits already.
*/
- if (size >= 4)
- return;
- __reg_combine_64_into_32(reg);
+ if (size < 4) {
+ __mark_reg32_unbounded(reg);
+ reg_bounds_sync(reg);
+ }
}
static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
@@ -6761,13 +6557,14 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env,
* The minimum valid offset is -MAX_BPF_STACK for writes, and
* -state->allocated_stack for reads.
*/
-static int check_stack_slot_within_bounds(int off,
- struct bpf_func_state *state,
- enum bpf_access_type t)
+static int check_stack_slot_within_bounds(struct bpf_verifier_env *env,
+ s64 off,
+ struct bpf_func_state *state,
+ enum bpf_access_type t)
{
int min_valid_off;
- if (t == BPF_WRITE)
+ if (t == BPF_WRITE || env->allow_uninit_stack)
min_valid_off = -MAX_BPF_STACK;
else
min_valid_off = -state->allocated_stack;
@@ -6790,7 +6587,7 @@ static int check_stack_access_within_bounds(
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
struct bpf_func_state *state = func(env, reg);
- int min_off, max_off;
+ s64 min_off, max_off;
int err;
char *err_extra;
@@ -6803,11 +6600,8 @@ static int check_stack_access_within_bounds(
err_extra = " write to";
if (tnum_is_const(reg->var_off)) {
- min_off = reg->var_off.value + off;
- if (access_size > 0)
- max_off = min_off + access_size - 1;
- else
- max_off = min_off;
+ min_off = (s64)reg->var_off.value + off;
+ max_off = min_off + access_size;
} else {
if (reg->smax_value >= BPF_MAX_VAR_OFF ||
reg->smin_value <= -BPF_MAX_VAR_OFF) {
@@ -6816,15 +6610,12 @@ static int check_stack_access_within_bounds(
return -EACCES;
}
min_off = reg->smin_value + off;
- if (access_size > 0)
- max_off = reg->smax_value + off + access_size - 1;
- else
- max_off = min_off;
+ max_off = reg->smax_value + off + access_size;
}
- err = check_stack_slot_within_bounds(min_off, state, type);
- if (!err)
- err = check_stack_slot_within_bounds(max_off, state, type);
+ err = check_stack_slot_within_bounds(env, min_off, state, type);
+ if (!err && max_off > 0)
+ err = -EINVAL; /* out of stack access into non-negative offsets */
if (err) {
if (tnum_is_const(reg->var_off)) {
@@ -6834,11 +6625,16 @@ static int check_stack_access_within_bounds(
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n",
- err_extra, regno, tn_buf, access_size);
+ verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n",
+ err_extra, regno, tn_buf, off, access_size);
}
+ return err;
}
- return err;
+
+ /* Note that there is no stack access with offset zero, so the needed stack
+ * size is -min_off, not -min_off+1.
+ */
+ return grow_stack_state(env, state, -min_off /* size */);
}
/* check whether memory at (regno + off) is accessible for t = (read | write)
@@ -6853,7 +6649,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
- struct bpf_func_state *state;
int size, err = 0;
size = bpf_size_to_bytes(bpf_size);
@@ -6996,11 +6791,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (err)
return err;
- state = func(env, reg);
- err = update_stack_depth(env, state, off);
- if (err)
- return err;
-
if (t == BPF_READ)
err = check_stack_read(env, regno, off, size,
value_regno);
@@ -7189,13 +6979,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
if (err)
return err;
-
return 0;
}
/* When register 'regno' is used to read the stack (either directly or through
* a helper function) make sure that it's within stack boundary and, depending
- * on the access type, that all elements of the stack are initialized.
+ * on the access type and privileges, that all elements of the stack are
+ * initialized.
*
* 'off' includes 'regno->off', but not its dynamic part (if any).
*
@@ -7303,8 +7093,11 @@ static int check_stack_range_initialized(
slot = -i - 1;
spi = slot / BPF_REG_SIZE;
- if (state->allocated_stack <= slot)
- goto err;
+ if (state->allocated_stack <= slot) {
+ verbose(env, "verifier bug: allocated_stack too small");
+ return -EFAULT;
+ }
+
stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
if (*stype == STACK_MISC)
goto mark;
@@ -7328,7 +7121,6 @@ static int check_stack_range_initialized(
goto mark;
}
-err:
if (tnum_is_const(reg->var_off)) {
verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n",
err_extra, regno, min_off, i - min_off, access_size);
@@ -7353,7 +7145,7 @@ mark:
* helper may write to the entire memory range.
*/
}
- return update_stack_depth(env, state, min_off);
+ return 0;
}
static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
@@ -7449,6 +7241,12 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
}
}
+/* verify arguments to helpers or kfuncs consisting of a pointer and an access
+ * size.
+ *
+ * @regno is the register containing the access size. regno-1 is the register
+ * containing the pointer.
+ */
static int check_mem_size_reg(struct bpf_verifier_env *env,
struct bpf_reg_state *reg, u32 regno,
bool zero_size_allowed,
@@ -7483,12 +7281,10 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
return -EACCES;
}
- if (reg->umin_value == 0) {
- err = check_helper_mem_access(env, regno - 1, 0,
- zero_size_allowed,
- meta);
- if (err)
- return err;
+ if (reg->umin_value == 0 && !zero_size_allowed) {
+ verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n",
+ regno, reg->umin_value, reg->umax_value);
+ return -EACCES;
}
if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
@@ -7504,8 +7300,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
return err;
}
-int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
- u32 regno, u32 mem_size)
+static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+ u32 regno, u32 mem_size)
{
bool may_be_null = type_may_be_null(reg->type);
struct bpf_reg_state saved_reg;
@@ -8150,7 +7946,7 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
/* switch to DRAINED state, but keep the depth unchanged */
/* mark current iter state as drained and assume returned NULL */
cur_iter->iter.state = BPF_ITER_STATE_DRAINED;
- __mark_reg_const_zero(&cur_fr->regs[BPF_REG_0]);
+ __mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]);
return 0;
}
@@ -8490,9 +8286,9 @@ reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields)
return field;
}
-int check_func_arg_reg_off(struct bpf_verifier_env *env,
- const struct bpf_reg_state *reg, int regno,
- enum bpf_arg_type arg_type)
+static int check_func_arg_reg_off(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno,
+ enum bpf_arg_type arg_type)
{
u32 type = reg->type;
@@ -8626,6 +8422,54 @@ static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env,
return state->stack[spi].spilled_ptr.dynptr.type;
}
+static int check_reg_const_str(struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg, u32 regno)
+{
+ struct bpf_map *map = reg->map_ptr;
+ int err;
+ int map_off;
+ u64 map_addr;
+ char *str_ptr;
+
+ if (reg->type != PTR_TO_MAP_VALUE)
+ return -EINVAL;
+
+ if (!bpf_map_is_rdonly(map)) {
+ verbose(env, "R%d does not point to a readonly map'\n", regno);
+ return -EACCES;
+ }
+
+ if (!tnum_is_const(reg->var_off)) {
+ verbose(env, "R%d is not a constant address'\n", regno);
+ return -EACCES;
+ }
+
+ if (!map->ops->map_direct_value_addr) {
+ verbose(env, "no direct value access support for this map type\n");
+ return -EACCES;
+ }
+
+ err = check_map_access(env, regno, reg->off,
+ map->value_size - reg->off, false,
+ ACCESS_HELPER);
+ if (err)
+ return err;
+
+ map_off = reg->off + reg->var_off.value;
+ err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
+ if (err) {
+ verbose(env, "direct value access on string failed\n");
+ return err;
+ }
+
+ str_ptr = (char *)(long)(map_addr);
+ if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
+ verbose(env, "string is not zero-terminated\n");
+ return -EINVAL;
+ }
+ return 0;
+}
+
static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
struct bpf_call_arg_meta *meta,
const struct bpf_func_proto *fn,
@@ -8870,44 +8714,9 @@ skip_type_check:
}
case ARG_PTR_TO_CONST_STR:
{
- struct bpf_map *map = reg->map_ptr;
- int map_off;
- u64 map_addr;
- char *str_ptr;
-
- if (!bpf_map_is_rdonly(map)) {
- verbose(env, "R%d does not point to a readonly map'\n", regno);
- return -EACCES;
- }
-
- if (!tnum_is_const(reg->var_off)) {
- verbose(env, "R%d is not a constant address'\n", regno);
- return -EACCES;
- }
-
- if (!map->ops->map_direct_value_addr) {
- verbose(env, "no direct value access support for this map type\n");
- return -EACCES;
- }
-
- err = check_map_access(env, regno, reg->off,
- map->value_size - reg->off, false,
- ACCESS_HELPER);
+ err = check_reg_const_str(env, reg, regno);
if (err)
return err;
-
- map_off = reg->off + reg->var_off.value;
- err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
- if (err) {
- verbose(env, "direct value access on string failed\n");
- return err;
- }
-
- str_ptr = (char *)(long)(map_addr);
- if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
- verbose(env, "string is not zero-terminated\n");
- return -EINVAL;
- }
break;
}
case ARG_PTR_TO_KPTR:
@@ -9440,6 +9249,102 @@ err_out:
return err;
}
+static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
+ const struct btf *btf,
+ struct bpf_reg_state *regs)
+{
+ struct bpf_subprog_info *sub = subprog_info(env, subprog);
+ struct bpf_verifier_log *log = &env->log;
+ u32 i;
+ int ret;
+
+ ret = btf_prepare_func_args(env, subprog);
+ if (ret)
+ return ret;
+
+ /* check that BTF function arguments match actual types that the
+ * verifier sees.
+ */
+ for (i = 0; i < sub->arg_cnt; i++) {
+ u32 regno = i + 1;
+ struct bpf_reg_state *reg = &regs[regno];
+ struct bpf_subprog_arg_info *arg = &sub->args[i];
+
+ if (arg->arg_type == ARG_ANYTHING) {
+ if (reg->type != SCALAR_VALUE) {
+ bpf_log(log, "R%d is not a scalar\n", regno);
+ return -EINVAL;
+ }
+ } else if (arg->arg_type == ARG_PTR_TO_CTX) {
+ ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE);
+ if (ret < 0)
+ return ret;
+ /* If function expects ctx type in BTF check that caller
+ * is passing PTR_TO_CTX.
+ */
+ if (reg->type != PTR_TO_CTX) {
+ bpf_log(log, "arg#%d expects pointer to ctx\n", i);
+ return -EINVAL;
+ }
+ } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
+ ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE);
+ if (ret < 0)
+ return ret;
+ if (check_mem_reg(env, reg, regno, arg->mem_size))
+ return -EINVAL;
+ if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) {
+ bpf_log(log, "arg#%d is expected to be non-NULL\n", i);
+ return -EINVAL;
+ }
+ } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
+ ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0);
+ if (ret)
+ return ret;
+ } else {
+ bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n",
+ i, arg->arg_type);
+ return -EFAULT;
+ }
+ }
+
+ return 0;
+}
+
+/* Compare BTF of a function call with given bpf_reg_state.
+ * Returns:
+ * EFAULT - there is a verifier bug. Abort verification.
+ * EINVAL - there is a type mismatch or BTF is not available.
+ * 0 - BTF matches with what bpf_reg_state expects.
+ * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
+ */
+static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
+ struct bpf_reg_state *regs)
+{
+ struct bpf_prog *prog = env->prog;
+ struct btf *btf = prog->aux->btf;
+ u32 btf_id;
+ int err;
+
+ if (!prog->aux->func_info)
+ return -EINVAL;
+
+ btf_id = prog->aux->func_info[subprog].type_id;
+ if (!btf_id)
+ return -EFAULT;
+
+ if (prog->aux->func_info_aux[subprog].unreliable)
+ return -EINVAL;
+
+ err = btf_check_func_arg_match(env, subprog, btf, regs);
+ /* Compiler optimizations can remove arguments from static functions
+ * or mismatched type can be passed into a global function.
+ * In such cases mark the function as unreliable from BTF point of view.
+ */
+ if (err)
+ prog->aux->func_info_aux[subprog].unreliable = true;
+ 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)
@@ -9529,13 +9434,18 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
if (err == -EFAULT)
return err;
if (subprog_is_global(env, subprog)) {
+ const char *sub_name = subprog_name(env, subprog);
+
if (err) {
- verbose(env, "Caller passes invalid args into func#%d\n", subprog);
+ verbose(env, "Caller passes invalid args into func#%d ('%s')\n",
+ subprog, sub_name);
return err;
}
- if (env->log.level & BPF_LOG_LEVEL)
- verbose(env, "Func#%d is global and valid. Skipping.\n", subprog);
+ verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
+ subprog, sub_name);
+ /* mark global subprog for verifying after main prog */
+ subprog_aux(env, subprog)->called = true;
clear_caller_saved_regs(env, caller->regs);
/* All global functions return a 64-bit SCALAR_VALUE */
@@ -9635,7 +9545,7 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env,
return err;
callee->in_callback_fn = true;
- callee->callback_ret_range = tnum_range(0, 1);
+ callee->callback_ret_range = retval_range(0, 1);
return 0;
}
@@ -9657,7 +9567,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env,
__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
callee->in_callback_fn = true;
- callee->callback_ret_range = tnum_range(0, 1);
+ callee->callback_ret_range = retval_range(0, 1);
return 0;
}
@@ -9687,7 +9597,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env,
__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
callee->in_async_callback_fn = true;
- callee->callback_ret_range = tnum_range(0, 1);
+ callee->callback_ret_range = retval_range(0, 1);
return 0;
}
@@ -9706,7 +9616,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env,
callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID;
__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
callee->regs[BPF_REG_2].btf = btf_vmlinux;
- callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA],
+ callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA];
/* pointer to stack or null */
callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4];
@@ -9715,7 +9625,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env,
__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
callee->in_callback_fn = true;
- callee->callback_ret_range = tnum_range(0, 1);
+ callee->callback_ret_range = retval_range(0, 1);
return 0;
}
@@ -9738,7 +9648,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
callee->in_callback_fn = true;
- callee->callback_ret_range = tnum_range(0, 1);
+ callee->callback_ret_range = retval_range(0, 1);
return 0;
}
@@ -9770,7 +9680,7 @@ static int set_rbtree_add_callback_state(struct bpf_verifier_env *env,
__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
callee->in_callback_fn = true;
- callee->callback_ret_range = tnum_range(0, 1);
+ callee->callback_ret_range = retval_range(0, 1);
return 0;
}
@@ -9799,6 +9709,11 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
return is_rbtree_lock_required_kfunc(kfunc_btf_id);
}
+static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg)
+{
+ return range.minval <= reg->smin_value && reg->smax_value <= range.maxval;
+}
+
static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state, *prev_st;
@@ -9822,15 +9737,21 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
caller = state->frame[state->curframe - 1];
if (callee->in_callback_fn) {
- /* enforce R0 return value range [0, 1]. */
- struct tnum range = callee->callback_ret_range;
-
if (r0->type != SCALAR_VALUE) {
verbose(env, "R0 not a scalar value\n");
return -EACCES;
}
- if (!tnum_in(range, r0->var_off)) {
- verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
+
+ /* we are going to rely on register's precise value */
+ err = mark_reg_read(env, r0, r0->parent, REG_LIVE_READ64);
+ err = err ?: mark_chain_precision(env, BPF_REG_0);
+ if (err)
+ return err;
+
+ /* enforce R0 return value range */
+ if (!retval_range_within(callee->callback_ret_range, r0)) {
+ verbose_invalid_scalar(env, r0, callee->callback_ret_range,
+ "At callback return", "R0");
return -EINVAL;
}
if (!calls_callback(env, callee->callsite)) {
@@ -9896,14 +9817,15 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
return 0;
}
-static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
- int func_id,
- struct bpf_call_arg_meta *meta)
+static int do_refine_retval_range(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, int ret_type,
+ int func_id,
+ struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
if (ret_type != RET_INTEGER)
- return;
+ return 0;
switch (func_id) {
case BPF_FUNC_get_stack:
@@ -9929,6 +9851,8 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
reg_bounds_sync(ret_reg);
break;
}
+
+ return reg_bounds_sanity_check(env, ret_reg, "retval");
}
static int
@@ -9998,7 +9922,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
val = reg->var_off.value;
max = map->max_entries;
- if (!(register_is_const(reg) && val < max)) {
+ if (!(is_reg_const(reg, false) && val < max)) {
bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
return 0;
}
@@ -10593,7 +10517,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
regs[BPF_REG_0].ref_obj_id = id;
}
- do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
+ err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
+ if (err)
+ return err;
err = check_map_func_compatibility(env, meta.map_ptr, func_id);
if (err)
@@ -10771,6 +10697,11 @@ static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param
return __kfunc_param_match_suffix(btf, arg, "__nullable");
}
+static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg)
+{
+ return __kfunc_param_match_suffix(btf, arg, "__str");
+}
+
static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
const struct btf_param *arg,
const char *name)
@@ -10914,6 +10845,7 @@ enum kfunc_ptr_arg_type {
KF_ARG_PTR_TO_RB_ROOT,
KF_ARG_PTR_TO_RB_NODE,
KF_ARG_PTR_TO_NULL,
+ KF_ARG_PTR_TO_CONST_STR,
};
enum special_kfunc_type {
@@ -11064,6 +10996,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
if (is_kfunc_arg_rbtree_node(meta->btf, &args[argno]))
return KF_ARG_PTR_TO_RB_NODE;
+ if (is_kfunc_arg_const_str(meta->btf, &args[argno]))
+ return KF_ARG_PTR_TO_CONST_STR;
+
if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) {
if (!btf_type_is_struct(ref_t)) {
verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n",
@@ -11695,6 +11630,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
case KF_ARG_PTR_TO_MEM_SIZE:
case KF_ARG_PTR_TO_CALLBACK:
case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
+ case KF_ARG_PTR_TO_CONST_STR:
/* Trusted by default */
break;
default:
@@ -11966,6 +11902,15 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
meta->arg_btf = reg->btf;
meta->arg_btf_id = reg->btf_id;
break;
+ case KF_ARG_PTR_TO_CONST_STR:
+ if (reg->type != PTR_TO_MAP_VALUE) {
+ verbose(env, "arg#%d doesn't point to a const string\n", i);
+ return -EINVAL;
+ }
+ ret = check_reg_const_str(env, reg, regno);
+ if (ret)
+ return ret;
+ break;
}
}
@@ -12020,7 +11965,7 @@ 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_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name);
static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx_p)
@@ -12157,7 +12102,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
* to bpf_throw becomes the return value of the program.
*/
if (!env->exception_callback_subprog) {
- err = check_return_code(env, BPF_REG_1);
+ err = check_return_code(env, BPF_REG_1, "R1");
if (err < 0)
return err;
}
@@ -12196,20 +12141,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
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;
@@ -12230,6 +12161,35 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EINVAL;
}
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) {
+ verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n",
+ ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE);
+ return -EINVAL;
+ }
+
+ if (!bpf_global_percpu_ma_set) {
+ mutex_lock(&bpf_percpu_ma_lock);
+ if (!bpf_global_percpu_ma_set) {
+ /* Charge memory allocated with bpf_global_percpu_ma to
+ * root memcg. The obj_cgroup for root memcg is NULL.
+ */
+ err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL);
+ if (!err)
+ bpf_global_percpu_ma_set = true;
+ }
+ mutex_unlock(&bpf_percpu_ma_lock);
+ if (err)
+ return err;
+ }
+
+ mutex_lock(&bpf_percpu_ma_lock);
+ err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size);
+ mutex_unlock(&bpf_percpu_ma_lock);
+ if (err)
+ return err;
+ }
+
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)) {
@@ -14086,13 +14046,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
/* check dest operand */
err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+ err = err ?: adjust_reg_min_max_vals(env, insn);
if (err)
return err;
-
- return adjust_reg_min_max_vals(env, insn);
}
- return 0;
+ return reg_bounds_sanity_check(env, &regs[insn->dst_reg], "alu");
}
static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
@@ -14174,161 +14133,130 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
}));
}
-static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
-{
- struct tnum subreg = tnum_subreg(reg->var_off);
- s32 sval = (s32)val;
-
- switch (opcode) {
- case BPF_JEQ:
- if (tnum_is_const(subreg))
- 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)
- return 1;
- if (!((subreg.mask | subreg.value) & val))
- return 0;
- break;
- case BPF_JGT:
- if (reg->u32_min_value > val)
- return 1;
- else if (reg->u32_max_value <= val)
- return 0;
- break;
- case BPF_JSGT:
- if (reg->s32_min_value > sval)
- return 1;
- else if (reg->s32_max_value <= sval)
- return 0;
- break;
- case BPF_JLT:
- if (reg->u32_max_value < val)
- return 1;
- else if (reg->u32_min_value >= val)
- return 0;
- break;
- case BPF_JSLT:
- if (reg->s32_max_value < sval)
- return 1;
- else if (reg->s32_min_value >= sval)
- return 0;
- break;
- case BPF_JGE:
- if (reg->u32_min_value >= val)
- return 1;
- else if (reg->u32_max_value < val)
- return 0;
- break;
- case BPF_JSGE:
- if (reg->s32_min_value >= sval)
- return 1;
- else if (reg->s32_max_value < sval)
- return 0;
- break;
- case BPF_JLE:
- if (reg->u32_max_value <= val)
- return 1;
- else if (reg->u32_min_value > val)
- return 0;
- break;
- case BPF_JSLE:
- if (reg->s32_max_value <= sval)
- return 1;
- else if (reg->s32_min_value > sval)
- return 0;
- break;
- }
-
- return -1;
-}
-
-
-static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
-{
- s64 sval = (s64)val;
+/*
+ * <reg1> <op> <reg2>, currently assuming reg2 is a constant
+ */
+static int is_scalar_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+ u8 opcode, bool is_jmp32)
+{
+ struct tnum t1 = is_jmp32 ? tnum_subreg(reg1->var_off) : reg1->var_off;
+ struct tnum t2 = is_jmp32 ? tnum_subreg(reg2->var_off) : reg2->var_off;
+ u64 umin1 = is_jmp32 ? (u64)reg1->u32_min_value : reg1->umin_value;
+ u64 umax1 = is_jmp32 ? (u64)reg1->u32_max_value : reg1->umax_value;
+ s64 smin1 = is_jmp32 ? (s64)reg1->s32_min_value : reg1->smin_value;
+ s64 smax1 = is_jmp32 ? (s64)reg1->s32_max_value : reg1->smax_value;
+ u64 umin2 = is_jmp32 ? (u64)reg2->u32_min_value : reg2->umin_value;
+ u64 umax2 = is_jmp32 ? (u64)reg2->u32_max_value : reg2->umax_value;
+ s64 smin2 = is_jmp32 ? (s64)reg2->s32_min_value : reg2->smin_value;
+ s64 smax2 = is_jmp32 ? (s64)reg2->s32_max_value : reg2->smax_value;
switch (opcode) {
case BPF_JEQ:
- 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)
+ /* constants, umin/umax and smin/smax checks would be
+ * redundant in this case because they all should match
+ */
+ if (tnum_is_const(t1) && tnum_is_const(t2))
+ return t1.value == t2.value;
+ /* non-overlapping ranges */
+ if (umin1 > umax2 || umax1 < umin2)
return 0;
- else if (sval < reg->smin_value || sval > reg->smax_value)
+ if (smin1 > smax2 || smax1 < smin2)
return 0;
+ if (!is_jmp32) {
+ /* if 64-bit ranges are inconclusive, see if we can
+ * utilize 32-bit subrange knowledge to eliminate
+ * branches that can't be taken a priori
+ */
+ if (reg1->u32_min_value > reg2->u32_max_value ||
+ reg1->u32_max_value < reg2->u32_min_value)
+ return 0;
+ if (reg1->s32_min_value > reg2->s32_max_value ||
+ reg1->s32_max_value < reg2->s32_min_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)
+ /* constants, umin/umax and smin/smax checks would be
+ * redundant in this case because they all should match
+ */
+ if (tnum_is_const(t1) && tnum_is_const(t2))
+ return t1.value != t2.value;
+ /* non-overlapping ranges */
+ if (umin1 > umax2 || umax1 < umin2)
return 1;
- else if (sval < reg->smin_value || sval > reg->smax_value)
+ if (smin1 > smax2 || smax1 < smin2)
return 1;
+ if (!is_jmp32) {
+ /* if 64-bit ranges are inconclusive, see if we can
+ * utilize 32-bit subrange knowledge to eliminate
+ * branches that can't be taken a priori
+ */
+ if (reg1->u32_min_value > reg2->u32_max_value ||
+ reg1->u32_max_value < reg2->u32_min_value)
+ return 1;
+ if (reg1->s32_min_value > reg2->s32_max_value ||
+ reg1->s32_max_value < reg2->s32_min_value)
+ return 1;
+ }
break;
case BPF_JSET:
- if ((~reg->var_off.mask & reg->var_off.value) & val)
+ if (!is_reg_const(reg2, is_jmp32)) {
+ swap(reg1, reg2);
+ swap(t1, t2);
+ }
+ if (!is_reg_const(reg2, is_jmp32))
+ return -1;
+ if ((~t1.mask & t1.value) & t2.value)
return 1;
- if (!((reg->var_off.mask | reg->var_off.value) & val))
+ if (!((t1.mask | t1.value) & t2.value))
return 0;
break;
case BPF_JGT:
- if (reg->umin_value > val)
+ if (umin1 > umax2)
return 1;
- else if (reg->umax_value <= val)
+ else if (umax1 <= umin2)
return 0;
break;
case BPF_JSGT:
- if (reg->smin_value > sval)
+ if (smin1 > smax2)
return 1;
- else if (reg->smax_value <= sval)
+ else if (smax1 <= smin2)
return 0;
break;
case BPF_JLT:
- if (reg->umax_value < val)
+ if (umax1 < umin2)
return 1;
- else if (reg->umin_value >= val)
+ else if (umin1 >= umax2)
return 0;
break;
case BPF_JSLT:
- if (reg->smax_value < sval)
+ if (smax1 < smin2)
return 1;
- else if (reg->smin_value >= sval)
+ else if (smin1 >= smax2)
return 0;
break;
case BPF_JGE:
- if (reg->umin_value >= val)
+ if (umin1 >= umax2)
return 1;
- else if (reg->umax_value < val)
+ else if (umax1 < umin2)
return 0;
break;
case BPF_JSGE:
- if (reg->smin_value >= sval)
+ if (smin1 >= smax2)
return 1;
- else if (reg->smax_value < sval)
+ else if (smax1 < smin2)
return 0;
break;
case BPF_JLE:
- if (reg->umax_value <= val)
+ if (umax1 <= umin2)
return 1;
- else if (reg->umin_value > val)
+ else if (umin1 > umax2)
return 0;
break;
case BPF_JSLE:
- if (reg->smax_value <= sval)
+ if (smax1 <= smin2)
return 1;
- else if (reg->smin_value > sval)
+ else if (smin1 > smax2)
return 0;
break;
}
@@ -14336,41 +14264,6 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return -1;
}
-/* compute branch direction of the expression "if (reg opcode val) goto target;"
- * and return:
- * 1 - branch will be taken and "goto target" will be executed
- * 0 - branch will not be taken and fall-through to next insn
- * -1 - unknown. Example: "if (reg < 5)" is unknown when register value
- * range [0,10]
- */
-static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
- bool is_jmp32)
-{
- if (__is_pointer_value(false, reg)) {
- if (!reg_not_null(reg))
- return -1;
-
- /* If pointer is valid tests against zero will fail so we can
- * use this to direct branch taken.
- */
- if (val != 0)
- return -1;
-
- switch (opcode) {
- case BPF_JEQ:
- return 0;
- case BPF_JNE:
- return 1;
- default:
- return -1;
- }
- }
-
- if (is_jmp32)
- return is_branch32_taken(reg, val, opcode);
- return is_branch64_taken(reg, val, opcode);
-}
-
static int flip_opcode(u32 opcode)
{
/* How can we transform "a <op> b" into "b <op> a"? */
@@ -14432,216 +14325,280 @@ static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
return -1;
}
-/* Adjusts the register min/max values in the case that the dst_reg is the
- * variable register that we are working on, and src_reg is a constant or we're
- * simply doing a BPF_K check.
- * In JEQ/JNE cases we also adjust the var_off values.
+/* compute branch direction of the expression "if (<reg1> opcode <reg2>) goto target;"
+ * and return:
+ * 1 - branch will be taken and "goto target" will be executed
+ * 0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg1 < 5)" is unknown when register value
+ * range [0,10]
*/
-static void reg_set_min_max(struct bpf_reg_state *true_reg,
- struct bpf_reg_state *false_reg,
- u64 val, u32 val32,
- u8 opcode, bool is_jmp32)
-{
- struct tnum false_32off = tnum_subreg(false_reg->var_off);
- struct tnum false_64off = false_reg->var_off;
- struct tnum true_32off = tnum_subreg(true_reg->var_off);
- struct tnum true_64off = true_reg->var_off;
- s64 sval = (s64)val;
- s32 sval32 = (s32)val32;
-
- /* If the dst_reg is a pointer, we can't learn anything about its
- * variable offset from the compare (unless src_reg were a pointer into
- * the same object, but we don't bother with that.
- * Since false_reg and true_reg have the same type by construction, we
- * only need to check one of them for pointerness.
- */
- if (__is_pointer_value(false, false_reg))
- return;
+static int is_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+ u8 opcode, bool is_jmp32)
+{
+ if (reg_is_pkt_pointer_any(reg1) && reg_is_pkt_pointer_any(reg2) && !is_jmp32)
+ return is_pkt_ptr_branch_taken(reg1, reg2, opcode);
+ if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) {
+ u64 val;
+
+ /* arrange that reg2 is a scalar, and reg1 is a pointer */
+ if (!is_reg_const(reg2, is_jmp32)) {
+ opcode = flip_opcode(opcode);
+ swap(reg1, reg2);
+ }
+ /* and ensure that reg2 is a constant */
+ if (!is_reg_const(reg2, is_jmp32))
+ return -1;
+
+ if (!reg_not_null(reg1))
+ return -1;
+
+ /* If pointer is valid tests against zero will fail so we can
+ * use this to direct branch taken.
+ */
+ val = reg_const_value(reg2, is_jmp32);
+ if (val != 0)
+ return -1;
+
+ switch (opcode) {
+ case BPF_JEQ:
+ return 0;
+ case BPF_JNE:
+ return 1;
+ default:
+ return -1;
+ }
+ }
+
+ /* now deal with two scalars, but not necessarily constants */
+ return is_scalar_branch_taken(reg1, reg2, opcode, is_jmp32);
+}
+
+/* Opcode that corresponds to a *false* branch condition.
+ * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2
+ */
+static u8 rev_opcode(u8 opcode)
+{
switch (opcode) {
- /* JEQ/JNE comparison doesn't change the register equivalence.
- *
- * r1 = r2;
- * if (r1 == 42) goto label;
- * ...
- * label: // here both r1 and r2 are known to be 42.
- *
- * Hence when marking register as known preserve it's ID.
+ case BPF_JEQ: return BPF_JNE;
+ case BPF_JNE: return BPF_JEQ;
+ /* JSET doesn't have it's reverse opcode in BPF, so add
+ * BPF_X flag to denote the reverse of that operation
*/
+ case BPF_JSET: return BPF_JSET | BPF_X;
+ case BPF_JSET | BPF_X: return BPF_JSET;
+ case BPF_JGE: return BPF_JLT;
+ case BPF_JGT: return BPF_JLE;
+ case BPF_JLE: return BPF_JGT;
+ case BPF_JLT: return BPF_JGE;
+ case BPF_JSGE: return BPF_JSLT;
+ case BPF_JSGT: return BPF_JSLE;
+ case BPF_JSLE: return BPF_JSGT;
+ case BPF_JSLT: return BPF_JSGE;
+ default: return 0;
+ }
+}
+
+/* Refine range knowledge for <reg1> <op> <reg>2 conditional operation. */
+static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+ u8 opcode, bool is_jmp32)
+{
+ struct tnum t;
+ u64 val;
+
+again:
+ switch (opcode) {
case BPF_JEQ:
if (is_jmp32) {
- __mark_reg32_known(true_reg, val32);
- true_32off = tnum_subreg(true_reg->var_off);
+ reg1->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value);
+ reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value);
+ reg1->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value);
+ reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value);
+ reg2->u32_min_value = reg1->u32_min_value;
+ reg2->u32_max_value = reg1->u32_max_value;
+ reg2->s32_min_value = reg1->s32_min_value;
+ reg2->s32_max_value = reg1->s32_max_value;
+
+ t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off));
+ reg1->var_off = tnum_with_subreg(reg1->var_off, t);
+ reg2->var_off = tnum_with_subreg(reg2->var_off, t);
} else {
- ___mark_reg_known(true_reg, val);
- true_64off = true_reg->var_off;
+ reg1->umin_value = max(reg1->umin_value, reg2->umin_value);
+ reg1->umax_value = min(reg1->umax_value, reg2->umax_value);
+ reg1->smin_value = max(reg1->smin_value, reg2->smin_value);
+ reg1->smax_value = min(reg1->smax_value, reg2->smax_value);
+ reg2->umin_value = reg1->umin_value;
+ reg2->umax_value = reg1->umax_value;
+ reg2->smin_value = reg1->smin_value;
+ reg2->smax_value = reg1->smax_value;
+
+ reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off);
+ reg2->var_off = reg1->var_off;
}
break;
case BPF_JNE:
+ if (!is_reg_const(reg2, is_jmp32))
+ swap(reg1, reg2);
+ if (!is_reg_const(reg2, is_jmp32))
+ break;
+
+ /* try to recompute the bound of reg1 if reg2 is a const and
+ * is exactly the edge of reg1.
+ */
+ val = reg_const_value(reg2, is_jmp32);
if (is_jmp32) {
- __mark_reg32_known(false_reg, val32);
- false_32off = tnum_subreg(false_reg->var_off);
+ /* u32_min_value is not equal to 0xffffffff at this point,
+ * because otherwise u32_max_value is 0xffffffff as well,
+ * in such a case both reg1 and reg2 would be constants,
+ * jump would be predicted and reg_set_min_max() won't
+ * be called.
+ *
+ * Same reasoning works for all {u,s}{min,max}{32,64} cases
+ * below.
+ */
+ if (reg1->u32_min_value == (u32)val)
+ reg1->u32_min_value++;
+ if (reg1->u32_max_value == (u32)val)
+ reg1->u32_max_value--;
+ if (reg1->s32_min_value == (s32)val)
+ reg1->s32_min_value++;
+ if (reg1->s32_max_value == (s32)val)
+ reg1->s32_max_value--;
} else {
- ___mark_reg_known(false_reg, val);
- false_64off = false_reg->var_off;
+ if (reg1->umin_value == (u64)val)
+ reg1->umin_value++;
+ if (reg1->umax_value == (u64)val)
+ reg1->umax_value--;
+ if (reg1->smin_value == (s64)val)
+ reg1->smin_value++;
+ if (reg1->smax_value == (s64)val)
+ reg1->smax_value--;
}
break;
case BPF_JSET:
+ if (!is_reg_const(reg2, is_jmp32))
+ swap(reg1, reg2);
+ if (!is_reg_const(reg2, is_jmp32))
+ break;
+ val = reg_const_value(reg2, is_jmp32);
+ /* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X)
+ * requires single bit to learn something useful. E.g., if we
+ * know that `r1 & 0x3` is true, then which bits (0, 1, or both)
+ * are actually set? We can learn something definite only if
+ * it's a single-bit value to begin with.
+ *
+ * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have
+ * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor
+ * bit 1 is set, which we can readily use in adjustments.
+ */
+ if (!is_power_of_2(val))
+ break;
if (is_jmp32) {
- false_32off = tnum_and(false_32off, tnum_const(~val32));
- if (is_power_of_2(val32))
- true_32off = tnum_or(true_32off,
- tnum_const(val32));
+ t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val));
+ reg1->var_off = tnum_with_subreg(reg1->var_off, t);
} else {
- false_64off = tnum_and(false_64off, tnum_const(~val));
- if (is_power_of_2(val))
- true_64off = tnum_or(true_64off,
- tnum_const(val));
+ reg1->var_off = tnum_or(reg1->var_off, tnum_const(val));
}
break;
- case BPF_JGE:
- case BPF_JGT:
- {
+ case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */
+ if (!is_reg_const(reg2, is_jmp32))
+ swap(reg1, reg2);
+ if (!is_reg_const(reg2, is_jmp32))
+ break;
+ val = reg_const_value(reg2, is_jmp32);
if (is_jmp32) {
- u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1;
- u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32;
-
- false_reg->u32_max_value = min(false_reg->u32_max_value,
- false_umax);
- true_reg->u32_min_value = max(true_reg->u32_min_value,
- true_umin);
+ t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val));
+ reg1->var_off = tnum_with_subreg(reg1->var_off, t);
} else {
- u64 false_umax = opcode == BPF_JGT ? val : val - 1;
- u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
-
- false_reg->umax_value = min(false_reg->umax_value, false_umax);
- true_reg->umin_value = max(true_reg->umin_value, true_umin);
+ reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val));
}
break;
- }
- case BPF_JSGE:
- case BPF_JSGT:
- {
+ case BPF_JLE:
if (is_jmp32) {
- s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1;
- s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32;
-
- false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax);
- true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin);
+ reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value);
+ reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value);
} else {
- s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1;
- s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
-
- false_reg->smax_value = min(false_reg->smax_value, false_smax);
- true_reg->smin_value = max(true_reg->smin_value, true_smin);
+ reg1->umax_value = min(reg1->umax_value, reg2->umax_value);
+ reg2->umin_value = max(reg1->umin_value, reg2->umin_value);
}
break;
- }
- case BPF_JLE:
case BPF_JLT:
- {
if (is_jmp32) {
- u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1;
- u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32;
-
- false_reg->u32_min_value = max(false_reg->u32_min_value,
- false_umin);
- true_reg->u32_max_value = min(true_reg->u32_max_value,
- true_umax);
+ reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1);
+ reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value);
} else {
- u64 false_umin = opcode == BPF_JLT ? val : val + 1;
- u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
-
- false_reg->umin_value = max(false_reg->umin_value, false_umin);
- true_reg->umax_value = min(true_reg->umax_value, true_umax);
+ reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1);
+ reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value);
}
break;
- }
case BPF_JSLE:
+ if (is_jmp32) {
+ reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value);
+ reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value);
+ } else {
+ reg1->smax_value = min(reg1->smax_value, reg2->smax_value);
+ reg2->smin_value = max(reg1->smin_value, reg2->smin_value);
+ }
+ break;
case BPF_JSLT:
- {
if (is_jmp32) {
- s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1;
- s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32;
-
- false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin);
- true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax);
+ reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1);
+ reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value);
} else {
- s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1;
- s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
-
- false_reg->smin_value = max(false_reg->smin_value, false_smin);
- true_reg->smax_value = min(true_reg->smax_value, true_smax);
+ reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1);
+ reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value);
}
break;
- }
+ case BPF_JGE:
+ case BPF_JGT:
+ case BPF_JSGE:
+ case BPF_JSGT:
+ /* just reuse LE/LT logic above */
+ opcode = flip_opcode(opcode);
+ swap(reg1, reg2);
+ goto again;
default:
return;
}
-
- if (is_jmp32) {
- false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off),
- tnum_subreg(false_32off));
- true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off),
- tnum_subreg(true_32off));
- __reg_combine_32_into_64(false_reg);
- __reg_combine_32_into_64(true_reg);
- } else {
- false_reg->var_off = false_64off;
- true_reg->var_off = true_64off;
- __reg_combine_64_into_32(false_reg);
- __reg_combine_64_into_32(true_reg);
- }
}
-/* Same as above, but for the case that dst_reg holds a constant and src_reg is
- * the variable reg.
+/* Adjusts the register min/max values in the case that the dst_reg and
+ * src_reg are both SCALAR_VALUE registers (or we are simply doing a BPF_K
+ * check, in which case we havea fake SCALAR_VALUE representing insn->imm).
+ * Technically we can do similar adjustments for pointers to the same object,
+ * but we don't support that right now.
*/
-static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
- struct bpf_reg_state *false_reg,
- u64 val, u32 val32,
- u8 opcode, bool is_jmp32)
+static int reg_set_min_max(struct bpf_verifier_env *env,
+ struct bpf_reg_state *true_reg1,
+ struct bpf_reg_state *true_reg2,
+ struct bpf_reg_state *false_reg1,
+ struct bpf_reg_state *false_reg2,
+ u8 opcode, bool is_jmp32)
{
- opcode = flip_opcode(opcode);
- /* This uses zero as "not present in table"; luckily the zero opcode,
- * BPF_JA, can't get here.
+ int err;
+
+ /* If either register is a pointer, we can't learn anything about its
+ * variable offset from the compare (unless they were a pointer into
+ * the same object, but we don't bother with that).
*/
- if (opcode)
- reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32);
-}
-
-/* Regs are known to be equal, so intersect their min/max/var_off */
-static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
- struct bpf_reg_state *dst_reg)
-{
- src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value,
- dst_reg->umin_value);
- src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value,
- dst_reg->umax_value);
- src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value,
- dst_reg->smin_value);
- src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value,
- dst_reg->smax_value);
- src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
- dst_reg->var_off);
- reg_bounds_sync(src_reg);
- reg_bounds_sync(dst_reg);
-}
+ if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE)
+ return 0;
-static void reg_combine_min_max(struct bpf_reg_state *true_src,
- struct bpf_reg_state *true_dst,
- struct bpf_reg_state *false_src,
- struct bpf_reg_state *false_dst,
- u8 opcode)
-{
- switch (opcode) {
- case BPF_JEQ:
- __reg_combine_min_max(true_src, true_dst);
- break;
- case BPF_JNE:
- __reg_combine_min_max(false_src, false_dst);
- break;
- }
+ /* fallthrough (FALSE) branch */
+ regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32);
+ reg_bounds_sync(false_reg1);
+ reg_bounds_sync(false_reg2);
+
+ /* jump (TRUE) branch */
+ regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32);
+ reg_bounds_sync(true_reg1);
+ reg_bounds_sync(true_reg2);
+
+ err = reg_bounds_sanity_check(env, true_reg1, "true_reg1");
+ err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2");
+ err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1");
+ err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2");
+ return err;
}
static void mark_ptr_or_null_reg(struct bpf_func_state *state,
@@ -14839,6 +14796,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL;
struct bpf_reg_state *eq_branch_regs;
+ struct bpf_reg_state fake_reg = {};
u8 opcode = BPF_OP(insn->code);
bool is_jmp32;
int pred = -1;
@@ -14879,42 +14837,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
return -EINVAL;
}
+ src_reg = &fake_reg;
+ src_reg->type = SCALAR_VALUE;
+ __mark_reg_known(src_reg, insn->imm);
}
is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
-
- if (BPF_SRC(insn->code) == BPF_K) {
- pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32);
- } else if (src_reg->type == SCALAR_VALUE &&
- is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) {
- pred = is_branch_taken(dst_reg,
- tnum_subreg(src_reg->var_off).value,
- opcode,
- is_jmp32);
- } else if (src_reg->type == SCALAR_VALUE &&
- !is_jmp32 && tnum_is_const(src_reg->var_off)) {
- pred = is_branch_taken(dst_reg,
- src_reg->var_off.value,
- opcode,
- is_jmp32);
- } else if (dst_reg->type == SCALAR_VALUE &&
- is_jmp32 && tnum_is_const(tnum_subreg(dst_reg->var_off))) {
- pred = is_branch_taken(src_reg,
- tnum_subreg(dst_reg->var_off).value,
- flip_opcode(opcode),
- is_jmp32);
- } else if (dst_reg->type == SCALAR_VALUE &&
- !is_jmp32 && tnum_is_const(dst_reg->var_off)) {
- pred = is_branch_taken(src_reg,
- dst_reg->var_off.value,
- flip_opcode(opcode),
- is_jmp32);
- } else if (reg_is_pkt_pointer_any(dst_reg) &&
- reg_is_pkt_pointer_any(src_reg) &&
- !is_jmp32) {
- pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode);
- }
-
+ pred = is_branch_taken(dst_reg, src_reg, opcode, is_jmp32);
if (pred >= 0) {
/* If we get here with a dst_reg pointer type it is because
* above is_branch_taken() special cased the 0 comparison.
@@ -14962,53 +14891,27 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return -EFAULT;
other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
- /* detect if we are comparing against a constant value so we can adjust
- * our min/max values for our dst register.
- * this is only legit if both are scalars (or pointers to the same
- * object, I suppose, see the PTR_MAYBE_NULL related if block below),
- * because otherwise the different base pointers mean the offsets aren't
- * comparable.
- */
if (BPF_SRC(insn->code) == BPF_X) {
- struct bpf_reg_state *src_reg = &regs[insn->src_reg];
-
- if (dst_reg->type == SCALAR_VALUE &&
- src_reg->type == SCALAR_VALUE) {
- if (tnum_is_const(src_reg->var_off) ||
- (is_jmp32 &&
- tnum_is_const(tnum_subreg(src_reg->var_off))))
- reg_set_min_max(&other_branch_regs[insn->dst_reg],
- dst_reg,
- src_reg->var_off.value,
- tnum_subreg(src_reg->var_off).value,
- opcode, is_jmp32);
- else if (tnum_is_const(dst_reg->var_off) ||
- (is_jmp32 &&
- tnum_is_const(tnum_subreg(dst_reg->var_off))))
- reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
- src_reg,
- dst_reg->var_off.value,
- tnum_subreg(dst_reg->var_off).value,
- opcode, is_jmp32);
- else if (!is_jmp32 &&
- (opcode == BPF_JEQ || opcode == BPF_JNE))
- /* Comparing for equality, we can combine knowledge */
- reg_combine_min_max(&other_branch_regs[insn->src_reg],
- &other_branch_regs[insn->dst_reg],
- src_reg, dst_reg, opcode);
- if (src_reg->id &&
- !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
- find_equal_scalars(this_branch, src_reg);
- find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
- }
-
- }
- } else if (dst_reg->type == SCALAR_VALUE) {
- reg_set_min_max(&other_branch_regs[insn->dst_reg],
- dst_reg, insn->imm, (u32)insn->imm,
- opcode, is_jmp32);
+ err = reg_set_min_max(env,
+ &other_branch_regs[insn->dst_reg],
+ &other_branch_regs[insn->src_reg],
+ dst_reg, src_reg, opcode, is_jmp32);
+ } else /* BPF_SRC(insn->code) == BPF_K */ {
+ err = reg_set_min_max(env,
+ &other_branch_regs[insn->dst_reg],
+ src_reg /* fake one */,
+ dst_reg, src_reg /* same fake one */,
+ opcode, is_jmp32);
}
+ if (err)
+ return err;
+ if (BPF_SRC(insn->code) == BPF_X &&
+ src_reg->type == SCALAR_VALUE && src_reg->id &&
+ !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
+ find_equal_scalars(this_branch, src_reg);
+ find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
+ }
if (dst_reg->type == SCALAR_VALUE && dst_reg->id &&
!WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) {
find_equal_scalars(this_branch, dst_reg);
@@ -15280,12 +15183,13 @@ 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, int regno)
+static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name)
{
+ const char *exit_ctx = "At program exit";
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), const_0 = tnum_const(0);
+ struct bpf_retval_range range = retval_range(0, 1);
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
int err;
struct bpf_func_state *frame = env->cur_state->frame[0];
@@ -15327,17 +15231,9 @@ static int check_return_code(struct bpf_verifier_env *env, int 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 R%d is not a known value (%s)\n",
- regno, reg_type_str(env, reg->type));
- return -EINVAL;
- }
-
- if (!tnum_in(const_0, reg->var_off)) {
- verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0");
- return -EINVAL;
- }
- return 0;
+ exit_ctx = "At async callback return";
+ range = retval_range(0, 0);
+ goto enforce_retval;
}
if (is_subprog && !frame->in_exception_callback_fn) {
@@ -15360,14 +15256,14 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
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_UNIX_GETSOCKNAME)
- range = tnum_range(1, 1);
+ range = retval_range(1, 1);
if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)
- range = tnum_range(0, 3);
+ range = retval_range(0, 3);
break;
case BPF_PROG_TYPE_CGROUP_SKB:
if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) {
- range = tnum_range(0, 3);
+ range = retval_range(0, 3);
enforce_attach_type_range = tnum_range(2, 3);
}
break;
@@ -15380,13 +15276,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
case BPF_PROG_TYPE_RAW_TRACEPOINT:
if (!env->prog->aux->attach_btf_id)
return 0;
- range = tnum_const(0);
+ range = retval_range(0, 0);
break;
case BPF_PROG_TYPE_TRACING:
switch (env->prog->expected_attach_type) {
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
- range = tnum_const(0);
+ range = retval_range(0, 0);
break;
case BPF_TRACE_RAW_TP:
case BPF_MODIFY_RETURN:
@@ -15398,7 +15294,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
}
break;
case BPF_PROG_TYPE_SK_LOOKUP:
- range = tnum_range(SK_DROP, SK_PASS);
+ range = retval_range(SK_DROP, SK_PASS);
break;
case BPF_PROG_TYPE_LSM:
@@ -15412,12 +15308,12 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
/* Make sure programs that attach to void
* hooks don't try to modify return value.
*/
- range = tnum_range(1, 1);
+ range = retval_range(1, 1);
}
break;
case BPF_PROG_TYPE_NETFILTER:
- range = tnum_range(NF_DROP, NF_ACCEPT);
+ range = retval_range(NF_DROP, NF_ACCEPT);
break;
case BPF_PROG_TYPE_EXT:
/* freplace program can return anything as its return value
@@ -15427,15 +15323,21 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
return 0;
}
+enforce_retval:
if (reg->type != SCALAR_VALUE) {
- verbose(env, "At program exit the register R%d is not a known value (%s)\n",
- regno, reg_type_str(env, reg->type));
+ verbose(env, "%s the register R%d is not a known value (%s)\n",
+ exit_ctx, regno, reg_type_str(env, reg->type));
return -EINVAL;
}
- if (!tnum_in(range, reg->var_off)) {
- verbose_invalid_scalar(env, reg, &range, "program exit", "R0");
- if (prog->expected_attach_type == BPF_LSM_CGROUP &&
+ err = mark_chain_precision(env, regno);
+ if (err)
+ return err;
+
+ if (!retval_range_within(range, reg)) {
+ verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name);
+ if (!is_subprog &&
+ prog->expected_attach_type == BPF_LSM_CGROUP &&
prog_type == BPF_PROG_TYPE_LSM &&
!prog->aux->attach_func_proto->type)
verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
@@ -17200,7 +17102,8 @@ hit:
* the precision needs to be propagated back in
* the current state.
*/
- err = err ? : push_jmp_history(env, cur);
+ if (is_jmp_point(env, env->insn_idx))
+ err = err ? : push_jmp_history(env, cur, 0);
err = err ? : propagate_precision(env, &sl->state);
if (err)
return err;
@@ -17425,6 +17328,9 @@ static int do_check(struct bpf_verifier_env *env)
u8 class;
int err;
+ /* reset current history entry on each new instruction */
+ env->cur_hist_ent = NULL;
+
env->prev_insn_idx = prev_insn_idx;
if (env->insn_idx >= insn_cnt) {
verbose(env, "invalid insn idx %d insn_cnt %d\n",
@@ -17464,7 +17370,7 @@ static int do_check(struct bpf_verifier_env *env)
}
if (is_jmp_point(env, env->insn_idx)) {
- err = push_jmp_history(env, state);
+ err = push_jmp_history(env, state, 0);
if (err)
return err;
}
@@ -17541,10 +17447,8 @@ static int do_check(struct bpf_verifier_env *env)
insn->off, BPF_SIZE(insn->code),
BPF_READ, insn->dst_reg, false,
BPF_MODE(insn->code) == BPF_MEMSX);
- if (err)
- return err;
-
- err = save_aux_ptr_type(env, src_reg_type, true);
+ err = err ?: save_aux_ptr_type(env, src_reg_type, true);
+ err = err ?: reg_bounds_sanity_check(env, &regs[insn->dst_reg], "ldx");
if (err)
return err;
} else if (class == BPF_STX) {
@@ -17720,7 +17624,7 @@ process_bpf_exit_full:
continue;
}
- err = check_return_code(env, BPF_REG_0);
+ err = check_return_code(env, BPF_REG_0, "R0");
if (err)
return err;
process_bpf_exit:
@@ -18181,10 +18085,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
return -E2BIG;
}
+ if (env->prog->aux->sleepable)
+ atomic64_inc(&map->sleepable_refcnt);
/* hold the map. If the program is rejected by verifier,
* the map will be released by release_maps() or it
* will be used by the valid program until it's unloaded
- * and all maps are released in free_used_maps()
+ * and all maps are released in bpf_free_used_maps()
*/
bpf_map_inc(map);
@@ -19401,9 +19307,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
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;
+ mark_subprog_exc_cb(env, env->exception_callback_subprog);
}
for (i = 0; i < insn_cnt; i++, insn++) {
@@ -20103,9 +20007,10 @@ static void free_states(struct bpf_verifier_env *env)
}
}
-static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb)
+static int do_check_common(struct bpf_verifier_env *env, int subprog)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
+ struct bpf_subprog_info *sub = subprog_info(env, subprog);
struct bpf_verifier_state *state;
struct bpf_reg_state *regs;
int ret, i;
@@ -20132,46 +20037,71 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex
state->first_insn_idx = env->subprog_info[subprog].start;
state->last_insn_idx = -1;
+
regs = state->frame[state->curframe]->regs;
if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
- ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb);
+ const char *sub_name = subprog_name(env, subprog);
+ struct bpf_subprog_arg_info *arg;
+ struct bpf_reg_state *reg;
+
+ verbose(env, "Validating %s() func#%d...\n", sub_name, subprog);
+ ret = btf_prepare_func_args(env, subprog);
if (ret)
goto out;
- for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
- if (regs[i].type == PTR_TO_CTX)
+
+ if (subprog_is_exc_cb(env, subprog)) {
+ state->frame[0]->in_exception_callback_fn = true;
+ /* 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 (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) {
+ verbose(env, "exception cb only supports single integer argument\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+ for (i = BPF_REG_1; i <= sub->arg_cnt; i++) {
+ arg = &sub->args[i - BPF_REG_1];
+ reg = &regs[i];
+
+ if (arg->arg_type == ARG_PTR_TO_CTX) {
+ reg->type = PTR_TO_CTX;
mark_reg_known_zero(env, regs, i);
- else if (regs[i].type == SCALAR_VALUE)
+ } else if (arg->arg_type == ARG_ANYTHING) {
+ reg->type = SCALAR_VALUE;
mark_reg_unknown(env, regs, i);
- else if (base_type(regs[i].type) == PTR_TO_MEM) {
- const u32 mem_size = regs[i].mem_size;
-
+ } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
+ /* assume unspecial LOCAL dynptr type */
+ __mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen);
+ } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
+ reg->type = PTR_TO_MEM;
+ if (arg->arg_type & PTR_MAYBE_NULL)
+ reg->type |= PTR_MAYBE_NULL;
mark_reg_known_zero(env, regs, i);
- regs[i].mem_size = mem_size;
- regs[i].id = ++env->id_gen;
+ reg->mem_size = arg->mem_size;
+ reg->id = ++env->id_gen;
+ } else {
+ WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n",
+ i - BPF_REG_1, arg->arg_type);
+ ret = -EFAULT;
+ goto out;
}
}
- 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 {
+ /* if main BPF program has associated BTF info, validate that
+ * it's matching expected signature, and otherwise mark BTF
+ * info for main program as unreliable
+ */
+ if (env->prog->aux->func_info_aux) {
+ ret = btf_prepare_func_args(env, 0);
+ if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX)
+ env->prog->aux->func_info_aux[0].unreliable = true;
+ }
+
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
mark_reg_known_zero(env, regs, BPF_REG_1);
- ret = btf_check_subprog_arg_match(env, subprog, regs);
- if (ret == -EFAULT)
- /* unlikely verifier bug. abort.
- * ret == 0 and ret < 0 are sadly acceptable for
- * main() function due to backward compatibility.
- * Like socket filter program may be written as:
- * int bpf_prog(struct pt_regs *ctx)
- * and never dereference that ctx in the program.
- * 'struct pt_regs' is a type mismatch for socket
- * filter that should be using 'struct __sk_buff'.
- */
- goto out;
}
ret = do_check(env);
@@ -20190,8 +20120,11 @@ out:
return ret;
}
-/* Verify all global functions in a BPF program one by one based on their BTF.
- * All global functions must pass verification. Otherwise the whole program is rejected.
+/* Lazily verify all global functions based on their BTF, if they are called
+ * from main BPF program or any of subprograms transitively.
+ * BPF global subprogs called from dead code are not validated.
+ * All callable global functions must pass verification.
+ * Otherwise the whole program is rejected.
* Consider:
* int bar(int);
* int foo(int f)
@@ -20210,25 +20143,50 @@ out:
static int do_check_subprogs(struct bpf_verifier_env *env)
{
struct bpf_prog_aux *aux = env->prog->aux;
- int i, ret;
+ struct bpf_func_info_aux *sub_aux;
+ int i, ret, new_cnt;
if (!aux->func_info)
return 0;
+ /* exception callback is presumed to be always called */
+ if (env->exception_callback_subprog)
+ subprog_aux(env, env->exception_callback_subprog)->called = true;
+
+again:
+ new_cnt = 0;
for (i = 1; i < env->subprog_cnt; i++) {
- if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL)
+ if (!subprog_is_global(env, i))
+ continue;
+
+ sub_aux = subprog_aux(env, i);
+ if (!sub_aux->called || sub_aux->verified)
continue;
+
env->insn_idx = env->subprog_info[i].start;
WARN_ON_ONCE(env->insn_idx == 0);
- ret = do_check_common(env, i, env->exception_callback_subprog == i);
+ ret = do_check_common(env, i);
if (ret) {
return ret;
} else if (env->log.level & BPF_LOG_LEVEL) {
- verbose(env,
- "Func#%d is safe for any args that match its prototype\n",
- i);
+ verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n",
+ i, subprog_name(env, i));
}
+
+ /* We verified new global subprog, it might have called some
+ * more global subprogs that we haven't verified yet, so we
+ * need to do another pass over subprogs to verify those.
+ */
+ sub_aux->verified = true;
+ new_cnt++;
}
+
+ /* We can't loop forever as we verify at least one global subprog on
+ * each pass.
+ */
+ if (new_cnt)
+ goto again;
+
return 0;
}
@@ -20237,7 +20195,7 @@ static int do_check_main(struct bpf_verifier_env *env)
int ret;
env->insn_idx = 0;
- ret = do_check_common(env, 0, false);
+ ret = do_check_common(env, 0);
if (!ret)
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return ret;
@@ -20359,6 +20317,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
struct bpf_attach_target_info *tgt_info)
{
bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
+ bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING;
const char prefix[] = "btf_trace_";
int ret = 0, subprog = -1, i;
const struct btf_type *t;
@@ -20429,10 +20388,21 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
bpf_log(log, "Can attach to only JITed progs\n");
return -EINVAL;
}
- if (tgt_prog->type == prog->type) {
- /* Cannot fentry/fexit another fentry/fexit program.
- * Cannot attach program extension to another extension.
- * It's ok to attach fentry/fexit to extension program.
+ if (prog_tracing) {
+ if (aux->attach_tracing_prog) {
+ /*
+ * Target program is an fentry/fexit which is already attached
+ * to another tracing program. More levels of nesting
+ * attachment are not allowed.
+ */
+ bpf_log(log, "Cannot nest tracing program attach more than once\n");
+ return -EINVAL;
+ }
+ } else if (tgt_prog->type == prog->type) {
+ /*
+ * To avoid potential call chain cycles, prevent attaching of a
+ * program extension to another extension. It's ok to attach
+ * fentry/fexit to extension program.
*/
bpf_log(log, "Cannot recursively attach\n");
return -EINVAL;
@@ -20445,16 +20415,15 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
* except fentry/fexit. The reason is the following.
* The fentry/fexit programs are used for performance
* analysis, stats and can be attached to any program
- * type except themselves. When extension program is
- * replacing XDP function it is necessary to allow
- * performance analysis of all functions. Both original
- * XDP program and its program extension. Hence
- * attaching fentry/fexit to BPF_PROG_TYPE_EXT is
- * allowed. If extending of fentry/fexit was allowed it
- * would be possible to create long call chain
- * fentry->extension->fentry->extension beyond
- * reasonable stack size. Hence extending fentry is not
- * allowed.
+ * type. When extension program is replacing XDP function
+ * it is necessary to allow performance analysis of all
+ * functions. Both original XDP program and its program
+ * extension. Hence attaching fentry/fexit to
+ * BPF_PROG_TYPE_EXT is allowed. If extending of
+ * fentry/fexit was allowed it would be possible to create
+ * long call chain fentry->extension->fentry->extension
+ * beyond reasonable stack size. Hence extending fentry
+ * is not allowed.
*/
bpf_log(log, "Cannot extend fentry/fexit\n");
return -EINVAL;
@@ -20831,6 +20800,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (is_priv)
env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
+ env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;
env->explored_states = kvcalloc(state_htab_size(env),
sizeof(struct bpf_verifier_state_list *),
@@ -20873,8 +20843,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (ret < 0)
goto skip_full_check;
- ret = do_check_subprogs(env);
- ret = ret ?: do_check_main(env);
+ ret = do_check_main(env);
+ ret = ret ?: do_check_subprogs(env);
if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux))
ret = bpf_prog_offload_finalize(env);
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c56071f150f2..520b90dd97ec 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -164,13 +164,13 @@ struct cgroup_mgctx {
#define DEFINE_CGROUP_MGCTX(name) \
struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
-extern spinlock_t css_set_lock;
extern struct cgroup_subsys *cgroup_subsys[];
extern struct list_head cgroup_roots;
/* iterate across the hierarchies */
#define for_each_root(root) \
- list_for_each_entry((root), &cgroup_roots, root_list)
+ list_for_each_entry_rcu((root), &cgroup_roots, root_list, \
+ lockdep_is_held(&cgroup_mutex))
/**
* for_each_subsys - iterate all enabled cgroup subsystems
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 9cb00ebe9ac6..520a11cb12f4 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1262,6 +1262,40 @@ int cgroup1_get_tree(struct fs_context *fc)
return ret;
}
+/**
+ * task_get_cgroup1 - Acquires the associated cgroup of a task within a
+ * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its
+ * hierarchy ID.
+ * @tsk: The target task
+ * @hierarchy_id: The ID of a cgroup1 hierarchy
+ *
+ * On success, the cgroup is returned. On failure, ERR_PTR is returned.
+ * We limit it to cgroup1 only.
+ */
+struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id)
+{
+ struct cgroup *cgrp = ERR_PTR(-ENOENT);
+ struct cgroup_root *root;
+ unsigned long flags;
+
+ rcu_read_lock();
+ for_each_root(root) {
+ /* cgroup1 only*/
+ if (root == &cgrp_dfl_root)
+ continue;
+ if (root->hierarchy_id != hierarchy_id)
+ continue;
+ spin_lock_irqsave(&css_set_lock, flags);
+ cgrp = task_cgroup_from_root(tsk, root);
+ if (!cgrp || !cgroup_tryget(cgrp))
+ cgrp = ERR_PTR(-ENOENT);
+ spin_unlock_irqrestore(&css_set_lock, flags);
+ break;
+ }
+ rcu_read_unlock();
+ return cgrp;
+}
+
static int __init cgroup1_wq_init(void)
{
/*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4bc8183b669f..a66c088c851c 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1315,7 +1315,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root)
void cgroup_free_root(struct cgroup_root *root)
{
- kfree(root);
+ kfree_rcu(root, rcu);
}
static void cgroup_destroy_root(struct cgroup_root *root)
@@ -1347,10 +1347,9 @@ static void cgroup_destroy_root(struct cgroup_root *root)
spin_unlock_irq(&css_set_lock);
- if (!list_empty(&root->root_list)) {
- list_del(&root->root_list);
- cgroup_root_count--;
- }
+ WARN_ON_ONCE(list_empty(&root->root_list));
+ list_del_rcu(&root->root_list);
+ cgroup_root_count--;
if (!have_favordynmods)
cgroup_favor_dynmods(root, false);
@@ -1390,7 +1389,15 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
}
}
- BUG_ON(!res_cgroup);
+ /*
+ * If cgroup_mutex is not held, the cgrp_cset_link will be freed
+ * before we remove the cgroup root from the root_list. Consequently,
+ * when accessing a cgroup root, the cset_link may have already been
+ * freed, resulting in a NULL res_cgroup. However, by holding the
+ * cgroup_mutex, we ensure that res_cgroup can't be NULL.
+ * If we don't hold cgroup_mutex in the caller, we must do the NULL
+ * check.
+ */
return res_cgroup;
}
@@ -1413,6 +1420,11 @@ current_cgns_cgroup_from_root(struct cgroup_root *root)
rcu_read_unlock();
+ /*
+ * The namespace_sem is held by current, so the root cgroup can't
+ * be umounted. Therefore, we can ensure that the res is non-NULL.
+ */
+ WARN_ON_ONCE(!res);
return res;
}
@@ -1449,7 +1461,6 @@ static struct cgroup *current_cgns_cgroup_dfl(void)
static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
struct cgroup_root *root)
{
- lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_lock);
return __cset_cgroup_from_root(cset, root);
@@ -1457,7 +1468,9 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
/*
* Return the cgroup for "task" from the given hierarchy. Must be
- * called with cgroup_mutex and css_set_lock held.
+ * called with css_set_lock held to prevent task's groups from being modified.
+ * Must be called with either cgroup_mutex or rcu read lock to prevent the
+ * cgroup root from being destroyed.
*/
struct cgroup *task_cgroup_from_root(struct task_struct *task,
struct cgroup_root *root)
@@ -2032,7 +2045,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx)
struct cgroup_root *root = ctx->root;
struct cgroup *cgrp = &root->cgrp;
- INIT_LIST_HEAD(&root->root_list);
+ INIT_LIST_HEAD_RCU(&root->root_list);
atomic_set(&root->nr_cgrps, 1);
cgrp->root = root;
init_cgroup_housekeeping(cgrp);
@@ -2115,7 +2128,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
* care of subsystems' refcounts, which are explicitly dropped in
* the failure exit path.
*/
- list_add(&root->root_list, &cgroup_roots);
+ list_add_rcu(&root->root_list, &cgroup_roots);
cgroup_root_count++;
/*
@@ -6242,7 +6255,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
if (!buf)
goto out;
- cgroup_lock();
+ rcu_read_lock();
spin_lock_irq(&css_set_lock);
for_each_root(root) {
@@ -6253,6 +6266,11 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible))
continue;
+ cgrp = task_cgroup_from_root(tsk, root);
+ /* The root has already been unmounted. */
+ if (!cgrp)
+ continue;
+
seq_printf(m, "%d:", root->hierarchy_id);
if (root != &cgrp_dfl_root)
for_each_subsys(ss, ssid)
@@ -6263,9 +6281,6 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
seq_printf(m, "%sname=%s", count ? "," : "",
root->name);
seq_putc(m, ':');
-
- cgrp = task_cgroup_from_root(tsk, root);
-
/*
* On traditional hierarchies, all zombie tasks show up as
* belonging to the root cgroup. On the default hierarchy,
@@ -6297,7 +6312,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
retval = 0;
out_unlock:
spin_unlock_irq(&css_set_lock);
- cgroup_unlock();
+ rcu_read_unlock();
kfree(buf);
out:
return retval;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index fb29158ae825..ba36c073304a 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -25,6 +25,7 @@
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/cpuset.h>
+#include <linux/delay.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
@@ -43,6 +44,7 @@
#include <linux/sched/isolation.h>
#include <linux/cgroup.h>
#include <linux/wait.h>
+#include <linux/workqueue.h>
DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
@@ -204,6 +206,11 @@ struct cpuset {
*/
static cpumask_var_t subpartitions_cpus;
+/*
+ * Exclusive CPUs in isolated partitions
+ */
+static cpumask_var_t isolated_cpus;
+
/* List of remote partition root children */
static struct list_head remote_children;
@@ -1317,6 +1324,7 @@ static void compute_effective_cpumask(struct cpumask *new_cpus,
*/
enum partition_cmd {
partcmd_enable, /* Enable partition root */
+ partcmd_enablei, /* Enable isolated partition root */
partcmd_disable, /* Disable partition root */
partcmd_update, /* Update parent's effective_cpus */
partcmd_invalidate, /* Make partition invalid */
@@ -1419,6 +1427,109 @@ static void reset_partition_data(struct cpuset *cs)
}
/*
+ * partition_xcpus_newstate - Exclusive CPUs state change
+ * @old_prs: old partition_root_state
+ * @new_prs: new partition_root_state
+ * @xcpus: exclusive CPUs with state change
+ */
+static void partition_xcpus_newstate(int old_prs, int new_prs, struct cpumask *xcpus)
+{
+ WARN_ON_ONCE(old_prs == new_prs);
+ if (new_prs == PRS_ISOLATED)
+ cpumask_or(isolated_cpus, isolated_cpus, xcpus);
+ else
+ cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
+}
+
+/*
+ * partition_xcpus_add - Add new exclusive CPUs to partition
+ * @new_prs: new partition_root_state
+ * @parent: parent cpuset
+ * @xcpus: exclusive CPUs to be added
+ * Return: true if isolated_cpus modified, false otherwise
+ *
+ * Remote partition if parent == NULL
+ */
+static bool partition_xcpus_add(int new_prs, struct cpuset *parent,
+ struct cpumask *xcpus)
+{
+ bool isolcpus_updated;
+
+ WARN_ON_ONCE(new_prs < 0);
+ lockdep_assert_held(&callback_lock);
+ if (!parent)
+ parent = &top_cpuset;
+
+
+ if (parent == &top_cpuset)
+ cpumask_or(subpartitions_cpus, subpartitions_cpus, xcpus);
+
+ isolcpus_updated = (new_prs != parent->partition_root_state);
+ if (isolcpus_updated)
+ partition_xcpus_newstate(parent->partition_root_state, new_prs,
+ xcpus);
+
+ cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus);
+ return isolcpus_updated;
+}
+
+/*
+ * partition_xcpus_del - Remove exclusive CPUs from partition
+ * @old_prs: old partition_root_state
+ * @parent: parent cpuset
+ * @xcpus: exclusive CPUs to be removed
+ * Return: true if isolated_cpus modified, false otherwise
+ *
+ * Remote partition if parent == NULL
+ */
+static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
+ struct cpumask *xcpus)
+{
+ bool isolcpus_updated;
+
+ WARN_ON_ONCE(old_prs < 0);
+ lockdep_assert_held(&callback_lock);
+ if (!parent)
+ parent = &top_cpuset;
+
+ if (parent == &top_cpuset)
+ cpumask_andnot(subpartitions_cpus, subpartitions_cpus, xcpus);
+
+ isolcpus_updated = (old_prs != parent->partition_root_state);
+ if (isolcpus_updated)
+ partition_xcpus_newstate(old_prs, parent->partition_root_state,
+ xcpus);
+
+ cpumask_and(xcpus, xcpus, cpu_active_mask);
+ cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
+ return isolcpus_updated;
+}
+
+static void update_unbound_workqueue_cpumask(bool isolcpus_updated)
+{
+ int ret;
+
+ lockdep_assert_cpus_held();
+
+ if (!isolcpus_updated)
+ return;
+
+ ret = workqueue_unbound_exclude_cpumask(isolated_cpus);
+ WARN_ON_ONCE(ret < 0);
+}
+
+/**
+ * cpuset_cpu_is_isolated - Check if the given CPU is isolated
+ * @cpu: the CPU number to be checked
+ * Return: true if CPU is used in an isolated partition, false otherwise
+ */
+bool cpuset_cpu_is_isolated(int cpu)
+{
+ return cpumask_test_cpu(cpu, isolated_cpus);
+}
+EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated);
+
+/*
* compute_effective_exclusive_cpumask - compute effective exclusive CPUs
* @cs: cpuset
* @xcpus: effective exclusive CPUs value to be set
@@ -1456,14 +1567,18 @@ static inline bool is_local_partition(struct cpuset *cs)
/*
* remote_partition_enable - Enable current cpuset as a remote partition root
* @cs: the cpuset to update
+ * @new_prs: new partition_root_state
* @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)
+static int remote_partition_enable(struct cpuset *cs, int new_prs,
+ struct tmpmasks *tmp)
{
+ bool isolcpus_updated;
+
/*
* The user must have sysadmin privilege.
*/
@@ -1485,26 +1600,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
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);
-
+ isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
+ list_add(&cs->remote_sibling, &remote_children);
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);
+ update_unbound_workqueue_cpumask(isolcpus_updated);
/*
* 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;
}
@@ -1519,23 +1630,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp)
*/
static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
{
+ bool isolcpus_updated;
+
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);
+ isolcpus_updated = partition_xcpus_del(cs->partition_root_state,
+ NULL, tmp->new_cpus);
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);
+ update_unbound_workqueue_cpumask(isolcpus_updated);
/*
* Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1557,6 +1667,8 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
struct tmpmasks *tmp)
{
bool adding, deleting;
+ int prs = cs->partition_root_state;
+ int isolcpus_updated = 0;
if (WARN_ON_ONCE(!is_remote_partition(cs)))
return;
@@ -1580,21 +1692,12 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
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);
- }
+ if (adding)
+ isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask);
+ if (deleting)
+ isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask);
spin_unlock_irq(&callback_lock);
+ update_unbound_workqueue_cpumask(isolcpus_updated);
/*
* Proprogate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1676,11 +1779,11 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
* @tmp: Temporary addmask and delmask
* 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 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
- * effective_xcpus can be granted or an error code will be returned.
+ * For partcmd_enable*, the cpuset is being transformed from a non-partition
+ * 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 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 effective_xcpus will be
@@ -1695,7 +1798,7 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
*
* For partcmd_invalidate, the current partition will be made invalid.
*
- * The partcmd_enable and partcmd_disable commands are used by
+ * The partcmd_enable* and partcmd_disable commands are used by
* update_prstate(). An error code may be returned and the caller will check
* for error.
*
@@ -1716,6 +1819,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
int part_error = PERR_NONE; /* Partition error? */
int subparts_delta = 0;
struct cpumask *xcpus; /* cs effective_xcpus */
+ int isolcpus_updated = 0;
bool nocpu;
lockdep_assert_held(&cpuset_mutex);
@@ -1760,7 +1864,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
nocpu = tasks_nocpu_error(parent, cs, xcpus);
- if (cmd == partcmd_enable) {
+ if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) {
/*
* Enabling partition root is not allowed if its
* effective_xcpus is empty or doesn't overlap with
@@ -1783,6 +1887,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
cpumask_copy(tmp->delmask, xcpus);
deleting = true;
subparts_delta++;
+ new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED;
} else if (cmd == partcmd_disable) {
/*
* May need to add cpus to parent's effective_cpus for
@@ -1792,6 +1897,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus);
if (adding)
subparts_delta--;
+ new_prs = PRS_MEMBER;
} else if (newmask) {
/*
* Empty cpumask is not allowed
@@ -1940,38 +2046,28 @@ write_error:
* newly deleted ones will be added back to effective_cpus.
*/
spin_lock_irq(&callback_lock);
- if (adding) {
- if (parent == &top_cpuset)
- cpumask_andnot(subpartitions_cpus,
- subpartitions_cpus, tmp->addmask);
- /*
- * Some of the CPUs in effective_xcpus might have been offlined.
- */
- cpumask_or(parent->effective_cpus,
- 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);
- }
-
- if (is_partition_valid(parent)) {
- parent->nr_subparts += subparts_delta;
- WARN_ON_ONCE(parent->nr_subparts < 0);
- }
-
if (old_prs != new_prs) {
cs->partition_root_state = new_prs;
if (new_prs <= 0)
cs->nr_subparts = 0;
}
+ /*
+ * Adding to parent's effective_cpus means deletion CPUs from cs
+ * and vice versa.
+ */
+ if (adding)
+ isolcpus_updated += partition_xcpus_del(old_prs, parent,
+ tmp->addmask);
+ if (deleting)
+ isolcpus_updated += partition_xcpus_add(new_prs, parent,
+ tmp->delmask);
+ if (is_partition_valid(parent)) {
+ parent->nr_subparts += subparts_delta;
+ WARN_ON_ONCE(parent->nr_subparts < 0);
+ }
spin_unlock_irq(&callback_lock);
+ update_unbound_workqueue_cpumask(isolcpus_updated);
if ((old_prs != new_prs) && (cmd == partcmd_update))
update_partition_exclusive(cs, new_prs);
@@ -2948,6 +3044,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
int err = PERR_NONE, old_prs = cs->partition_root_state;
struct cpuset *parent = parent_cs(cs);
struct tmpmasks tmpmask;
+ bool new_xcpus_state = false;
if (old_prs == new_prs)
return 0;
@@ -2977,6 +3074,9 @@ static int update_prstate(struct cpuset *cs, int new_prs)
goto out;
if (!old_prs) {
+ enum partition_cmd cmd = (new_prs == PRS_ROOT)
+ ? partcmd_enable : partcmd_enablei;
+
/*
* cpus_allowed cannot be empty.
*/
@@ -2985,19 +3085,18 @@ static int update_prstate(struct cpuset *cs, int new_prs)
goto out;
}
- err = update_parent_effective_cpumask(cs, partcmd_enable,
- NULL, &tmpmask);
+ err = update_parent_effective_cpumask(cs, cmd, 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))
+ if (err && remote_partition_enable(cs, new_prs, &tmpmask))
err = 0;
} else if (old_prs && new_prs) {
/*
* A change in load balance state only, no change in cpumasks.
*/
- ;
+ new_xcpus_state = true;
} else {
/*
* Switching back to member is always allowed even if it
@@ -3029,7 +3128,10 @@ out:
WRITE_ONCE(cs->prs_err, err);
if (!is_partition_valid(cs))
reset_partition_data(cs);
+ else if (new_xcpus_state)
+ partition_xcpus_newstate(old_prs, new_prs, cs->effective_xcpus);
spin_unlock_irq(&callback_lock);
+ update_unbound_workqueue_cpumask(new_xcpus_state);
/* Force update if switching back to member */
update_cpumasks_hier(cs, &tmpmask, !new_prs ? HIER_CHECKALL : 0);
@@ -3386,6 +3488,7 @@ typedef enum {
FILE_SUBPARTS_CPULIST,
FILE_EXCLUSIVE_CPULIST,
FILE_EFFECTIVE_XCPULIST,
+ FILE_ISOLATED_CPULIST,
FILE_CPU_EXCLUSIVE,
FILE_MEM_EXCLUSIVE,
FILE_MEM_HARDWALL,
@@ -3582,6 +3685,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
case FILE_SUBPARTS_CPULIST:
seq_printf(sf, "%*pbl\n", cpumask_pr_args(subpartitions_cpus));
break;
+ case FILE_ISOLATED_CPULIST:
+ seq_printf(sf, "%*pbl\n", cpumask_pr_args(isolated_cpus));
+ break;
default:
ret = -EINVAL;
}
@@ -3875,6 +3981,13 @@ static struct cftype dfl_files[] = {
.flags = CFTYPE_ONLY_ON_ROOT | CFTYPE_DEBUG,
},
+ {
+ .name = "cpus.isolated",
+ .seq_show = cpuset_common_seq_show,
+ .private = FILE_ISOLATED_CPULIST,
+ .flags = CFTYPE_ONLY_ON_ROOT,
+ },
+
{ } /* terminate */
};
@@ -4194,6 +4307,7 @@ int __init cpuset_init(void)
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));
+ BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL));
cpumask_setall(top_cpuset.cpus_allowed);
nodes_setall(top_cpuset.mems_allowed);
@@ -4306,6 +4420,30 @@ void cpuset_force_rebuild(void)
force_rebuild = true;
}
+/*
+ * Attempt to acquire a cpus_read_lock while a hotplug operation may be in
+ * progress.
+ * Return: true if successful, false otherwise
+ *
+ * To avoid circular lock dependency between cpuset_mutex and cpus_read_lock,
+ * cpus_read_trylock() is used here to acquire the lock.
+ */
+static bool cpuset_hotplug_cpus_read_trylock(void)
+{
+ int retries = 0;
+
+ while (!cpus_read_trylock()) {
+ /*
+ * CPU hotplug still in progress. Retry 5 times
+ * with a 10ms wait before bailing out.
+ */
+ if (++retries > 5)
+ return false;
+ msleep(10);
+ }
+ return true;
+}
+
/**
* cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug
* @cs: cpuset in interest
@@ -4322,6 +4460,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
bool cpus_updated;
bool mems_updated;
bool remote;
+ int partcmd = -1;
struct cpuset *parent;
retry:
wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
@@ -4353,11 +4492,13 @@ retry:
compute_partition_effective_cpumask(cs, &new_cpus);
if (remote && cpumask_empty(&new_cpus) &&
- partition_is_populated(cs, NULL)) {
+ partition_is_populated(cs, NULL) &&
+ cpuset_hotplug_cpus_read_trylock()) {
remote_partition_disable(cs, tmp);
compute_effective_cpumask(&new_cpus, cs, parent);
remote = false;
cpuset_force_rebuild();
+ cpus_read_unlock();
}
/*
@@ -4368,18 +4509,28 @@ retry:
* partitions.
*/
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();
- }
+ tasks_nocpu_error(parent, cs, &new_cpus)))
+ partcmd = partcmd_invalidate;
/*
* 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_effective_cpumask(cs, partcmd_update, NULL, tmp);
- if (is_partition_valid(cs)) {
+ else if (is_partition_valid(parent) && is_partition_invalid(cs))
+ partcmd = partcmd_update;
+
+ /*
+ * cpus_read_lock needs to be held before calling
+ * update_parent_effective_cpumask(). To avoid circular lock
+ * dependency between cpuset_mutex and cpus_read_lock,
+ * cpus_read_trylock() is used here to acquire the lock.
+ */
+ if (partcmd >= 0) {
+ if (!cpuset_hotplug_cpus_read_trylock())
+ goto update_tasks;
+
+ update_parent_effective_cpumask(cs, partcmd, NULL, tmp);
+ cpus_read_unlock();
+ if ((partcmd == partcmd_invalidate) || is_partition_valid(cs)) {
compute_partition_effective_cpumask(cs, &new_cpus);
cpuset_force_rebuild();
}
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/rstat.c b/kernel/cgroup/rstat.c
index c0adb7254b45..a8350d2d63e6 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -74,64 +74,109 @@ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
}
/**
- * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree
- * @pos: current position
- * @root: root of the tree to traversal
+ * cgroup_rstat_push_children - push children cgroups into the given list
+ * @head: current head of the list (= subtree root)
+ * @child: first child of the root
* @cpu: target cpu
+ * Return: A new singly linked list of cgroups to be flush
*
- * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts
- * the traversal and %NULL return indicates the end. During traversal,
- * each returned cgroup is unlinked from the tree. Must be called with the
- * matching cgroup_rstat_cpu_lock held.
+ * Iteratively traverse down the cgroup_rstat_cpu updated tree level by
+ * level and push all the parents first before their next level children
+ * into a singly linked list built from the tail backward like "pushing"
+ * cgroups into a stack. The root is pushed by the caller.
+ */
+static struct cgroup *cgroup_rstat_push_children(struct cgroup *head,
+ struct cgroup *child, int cpu)
+{
+ struct cgroup *chead = child; /* Head of child cgroup level */
+ struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */
+ struct cgroup *parent, *grandchild;
+ struct cgroup_rstat_cpu *crstatc;
+
+ child->rstat_flush_next = NULL;
+
+next_level:
+ while (chead) {
+ child = chead;
+ chead = child->rstat_flush_next;
+ parent = cgroup_parent(child);
+
+ /* updated_next is parent cgroup terminated */
+ while (child != parent) {
+ child->rstat_flush_next = head;
+ head = child;
+ crstatc = cgroup_rstat_cpu(child, cpu);
+ grandchild = crstatc->updated_children;
+ if (grandchild != child) {
+ /* Push the grand child to the next level */
+ crstatc->updated_children = child;
+ grandchild->rstat_flush_next = ghead;
+ ghead = grandchild;
+ }
+ child = crstatc->updated_next;
+ crstatc->updated_next = NULL;
+ }
+ }
+
+ if (ghead) {
+ chead = ghead;
+ ghead = NULL;
+ goto next_level;
+ }
+ return head;
+}
+
+/**
+ * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed
+ * @root: root of the cgroup subtree to traverse
+ * @cpu: target cpu
+ * Return: A singly linked list of cgroups to be flushed
+ *
+ * Walks the updated rstat_cpu tree on @cpu from @root. During traversal,
+ * each returned cgroup is unlinked from the updated tree.
*
* The only ordering guarantee is that, for a parent and a child pair
- * covered by a given traversal, if a child is visited, its parent is
- * guaranteed to be visited afterwards.
+ * covered by a given traversal, the child is before its parent in
+ * the list.
+ *
+ * Note that updated_children is self terminated and points to a list of
+ * child cgroups if not empty. Whereas updated_next is like a sibling link
+ * within the children list and terminated by the parent cgroup. An exception
+ * here is the cgroup root whose updated_next can be self terminated.
*/
-static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
- struct cgroup *root, int cpu)
+static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
{
- struct cgroup_rstat_cpu *rstatc;
- struct cgroup *parent;
-
- if (pos == root)
- return NULL;
+ raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
+ struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu);
+ struct cgroup *head = NULL, *parent, *child;
+ unsigned long flags;
/*
- * We're gonna walk down to the first leaf and visit/remove it. We
- * can pick whatever unvisited node as the starting point.
+ * The _irqsave() is needed because cgroup_rstat_lock is
+ * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
+ * this lock with the _irq() suffix only disables interrupts on
+ * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
+ * interrupts on both configurations. The _irqsave() ensures
+ * that interrupts are always disabled and later restored.
*/
- if (!pos) {
- pos = root;
- /* return NULL if this subtree is not on-list */
- if (!cgroup_rstat_cpu(pos, cpu)->updated_next)
- return NULL;
- } else {
- pos = cgroup_parent(pos);
- }
+ raw_spin_lock_irqsave(cpu_lock, flags);
- /* walk down to the first leaf */
- while (true) {
- rstatc = cgroup_rstat_cpu(pos, cpu);
- if (rstatc->updated_children == pos)
- break;
- pos = rstatc->updated_children;
- }
+ /* Return NULL if this subtree is not on-list */
+ if (!rstatc->updated_next)
+ goto unlock_ret;
/*
- * Unlink @pos from the tree. As the updated_children list is
+ * Unlink @root from its parent. As the updated_children list is
* singly linked, we have to walk it to find the removal point.
- * However, due to the way we traverse, @pos will be the first
- * child in most cases. The only exception is @root.
*/
- parent = cgroup_parent(pos);
+ parent = cgroup_parent(root);
if (parent) {
struct cgroup_rstat_cpu *prstatc;
struct cgroup **nextp;
prstatc = cgroup_rstat_cpu(parent, cpu);
nextp = &prstatc->updated_children;
- while (*nextp != pos) {
+ while (*nextp != root) {
struct cgroup_rstat_cpu *nrstatc;
nrstatc = cgroup_rstat_cpu(*nextp, cpu);
@@ -142,7 +187,17 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
}
rstatc->updated_next = NULL;
- return pos;
+
+ /* Push @root to the list first before pushing the children */
+ head = root;
+ root->rstat_flush_next = NULL;
+ child = rstatc->updated_children;
+ rstatc->updated_children = root;
+ if (child != root)
+ head = cgroup_rstat_push_children(head, child, cpu);
+unlock_ret:
+ raw_spin_unlock_irqrestore(cpu_lock, flags);
+ return head;
}
/*
@@ -176,21 +231,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
lockdep_assert_held(&cgroup_rstat_lock);
for_each_possible_cpu(cpu) {
- raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock,
- cpu);
- struct cgroup *pos = NULL;
- unsigned long flags;
+ struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
- /*
- * The _irqsave() is needed because cgroup_rstat_lock is
- * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
- * this lock with the _irq() suffix only disables interrupts on
- * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
- * interrupts on both configurations. The _irqsave() ensures
- * that interrupts are always disabled and later restored.
- */
- raw_spin_lock_irqsave(cpu_lock, flags);
- while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) {
+ for (; pos; pos = pos->rstat_flush_next) {
struct cgroup_subsys_state *css;
cgroup_base_stat_flush(pos, cpu);
@@ -202,7 +245,6 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
css->ss->css_rstat_flush(css, cpu);
rcu_read_unlock();
}
- raw_spin_unlock_irqrestore(cpu_lock, flags);
/* play nice and yield if necessary */
if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a86972a91991..e6ec3ba4950b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2125,11 +2125,6 @@ static struct cpuhp_step cpuhp_hp_states[] = {
.startup.single = relay_prepare_cpu,
.teardown.single = NULL,
},
- [CPUHP_SLAB_PREPARE] = {
- .name = "slab:prepare",
- .startup.single = slab_prepare_cpu,
- .teardown.single = slab_dead_cpu,
- },
[CPUHP_RCUTREE_PREP] = {
.name = "RCU/tree:prepare",
.startup.single = rcutree_prepare_cpu,
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index efe87d501c8c..75cd6a736d03 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -13,7 +13,6 @@
#include <linux/memory.h>
#include <linux/cpuhotplug.h>
#include <linux/memblock.h>
-#include <linux/kexec.h>
#include <linux/kmemleak.h>
#include <asm/page.h>
@@ -199,7 +198,7 @@ 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;
@@ -268,9 +267,9 @@ static int __init __parse_crashkernel(char *cmdline,
unsigned long long *crash_base,
const char *suffix)
{
- char *first_colon, *first_space;
- char *ck_cmdline;
- char *name = "crashkernel=";
+ char *first_colon, *first_space;
+ char *ck_cmdline;
+ char *name = "crashkernel=";
BUG_ON(!crash_size || !crash_base);
*crash_size = 0;
@@ -377,7 +376,6 @@ static int __init reserve_crashkernel_low(unsigned long long low_size)
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;
}
@@ -440,7 +438,7 @@ retry:
return;
}
- if ((crash_base > CRASH_ADDR_LOW_MAX) &&
+ if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
crash_low_size && reserve_crashkernel_low(crash_low_size)) {
memblock_phys_free(crash_base, crash_size);
return;
@@ -459,8 +457,19 @@ retry:
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
- insert_resource(&iomem_resource, &crashk_res);
}
+
+static __init int insert_crashkernel_resources(void)
+{
+ if (crashk_res.start < crashk_res.end)
+ insert_resource(&iomem_resource, &crashk_res);
+
+ if (crashk_low_res.start < crashk_low_res.end)
+ insert_resource(&iomem_resource, &crashk_low_res);
+
+ return 0;
+}
+early_initcall(insert_crashkernel_resources);
#endif
int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
@@ -551,9 +560,11 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
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);
+#ifdef CONFIG_KEXEC_FILE
+ kexec_dprintk("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);
+#endif
phdr++;
}
@@ -565,9 +576,8 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
int crash_exclude_mem_range(struct crash_mem *mem,
unsigned long long mstart, unsigned long long mend)
{
- int i, j;
+ int i;
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;
@@ -575,72 +585,51 @@ int crash_exclude_mem_range(struct crash_mem *mem,
p_start = mstart;
p_end = mend;
- if (mstart > end || mend < start)
+ if (p_start > end)
continue;
+ /*
+ * Because the memory ranges in mem->ranges are stored in
+ * ascending order, when we detect `p_end < start`, we can
+ * immediately exit the for loop, as the subsequent memory
+ * ranges will definitely be outside the range we are looking
+ * for.
+ */
+ if (p_end < start)
+ break;
+
/* Truncate any area outside of range */
- if (mstart < start)
+ if (p_start < start)
p_start = start;
- if (mend > end)
+ if (p_end > 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;
- }
+ memmove(&mem->ranges[i], &mem->ranges[i + 1],
+ (mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i]));
+ i--;
mem->nr_ranges--;
- return 0;
- }
-
- if (p_start > start && p_end < end) {
+ } else if (p_start > start && p_end < end) {
/* Split original range */
+ if (mem->nr_ranges >= mem->max_nr_ranges)
+ return -ENOMEM;
+
+ memmove(&mem->ranges[i + 2], &mem->ranges[i + 1],
+ (mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i]));
+
mem->ranges[i].end = p_start - 1;
- temp_range.start = p_end + 1;
- temp_range.end = end;
+ mem->ranges[i + 1].start = p_end + 1;
+ mem->ranges[i + 1].end = end;
+
+ i++;
+ mem->nr_ranges++;
} 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;
}
@@ -802,7 +791,7 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_OFFSET(list_head, prev);
VMCOREINFO_OFFSET(vmap_area, va_start);
VMCOREINFO_OFFSET(vmap_area, list);
- VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER + 1);
+ VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS);
log_buf_vmcoreinfo_setup();
VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
VMCOREINFO_NUMBER(NR_FREE_PAGES);
@@ -888,7 +877,7 @@ subsys_initcall(crash_notes_memory_init);
* regions are online. So mutex lock __crash_hotplug_lock is used to
* serialize the crash hotplug handling specifically.
*/
-DEFINE_MUTEX(__crash_hotplug_lock);
+static DEFINE_MUTEX(__crash_hotplug_lock);
#define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock)
#define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock)
diff --git a/kernel/cred.c b/kernel/cred.c
index 3c714cb31660..c033a201c808 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -43,10 +43,6 @@ static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) };
*/
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,
@@ -66,31 +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
*/
@@ -100,20 +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);
@@ -137,16 +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);
@@ -164,9 +118,8 @@ void exit_creds(struct task_struct *tsk)
{
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));
real_cred = (struct cred *) tsk->real_cred;
tsk->real_cred = NULL;
@@ -174,15 +127,10 @@ void exit_creds(struct task_struct *tsk)
cred = (struct cred *) tsk->cred;
tsk->cred = NULL;
- validate_creds(cred);
if (real_cred == cred) {
- alter_cred_subscribers(cred, -2);
put_cred_many(cred, 2);
} else {
- validate_creds(real_cred);
- alter_cred_subscribers(real_cred, -1);
put_cred(real_cred);
- alter_cred_subscribers(cred, -1);
put_cred(cred);
}
@@ -230,10 +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;
@@ -264,8 +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;
@@ -276,8 +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);
@@ -300,7 +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:
@@ -362,10 +303,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
clone_flags & CLONE_THREAD
) {
p->real_cred = get_cred_many(p->cred, 2);
- alter_cred_subscribers(p->cred, 2);
- kdebug("share_creds(%p{%d,%d})",
- p->cred, atomic_read(&p->cred->usage),
- read_cred_subscribers(p->cred));
+ 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;
}
@@ -404,8 +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:
@@ -457,17 +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 */
@@ -502,14 +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) ||
@@ -539,14 +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);
@@ -562,12 +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()'.
@@ -576,18 +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);
@@ -603,15 +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);
@@ -731,12 +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);
@@ -760,7 +668,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
goto error;
put_cred(old);
- validate_creds(new);
return new;
error:
@@ -825,109 +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)
-{
- pr_err("%s credentials: %p %s%s%s\n",
- label, cred,
- cred == &init_cred ? "[init]" : "",
- cred == tsk->real_cred ? "[real]" : "",
- cred == tsk->cred ? "[eff]" : "");
- pr_err("->magic=%x, put_addr=%p\n",
- cred->magic, cred->put_addr);
- pr_err("->usage=%d, subscr=%d\n",
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
- pr_err("->*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));
- pr_err("->*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
- pr_err("->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)))
- pr_err("->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)
-{
- pr_err("Invalid credentials\n");
- pr_err("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:
- pr_err("Invalid process credentials\n");
- pr_err("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
- pr_err("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/dma/coherent.c b/kernel/dma/coherent.c
index c21abc77c53e..ff5683a57f77 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -132,8 +132,10 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
void dma_release_coherent_memory(struct device *dev)
{
- if (dev)
+ if (dev) {
_dma_release_coherent_memory(dev->dma_mem);
+ dev->dma_mem = NULL;
+ }
}
static void *__dma_alloc_from_coherent(struct device *dev,
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 3de494375b7b..1a5c86dd87d5 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -876,7 +876,7 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti
return 0;
}
-void dma_debug_add_bus(struct bus_type *bus)
+void dma_debug_add_bus(const struct bus_type *bus)
{
struct notifier_block *nb;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 73c95815789a..98b2e192fd69 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -677,7 +677,6 @@ int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
return -ENOMEM;
map[0].cpu_start = cpu_start;
map[0].dma_start = dma_start;
- map[0].offset = offset;
map[0].size = size;
dev->dma_range_map = map;
return 0;
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index b481c48a31a6..d10613eb0f63 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -84,8 +84,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
void *addr;
int ret = -ENOMEM;
- /* Cannot allocate larger than MAX_ORDER */
- order = min(get_order(pool_size), MAX_ORDER);
+ /* Cannot allocate larger than MAX_PAGE_ORDER */
+ order = min(get_order(pool_size), MAX_PAGE_ORDER);
do {
pool_size = 1 << (PAGE_SHIFT + order);
@@ -190,7 +190,7 @@ static int __init dma_atomic_pool_init(void)
/*
* If coherent_pool was not used on the command line, default the pool
- * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER.
+ * sizes to 128KB per 1GB of memory, min 128KB, max MAX_PAGE_ORDER.
*/
if (!atomic_pool_size) {
unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 33d942615be5..97c298b210bc 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -686,8 +686,8 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
size_t pool_size;
size_t tlb_size;
- if (nslabs > SLABS_PER_PAGE << MAX_ORDER) {
- nslabs = SLABS_PER_PAGE << MAX_ORDER;
+ if (nslabs > SLABS_PER_PAGE << MAX_PAGE_ORDER) {
+ nslabs = SLABS_PER_PAGE << MAX_PAGE_ORDER;
nareas = limit_nareas(nareas, nslabs);
}
@@ -957,7 +957,7 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
#endif /* CONFIG_DEBUG_FS */
/**
- * swiotlb_area_find_slots() - search for slots in one IO TLB memory area
+ * swiotlb_search_pool_area() - search one memory area in one pool
* @dev: Device which maps the buffer.
* @pool: Memory pool to be searched.
* @area_index: Index of the IO TLB memory area to be searched.
@@ -972,7 +972,7 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
*
* Return: Index of the first allocated slot, or -1 on error.
*/
-static int swiotlb_area_find_slots(struct device *dev, struct io_tlb_pool *pool,
+static int swiotlb_search_pool_area(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)
{
@@ -1066,41 +1066,50 @@ found:
return slot_index;
}
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+
/**
- * swiotlb_pool_find_slots() - search for slots in one memory pool
+ * swiotlb_search_area() - search one memory area in all pools
* @dev: Device which maps the buffer.
- * @pool: Memory pool to be searched.
+ * @start_cpu: Start CPU number.
+ * @cpu_offset: Offset from @start_cpu.
* @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 one memory pool to find a sequence of slots that match the
+ * Search one memory area in all pools for 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)
+static int swiotlb_search_area(struct device *dev, int start_cpu,
+ int cpu_offset, phys_addr_t orig_addr, size_t alloc_size,
+ unsigned int alloc_align_mask, struct io_tlb_pool **retpool)
{
- int start = raw_smp_processor_id() & (pool->nareas - 1);
- int i = start, index;
-
- do {
- index = swiotlb_area_find_slots(dev, pool, i, orig_addr,
- alloc_size, alloc_align_mask);
- if (index >= 0)
- return index;
- if (++i >= pool->nareas)
- i = 0;
- } while (i != start);
+ struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+ struct io_tlb_pool *pool;
+ int area_index;
+ int index = -1;
- return -1;
+ rcu_read_lock();
+ list_for_each_entry_rcu(pool, &mem->pools, node) {
+ if (cpu_offset >= pool->nareas)
+ continue;
+ area_index = (start_cpu + cpu_offset) & (pool->nareas - 1);
+ index = swiotlb_search_pool_area(dev, pool, area_index,
+ orig_addr, alloc_size,
+ alloc_align_mask);
+ if (index >= 0) {
+ *retpool = pool;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ return index;
}
-#ifdef CONFIG_SWIOTLB_DYNAMIC
-
/**
* swiotlb_find_slots() - search for slots in the whole swiotlb
* @dev: Device which maps the buffer.
@@ -1124,18 +1133,17 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
unsigned long nslabs;
unsigned long flags;
u64 phys_limit;
+ int cpu, i;
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();
+ cpu = raw_smp_processor_id();
+ for (i = 0; i < default_nareas; ++i) {
+ index = swiotlb_search_area(dev, cpu, i, orig_addr, alloc_size,
+ alloc_align_mask, &pool);
+ if (index >= 0)
goto found;
- }
}
- rcu_read_unlock();
+
if (!mem->can_grow)
return -1;
@@ -1148,8 +1156,8 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
if (!pool)
return -1;
- index = swiotlb_pool_find_slots(dev, pool, orig_addr,
- alloc_size, alloc_align_mask);
+ index = swiotlb_search_pool_area(dev, pool, 0, orig_addr,
+ alloc_size, alloc_align_mask);
if (index < 0) {
swiotlb_dyn_free(&pool->rcu);
return -1;
@@ -1192,9 +1200,21 @@ 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);
+ struct io_tlb_pool *pool;
+ int start, i;
+ int index;
+
+ *retpool = pool = &dev->dma_io_tlb_mem->defpool;
+ i = start = raw_smp_processor_id() & (pool->nareas - 1);
+ do {
+ index = swiotlb_search_pool_area(dev, pool, i, orig_addr,
+ alloc_size, alloc_align_mask);
+ if (index >= 0)
+ return index;
+ if (++i >= pool->nareas)
+ i = 0;
+ } while (i != start);
+ return -1;
}
#endif /* CONFIG_SWIOTLB_DYNAMIC */
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index d7ee4bc3f2ba..88cb3c88aaa5 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -15,26 +15,6 @@
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
-/* See comment for enter_from_user_mode() in entry-common.h */
-static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
-{
- arch_enter_from_user_mode(regs);
- lockdep_hardirqs_off(CALLER_ADDR0);
-
- CT_WARN_ON(__ct_state() != CONTEXT_USER);
- user_exit_irqoff();
-
- instrumentation_begin();
- kmsan_unpoison_entry_regs(regs);
- trace_hardirqs_off_finish();
- instrumentation_end();
-}
-
-void noinstr enter_from_user_mode(struct pt_regs *regs)
-{
- __enter_from_user_mode(regs);
-}
-
static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
{
if (unlikely(audit_context())) {
@@ -45,7 +25,7 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
}
}
-static long syscall_trace_enter(struct pt_regs *regs, long syscall,
+long syscall_trace_enter(struct pt_regs *regs, long syscall,
unsigned long work)
{
long ret = 0;
@@ -85,67 +65,24 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
return ret ? : syscall;
}
-static __always_inline long
-__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
-{
- unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
-
- if (work & SYSCALL_WORK_ENTER)
- syscall = syscall_trace_enter(regs, syscall, work);
-
- return syscall;
-}
-
-long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
-{
- return __syscall_enter_from_user_work(regs, syscall);
-}
-
-noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
-{
- long ret;
-
- __enter_from_user_mode(regs);
-
- instrumentation_begin();
- local_irq_enable();
- ret = __syscall_enter_from_user_work(regs, syscall);
- instrumentation_end();
-
- return ret;
-}
-
noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
{
- __enter_from_user_mode(regs);
+ enter_from_user_mode(regs);
instrumentation_begin();
local_irq_enable();
instrumentation_end();
}
-/* See comment for exit_to_user_mode() in entry-common.h */
-static __always_inline void __exit_to_user_mode(void)
-{
- instrumentation_begin();
- trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare();
- instrumentation_end();
-
- user_enter_irqoff();
- arch_exit_to_user_mode();
- lockdep_hardirqs_on(CALLER_ADDR0);
-}
-
-void noinstr exit_to_user_mode(void)
-{
- __exit_to_user_mode();
-}
-
/* Workaround to allow gradual conversion of architecture code */
void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
-static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
- unsigned long ti_work)
+/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ * @regs: Pointer to pt_regs on entry stack
+ * @ti_work: TIF work flags as read by the caller
+ */
+__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+ unsigned long ti_work)
{
/*
* Before returning to user space ensure that all pending work
@@ -190,27 +127,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
return ti_work;
}
-static void exit_to_user_mode_prepare(struct pt_regs *regs)
-{
- unsigned long ti_work;
-
- lockdep_assert_irqs_disabled();
-
- /* Flush pending rcuog wakeup before the last need_resched() check */
- tick_nohz_user_enter_prepare();
-
- ti_work = read_thread_flags();
- if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
- ti_work = exit_to_user_mode_loop(regs, ti_work);
-
- arch_exit_to_user_mode_prepare(regs, ti_work);
-
- /* Ensure that kernel state is sane for a return to userspace */
- kmap_assert_nomap();
- lockdep_assert_irqs_disabled();
- lockdep_sys_exit();
-}
-
/*
* If SYSCALL_EMU is set, then the only reason to report is when
* SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
@@ -295,12 +211,12 @@ __visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
instrumentation_begin();
__syscall_exit_to_user_mode_work(regs);
instrumentation_end();
- __exit_to_user_mode();
+ exit_to_user_mode();
}
noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
{
- __enter_from_user_mode(regs);
+ enter_from_user_mode(regs);
}
noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
@@ -308,7 +224,7 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
instrumentation_begin();
exit_to_user_mode_prepare(regs);
instrumentation_end();
- __exit_to_user_mode();
+ exit_to_user_mode();
}
noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b704d83a28b2..f0f0f71213a1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1814,31 +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)
@@ -1888,8 +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);
}
@@ -1920,23 +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;
}
@@ -7372,6 +7397,14 @@ void perf_output_sample(struct perf_output_handle *handle,
if (branch_sample_hw_index(event))
perf_output_put(handle, data->br_stack->hw_idx);
perf_output_copy(handle, data->br_stack->entries, size);
+ /*
+ * Add the extension space which is appended
+ * right after the struct perf_branch_stack.
+ */
+ if (data->br_stack_cntr) {
+ size = data->br_stack->nr * sizeof(u64);
+ perf_output_copy(handle, data->br_stack_cntr, size);
+ }
} else {
/*
* we always store at least the value of nr
@@ -11400,9 +11433,30 @@ static DEVICE_ATTR_RW(perf_event_mux_interval_ms);
static struct attribute *pmu_dev_attrs[] = {
&dev_attr_type.attr,
&dev_attr_perf_event_mux_interval_ms.attr,
+ &dev_attr_nr_addr_filters.attr,
+ NULL,
+};
+
+static umode_t pmu_dev_is_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ struct pmu *pmu = dev_get_drvdata(dev);
+
+ if (n == 2 && !pmu->nr_addr_filters)
+ return 0;
+
+ return a->mode;
+}
+
+static struct attribute_group pmu_dev_attr_group = {
+ .is_visible = pmu_dev_is_visible,
+ .attrs = pmu_dev_attrs,
+};
+
+static const struct attribute_group *pmu_dev_groups[] = {
+ &pmu_dev_attr_group,
NULL,
};
-ATTRIBUTE_GROUPS(pmu_dev);
static int pmu_bus_running;
static struct bus_type pmu_bus = {
@@ -11439,18 +11493,11 @@ static int pmu_dev_alloc(struct pmu *pmu)
if (ret)
goto free_dev;
- /* For PMUs with address filters, throw in an extra attribute: */
- if (pmu->nr_addr_filters)
- ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters);
-
- if (ret)
- goto del_dev;
-
- if (pmu->attr_update)
+ if (pmu->attr_update) {
ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update);
-
- if (ret)
- goto del_dev;
+ if (ret)
+ goto del_dev;
+ }
out:
return ret;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e8d82c2f07d0..60ed43d1c29e 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -610,8 +610,8 @@ static struct page *rb_alloc_aux_page(int node, int order)
{
struct page *page;
- if (order > MAX_ORDER)
- order = MAX_ORDER;
+ if (order > MAX_PAGE_ORDER)
+ order = MAX_PAGE_ORDER;
do {
page = alloc_pages_node(node, PERF_AUX_GFP, order);
@@ -702,9 +702,9 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
/*
* kcalloc_node() is unable to allocate buffer if the size is larger
- * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case.
+ * than: PAGE_SIZE << MAX_PAGE_ORDER; directly bail out in this case.
*/
- if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER)
+ if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_PAGE_ORDER)
return -ENOMEM;
rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,
node);
@@ -821,7 +821,7 @@ struct perf_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
size = sizeof(struct perf_buffer);
size += nr_pages * sizeof(void *);
- if (order_base_2(size) > PAGE_SHIFT+MAX_ORDER)
+ if (order_base_2(size) > PAGE_SHIFT+MAX_PAGE_ORDER)
goto fail;
node = (cpu == -1) ? cpu : cpu_to_node(cpu);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 435aac1d8c27..485bb0389b48 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -181,7 +181,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
if (new_page) {
folio_get(new_folio);
- page_add_new_anon_rmap(new_page, vma, addr);
+ folio_add_new_anon_rmap(new_folio, vma, addr);
folio_add_lru_vma(new_folio, vma);
} else
/* no new page, just dec_mm_counter for old_page */
@@ -198,7 +198,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
set_pte_at_notify(mm, addr, pvmw.pte,
mk_pte(new_page, vma->vm_page_prot));
- page_remove_rmap(old_page, vma, false);
+ folio_remove_rmap_pte(old_folio, old_page, vma);
if (!folio_mapped(old_folio))
folio_free_swap(old_folio);
page_vma_mapped_walk_done(&pvmw);
diff --git a/kernel/exit.c b/kernel/exit.c
index ee9f43bed49a..3988a02efaef 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -69,8 +69,10 @@
#include <linux/rethook.h>
#include <linux/sysfs.h>
#include <linux/user_events.h>
-
#include <linux/uaccess.h>
+
+#include <uapi/linux/wait.h>
+
#include <asm/unistd.h>
#include <asm/mmu_context.h>
@@ -824,8 +826,6 @@ 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 */
@@ -909,7 +909,6 @@ 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();
diff --git a/kernel/fork.c b/kernel/fork.c
index 10917c3e1f03..c981fa6171c1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -53,6 +53,7 @@
#include <linux/seccomp.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
+#include <linux/syscall_user_dispatch.h>
#include <linux/jiffies.h>
#include <linux/futex.h>
#include <linux/compat.h>
@@ -99,6 +100,7 @@
#include <linux/stackprotector.h>
#include <linux/user_events.h>
#include <linux/iommu.h>
+#include <linux/rseq.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
@@ -165,7 +167,6 @@ void __weak arch_release_task_struct(struct task_struct *tsk)
{
}
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static struct kmem_cache *task_struct_cachep;
static inline struct task_struct *alloc_task_struct_node(int node)
@@ -177,9 +178,6 @@ static inline void free_task_struct(struct task_struct *tsk)
{
kmem_cache_free(task_struct_cachep, tsk);
}
-#endif
-
-#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
@@ -412,24 +410,6 @@ void thread_stack_cache_init(void)
}
# endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */
-#else /* CONFIG_ARCH_THREAD_STACK_ALLOCATOR */
-
-static int alloc_thread_stack_node(struct task_struct *tsk, int node)
-{
- unsigned long *stack;
-
- stack = arch_alloc_thread_stack_node(tsk, node);
- tsk->stack = stack;
- return stack ? 0 : -ENOMEM;
-}
-
-static void free_thread_stack(struct task_struct *tsk)
-{
- arch_free_thread_stack(tsk);
- tsk->stack = NULL;
-}
-
-#endif /* !CONFIG_ARCH_THREAD_STACK_ALLOCATOR */
/* SLAB cache for signal_struct structures (tsk->signal) */
static struct kmem_cache *signal_cachep;
@@ -650,7 +630,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
int retval;
unsigned long charge = 0;
LIST_HEAD(uf);
- VMA_ITERATOR(old_vmi, oldmm, 0);
VMA_ITERATOR(vmi, mm, 0);
uprobe_start_dup_mmap();
@@ -678,16 +657,22 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
goto out;
khugepaged_fork(mm, oldmm);
- retval = vma_iter_bulk_alloc(&vmi, oldmm->map_count);
- if (retval)
+ /* Use __mt_dup() to efficiently build an identical maple tree. */
+ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
+ if (unlikely(retval))
goto out;
mt_clear_in_rcu(vmi.mas.tree);
- for_each_vma(old_vmi, mpnt) {
+ for_each_vma(vmi, mpnt) {
struct file *file;
vma_start_write(mpnt);
if (mpnt->vm_flags & VM_DONTCOPY) {
+ retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start,
+ mpnt->vm_end, GFP_KERNEL);
+ if (retval)
+ goto loop_out;
+
vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
continue;
}
@@ -749,9 +734,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
if (is_vm_hugetlb_page(tmp))
hugetlb_dup_vma_private(tmp);
- /* Link the vma into the MT */
- if (vma_iter_bulk_store(&vmi, tmp))
- goto fail_nomem_vmi_store;
+ /*
+ * Link the vma into the MT. After using __mt_dup(), memory
+ * allocation is not necessary here, so it cannot fail.
+ */
+ vma_iter_bulk_store(&vmi, tmp);
mm->map_count++;
if (!(tmp->vm_flags & VM_WIPEONFORK))
@@ -760,15 +747,28 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
if (tmp->vm_ops && tmp->vm_ops->open)
tmp->vm_ops->open(tmp);
- if (retval)
+ if (retval) {
+ mpnt = vma_next(&vmi);
goto loop_out;
+ }
}
/* a new mm has just been created */
retval = arch_dup_mmap(oldmm, mm);
loop_out:
vma_iter_free(&vmi);
- if (!retval)
+ if (!retval) {
mt_set_in_rcu(vmi.mas.tree);
+ } else if (mpnt) {
+ /*
+ * The entire maple tree has already been duplicated. If the
+ * mmap duplication fails, mark the failure point with
+ * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered,
+ * stop releasing VMAs that have not been duplicated after this
+ * point.
+ */
+ mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
+ mas_store(&vmi.mas, XA_ZERO_ENTRY);
+ }
out:
mmap_write_unlock(mm);
flush_tlb_mm(oldmm);
@@ -778,8 +778,6 @@ fail_uprobe_end:
uprobe_end_dup_mmap();
return retval;
-fail_nomem_vmi_store:
- unlink_anon_vmas(tmp);
fail_nomem_anon_vma_fork:
mpol_put(vma_policy(tmp));
fail_nomem_policy:
@@ -1021,7 +1019,6 @@ static void set_max_threads(unsigned int max_threads_suggested)
int arch_task_struct_size __read_mostly;
#endif
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
{
/* Fetch thread_struct whitelist for the architecture. */
@@ -1036,12 +1033,10 @@ static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
else
*offset += offsetof(struct task_struct, thread);
}
-#endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */
void __init fork_init(void)
{
int i;
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
#define ARCH_MIN_TASKALIGN 0
#endif
@@ -1054,7 +1049,6 @@ void __init fork_init(void)
arch_task_struct_size, align,
SLAB_PANIC|SLAB_ACCOUNT,
useroffset, usersize, NULL);
-#endif
/* do the arch specific task caches init */
arch_task_cache_init();
@@ -1588,7 +1582,7 @@ static void complete_vfork_done(struct task_struct *tsk)
static int wait_for_vfork_done(struct task_struct *child,
struct completion *vfork)
{
- unsigned int state = TASK_UNINTERRUPTIBLE|TASK_KILLABLE|TASK_FREEZABLE;
+ unsigned int state = TASK_KILLABLE|TASK_FREEZABLE;
int killed;
cgroup_enter_frozen();
@@ -2928,7 +2922,7 @@ pid_t kernel_clone(struct kernel_clone_args *args)
get_task_struct(p);
}
- if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
+ if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) {
/* lock the task to synchronize with memcg migration */
task_lock(p);
lru_gen_add_mm(p->mm);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index c450fa8b8b5e..f57aaf96b829 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -187,6 +187,7 @@ static int __restore_freezer_state(struct task_struct *p, void *arg)
if (state != TASK_RUNNING) {
WRITE_ONCE(p->__state, state);
+ p->saved_state = TASK_RUNNING;
return 1;
}
@@ -201,7 +202,7 @@ void __thaw_task(struct task_struct *p)
if (WARN_ON_ONCE(freezing(p)))
goto unlock;
- if (task_call_func(p, __restore_freezer_state, NULL))
+ if (!frozen(p) || task_call_func(p, __restore_freezer_state, NULL))
goto unlock;
wake_up_state(p, TASK_FROZEN);
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index dad981a865b8..e0e853412c15 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -34,6 +34,7 @@
#include <linux/compat.h>
#include <linux/jhash.h>
#include <linux/pagemap.h>
+#include <linux/plist.h>
#include <linux/memblock.h>
#include <linux/fault-inject.h>
#include <linux/slab.h>
diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c
index eb21f065816b..b47bb764b352 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/plist.h>
#include <linux/sched/signal.h>
#include "futex.h"
diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c
index 61b112897a84..3a10375d9521 100644
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/plist.h>
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
#include <linux/freezer.h>
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index be5642a4ec49..d08fc7b5db97 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -52,6 +52,8 @@ atomic_t __kexec_lock = ATOMIC_INIT(0);
/* Flag to indicate we are going to kexec a new kernel */
bool kexec_in_progress = false;
+bool kexec_file_dbg_print;
+
int kexec_should_crash(struct task_struct *p)
{
/*
@@ -276,8 +278,8 @@ int kimage_is_destination_range(struct kimage *image,
unsigned long mstart, mend;
mstart = image->segment[i].mem;
- mend = mstart + image->segment[i].memsz;
- if ((end > mstart) && (start < mend))
+ mend = mstart + image->segment[i].memsz - 1;
+ if ((end >= mstart) && (start <= mend))
return 1;
}
@@ -370,7 +372,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
pfn = page_to_boot_pfn(pages);
epfn = pfn + count;
addr = pfn << PAGE_SHIFT;
- eaddr = epfn << PAGE_SHIFT;
+ eaddr = (epfn << PAGE_SHIFT) - 1;
if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
kimage_is_destination_range(image, addr, eaddr)) {
list_add(&pages->lru, &extra_pages);
@@ -430,7 +432,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
pages = NULL;
size = (1 << order) << PAGE_SHIFT;
- hole_start = (image->control_page + (size - 1)) & ~(size - 1);
+ hole_start = ALIGN(image->control_page, size);
hole_end = hole_start + size - 1;
while (hole_end <= crashk_res.end) {
unsigned long i;
@@ -447,7 +449,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
mend = mstart + image->segment[i].memsz - 1;
if ((hole_end >= mstart) && (hole_start <= mend)) {
/* Advance the hole to the end of the segment */
- hole_start = (mend + (size - 1)) & ~(size - 1);
+ hole_start = ALIGN(mend, size);
hole_end = hole_start + size - 1;
break;
}
@@ -455,7 +457,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
/* If I don't overlap any segments I have found my hole! */
if (i == image->nr_segments) {
pages = pfn_to_page(hole_start >> PAGE_SHIFT);
- image->control_page = hole_end;
+ image->control_page = hole_end + 1;
break;
}
}
@@ -716,7 +718,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
/* If the page is not a destination page use it */
if (!kimage_is_destination_range(image, addr,
- addr + PAGE_SIZE))
+ addr + PAGE_SIZE - 1))
break;
/*
@@ -1063,9 +1065,10 @@ __bpf_kfunc void crash_kexec(struct pt_regs *regs)
* panic(). Otherwise parallel calls of panic() and crash_kexec()
* may stop each other. To exclude them, we use panic_cpu here too.
*/
+ 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) {
+
+ if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) {
/* This is the 1st CPU which comes here, so go ahead. */
__crash_kexec(regs);
@@ -1254,6 +1257,7 @@ int kernel_kexec(void)
kexec_in_progress = true;
kernel_restart_prepare("kexec reboot");
migrate_to_reboot_cpu();
+ syscore_shutdown();
/*
* migrate_to_reboot_cpu() disables CPU hotplug assuming that
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f9a419cd22d4..bef2f6f2571b 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -123,6 +123,8 @@ void kimage_file_post_load_cleanup(struct kimage *image)
*/
kfree(image->image_loader_data);
image->image_loader_data = NULL;
+
+ kexec_file_dbg_print = false;
}
#ifdef CONFIG_KEXEC_SIG
@@ -202,6 +204,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
if (ret < 0)
return ret;
image->kernel_buf_len = ret;
+ kexec_dprintk("kernel: %p kernel_size: %#lx\n",
+ image->kernel_buf, image->kernel_buf_len);
/* Call arch image probe handlers */
ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
@@ -278,6 +282,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
if (!image)
return -ENOMEM;
+ kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG);
image->file_mode = 1;
if (kexec_on_panic) {
@@ -384,13 +389,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
if (ret)
goto out;
+ kexec_dprintk("nr_segments = %lu\n", image->nr_segments);
for (i = 0; i < image->nr_segments; i++) {
struct kexec_segment *ksegment;
ksegment = &image->segment[i];
- pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n",
- i, ksegment->buf, ksegment->bufsz, ksegment->mem,
- ksegment->memsz);
+ kexec_dprintk("segment[%d]: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n",
+ i, ksegment->buf, ksegment->bufsz, ksegment->mem,
+ ksegment->memsz);
ret = kimage_load_segment(image, &image->segment[i]);
if (ret)
@@ -403,6 +409,8 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
if (ret)
goto out;
+ kexec_dprintk("kexec_file_load: type:%u, start:0x%lx head:0x%lx flags:0x%lx\n",
+ image->type, image->start, image->head, flags);
/*
* Free up any temporary buffers allocated which are not needed
* after image has been loaded
@@ -426,11 +434,11 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
unsigned long temp_start, temp_end;
temp_end = min(end, kbuf->buf_max);
- temp_start = temp_end - kbuf->memsz;
+ temp_start = temp_end - kbuf->memsz + 1;
do {
/* align down start */
- temp_start = temp_start & (~(kbuf->buf_align - 1));
+ temp_start = ALIGN_DOWN(temp_start, kbuf->buf_align);
if (temp_start < start || temp_start < kbuf->buf_min)
return 0;
@@ -592,6 +600,8 @@ static int kexec_walk_resources(struct kexec_buf *kbuf,
IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
crashk_res.start, crashk_res.end,
kbuf, func);
+ else if (kbuf->top_down)
+ return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func);
else
return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 075a632e6c7c..d5a0ee40bf66 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2252,7 +2252,7 @@ int register_kretprobe(struct kretprobe *rp)
rp->rph = NULL;
return -ENOMEM;
}
- rp->rph->rp = rp;
+ rcu_assign_pointer(rp->rph->rp, rp);
rp->nmissed = 0;
/* Establish function entry probe point */
ret = register_kprobe(&rp->kp);
@@ -2300,7 +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/locking/locktorture.c b/kernel/locking/locktorture.c
index 69d3cd2cfc3b..415d81e6ce70 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -124,7 +124,7 @@ struct call_rcu_chain {
struct rcu_head crc_rh;
bool crc_stop;
};
-struct call_rcu_chain *call_rcu_chain;
+struct call_rcu_chain *call_rcu_chain_list;
/* Forward reference. */
static void lock_torture_cleanup(void);
@@ -1074,12 +1074,12 @@ static int call_rcu_chain_init(void)
if (call_rcu_chains <= 0)
return 0;
- call_rcu_chain = kcalloc(call_rcu_chains, sizeof(*call_rcu_chain), GFP_KERNEL);
- if (!call_rcu_chain)
+ call_rcu_chain_list = kcalloc(call_rcu_chains, sizeof(*call_rcu_chain_list), GFP_KERNEL);
+ if (!call_rcu_chain_list)
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);
+ call_rcu_chain_list[i].crc_stop = false;
+ call_rcu(&call_rcu_chain_list[i].crc_rh, call_rcu_chain_cb);
}
return 0;
}
@@ -1089,13 +1089,13 @@ static void call_rcu_chain_cleanup(void)
{
int i;
- if (!call_rcu_chain)
+ if (!call_rcu_chain_list)
return;
for (i = 0; i < call_rcu_chains; i++)
- smp_store_release(&call_rcu_chain[i].crc_stop, true);
+ smp_store_release(&call_rcu_chain_list[i].crc_stop, true);
rcu_barrier();
- kfree(call_rcu_chain);
- call_rcu_chain = NULL;
+ kfree(call_rcu_chain_list);
+ call_rcu_chain_list = NULL;
}
static void lock_torture_cleanup(void)
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 2deeeca3e71b..cbae8c0b89ab 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -532,6 +532,11 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
* This function must not be used in interrupt context. Unlocking
* of a not locked mutex is not allowed.
*
+ * The caller must ensure that the mutex stays alive until this function has
+ * returned - mutex_unlock() can NOT directly be used to release an object such
+ * that another concurrent task can free it.
+ * Mutexes are different from spinlocks & refcounts in this aspect.
+ *
* This function is similar to (but not equivalent to) up().
*/
void __sched mutex_unlock(struct mutex *lock)
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index d5610ad52b92..75a6f6133866 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -11,6 +11,13 @@
* called from interrupt context and we have preemption disabled while
* spinning.
*/
+
+struct optimistic_spin_node {
+ struct optimistic_spin_node *next, *prev;
+ int locked; /* 1 if lock acquired */
+ int cpu; /* encoded CPU # + 1 value */
+};
+
static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
/*
@@ -37,32 +44,28 @@ static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
/*
* Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
* Can return NULL in case we were the last queued and we updated @lock instead.
+ *
+ * If osq_lock() is being cancelled there must be a previous node
+ * and 'old_cpu' is its CPU #.
+ * For osq_unlock() there is never a previous node and old_cpu is
+ * set to OSQ_UNLOCKED_VAL.
*/
static inline struct optimistic_spin_node *
osq_wait_next(struct optimistic_spin_queue *lock,
struct optimistic_spin_node *node,
- struct optimistic_spin_node *prev)
+ int old_cpu)
{
- struct optimistic_spin_node *next = NULL;
int curr = encode_cpu(smp_processor_id());
- int old;
-
- /*
- * If there is a prev node in queue, then the 'old' value will be
- * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
- * we're currently last in queue, then the queue will then become empty.
- */
- old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
for (;;) {
if (atomic_read(&lock->tail) == curr &&
- atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) {
+ atomic_cmpxchg_acquire(&lock->tail, curr, old_cpu) == curr) {
/*
* We were the last queued, we moved @lock back. @prev
* will now observe @lock and will complete its
* unlock()/unqueue().
*/
- break;
+ return NULL;
}
/*
@@ -76,15 +79,15 @@ osq_wait_next(struct optimistic_spin_queue *lock,
* wait for a new @node->next from its Step-C.
*/
if (node->next) {
+ struct optimistic_spin_node *next;
+
next = xchg(&node->next, NULL);
if (next)
- break;
+ return next;
}
cpu_relax();
}
-
- return next;
}
bool osq_lock(struct optimistic_spin_queue *lock)
@@ -186,7 +189,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
* back to @prev.
*/
- next = osq_wait_next(lock, node, prev);
+ next = osq_wait_next(lock, node, prev->cpu);
if (!next)
return false;
@@ -226,7 +229,7 @@ void osq_unlock(struct optimistic_spin_queue *lock)
return;
}
- next = osq_wait_next(lock, node, NULL);
+ next = osq_wait_next(lock, node, OSQ_UNLOCKED_VAL);
if (next)
WRITE_ONCE(next->locked, 1);
}
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 14235671a1a7..87b03d2e41db 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -12,6 +12,7 @@
#include <linux/debug_locks.h>
#include <linux/delay.h>
#include <linux/export.h>
+#include <linux/pid.h>
void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
struct lock_class_key *key, short inner)
diff --git a/kernel/module/dups.c b/kernel/module/dups.c
index f3d7ea1e96d8..9a92f2f8c9d3 100644
--- a/kernel/module/dups.c
+++ b/kernel/module/dups.c
@@ -207,7 +207,7 @@ bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret)
* optimization enabled ...
*/
ret = wait_for_completion_state(&kmod_req->first_req_done,
- TASK_UNINTERRUPTIBLE | TASK_KILLABLE);
+ TASK_KILLABLE);
if (ret) {
*dup_ret = ret;
return true;
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 98fedfdb8db5..36681911c05a 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2199,6 +2199,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
mod->kunit_suites = section_objs(info, ".kunit_test_suites",
sizeof(*mod->kunit_suites),
&mod->num_kunit_suites);
+ mod->kunit_init_suites = section_objs(info, ".kunit_init_test_suites",
+ sizeof(*mod->kunit_init_suites),
+ &mod->num_kunit_init_suites);
#endif
mod->extable = section_objs(info, "__ex_table",
diff --git a/kernel/numa.c b/kernel/numa.c
new file mode 100644
index 000000000000..67ca6b8585c0
--- /dev/null
+++ b/kernel/numa.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/printk.h>
+#include <linux/numa.h>
+
+/* Stub functions: */
+
+#ifndef memory_add_physaddr_to_nid
+int memory_add_physaddr_to_nid(u64 start)
+{
+ pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
+ start);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif
+
+#ifndef phys_to_target_node
+int phys_to_target_node(u64 start)
+{
+ pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+ start);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(phys_to_target_node);
+#endif
diff --git a/kernel/params.c b/kernel/params.c
index 2d4a0564697e..2e447f8ae183 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -1,19 +1,20 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* Helpers for initial module or kernel cmdline parsing
- Copyright (C) 2001 Rusty Russell.
-
-*/
+/*
+ * Helpers for initial module or kernel cmdline parsing
+ * Copyright (C) 2001 Rusty Russell.
+ */
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/kstrtox.h>
-#include <linux/string.h>
-#include <linux/errno.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-#include <linux/ctype.h>
+#include <linux/overflow.h>
#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/string.h>
#ifdef CONFIG_SYSFS
/* Protects all built-in parameters, modules use their own param_lock */
@@ -48,7 +49,7 @@ static void *kmalloc_parameter(unsigned int size)
{
struct kmalloced_param *p;
- p = kmalloc(sizeof(*p) + size, GFP_KERNEL);
+ p = kmalloc(size_add(sizeof(*p), size), GFP_KERNEL);
if (!p)
return NULL;
@@ -120,9 +121,7 @@ static int parse_one(char *param,
unsigned num_params,
s16 min_level,
s16 max_level,
- void *arg,
- int (*handle_unknown)(char *param, char *val,
- const char *doing, void *arg))
+ void *arg, parse_unknown_fn handle_unknown)
{
unsigned int i;
int err;
@@ -165,9 +164,7 @@ char *parse_args(const char *doing,
unsigned num,
s16 min_level,
s16 max_level,
- void *arg,
- int (*unknown)(char *param, char *val,
- const char *doing, void *arg))
+ void *arg, parse_unknown_fn unknown)
{
char *param, *val, *err = NULL;
@@ -264,17 +261,22 @@ EXPORT_SYMBOL_GPL(param_set_uint_minmax);
int param_set_charp(const char *val, const struct kernel_param *kp)
{
- if (strlen(val) > 1024) {
+ size_t len, maxlen = 1024;
+
+ len = strnlen(val, maxlen + 1);
+ if (len == maxlen + 1) {
pr_err("%s: string parameter too long\n", kp->name);
return -ENOSPC;
}
maybe_kfree_parameter(*(char **)kp->arg);
- /* This is a hack. We can't kmalloc in early boot, and we
- * don't need to; this mangled commandline is preserved. */
+ /*
+ * This is a hack. We can't kmalloc() in early boot, and we
+ * don't need to; this mangled commandline is preserved.
+ */
if (slab_is_available()) {
- *(char **)kp->arg = kmalloc_parameter(strlen(val)+1);
+ *(char **)kp->arg = kmalloc_parameter(len + 1);
if (!*(char **)kp->arg)
return -ENOMEM;
strcpy(*(char **)kp->arg, val);
@@ -512,7 +514,7 @@ int param_set_copystring(const char *val, const struct kernel_param *kp)
{
const struct kparam_string *kps = kp->str;
- if (strlen(val)+1 > kps->maxlen) {
+ if (strnlen(val, kps->maxlen) == kps->maxlen) {
pr_err("%s: string doesn't fit in %u chars.\n",
kp->name, kps->maxlen-1);
return -ENOSPC;
@@ -743,8 +745,10 @@ void module_param_sysfs_remove(struct module *mod)
{
if (mod->mkobj.mp) {
sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp);
- /* We are positive that no one is using any param
- * attrs at this point. Deallocate immediately. */
+ /*
+ * We are positive that no one is using any param
+ * attrs at this point. Deallocate immediately.
+ */
free_module_param_attrs(&mod->mkobj);
}
}
diff --git a/kernel/pid.c b/kernel/pid.c
index 6500ef956f2f..b52b10865454 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -700,7 +700,7 @@ static int pidfd_getfd(struct pid *pid, int fd)
if (IS_ERR(file))
return PTR_ERR(file);
- ret = receive_fd(file, O_CLOEXEC);
+ ret = receive_fd(file, NULL, O_CLOEXEC);
fput(file);
return ret;
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 3028b2218aa4..7ade20e95232 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -23,6 +23,7 @@
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
#include <linux/idr.h>
+#include <uapi/linux/wait.h>
#include "pid_sysctl.h"
static DEFINE_MUTEX(pid_caches_mutex);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index dee341ae4ace..4b0b7cf2e019 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -642,9 +642,9 @@ int hibernation_platform_enter(void)
*/
static void power_down(void)
{
-#ifdef CONFIG_SUSPEND
int error;
+#ifdef CONFIG_SUSPEND
if (hibernation_mode == HIBERNATION_SUSPEND) {
error = suspend_devices_and_enter(mem_sleep_current);
if (error) {
@@ -667,7 +667,13 @@ static void power_down(void)
kernel_restart(NULL);
break;
case HIBERNATION_PLATFORM:
- hibernation_platform_enter();
+ error = hibernation_platform_enter();
+ if (error == -EAGAIN || error == -EBUSY) {
+ swsusp_unmark();
+ events_check_enabled = false;
+ pr_info("Wakeup event detected during hibernation, rolling back.\n");
+ return;
+ }
fallthrough;
case HIBERNATION_SHUTDOWN:
if (kernel_can_power_off())
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f6425ae3e8b0..b1ae9b677d03 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -60,22 +60,6 @@ EXPORT_SYMBOL_GPL(lock_system_sleep);
void unlock_system_sleep(unsigned int flags)
{
- /*
- * Don't use freezer_count() because we don't want the call to
- * try_to_freeze() here.
- *
- * Reason:
- * Fundamentally, we just don't need it, because freezing condition
- * doesn't come into effect until we release the
- * system_transition_mutex lock, since the freezer always works with
- * system_transition_mutex held.
- *
- * More importantly, in the case of hibernation,
- * unlock_system_sleep() gets called in snapshot_read() and
- * snapshot_write() when the freezing condition is still in effect.
- * Which means, if we use try_to_freeze() here, it would make them
- * enter the refrigerator, thus causing hibernation to lockup.
- */
if (!(flags & PF_NOFREEZE))
current->flags &= ~PF_NOFREEZE;
mutex_unlock(&system_transition_mutex);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 17fd9aaaf084..8499a39c62f4 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -175,6 +175,8 @@ extern int swsusp_write(unsigned int flags);
void swsusp_close(void);
#ifdef CONFIG_SUSPEND
extern int swsusp_unmark(void);
+#else
+static inline int swsusp_unmark(void) { return 0; }
#endif
struct __kernel_old_timeval;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 50a15408c3fc..5c96ff067c64 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1119,7 +1119,7 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
int create_basic_memory_bitmaps(void)
{
struct memory_bitmap *bm1, *bm2;
- int error = 0;
+ int error;
if (forbidden_pages_map && free_pages_map)
return 0;
@@ -1487,11 +1487,11 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
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);
+ src = kmap_local_page(s_page);
+ dst = kmap_local_page(d_page);
zeros_only = do_copy_page(dst, src);
- kunmap_atomic(dst);
- kunmap_atomic(src);
+ kunmap_local(dst);
+ kunmap_local(src);
} else {
if (PageHighMem(d_page)) {
/*
@@ -1499,9 +1499,9 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
* data modified by kmap_atomic()
*/
zeros_only = safe_copy_page(buffer, s_page);
- dst = kmap_atomic(d_page);
+ dst = kmap_local_page(d_page);
copy_page(dst, buffer);
- kunmap_atomic(dst);
+ kunmap_local(dst);
} else {
zeros_only = safe_copy_page(page_address(d_page), s_page);
}
@@ -2778,7 +2778,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
int snapshot_write_next(struct snapshot_handle *handle)
{
static struct chain_allocator ca;
- int error = 0;
+ int error;
next:
/* Check if we have already loaded the entire image */
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a2cb0babb5ec..6053ddddaf65 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -451,7 +451,7 @@ err_close:
static int swap_write_page(struct swap_map_handle *handle, void *buf,
struct hib_bio_batch *hb)
{
- int error = 0;
+ int error;
sector_t offset;
if (!handle->cur)
@@ -606,11 +606,11 @@ static int crc32_threadfn(void *data)
unsigned i;
while (1) {
- wait_event(d->go, atomic_read(&d->ready) ||
+ wait_event(d->go, atomic_read_acquire(&d->ready) ||
kthread_should_stop());
if (kthread_should_stop()) {
d->thr = NULL;
- atomic_set(&d->stop, 1);
+ atomic_set_release(&d->stop, 1);
wake_up(&d->done);
break;
}
@@ -619,7 +619,7 @@ static int crc32_threadfn(void *data)
for (i = 0; i < d->run_threads; i++)
*d->crc32 = crc32_le(*d->crc32,
d->unc[i], *d->unc_len[i]);
- atomic_set(&d->stop, 1);
+ atomic_set_release(&d->stop, 1);
wake_up(&d->done);
}
return 0;
@@ -649,12 +649,12 @@ static int lzo_compress_threadfn(void *data)
struct cmp_data *d = data;
while (1) {
- wait_event(d->go, atomic_read(&d->ready) ||
+ wait_event(d->go, atomic_read_acquire(&d->ready) ||
kthread_should_stop());
if (kthread_should_stop()) {
d->thr = NULL;
d->ret = -1;
- atomic_set(&d->stop, 1);
+ atomic_set_release(&d->stop, 1);
wake_up(&d->done);
break;
}
@@ -663,7 +663,7 @@ static int lzo_compress_threadfn(void *data)
d->ret = lzo1x_1_compress(d->unc, d->unc_len,
d->cmp + LZO_HEADER, &d->cmp_len,
d->wrk);
- atomic_set(&d->stop, 1);
+ atomic_set_release(&d->stop, 1);
wake_up(&d->done);
}
return 0;
@@ -798,7 +798,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
data[thr].unc_len = off;
- atomic_set(&data[thr].ready, 1);
+ atomic_set_release(&data[thr].ready, 1);
wake_up(&data[thr].go);
}
@@ -806,12 +806,12 @@ static int save_image_lzo(struct swap_map_handle *handle,
break;
crc->run_threads = thr;
- atomic_set(&crc->ready, 1);
+ atomic_set_release(&crc->ready, 1);
wake_up(&crc->go);
for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
wait_event(data[thr].done,
- atomic_read(&data[thr].stop));
+ atomic_read_acquire(&data[thr].stop));
atomic_set(&data[thr].stop, 0);
ret = data[thr].ret;
@@ -850,7 +850,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
}
}
- wait_event(crc->done, atomic_read(&crc->stop));
+ wait_event(crc->done, atomic_read_acquire(&crc->stop));
atomic_set(&crc->stop, 0);
}
@@ -1132,12 +1132,12 @@ static int lzo_decompress_threadfn(void *data)
struct dec_data *d = data;
while (1) {
- wait_event(d->go, atomic_read(&d->ready) ||
+ wait_event(d->go, atomic_read_acquire(&d->ready) ||
kthread_should_stop());
if (kthread_should_stop()) {
d->thr = NULL;
d->ret = -1;
- atomic_set(&d->stop, 1);
+ atomic_set_release(&d->stop, 1);
wake_up(&d->done);
break;
}
@@ -1150,7 +1150,7 @@ static int lzo_decompress_threadfn(void *data)
flush_icache_range((unsigned long)d->unc,
(unsigned long)d->unc + d->unc_len);
- atomic_set(&d->stop, 1);
+ atomic_set_release(&d->stop, 1);
wake_up(&d->done);
}
return 0;
@@ -1335,7 +1335,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
}
if (crc->run_threads) {
- wait_event(crc->done, atomic_read(&crc->stop));
+ wait_event(crc->done, atomic_read_acquire(&crc->stop));
atomic_set(&crc->stop, 0);
crc->run_threads = 0;
}
@@ -1371,7 +1371,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
pg = 0;
}
- atomic_set(&data[thr].ready, 1);
+ atomic_set_release(&data[thr].ready, 1);
wake_up(&data[thr].go);
}
@@ -1390,7 +1390,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
wait_event(data[thr].done,
- atomic_read(&data[thr].stop));
+ atomic_read_acquire(&data[thr].stop));
atomic_set(&data[thr].stop, 0);
ret = data[thr].ret;
@@ -1421,7 +1421,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
ret = snapshot_write_next(snapshot);
if (ret <= 0) {
crc->run_threads = thr + 1;
- atomic_set(&crc->ready, 1);
+ atomic_set_release(&crc->ready, 1);
wake_up(&crc->go);
goto out_finish;
}
@@ -1429,13 +1429,13 @@ static int load_image_lzo(struct swap_map_handle *handle,
}
crc->run_threads = thr;
- atomic_set(&crc->ready, 1);
+ atomic_set_release(&crc->ready, 1);
wake_up(&crc->go);
}
out_finish:
if (crc->run_threads) {
- wait_event(crc->done, atomic_read(&crc->stop));
+ wait_event(crc->done, atomic_read_acquire(&crc->stop));
atomic_set(&crc->stop, 0);
}
stop = ktime_get();
@@ -1566,7 +1566,6 @@ put:
/**
* swsusp_close - close resume device.
- * @exclusive: Close the resume device which is exclusively opened.
*/
void swsusp_close(void)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index d8b5e13a2229..2fabd497d659 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -145,20 +145,9 @@ void __ptrace_unlink(struct task_struct *child)
*/
if (!(child->flags & PF_EXITING) &&
(child->signal->flags & SIGNAL_STOP_STOPPED ||
- child->signal->group_stop_count)) {
+ child->signal->group_stop_count))
child->jobctl |= JOBCTL_STOP_PENDING;
- /*
- * This is only possible if this thread was cloned by the
- * traced task running in the stopped group, set the signal
- * for the future reports.
- * FIXME: we should change ptrace_init_task() to handle this
- * case.
- */
- if (!(child->jobctl & JOBCTL_STOP_SIGMASK))
- child->jobctl |= SIGSTOP;
- }
-
/*
* If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
* @child in the butt. Note that @resume should be used iff @child
@@ -386,6 +375,34 @@ static int check_ptrace_options(unsigned long data)
return 0;
}
+static inline void ptrace_set_stopped(struct task_struct *task)
+{
+ guard(spinlock)(&task->sighand->siglock);
+
+ /*
+ * If the task is already STOPPED, set JOBCTL_TRAP_STOP and
+ * TRAPPING, and kick it so that it transits to TRACED. TRAPPING
+ * will be cleared if the child completes the transition or any
+ * event which clears the group stop states happens. We'll wait
+ * for the transition to complete before returning from this
+ * function.
+ *
+ * This hides STOPPED -> RUNNING -> TRACED transition from the
+ * attaching thread but a different thread in the same group can
+ * still observe the transient RUNNING state. IOW, if another
+ * thread's WNOHANG wait(2) on the stopped tracee races against
+ * ATTACH, the wait(2) may fail due to the transient RUNNING.
+ *
+ * The following task_is_stopped() test is safe as both transitions
+ * in and out of STOPPED are protected by siglock.
+ */
+ if (task_is_stopped(task) &&
+ task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
+ task->jobctl &= ~JOBCTL_STOPPED;
+ signal_wake_up_state(task, __TASK_STOPPED);
+ }
+}
+
static int ptrace_attach(struct task_struct *task, long request,
unsigned long addr,
unsigned long flags)
@@ -393,17 +410,17 @@ static int ptrace_attach(struct task_struct *task, long request,
bool seize = (request == PTRACE_SEIZE);
int retval;
- retval = -EIO;
if (seize) {
if (addr != 0)
- goto out;
+ return -EIO;
/*
* This duplicates the check in check_ptrace_options() because
* ptrace_attach() and ptrace_setoptions() have historically
* used different error codes for unknown ptrace options.
*/
if (flags & ~(unsigned long)PTRACE_O_MASK)
- goto out;
+ return -EIO;
+
retval = check_ptrace_options(flags);
if (retval)
return retval;
@@ -414,88 +431,54 @@ static int ptrace_attach(struct task_struct *task, long request,
audit_ptrace(task);
- retval = -EPERM;
if (unlikely(task->flags & PF_KTHREAD))
- goto out;
+ return -EPERM;
if (same_thread_group(task, current))
- goto out;
+ return -EPERM;
/*
* Protect exec's credential calculations against our interference;
* SUID, SGID and LSM creds get determined differently
* under ptrace.
*/
- retval = -ERESTARTNOINTR;
- if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
- goto out;
+ scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR,
+ &task->signal->cred_guard_mutex) {
- task_lock(task);
- retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
- task_unlock(task);
- if (retval)
- goto unlock_creds;
+ scoped_guard (task_lock, task) {
+ retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
+ if (retval)
+ return retval;
+ }
- write_lock_irq(&tasklist_lock);
- retval = -EPERM;
- if (unlikely(task->exit_state))
- goto unlock_tasklist;
- if (task->ptrace)
- goto unlock_tasklist;
+ scoped_guard (write_lock_irq, &tasklist_lock) {
+ if (unlikely(task->exit_state))
+ return -EPERM;
+ if (task->ptrace)
+ return -EPERM;
- task->ptrace = flags;
+ task->ptrace = flags;
- ptrace_link(task, current);
+ ptrace_link(task, current);
- /* SEIZE doesn't trap tracee on attach */
- if (!seize)
- send_sig_info(SIGSTOP, SEND_SIG_PRIV, task);
+ /* SEIZE doesn't trap tracee on attach */
+ if (!seize)
+ send_sig_info(SIGSTOP, SEND_SIG_PRIV, task);
- spin_lock(&task->sighand->siglock);
+ ptrace_set_stopped(task);
+ }
+ }
/*
- * If the task is already STOPPED, set JOBCTL_TRAP_STOP and
- * TRAPPING, and kick it so that it transits to TRACED. TRAPPING
- * will be cleared if the child completes the transition or any
- * event which clears the group stop states happens. We'll wait
- * for the transition to complete before returning from this
- * function.
- *
- * This hides STOPPED -> RUNNING -> TRACED transition from the
- * attaching thread but a different thread in the same group can
- * still observe the transient RUNNING state. IOW, if another
- * thread's WNOHANG wait(2) on the stopped tracee races against
- * ATTACH, the wait(2) may fail due to the transient RUNNING.
- *
- * The following task_is_stopped() test is safe as both transitions
- * in and out of STOPPED are protected by siglock.
+ * We do not bother to change retval or clear JOBCTL_TRAPPING
+ * if wait_on_bit() was interrupted by SIGKILL. The tracer will
+ * not return to user-mode, it will exit and clear this bit in
+ * __ptrace_unlink() if it wasn't already cleared by the tracee;
+ * and until then nobody can ptrace this task.
*/
- if (task_is_stopped(task) &&
- task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
- task->jobctl &= ~JOBCTL_STOPPED;
- signal_wake_up_state(task, __TASK_STOPPED);
- }
-
- spin_unlock(&task->sighand->siglock);
-
- retval = 0;
-unlock_tasklist:
- write_unlock_irq(&tasklist_lock);
-unlock_creds:
- mutex_unlock(&task->signal->cred_guard_mutex);
-out:
- if (!retval) {
- /*
- * We do not bother to change retval or clear JOBCTL_TRAPPING
- * if wait_on_bit() was interrupted by SIGKILL. The tracer will
- * not return to user-mode, it will exit and clear this bit in
- * __ptrace_unlink() if it wasn't already cleared by the tracee;
- * and until then nobody can ptrace this task.
- */
- wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
- proc_ptrace_connector(task, PTRACE_ATTACH);
- }
+ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
+ proc_ptrace_connector(task, PTRACE_ATTACH);
- return retval;
+ return 0;
}
/**
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 2984de629f74..9b0b52e1836f 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -105,6 +105,31 @@ config RCU_CPU_STALL_CPUTIME
The boot option rcupdate.rcu_cpu_stall_cputime has the same function
as this one, but will override this if it exists.
+config RCU_CPU_STALL_NOTIFIER
+ bool "Provide RCU CPU-stall notifiers"
+ depends on RCU_STALL_COMMON
+ depends on DEBUG_KERNEL
+ depends on RCU_EXPERT
+ default n
+ help
+ WARNING: You almost certainly do not want this!!!
+
+ Enable RCU CPU-stall notifiers, which are invoked just before
+ printing the RCU CPU stall warning. As such, bugs in notifier
+ callbacks can prevent stall warnings from being printed.
+ And the whole reason that a stall warning is being printed is
+ that something is hung up somewhere. Therefore, the notifier
+ callbacks must be written extremely carefully, preferably
+ containing only lockless code. After all, it is quite possible
+ that the whole reason that the RCU CPU stall is happening in
+ the first place is that someone forgot to release whatever lock
+ that you are thinking of acquiring. In which case, having your
+ notifier callback acquire that lock will hang, preventing the
+ RCU CPU stall warning from appearing.
+
+ Say Y here if you want RCU CPU stall notifiers (you don't want them)
+ Say N if you are unsure.
+
config RCU_TRACE
bool "Enable tracing for RCU"
depends on DEBUG_KERNEL
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index b531c33e9545..f94f65877f2b 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -262,6 +262,8 @@ static inline bool rcu_stall_is_suppressed_at_boot(void)
return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();
}
+extern int rcu_cpu_stall_notifiers;
+
#ifdef CONFIG_RCU_STALL_COMMON
extern int rcu_cpu_stall_ftrace_dump;
@@ -659,10 +661,10 @@ static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
bool rcu_cpu_beenfullyonline(int cpu);
#endif
-#ifdef CONFIG_RCU_STALL_COMMON
+#if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
int rcu_stall_notifier_call_chain(unsigned long val, void *v);
-#else // #ifdef CONFIG_RCU_STALL_COMMON
+#else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
static inline int rcu_stall_notifier_call_chain(unsigned long val, void *v) { return NOTIFY_DONE; }
-#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+#endif // #else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
#endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 30fc9d34e329..7567ca8e743c 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -2450,10 +2450,12 @@ static int rcu_torture_stall(void *args)
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 (rcu_cpu_stall_notifiers) {
+ 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);
@@ -2497,7 +2499,7 @@ static int rcu_torture_stall(void *args)
cur_ops->readunlock(idx);
}
pr_alert("%s end.\n", __func__);
- if (!ret) {
+ if (rcu_cpu_stall_notifiers && !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);
@@ -3872,7 +3874,9 @@ rcu_torture_init(void)
}
if (fqs_duration < 0)
fqs_duration = 0;
- if (fqs_duration) {
+ if (fqs_holdoff < 0)
+ fqs_holdoff = 0;
+ if (fqs_duration && fqs_holdoff) {
/* Create the fqs thread */
firsterr = torture_create_kthread(rcu_torture_fqs, NULL,
fqs_task);
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 560e99ec5333..0351a4e83529 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -772,20 +772,10 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock_nmisafe);
*/
static void srcu_gp_start(struct srcu_struct *ssp)
{
- struct srcu_data *sdp;
int state;
- if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
- sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id());
- else
- sdp = this_cpu_ptr(ssp->sda);
lockdep_assert_held(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed));
- spin_lock_rcu_node(sdp); /* Interrupts already disabled. */
- rcu_segcblist_advance(&sdp->srcu_cblist,
- rcu_seq_current(&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);
smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
@@ -1271,9 +1261,11 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
* 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));
- WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp);
+ if (rhp) {
+ rcu_segcblist_advance(&sdp->srcu_cblist,
+ rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
+ WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s));
+ }
if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
sdp->srcu_gp_seq_needed = s;
needgp = true;
@@ -1723,6 +1715,11 @@ static void srcu_invoke_callbacks(struct work_struct *work)
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));
+ /*
+ * Although this function is theoretically re-entrant, concurrent
+ * callbacks invocation is disallowed to avoid executing an SRCU barrier
+ * too early.
+ */
if (sdp->srcu_cblist_invoking ||
!rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
spin_unlock_irq_rcu_node(sdp);
@@ -1753,6 +1750,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
sdp->srcu_cblist_invoking = false;
more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
spin_unlock_irq_rcu_node(sdp);
+ /* An SRCU barrier or callbacks from previous nesting work pending */
if (more)
srcu_schedule_cbs_sdp(sdp, 0);
}
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index f54d5782eca0..732ad5b39946 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -975,7 +975,7 @@ static void check_holdout_task(struct task_struct *t,
t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
!rcu_tasks_is_holdout(t) ||
(IS_ENABLED(CONFIG_NO_HZ_FULL) &&
- !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
+ !is_idle_task(t) && READ_ONCE(t->rcu_tasks_idle_cpu) >= 0)) {
WRITE_ONCE(t->rcu_tasks_holdout, false);
list_del_init(&t->rcu_tasks_holdout_list);
put_task_struct(t);
@@ -993,7 +993,7 @@ static void check_holdout_task(struct task_struct *t,
t, ".I"[is_idle_task(t)],
"N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
- t->rcu_tasks_idle_cpu, cpu);
+ data_race(t->rcu_tasks_idle_cpu), cpu);
sched_show_task(t);
}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3ac3c846105f..1ae851777806 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2338,6 +2338,8 @@ void rcu_force_quiescent_state(void)
struct rcu_node *rnp;
struct rcu_node *rnp_old = NULL;
+ if (!rcu_gp_in_progress())
+ return;
/* Funnel through hierarchy to reduce memory contention. */
rnp = raw_cpu_read(rcu_data.mynode);
for (; rnp != NULL; rnp = rnp->parent) {
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index ac8e86babe44..5d666428546b 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -1061,6 +1061,7 @@ static int __init rcu_sysrq_init(void)
}
early_initcall(rcu_sysrq_init);
+#ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
//////////////////////////////////////////////////////////////////////////////
//
@@ -1081,7 +1082,13 @@ static ATOMIC_NOTIFIER_HEAD(rcu_cpu_stall_notifier_list);
*/
int rcu_stall_chain_notifier_register(struct notifier_block *n)
{
- return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+ int rcsn = rcu_cpu_stall_notifiers;
+
+ WARN(1, "Adding %pS() to RCU stall notifier list (%s).\n", n->notifier_call,
+ rcsn ? "possibly suppressing RCU CPU stall warnings" : "failed, so all is well");
+ if (rcsn)
+ return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+ return -EEXIST;
}
EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_register);
@@ -1115,3 +1122,5 @@ int rcu_stall_notifier_call_chain(unsigned long val, void *v)
{
return atomic_notifier_call_chain(&rcu_cpu_stall_notifier_list, val, v);
}
+
+#endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index c534d6806d3d..46aaaa9fe339 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -538,9 +538,15 @@ long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
EXPORT_SYMBOL_GPL(torture_sched_setaffinity);
#endif
+int rcu_cpu_stall_notifiers __read_mostly; // !0 = provide stall notifiers (rarely useful)
+EXPORT_SYMBOL_GPL(rcu_cpu_stall_notifiers);
+
#ifdef CONFIG_RCU_STALL_COMMON
int rcu_cpu_stall_ftrace_dump __read_mostly;
module_param(rcu_cpu_stall_ftrace_dump, int, 0644);
+#ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
+module_param(rcu_cpu_stall_notifiers, int, 0444);
+#endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
int rcu_cpu_stall_suppress __read_mostly; // !0 = suppress stall warnings.
EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
module_param(rcu_cpu_stall_suppress, int, 0644);
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 395a0ea3c7a8..22c16e2564cc 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -59,6 +59,14 @@ struct sys_off_handler {
};
/*
+ * This variable is used to indicate if a halt was initiated instead of a
+ * reboot when the reboot call was invoked with LINUX_REBOOT_CMD_POWER_OFF, but
+ * the system cannot be powered off. This allowes kernel_halt() to notify users
+ * of that.
+ */
+static bool poweroff_fallback_to_halt;
+
+/*
* Temporary stub that prevents linkage failure while we're in process
* of removing all uses of legacy pm_power_off() around the kernel.
*/
@@ -297,7 +305,10 @@ void kernel_halt(void)
kernel_shutdown_prepare(SYSTEM_HALT);
migrate_to_reboot_cpu();
syscore_shutdown();
- pr_emerg("System halted\n");
+ if (poweroff_fallback_to_halt)
+ pr_emerg("Power off not available: System halted instead\n");
+ else
+ pr_emerg("System halted\n");
kmsg_dump(KMSG_DUMP_SHUTDOWN);
machine_halt();
}
@@ -732,8 +743,10 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
/* Instead of trying to make the power_off code look like
* halt when pm_power_off is not set do it the easy way.
*/
- if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off())
+ if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off()) {
+ poweroff_fallback_to_halt = true;
cmd = LINUX_REBOOT_CMD_HALT;
+ }
mutex_lock(&system_transition_mutex);
switch (cmd) {
@@ -957,21 +970,24 @@ static void hw_failure_emergency_poweroff(int poweroff_delay_ms)
}
/**
- * hw_protection_shutdown - Trigger an emergency system poweroff
+ * __hw_protection_shutdown - Trigger an emergency system shutdown or reboot
*
- * @reason: Reason of emergency shutdown to be printed.
- * @ms_until_forced: Time to wait for orderly shutdown before tiggering a
- * forced shudown. Negative value disables the forced
- * shutdown.
+ * @reason: Reason of emergency shutdown or reboot to be printed.
+ * @ms_until_forced: Time to wait for orderly shutdown or reboot before
+ * triggering it. Negative value disables the forced
+ * shutdown or reboot.
+ * @shutdown: If true, indicates that a shutdown will happen
+ * after the critical tempeature is reached.
+ * If false, indicates that a reboot will happen
+ * after the critical tempeature is reached.
*
- * Initiate an emergency system shutdown in order to protect hardware from
- * further damage. Usage examples include a thermal protection or a voltage or
- * current regulator failures.
- * NOTE: The request is ignored if protection shutdown is already pending even
- * if the previous request has given a large timeout for forced shutdown.
- * Can be called from any context.
+ * Initiate an emergency system shutdown or reboot in order to protect
+ * hardware from further damage. Usage examples include a thermal protection.
+ * NOTE: The request is ignored if protection shutdown or reboot is already
+ * pending even if the previous request has given a large timeout for forced
+ * shutdown/reboot.
*/
-void hw_protection_shutdown(const char *reason, int ms_until_forced)
+void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown)
{
static atomic_t allow_proceed = ATOMIC_INIT(1);
@@ -986,9 +1002,12 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced)
* orderly_poweroff failure
*/
hw_failure_emergency_poweroff(ms_until_forced);
- orderly_poweroff(true);
+ if (shutdown)
+ orderly_poweroff(true);
+ else
+ orderly_reboot();
}
-EXPORT_SYMBOL_GPL(hw_protection_shutdown);
+EXPORT_SYMBOL_GPL(__hw_protection_shutdown);
static int __init reboot_setup(char *str)
{
diff --git a/kernel/relay.c b/kernel/relay.c
index 83fe0325cde1..a8e90e98bf2c 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1073,167 +1073,6 @@ static ssize_t relay_file_read(struct file *filp,
return written;
}
-static void relay_consume_bytes(struct rchan_buf *rbuf, int bytes_consumed)
-{
- rbuf->bytes_consumed += bytes_consumed;
-
- if (rbuf->bytes_consumed >= rbuf->chan->subbuf_size) {
- relay_subbufs_consumed(rbuf->chan, rbuf->cpu, 1);
- rbuf->bytes_consumed %= rbuf->chan->subbuf_size;
- }
-}
-
-static void relay_pipe_buf_release(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- struct rchan_buf *rbuf;
-
- rbuf = (struct rchan_buf *)page_private(buf->page);
- relay_consume_bytes(rbuf, buf->private);
-}
-
-static const struct pipe_buf_operations relay_pipe_buf_ops = {
- .release = relay_pipe_buf_release,
- .try_steal = generic_pipe_buf_try_steal,
- .get = generic_pipe_buf_get,
-};
-
-static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i)
-{
-}
-
-/*
- * subbuf_splice_actor - splice up to one subbuf's worth of data
- */
-static ssize_t subbuf_splice_actor(struct file *in,
- loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t len,
- unsigned int flags,
- int *nonpad_ret)
-{
- unsigned int pidx, poff, total_len, subbuf_pages, nr_pages;
- struct rchan_buf *rbuf = in->private_data;
- unsigned int subbuf_size = rbuf->chan->subbuf_size;
- uint64_t pos = (uint64_t) *ppos;
- uint32_t alloc_size = (uint32_t) rbuf->chan->alloc_size;
- size_t read_start = (size_t) do_div(pos, alloc_size);
- size_t read_subbuf = read_start / subbuf_size;
- size_t padding = rbuf->padding[read_subbuf];
- size_t nonpad_end = read_subbuf * subbuf_size + subbuf_size - padding;
- struct page *pages[PIPE_DEF_BUFFERS];
- struct partial_page partial[PIPE_DEF_BUFFERS];
- struct splice_pipe_desc spd = {
- .pages = pages,
- .nr_pages = 0,
- .nr_pages_max = PIPE_DEF_BUFFERS,
- .partial = partial,
- .ops = &relay_pipe_buf_ops,
- .spd_release = relay_page_release,
- };
- ssize_t ret;
-
- if (rbuf->subbufs_produced == rbuf->subbufs_consumed)
- return 0;
- if (splice_grow_spd(pipe, &spd))
- return -ENOMEM;
-
- /*
- * Adjust read len, if longer than what is available
- */
- if (len > (subbuf_size - read_start % subbuf_size))
- len = subbuf_size - read_start % subbuf_size;
-
- subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT;
- pidx = (read_start / PAGE_SIZE) % subbuf_pages;
- poff = read_start & ~PAGE_MASK;
- nr_pages = min_t(unsigned int, subbuf_pages, spd.nr_pages_max);
-
- for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) {
- unsigned int this_len, this_end, private;
- unsigned int cur_pos = read_start + total_len;
-
- if (!len)
- break;
-
- this_len = min_t(unsigned long, len, PAGE_SIZE - poff);
- private = this_len;
-
- spd.pages[spd.nr_pages] = rbuf->page_array[pidx];
- spd.partial[spd.nr_pages].offset = poff;
-
- this_end = cur_pos + this_len;
- if (this_end >= nonpad_end) {
- this_len = nonpad_end - cur_pos;
- private = this_len + padding;
- }
- spd.partial[spd.nr_pages].len = this_len;
- spd.partial[spd.nr_pages].private = private;
-
- len -= this_len;
- total_len += this_len;
- poff = 0;
- pidx = (pidx + 1) % subbuf_pages;
-
- if (this_end >= nonpad_end) {
- spd.nr_pages++;
- break;
- }
- }
-
- ret = 0;
- if (!spd.nr_pages)
- goto out;
-
- ret = *nonpad_ret = splice_to_pipe(pipe, &spd);
- if (ret < 0 || ret < total_len)
- goto out;
-
- if (read_start + ret == nonpad_end)
- ret += padding;
-
-out:
- splice_shrink_spd(&spd);
- return ret;
-}
-
-static ssize_t relay_file_splice_read(struct file *in,
- loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t len,
- unsigned int flags)
-{
- ssize_t spliced;
- int ret;
- int nonpad_ret = 0;
-
- ret = 0;
- spliced = 0;
-
- while (len && !spliced) {
- ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret);
- if (ret < 0)
- break;
- else if (!ret) {
- if (flags & SPLICE_F_NONBLOCK)
- ret = -EAGAIN;
- break;
- }
-
- *ppos += ret;
- if (ret > len)
- len = 0;
- else
- len -= ret;
- spliced += nonpad_ret;
- nonpad_ret = 0;
- }
-
- if (spliced)
- return spliced;
-
- return ret;
-}
const struct file_operations relay_file_operations = {
.open = relay_file_open,
@@ -1242,6 +1081,5 @@ const struct file_operations relay_file_operations = {
.read = relay_file_read,
.llseek = no_llseek,
.release = relay_file_release,
- .splice_read = relay_file_splice_read,
};
EXPORT_SYMBOL_GPL(relay_file_operations);
diff --git a/kernel/resource.c b/kernel/resource.c
index 866ef3663a0b..fcbca39dbc45 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -27,6 +27,8 @@
#include <linux/mount.h>
#include <linux/resource_ext.h>
#include <uapi/linux/magic.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
#include <asm/io.h>
@@ -430,6 +432,61 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
}
/*
+ * This function, being a variant of walk_system_ram_res(), calls the @func
+ * callback against all memory ranges of type System RAM which are marked as
+ * IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY in reversed order, i.e., from
+ * higher to lower.
+ */
+int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+ int (*func)(struct resource *, void *))
+{
+ struct resource res, *rams;
+ int rams_size = 16, i;
+ unsigned long flags;
+ int ret = -1;
+
+ /* create a list */
+ rams = kvcalloc(rams_size, sizeof(struct resource), GFP_KERNEL);
+ if (!rams)
+ return ret;
+
+ flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ i = 0;
+ while ((start < end) &&
+ (!find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res))) {
+ if (i >= rams_size) {
+ /* re-alloc */
+ struct resource *rams_new;
+
+ rams_new = kvrealloc(rams, rams_size * sizeof(struct resource),
+ (rams_size + 16) * sizeof(struct resource),
+ GFP_KERNEL);
+ if (!rams_new)
+ goto out;
+
+ rams = rams_new;
+ rams_size += 16;
+ }
+
+ rams[i].start = res.start;
+ rams[i++].end = res.end;
+
+ start = res.end + 1;
+ }
+
+ /* go reverse */
+ for (i--; i >= 0; i--) {
+ ret = (*func)(&rams[i], arg);
+ if (ret)
+ break;
+ }
+
+out:
+ kvfree(rams);
+ return ret;
+}
+
+/*
* This function calls the @func callback against all memory ranges, which
* are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY.
*/
@@ -1844,8 +1901,8 @@ 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/sched/core.c b/kernel/sched/core.c
index a708d225c28e..9116bcc90346 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -57,6 +57,7 @@
#include <linux/profile.h>
#include <linux/psi.h>
#include <linux/rcuwait_api.h>
+#include <linux/rseq.h>
#include <linux/sched/wake_q.h>
#include <linux/scs.h>
#include <linux/slab.h>
@@ -1131,6 +1132,28 @@ static void wake_up_idle_cpu(int cpu)
if (cpu == smp_processor_id())
return;
+ /*
+ * Set TIF_NEED_RESCHED and send an IPI if in the non-polling
+ * part of the idle loop. This forces an exit from the idle loop
+ * and a round trip to schedule(). Now this could be optimized
+ * because a simple new idle loop iteration is enough to
+ * re-evaluate the next tick. Provided some re-ordering of tick
+ * nohz functions that would need to follow TIF_NR_POLLING
+ * clearing:
+ *
+ * - On most archs, a simple fetch_or on ti::flags with a
+ * "0" value would be enough to know if an IPI needs to be sent.
+ *
+ * - x86 needs to perform a last need_resched() check between
+ * monitor and mwait which doesn't take timers into account.
+ * There a dedicated TIF_TIMER flag would be required to
+ * fetch_or here and be checked along with TIF_NEED_RESCHED
+ * before mwait().
+ *
+ * However, remote timer enqueue is not such a frequent event
+ * and testing of the above solutions didn't appear to report
+ * much benefits.
+ */
if (set_nr_and_not_polling(rq->idle))
smp_send_reschedule(cpu);
else
@@ -2124,12 +2147,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
enqueue_task(rq, p, flags);
- p->on_rq = TASK_ON_RQ_QUEUED;
+ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
+ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
}
void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{
- p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+ WRITE_ONCE(p->on_rq, (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING);
+ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
dequeue_task(rq, p, flags);
}
@@ -3795,6 +3820,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
rq->idle_stamp = 0;
}
#endif
+
+ p->dl_server = NULL;
}
/*
@@ -4509,10 +4536,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
memset(&p->stats, 0, sizeof(p->stats));
#endif
- RB_CLEAR_NODE(&p->dl.rb_node);
- init_dl_task_timer(&p->dl);
- init_dl_inactive_task_timer(&p->dl);
- __dl_clear_params(p);
+ init_dl_entity(&p->dl);
INIT_LIST_HEAD(&p->rt.run_list);
p->rt.timeout = 0;
@@ -6004,12 +6028,27 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
p = pick_next_task_idle(rq);
}
+ /*
+ * This is the fast path; it cannot be a DL server pick;
+ * therefore even if @p == @prev, ->dl_server must be NULL.
+ */
+ if (p->dl_server)
+ p->dl_server = NULL;
+
return p;
}
restart:
put_prev_task_balance(rq, prev, rf);
+ /*
+ * We've updated @prev and no longer need the server link, clear it.
+ * Must be done before ->pick_next_task() because that can (re)set
+ * ->dl_server.
+ */
+ if (prev->dl_server)
+ prev->dl_server = NULL;
+
for_each_class(class) {
p = class->pick_next_task(rq);
if (p)
@@ -7429,18 +7468,13 @@ int sched_core_idle_cpu(int cpu)
* required to meet deadlines.
*/
unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
- enum cpu_util_type type,
- struct task_struct *p)
+ unsigned long *min,
+ unsigned long *max)
{
- unsigned long dl_util, util, irq, max;
+ unsigned long util, irq, scale;
struct rq *rq = cpu_rq(cpu);
- max = arch_scale_cpu_capacity(cpu);
-
- if (!uclamp_is_used() &&
- type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
- return max;
- }
+ scale = arch_scale_cpu_capacity(cpu);
/*
* Early check to see if IRQ/steal time saturates the CPU, can be
@@ -7448,45 +7482,49 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
* update_irq_load_avg().
*/
irq = cpu_util_irq(rq);
- if (unlikely(irq >= max))
- return max;
+ if (unlikely(irq >= scale)) {
+ if (min)
+ *min = scale;
+ if (max)
+ *max = scale;
+ return scale;
+ }
+
+ if (min) {
+ /*
+ * The minimum utilization returns the highest level between:
+ * - the computed DL bandwidth needed with the IRQ pressure which
+ * steals time to the deadline task.
+ * - The minimum performance requirement for CFS and/or RT.
+ */
+ *min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
+
+ /*
+ * When an RT task is runnable and uclamp is not used, we must
+ * ensure that the task will run at maximum compute capacity.
+ */
+ if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
+ *min = max(*min, scale);
+ }
/*
* Because the time spend on RT/DL tasks is visible as 'lost' time to
* CFS tasks and we use the same metric to track the effective
* utilization (PELT windows are synchronized) we can directly add them
* to obtain the CPU's actual utilization.
- *
- * CFS and RT utilization can be boosted or capped, depending on
- * utilization clamp constraints requested by currently RUNNABLE
- * tasks.
- * When there are no CFS RUNNABLE tasks, clamps are released and
- * frequency will be gracefully reduced with the utilization decay.
*/
util = util_cfs + cpu_util_rt(rq);
- if (type == FREQUENCY_UTIL)
- util = uclamp_rq_util_with(rq, util, p);
-
- dl_util = cpu_util_dl(rq);
+ util += cpu_util_dl(rq);
/*
- * For frequency selection we do not make cpu_util_dl() a permanent part
- * of this sum because we want to use cpu_bw_dl() later on, but we need
- * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
- * that we select f_max when there is no idle time.
- *
- * NOTE: numerical errors or stop class might cause us to not quite hit
- * saturation when we should -- something for later.
+ * The maximum hint is a soft bandwidth requirement, which can be lower
+ * than the actual utilization because of uclamp_max requirements.
*/
- if (util + dl_util >= max)
- return max;
+ if (max)
+ *max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
- /*
- * OTOH, for energy computation we need the estimated running time, so
- * include util_dl and ignore dl_bw.
- */
- if (type == ENERGY_UTIL)
- util += dl_util;
+ if (util >= scale)
+ return scale;
/*
* There is still idle time; further improve the number by using the
@@ -7497,28 +7535,15 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
* U' = irq + --------- * U
* max
*/
- util = scale_irq_capacity(util, irq, max);
+ util = scale_irq_capacity(util, irq, scale);
util += irq;
- /*
- * Bandwidth required by DEADLINE must always be granted while, for
- * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
- * to gracefully reduce the frequency when no tasks show up for longer
- * periods of time.
- *
- * Ideally we would like to set bw_dl as min/guaranteed freq and util +
- * bw_dl as requested freq. However, cpufreq is not yet ready for such
- * an interface. So, we only do the latter for now.
- */
- if (type == FREQUENCY_UTIL)
- util += cpu_bw_dl(rq);
-
- return min(max, util);
+ return min(scale, util);
}
unsigned long sched_cpu_util(int cpu)
{
- return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL);
+ return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
}
#endif /* CONFIG_SMP */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 5888176354e2..95c3c097083e 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -47,7 +47,7 @@ struct sugov_cpu {
u64 last_update;
unsigned long util;
- unsigned long bw_dl;
+ unsigned long bw_min;
/* The field below is for single-CPU policies only: */
#ifdef CONFIG_NO_HZ_COMMON
@@ -115,6 +115,28 @@ static void sugov_deferred_update(struct sugov_policy *sg_policy)
}
/**
+ * get_capacity_ref_freq - get the reference frequency that has been used to
+ * correlate frequency and compute capacity for a given cpufreq policy. We use
+ * the CPU managing it for the arch_scale_freq_ref() call in the function.
+ * @policy: the cpufreq policy of the CPU in question.
+ *
+ * Return: the reference CPU frequency to compute a capacity.
+ */
+static __always_inline
+unsigned long get_capacity_ref_freq(struct cpufreq_policy *policy)
+{
+ unsigned int freq = arch_scale_freq_ref(policy->cpu);
+
+ if (freq)
+ return freq;
+
+ if (arch_scale_freq_invariant())
+ return policy->cpuinfo.max_freq;
+
+ return policy->cur;
+}
+
+/**
* get_next_freq - Compute a new frequency for a given cpufreq policy.
* @sg_policy: schedutil policy object to compute the new frequency for.
* @util: Current CPU utilization.
@@ -140,10 +162,9 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
unsigned long util, unsigned long max)
{
struct cpufreq_policy *policy = sg_policy->policy;
- unsigned int freq = arch_scale_freq_invariant() ?
- policy->cpuinfo.max_freq : policy->cur;
+ unsigned int freq;
- util = map_util_perf(util);
+ freq = get_capacity_ref_freq(policy);
freq = map_util_freq(util, freq, max);
if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
@@ -153,14 +174,31 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
return cpufreq_driver_resolve_freq(policy, freq);
}
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
+ unsigned long min,
+ unsigned long max)
+{
+ /* Add dvfs headroom to actual utilization */
+ actual = map_util_perf(actual);
+ /* Actually we don't need to target the max performance */
+ if (actual < max)
+ max = actual;
+
+ /*
+ * Ensure at least minimum performance while providing more compute
+ * capacity when possible.
+ */
+ return max(min, max);
+}
+
+static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
{
- unsigned long util = cpu_util_cfs_boost(sg_cpu->cpu);
- struct rq *rq = cpu_rq(sg_cpu->cpu);
+ unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
- sg_cpu->bw_dl = cpu_bw_dl(rq);
- sg_cpu->util = effective_cpu_util(sg_cpu->cpu, util,
- FREQUENCY_UTIL, NULL);
+ util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
+ util = max(util, boost);
+ sg_cpu->bw_min = min;
+ sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
}
/**
@@ -251,18 +289,16 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
* This mechanism is designed to boost high frequently IO waiting tasks, while
* being more conservative on tasks which does sporadic IO operations.
*/
-static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
unsigned long max_cap)
{
- unsigned long boost;
-
/* No boost currently required */
if (!sg_cpu->iowait_boost)
- return;
+ return 0;
/* Reset boost if the CPU appears to have been idle enough */
if (sugov_iowait_reset(sg_cpu, time, false))
- return;
+ return 0;
if (!sg_cpu->iowait_boost_pending) {
/*
@@ -271,7 +307,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
sg_cpu->iowait_boost >>= 1;
if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
sg_cpu->iowait_boost = 0;
- return;
+ return 0;
}
}
@@ -281,10 +317,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
* sg_cpu->util is already in capacity scale; convert iowait_boost
* into the same scale so we can compare.
*/
- boost = (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT;
- boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
- if (sg_cpu->util < boost)
- sg_cpu->util = boost;
+ return (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT;
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -306,7 +339,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
*/
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
{
- if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
+ if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
sg_cpu->sg_policy->limits_changed = true;
}
@@ -314,6 +347,8 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
u64 time, unsigned long max_cap,
unsigned int flags)
{
+ unsigned long boost;
+
sugov_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
@@ -322,8 +357,8 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
if (!sugov_should_update_freq(sg_cpu->sg_policy, time))
return false;
- sugov_get_util(sg_cpu);
- sugov_iowait_apply(sg_cpu, time, max_cap);
+ boost = sugov_iowait_apply(sg_cpu, time, max_cap);
+ sugov_get_util(sg_cpu, boost);
return true;
}
@@ -407,8 +442,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
sg_cpu->util = prev_util;
- cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
- map_util_perf(sg_cpu->util), max_cap);
+ cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min,
+ sg_cpu->util, max_cap);
sg_cpu->sg_policy->last_freq_update_time = time;
}
@@ -424,9 +459,10 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
for_each_cpu(j, policy->cpus) {
struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
+ unsigned long boost;
- sugov_get_util(j_sg_cpu);
- sugov_iowait_apply(j_sg_cpu, time, max_cap);
+ boost = sugov_iowait_apply(j_sg_cpu, time, max_cap);
+ sugov_get_util(j_sg_cpu, boost);
util = max(j_sg_cpu->util, util);
}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b28114478b82..a04a436af8cc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -54,8 +54,14 @@ static int __init sched_dl_sysctl_init(void)
late_initcall(sched_dl_sysctl_init);
#endif
+static bool dl_server(struct sched_dl_entity *dl_se)
+{
+ return dl_se->dl_server;
+}
+
static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
{
+ BUG_ON(dl_server(dl_se));
return container_of(dl_se, struct task_struct, dl);
}
@@ -64,12 +70,19 @@ static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
return container_of(dl_rq, struct rq, dl);
}
-static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+static inline struct rq *rq_of_dl_se(struct sched_dl_entity *dl_se)
{
- struct task_struct *p = dl_task_of(dl_se);
- struct rq *rq = task_rq(p);
+ struct rq *rq = dl_se->rq;
+
+ if (!dl_server(dl_se))
+ rq = task_rq(dl_task_of(dl_se));
+
+ return rq;
+}
- return &rq->dl;
+static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+{
+ return &rq_of_dl_se(dl_se)->dl;
}
static inline int on_dl_rq(struct sched_dl_entity *dl_se)
@@ -335,6 +348,8 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
__add_rq_bw(new_bw, &rq->dl);
}
+static void __dl_clear_params(struct sched_dl_entity *dl_se);
+
/*
* The utilization of a task cannot be immediately removed from
* the rq active utilization (running_bw) when the task blocks.
@@ -389,12 +404,11 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
* up, and checks if the task is still in the "ACTIVE non contending"
* state or not (in the second case, it updates running_bw).
*/
-static void task_non_contending(struct task_struct *p)
+static void task_non_contending(struct sched_dl_entity *dl_se)
{
- struct sched_dl_entity *dl_se = &p->dl;
struct hrtimer *timer = &dl_se->inactive_timer;
- struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
- struct rq *rq = rq_of_dl_rq(dl_rq);
+ struct rq *rq = rq_of_dl_se(dl_se);
+ struct dl_rq *dl_rq = &rq->dl;
s64 zerolag_time;
/*
@@ -424,24 +438,33 @@ static void task_non_contending(struct task_struct *p)
* utilization now, instead of starting a timer
*/
if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
- if (dl_task(p))
+ if (dl_server(dl_se)) {
sub_running_bw(dl_se, dl_rq);
- if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
- struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-
- if (READ_ONCE(p->__state) == TASK_DEAD)
- sub_rq_bw(&p->dl, &rq->dl);
- raw_spin_lock(&dl_b->lock);
- __dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
- raw_spin_unlock(&dl_b->lock);
- __dl_clear_params(p);
+ } else {
+ struct task_struct *p = dl_task_of(dl_se);
+
+ if (dl_task(p))
+ sub_running_bw(dl_se, dl_rq);
+
+ if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
+ struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+ if (READ_ONCE(p->__state) == TASK_DEAD)
+ sub_rq_bw(dl_se, &rq->dl);
+ raw_spin_lock(&dl_b->lock);
+ __dl_sub(dl_b, dl_se->dl_bw, dl_bw_cpus(task_cpu(p)));
+ raw_spin_unlock(&dl_b->lock);
+ __dl_clear_params(dl_se);
+ }
}
return;
}
dl_se->dl_non_contending = 1;
- get_task_struct(p);
+ if (!dl_server(dl_se))
+ get_task_struct(dl_task_of(dl_se));
+
hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
}
@@ -468,8 +491,10 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
* will not touch the rq's active utilization,
* so we are still safe.
*/
- if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1)
- put_task_struct(dl_task_of(dl_se));
+ if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) {
+ if (!dl_server(dl_se))
+ put_task_struct(dl_task_of(dl_se));
+ }
} else {
/*
* Since "dl_non_contending" is not set, the
@@ -482,10 +507,8 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
}
}
-static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
+static inline int is_leftmost(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
- struct sched_dl_entity *dl_se = &p->dl;
-
return rb_first_cached(&dl_rq->root) == &dl_se->rb_node;
}
@@ -737,8 +760,10 @@ static inline void deadline_queue_pull_task(struct rq *rq)
}
#endif /* CONFIG_SMP */
+static void
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags);
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 dequeue_dl_entity(struct sched_dl_entity *dl_se, 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,
@@ -986,8 +1011,7 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
*/
static void update_dl_entity(struct sched_dl_entity *dl_se)
{
- struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
- struct rq *rq = rq_of_dl_rq(dl_rq);
+ struct rq *rq = rq_of_dl_se(dl_se);
if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
dl_entity_overflow(dl_se, rq_clock(rq))) {
@@ -1018,11 +1042,11 @@ static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
* actually started or not (i.e., the replenishment instant is in
* the future or in the past).
*/
-static int start_dl_timer(struct task_struct *p)
+static int start_dl_timer(struct sched_dl_entity *dl_se)
{
- struct sched_dl_entity *dl_se = &p->dl;
struct hrtimer *timer = &dl_se->dl_timer;
- struct rq *rq = task_rq(p);
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
ktime_t now, act;
s64 delta;
@@ -1056,13 +1080,33 @@ static int start_dl_timer(struct task_struct *p)
* and observe our state.
*/
if (!hrtimer_is_queued(timer)) {
- get_task_struct(p);
+ if (!dl_server(dl_se))
+ get_task_struct(dl_task_of(dl_se));
hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD);
}
return 1;
}
+static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
+{
+#ifdef CONFIG_SMP
+ /*
+ * Queueing this task back might have overloaded rq, check if we need
+ * to kick someone away.
+ */
+ if (has_pushable_dl_tasks(rq)) {
+ /*
+ * Nothing relies on rq->lock after this, so its safe to drop
+ * rq->lock.
+ */
+ rq_unpin_lock(rq, rf);
+ push_dl_task(rq);
+ rq_repin_lock(rq, rf);
+ }
+#endif
+}
+
/*
* This is the bandwidth enforcement timer callback. If here, we know
* a task is not on its dl_rq, since the fact that the timer was running
@@ -1081,10 +1125,34 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
struct sched_dl_entity *dl_se = container_of(timer,
struct sched_dl_entity,
dl_timer);
- struct task_struct *p = dl_task_of(dl_se);
+ struct task_struct *p;
struct rq_flags rf;
struct rq *rq;
+ if (dl_server(dl_se)) {
+ struct rq *rq = rq_of_dl_se(dl_se);
+ struct rq_flags rf;
+
+ rq_lock(rq, &rf);
+ if (dl_se->dl_throttled) {
+ sched_clock_tick();
+ update_rq_clock(rq);
+
+ if (dl_se->server_has_tasks(dl_se)) {
+ enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+ resched_curr(rq);
+ __push_dl_task(rq, &rf);
+ } else {
+ replenish_dl_entity(dl_se);
+ }
+
+ }
+ rq_unlock(rq, &rf);
+
+ return HRTIMER_NORESTART;
+ }
+
+ p = dl_task_of(dl_se);
rq = task_rq_lock(p, &rf);
/*
@@ -1155,21 +1223,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
else
resched_curr(rq);
-#ifdef CONFIG_SMP
- /*
- * Queueing this task back might have overloaded rq, check if we need
- * to kick someone away.
- */
- if (has_pushable_dl_tasks(rq)) {
- /*
- * Nothing relies on rq->lock after this, so its safe to drop
- * rq->lock.
- */
- rq_unpin_lock(rq, &rf);
- push_dl_task(rq);
- rq_repin_lock(rq, &rf);
- }
-#endif
+ __push_dl_task(rq, &rf);
unlock:
task_rq_unlock(rq, p, &rf);
@@ -1183,7 +1237,7 @@ unlock:
return HRTIMER_NORESTART;
}
-void init_dl_task_timer(struct sched_dl_entity *dl_se)
+static void init_dl_task_timer(struct sched_dl_entity *dl_se)
{
struct hrtimer *timer = &dl_se->dl_timer;
@@ -1211,12 +1265,11 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
*/
static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
{
- struct task_struct *p = dl_task_of(dl_se);
- struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+ struct rq *rq = rq_of_dl_se(dl_se);
if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
- if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
+ if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se)))
return;
dl_se->dl_throttled = 1;
if (dl_se->runtime > 0)
@@ -1267,44 +1320,19 @@ static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
return (delta * u_act) >> BW_SHIFT;
}
-/*
- * Update the current task's runtime statistics (provided it is still
- * a -deadline task and has not been removed from the dl_rq).
- */
-static void update_curr_dl(struct rq *rq)
+static inline void
+update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
+ int flags);
+static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
{
- struct task_struct *curr = rq->curr;
- struct sched_dl_entity *dl_se = &curr->dl;
- u64 delta_exec, scaled_delta_exec;
- int cpu = cpu_of(rq);
- u64 now;
-
- if (!dl_task(curr) || !on_dl_rq(dl_se))
- return;
+ s64 scaled_delta_exec;
- /*
- * Consumed budget is computed considering the time as
- * observed by schedulable tasks (excluding time spent
- * in hardirq context, etc.). Deadlines are instead
- * computed using hard walltime. This seems to be the more
- * natural solution, but the full ramifications of this
- * approach need further study.
- */
- now = rq_clock_task(rq);
- delta_exec = now - curr->se.exec_start;
- if (unlikely((s64)delta_exec <= 0)) {
+ if (unlikely(delta_exec <= 0)) {
if (unlikely(dl_se->dl_yielded))
goto throttle;
return;
}
- schedstat_set(curr->stats.exec_max,
- max(curr->stats.exec_max, delta_exec));
-
- trace_sched_stat_runtime(curr, delta_exec, 0);
-
- update_current_exec_runtime(curr, now, delta_exec);
-
if (dl_entity_is_special(dl_se))
return;
@@ -1316,10 +1344,9 @@ static void update_curr_dl(struct rq *rq)
* according to current frequency and CPU maximum capacity.
*/
if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) {
- scaled_delta_exec = grub_reclaim(delta_exec,
- rq,
- &curr->dl);
+ scaled_delta_exec = grub_reclaim(delta_exec, rq, dl_se);
} else {
+ int cpu = cpu_of(rq);
unsigned long scale_freq = arch_scale_freq_capacity(cpu);
unsigned long scale_cpu = arch_scale_cpu_capacity(cpu);
@@ -1338,11 +1365,20 @@ throttle:
(dl_se->flags & SCHED_FLAG_DL_OVERRUN))
dl_se->dl_overrun = 1;
- __dequeue_task_dl(rq, curr, 0);
- if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
- enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
+ dequeue_dl_entity(dl_se, 0);
+ if (!dl_server(dl_se)) {
+ update_stats_dequeue_dl(&rq->dl, dl_se, 0);
+ dequeue_pushable_dl_task(rq, dl_task_of(dl_se));
+ }
+
+ if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) {
+ if (dl_server(dl_se))
+ enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+ else
+ enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH);
+ }
- if (!is_leftmost(curr, &rq->dl))
+ if (!is_leftmost(dl_se, &rq->dl))
resched_curr(rq);
}
@@ -1372,20 +1408,82 @@ throttle:
}
}
+void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
+{
+ update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+}
+
+void dl_server_start(struct sched_dl_entity *dl_se)
+{
+ if (!dl_server(dl_se)) {
+ dl_se->dl_server = 1;
+ setup_new_dl_entity(dl_se);
+ }
+ enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
+}
+
+void dl_server_stop(struct sched_dl_entity *dl_se)
+{
+ dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
+}
+
+void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
+ dl_server_has_tasks_f has_tasks,
+ dl_server_pick_f pick)
+{
+ dl_se->rq = rq;
+ dl_se->server_has_tasks = has_tasks;
+ dl_se->server_pick = pick;
+}
+
+/*
+ * Update the current task's runtime statistics (provided it is still
+ * a -deadline task and has not been removed from the dl_rq).
+ */
+static void update_curr_dl(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct sched_dl_entity *dl_se = &curr->dl;
+ s64 delta_exec;
+
+ if (!dl_task(curr) || !on_dl_rq(dl_se))
+ return;
+
+ /*
+ * Consumed budget is computed considering the time as
+ * observed by schedulable tasks (excluding time spent
+ * in hardirq context, etc.). Deadlines are instead
+ * computed using hard walltime. This seems to be the more
+ * natural solution, but the full ramifications of this
+ * approach need further study.
+ */
+ delta_exec = update_curr_common(rq);
+ update_curr_dl_se(rq, dl_se, delta_exec);
+}
+
static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
{
struct sched_dl_entity *dl_se = container_of(timer,
struct sched_dl_entity,
inactive_timer);
- struct task_struct *p = dl_task_of(dl_se);
+ struct task_struct *p = NULL;
struct rq_flags rf;
struct rq *rq;
- rq = task_rq_lock(p, &rf);
+ if (!dl_server(dl_se)) {
+ p = dl_task_of(dl_se);
+ rq = task_rq_lock(p, &rf);
+ } else {
+ rq = dl_se->rq;
+ rq_lock(rq, &rf);
+ }
sched_clock_tick();
update_rq_clock(rq);
+ if (dl_server(dl_se))
+ goto no_task;
+
if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
@@ -1398,23 +1496,30 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
raw_spin_lock(&dl_b->lock);
__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
raw_spin_unlock(&dl_b->lock);
- __dl_clear_params(p);
+ __dl_clear_params(dl_se);
goto unlock;
}
+
+no_task:
if (dl_se->dl_non_contending == 0)
goto unlock;
sub_running_bw(dl_se, &rq->dl);
dl_se->dl_non_contending = 0;
unlock:
- task_rq_unlock(rq, p, &rf);
- put_task_struct(p);
+
+ if (!dl_server(dl_se)) {
+ task_rq_unlock(rq, p, &rf);
+ put_task_struct(p);
+ } else {
+ rq_unlock(rq, &rf);
+ }
return HRTIMER_NORESTART;
}
-void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
+static void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
{
struct hrtimer *timer = &dl_se->inactive_timer;
@@ -1472,10 +1577,8 @@ static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
static inline
void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
- int prio = dl_task_of(dl_se)->prio;
u64 deadline = dl_se->deadline;
- WARN_ON(!dl_prio(prio));
dl_rq->dl_nr_running++;
add_nr_running(rq_of_dl_rq(dl_rq), 1);
@@ -1485,9 +1588,6 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
static inline
void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
- int prio = dl_task_of(dl_se)->prio;
-
- WARN_ON(!dl_prio(prio));
WARN_ON(!dl_rq->dl_nr_running);
dl_rq->dl_nr_running--;
sub_nr_running(rq_of_dl_rq(dl_rq), 1);
@@ -1609,6 +1709,41 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags);
/*
+ * Check if a constrained deadline task was activated
+ * after the deadline but before the next period.
+ * If that is the case, the task will be throttled and
+ * the replenishment timer will be set to the next period.
+ */
+ if (!dl_se->dl_throttled && !dl_is_implicit(dl_se))
+ dl_check_constrained_dl(dl_se);
+
+ if (flags & (ENQUEUE_RESTORE|ENQUEUE_MIGRATING)) {
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+ add_rq_bw(dl_se, dl_rq);
+ add_running_bw(dl_se, dl_rq);
+ }
+
+ /*
+ * If p is throttled, we do not enqueue it. In fact, if it exhausted
+ * its budget it needs a replenishment and, since it now is on
+ * its rq, the bandwidth timer callback (which clearly has not
+ * run yet) will take care of this.
+ * However, the active utilization does not depend on the fact
+ * that the task is on the runqueue or not (but depends on the
+ * task's state - in GRUB parlance, "inactive" vs "active contending").
+ * In other words, even if a task is throttled its utilization must
+ * be counted in the active utilization; hence, we need to call
+ * add_running_bw().
+ */
+ if (dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
+ if (flags & ENQUEUE_WAKEUP)
+ task_contending(dl_se, flags);
+
+ return;
+ }
+
+ /*
* If this is a wakeup or a new instance, the scheduling
* parameters of the task might need updating. Otherwise,
* we want a replenishment of its runtime.
@@ -1619,17 +1754,35 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
} else if (flags & ENQUEUE_REPLENISH) {
replenish_dl_entity(dl_se);
} else if ((flags & ENQUEUE_RESTORE) &&
- dl_time_before(dl_se->deadline,
- rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
+ dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_se(dl_se)))) {
setup_new_dl_entity(dl_se);
}
__enqueue_dl_entity(dl_se);
}
-static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags)
{
__dequeue_dl_entity(dl_se);
+
+ if (flags & (DEQUEUE_SAVE|DEQUEUE_MIGRATING)) {
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+ sub_running_bw(dl_se, dl_rq);
+ sub_rq_bw(dl_se, dl_rq);
+ }
+
+ /*
+ * This check allows to start the inactive timer (or to immediately
+ * decrease the active utilization, if needed) in two cases:
+ * when the task blocks and when it is terminating
+ * (p->state == TASK_DEAD). We can handle the two cases in the same
+ * way, because from GRUB's point of view the same thing is happening
+ * (the task moves from "active contending" to "active non contending"
+ * or "inactive")
+ */
+ if (flags & DEQUEUE_SLEEP)
+ task_non_contending(dl_se);
}
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -1674,76 +1827,31 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
return;
}
- /*
- * Check if a constrained deadline task was activated
- * after the deadline but before the next period.
- * If that is the case, the task will be throttled and
- * the replenishment timer will be set to the next period.
- */
- if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl))
- dl_check_constrained_dl(&p->dl);
-
- if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) {
- add_rq_bw(&p->dl, &rq->dl);
- add_running_bw(&p->dl, &rq->dl);
- }
-
- /*
- * If p is throttled, we do not enqueue it. In fact, if it exhausted
- * its budget it needs a replenishment and, since it now is on
- * its rq, the bandwidth timer callback (which clearly has not
- * run yet) will take care of this.
- * However, the active utilization does not depend on the fact
- * that the task is on the runqueue or not (but depends on the
- * task's state - in GRUB parlance, "inactive" vs "active contending").
- * In other words, even if a task is throttled its utilization must
- * be counted in the active utilization; hence, we need to call
- * add_running_bw().
- */
- if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
- if (flags & ENQUEUE_WAKEUP)
- task_contending(&p->dl, flags);
-
- return;
- }
-
check_schedstat_required();
update_stats_wait_start_dl(dl_rq_of_se(&p->dl), &p->dl);
+ if (p->on_rq == TASK_ON_RQ_MIGRATING)
+ flags |= ENQUEUE_MIGRATING;
+
enqueue_dl_entity(&p->dl, flags);
- if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
- enqueue_pushable_dl_task(rq, p);
-}
+ if (dl_server(&p->dl))
+ return;
-static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
-{
- update_stats_dequeue_dl(&rq->dl, &p->dl, flags);
- dequeue_dl_entity(&p->dl);
- dequeue_pushable_dl_task(rq, p);
+ if (!task_current(rq, p) && !p->dl.dl_throttled && p->nr_cpus_allowed > 1)
+ enqueue_pushable_dl_task(rq, p);
}
static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
update_curr_dl(rq);
- __dequeue_task_dl(rq, p, flags);
- if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) {
- sub_running_bw(&p->dl, &rq->dl);
- sub_rq_bw(&p->dl, &rq->dl);
- }
+ if (p->on_rq == TASK_ON_RQ_MIGRATING)
+ flags |= DEQUEUE_MIGRATING;
- /*
- * This check allows to start the inactive timer (or to immediately
- * decrease the active utilization, if needed) in two cases:
- * when the task blocks and when it is terminating
- * (p->state == TASK_DEAD). We can handle the two cases in the same
- * way, because from GRUB's point of view the same thing is happening
- * (the task moves from "active contending" to "active non contending"
- * or "inactive")
- */
- if (flags & DEQUEUE_SLEEP)
- task_non_contending(p);
+ dequeue_dl_entity(&p->dl, flags);
+ if (!p->dl.dl_throttled && !dl_server(&p->dl))
+ dequeue_pushable_dl_task(rq, p);
}
/*
@@ -1933,12 +2041,12 @@ static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
}
#ifdef CONFIG_SCHED_HRTICK
-static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
{
- hrtick_start(rq, p->dl.runtime);
+ hrtick_start(rq, dl_se->runtime);
}
#else /* !CONFIG_SCHED_HRTICK */
-static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
{
}
#endif
@@ -1958,9 +2066,6 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
if (!first)
return;
- if (hrtick_enabled_dl(rq))
- start_hrtick_dl(rq, p);
-
if (rq->curr->sched_class != &dl_sched_class)
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
@@ -1983,12 +2088,25 @@ static struct task_struct *pick_task_dl(struct rq *rq)
struct dl_rq *dl_rq = &rq->dl;
struct task_struct *p;
+again:
if (!sched_dl_runnable(rq))
return NULL;
dl_se = pick_next_dl_entity(dl_rq);
WARN_ON_ONCE(!dl_se);
- p = dl_task_of(dl_se);
+
+ if (dl_server(dl_se)) {
+ p = dl_se->server_pick(dl_se);
+ if (!p) {
+ WARN_ON_ONCE(1);
+ dl_se->dl_yielded = 1;
+ update_curr_dl_se(rq, dl_se, 0);
+ goto again;
+ }
+ p->dl_server = dl_se;
+ } else {
+ p = dl_task_of(dl_se);
+ }
return p;
}
@@ -1998,9 +2116,15 @@ static struct task_struct *pick_next_task_dl(struct rq *rq)
struct task_struct *p;
p = pick_task_dl(rq);
- if (p)
+ if (!p)
+ return p;
+
+ if (!p->dl_server)
set_next_task_dl(rq, p, true);
+ if (hrtick_enabled(rq))
+ start_hrtick_dl(rq, &p->dl);
+
return p;
}
@@ -2038,8 +2162,8 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
* be set and schedule() will start a new hrtick for the next task.
*/
if (hrtick_enabled_dl(rq) && queued && p->dl.runtime > 0 &&
- is_leftmost(p, &rq->dl))
- start_hrtick_dl(rq, p);
+ is_leftmost(&p->dl, &rq->dl))
+ start_hrtick_dl(rq, &p->dl);
}
static void task_fork_dl(struct task_struct *p)
@@ -2558,7 +2682,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
* will reset the task parameters.
*/
if (task_on_rq_queued(p) && p->dl.dl_runtime)
- task_non_contending(p);
+ task_non_contending(&p->dl);
/*
* In case a task is setscheduled out from SCHED_DEADLINE we need to
@@ -2966,10 +3090,8 @@ bool __checkparam_dl(const struct sched_attr *attr)
/*
* This function clears the sched_dl_entity static params.
*/
-void __dl_clear_params(struct task_struct *p)
+static void __dl_clear_params(struct sched_dl_entity *dl_se)
{
- struct sched_dl_entity *dl_se = &p->dl;
-
dl_se->dl_runtime = 0;
dl_se->dl_deadline = 0;
dl_se->dl_period = 0;
@@ -2981,12 +3103,21 @@ void __dl_clear_params(struct task_struct *p)
dl_se->dl_yielded = 0;
dl_se->dl_non_contending = 0;
dl_se->dl_overrun = 0;
+ dl_se->dl_server = 0;
#ifdef CONFIG_RT_MUTEXES
dl_se->pi_se = dl_se;
#endif
}
+void init_dl_entity(struct sched_dl_entity *dl_se)
+{
+ RB_CLEAR_NODE(&dl_se->rb_node);
+ init_dl_task_timer(dl_se);
+ init_dl_inactive_task_timer(dl_se);
+ __dl_clear_params(dl_se);
+}
+
bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
{
struct sched_dl_entity *dl_se = &p->dl;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4580a450700e..8d5d98a5834d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -628,8 +628,8 @@ 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 left_vruntime = -1, min_vruntime, right_vruntime = -1, spread;
- struct sched_entity *last, *first;
+ s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread;
+ struct sched_entity *last, *first, *root;
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
@@ -644,15 +644,20 @@ 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);
+ root = __pick_root_entity(cfs_rq);
+ if (root)
+ left_vruntime = root->min_vruntime;
first = __pick_first_entity(cfs_rq);
if (first)
- left_vruntime = first->vruntime;
+ left_deadline = first->deadline;
last = __pick_last_entity(cfs_rq);
if (last)
right_vruntime = last->vruntime;
min_vruntime = cfs_rq->min_vruntime;
raw_spin_rq_unlock_irqrestore(rq, flags);
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_deadline",
+ SPLIT_NS(left_deadline));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime",
SPLIT_NS(left_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
@@ -679,8 +684,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
cfs_rq->avg.runnable_avg);
SEQ_printf(m, " .%-30s: %lu\n", "util_avg",
cfs_rq->avg.util_avg);
- SEQ_printf(m, " .%-30s: %u\n", "util_est_enqueued",
- cfs_rq->avg.util_est.enqueued);
+ SEQ_printf(m, " .%-30s: %u\n", "util_est",
+ cfs_rq->avg.util_est);
SEQ_printf(m, " .%-30s: %ld\n", "removed.load_avg",
cfs_rq->removed.load_avg);
SEQ_printf(m, " .%-30s: %ld\n", "removed.util_avg",
@@ -1070,8 +1075,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
P(se.avg.runnable_avg);
P(se.avg.util_avg);
P(se.avg.last_update_time);
- P(se.avg.util_est.ewma);
- PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED);
+ PM(se.avg.util_est, ~UTIL_AVG_UNCHANGED);
#endif
#ifdef CONFIG_UCLAMP_TASK
__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d7a3c63a2171..533547e3c90a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -551,7 +551,11 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
static inline bool entity_before(const struct sched_entity *a,
const struct sched_entity *b)
{
- return (s64)(a->vruntime - b->vruntime) < 0;
+ /*
+ * Tiebreak on vruntime seems unnecessary since it can
+ * hardly happen.
+ */
+ return (s64)(a->deadline - b->deadline) < 0;
}
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -720,7 +724,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
* 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)
+static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
{
struct sched_entity *curr = cfs_rq->curr;
s64 avg = cfs_rq->avg_vruntime;
@@ -733,7 +737,12 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
load += weight;
}
- return avg >= entity_key(cfs_rq, se) * load;
+ return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load;
+}
+
+int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ return vruntime_eligible(cfs_rq, se->vruntime);
}
static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
@@ -752,9 +761,8 @@ static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = __pick_first_entity(cfs_rq);
+ struct sched_entity *se = __pick_root_entity(cfs_rq);
struct sched_entity *curr = cfs_rq->curr;
-
u64 vruntime = cfs_rq->min_vruntime;
if (curr) {
@@ -766,9 +774,9 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
if (se) {
if (!curr)
- vruntime = se->vruntime;
+ vruntime = se->min_vruntime;
else
- vruntime = min_vruntime(vruntime, se->vruntime);
+ vruntime = min_vruntime(vruntime, se->min_vruntime);
}
/* ensure we never gain time by being placed backwards. */
@@ -781,34 +789,34 @@ 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; })
+#define vruntime_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
-static inline void __update_min_deadline(struct sched_entity *se, struct rb_node *node)
+static inline void __min_vruntime_update(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;
+ if (vruntime_gt(min_vruntime, se, rse))
+ se->min_vruntime = rse->min_vruntime;
}
}
/*
- * se->min_deadline = min(se->deadline, left->min_deadline, right->min_deadline)
+ * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
*/
-static inline bool min_deadline_update(struct sched_entity *se, bool exit)
+static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
{
- u64 old_min_deadline = se->min_deadline;
+ u64 old_min_vruntime = se->min_vruntime;
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);
+ se->min_vruntime = se->vruntime;
+ __min_vruntime_update(se, node->rb_right);
+ __min_vruntime_update(se, node->rb_left);
- return se->min_deadline == old_min_deadline;
+ return se->min_vruntime == old_min_vruntime;
}
-RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
- run_node, min_deadline, min_deadline_update);
+RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
+ run_node, min_vruntime, min_vruntime_update);
/*
* Enqueue an entity into the rb-tree:
@@ -816,18 +824,28 @@ RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
avg_vruntime_add(cfs_rq, se);
- se->min_deadline = se->deadline;
+ se->min_vruntime = se->vruntime;
rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
- __entity_less, &min_deadline_cb);
+ __entity_less, &min_vruntime_cb);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
- &min_deadline_cb);
+ &min_vruntime_cb);
avg_vruntime_sub(cfs_rq, se);
}
+struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
+{
+ struct rb_node *root = cfs_rq->tasks_timeline.rb_root.rb_node;
+
+ if (!root)
+ return NULL;
+
+ return __node_2_se(root);
+}
+
struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);
@@ -850,23 +868,29 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
* 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:
+ * tree keeps the entries sorted on deadline, but also functions as a
+ * heap based on the vruntime by keeping:
*
- * se->min_deadline = min(se->deadline, se->{left,right}->min_deadline)
+ * se->min_vruntime = min(se->vruntime, se->{left,right}->min_vruntime)
*
- * Which allows an EDF like search on (sub)trees.
+ * Which allows tree pruning through eligibility.
*/
-static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
+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 *se = __pick_first_entity(cfs_rq);
struct sched_entity *curr = cfs_rq->curr;
struct sched_entity *best = NULL;
- struct sched_entity *best_left = NULL;
+
+ /*
+ * We can safely skip eligibility check if there is only one entity
+ * in this cfs_rq, saving some cycles.
+ */
+ if (cfs_rq->nr_running == 1)
+ return curr && curr->on_rq ? curr : se;
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
@@ -875,95 +899,45 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
return curr;
+ /* Pick the leftmost entity if it's eligible */
+ if (se && entity_eligible(cfs_rq, se)) {
+ best = se;
+ goto found;
+ }
+
+ /* Heap search for the EEVD entity */
while (node) {
- struct sched_entity *se = __node_2_se(node);
+ struct rb_node *left = node->rb_left;
/*
- * If this entity is not eligible, try the left subtree.
+ * Eligible entities in left subtree are always better
+ * choices, since they have earlier deadlines.
*/
- if (!entity_eligible(cfs_rq, se)) {
- node = node->rb_left;
+ if (left && vruntime_eligible(cfs_rq,
+ __node_2_se(left)->min_vruntime)) {
+ node = left;
continue;
}
- /*
- * Now we heap search eligible trees for the best (min_)deadline
- */
- if (!best || deadline_gt(deadline, best, se))
- best = se;
+ se = __node_2_se(node);
/*
- * Every se in a left branch is eligible, keep track of the
- * branch with the best min_deadline
+ * The left subtree either is empty or has no eligible
+ * entity, so check the current node since it is the one
+ * with earliest deadline that might be eligible.
*/
- 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)
+ if (entity_eligible(cfs_rq, se)) {
+ best = se;
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 sched_entity *se = __pick_eevdf(cfs_rq);
+found:
+ if (!best || (curr && entity_before(curr, best)))
+ best = curr;
- if (!se) {
- struct sched_entity *left = __pick_first_entity(cfs_rq);
- if (left) {
- pr_err("EEVDF scheduling fail, picking leftmost\n");
- return left;
- }
- }
-
- return se;
+ return best;
}
#ifdef CONFIG_SCHED_DEBUG
@@ -1129,23 +1103,17 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq)
}
#endif /* CONFIG_SMP */
-/*
- * Update the current task's runtime statistics.
- */
-static void update_curr(struct cfs_rq *cfs_rq)
+static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
{
- struct sched_entity *curr = cfs_rq->curr;
- u64 now = rq_clock_task(rq_of(cfs_rq));
- u64 delta_exec;
-
- if (unlikely(!curr))
- return;
+ u64 now = rq_clock_task(rq);
+ s64 delta_exec;
delta_exec = now - curr->exec_start;
- if (unlikely((s64)delta_exec <= 0))
- return;
+ if (unlikely(delta_exec <= 0))
+ return delta_exec;
curr->exec_start = now;
+ curr->sum_exec_runtime += delta_exec;
if (schedstat_enabled()) {
struct sched_statistics *stats;
@@ -1155,20 +1123,54 @@ static void update_curr(struct cfs_rq *cfs_rq)
max(delta_exec, stats->exec_max));
}
- curr->sum_exec_runtime += delta_exec;
- schedstat_add(cfs_rq->exec_clock, delta_exec);
+ return delta_exec;
+}
+
+static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
+{
+ trace_sched_stat_runtime(p, delta_exec);
+ account_group_exec_runtime(p, delta_exec);
+ cgroup_account_cputime(p, delta_exec);
+ if (p->dl_server)
+ dl_server_update(p->dl_server, delta_exec);
+}
+
+/*
+ * Used by other classes to account runtime.
+ */
+s64 update_curr_common(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ s64 delta_exec;
+
+ delta_exec = update_curr_se(rq, &curr->se);
+ if (likely(delta_exec > 0))
+ update_curr_task(curr, delta_exec);
+
+ return delta_exec;
+}
+
+/*
+ * Update the current task's runtime statistics.
+ */
+static void update_curr(struct cfs_rq *cfs_rq)
+{
+ struct sched_entity *curr = cfs_rq->curr;
+ s64 delta_exec;
+
+ if (unlikely(!curr))
+ return;
+
+ delta_exec = update_curr_se(rq_of(cfs_rq), curr);
+ if (unlikely(delta_exec <= 0))
+ return;
curr->vruntime += calc_delta_fair(delta_exec, curr);
update_deadline(cfs_rq, curr);
update_min_vruntime(cfs_rq);
- if (entity_is_task(curr)) {
- struct task_struct *curtask = task_of(curr);
-
- trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
- cgroup_account_cputime(curtask, delta_exec);
- account_group_exec_runtime(curtask, delta_exec);
- }
+ if (entity_is_task(curr))
+ update_curr_task(task_of(curr), delta_exec);
account_cfs_rq_runtime(cfs_rq, delta_exec);
}
@@ -3164,7 +3166,7 @@ static bool vma_is_accessed(struct mm_struct *mm, struct vm_area_struct *vma)
* This is also done to avoid any side effect of task scanning
* amplifying the unfairness of disjoint set of VMAs' access.
*/
- if (READ_ONCE(current->mm->numa_scan_seq) < 2)
+ if ((READ_ONCE(current->mm->numa_scan_seq) - vma->numab_state->start_scan_seq) < 2)
return true;
pids = vma->numab_state->pids_active[0] | vma->numab_state->pids_active[1];
@@ -3307,6 +3309,8 @@ retry_pids:
if (!vma->numab_state)
continue;
+ vma->numab_state->start_scan_seq = mm->numa_scan_seq;
+
vma->numab_state->next_scan = now +
msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
@@ -3811,17 +3815,17 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
enqueue_load_avg(cfs_rq, se);
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.
- */
+ if (!curr)
__enqueue_entity(cfs_rq, se);
- update_min_vruntime(cfs_rq);
- }
+
+ /*
+ * 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.
+ */
+ update_min_vruntime(cfs_rq);
}
}
@@ -4096,6 +4100,10 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
if (cfs_rq->tg == &root_task_group)
return;
+ /* rq has been offline and doesn't contribute to the share anymore: */
+ if (!cpu_active(cpu_of(rq_of(cfs_rq))))
+ return;
+
/*
* For migration heavy workloads, access to tg->load_avg can be
* unbound. Limit the update rate to at most once per ms.
@@ -4112,6 +4120,49 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
}
}
+static inline void clear_tg_load_avg(struct cfs_rq *cfs_rq)
+{
+ long delta;
+ u64 now;
+
+ /*
+ * No need to update load_avg for root_task_group, as it is not used.
+ */
+ if (cfs_rq->tg == &root_task_group)
+ return;
+
+ now = sched_clock_cpu(cpu_of(rq_of(cfs_rq)));
+ delta = 0 - cfs_rq->tg_load_avg_contrib;
+ atomic_long_add(delta, &cfs_rq->tg->load_avg);
+ cfs_rq->tg_load_avg_contrib = 0;
+ cfs_rq->last_update_tg_load_avg = now;
+}
+
+/* CPU offline callback: */
+static void __maybe_unused clear_tg_offline_cfs_rqs(struct rq *rq)
+{
+ struct task_group *tg;
+
+ lockdep_assert_rq_held(rq);
+
+ /*
+ * The rq clock has already been updated in
+ * set_rq_offline(), so we should skip updating
+ * the rq clock again in unthrottle_cfs_rq().
+ */
+ rq_clock_start_loop_update(rq);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(tg, &task_groups, list) {
+ struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+
+ clear_tg_load_avg(cfs_rq);
+ }
+ rcu_read_unlock();
+
+ rq_clock_stop_loop_update(rq);
+}
+
/*
* Called within set_task_rq() right before setting a task's CPU. The
* caller only guarantees p->pi_lock is held; no other assumptions,
@@ -4408,6 +4459,8 @@ static inline bool skip_blocked_update(struct sched_entity *se)
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {}
+static inline void clear_tg_offline_cfs_rqs(struct rq *rq) {}
+
static inline int propagate_entity_load_avg(struct sched_entity *se)
{
return 0;
@@ -4770,11 +4823,14 @@ static inline unsigned long task_util(struct task_struct *p)
return READ_ONCE(p->se.avg.util_avg);
}
-static inline unsigned long _task_util_est(struct task_struct *p)
+static inline unsigned long task_runnable(struct task_struct *p)
{
- struct util_est ue = READ_ONCE(p->se.avg.util_est);
+ return READ_ONCE(p->se.avg.runnable_avg);
+}
- return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED));
+static inline unsigned long _task_util_est(struct task_struct *p)
+{
+ return READ_ONCE(p->se.avg.util_est) & ~UTIL_AVG_UNCHANGED;
}
static inline unsigned long task_util_est(struct task_struct *p)
@@ -4791,9 +4847,9 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
return;
/* Update root cfs_rq's estimated utilization */
- enqueued = cfs_rq->avg.util_est.enqueued;
+ enqueued = cfs_rq->avg.util_est;
enqueued += _task_util_est(p);
- WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+ WRITE_ONCE(cfs_rq->avg.util_est, enqueued);
trace_sched_util_est_cfs_tp(cfs_rq);
}
@@ -4807,34 +4863,20 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq,
return;
/* Update root cfs_rq's estimated utilization */
- enqueued = cfs_rq->avg.util_est.enqueued;
+ enqueued = cfs_rq->avg.util_est;
enqueued -= min_t(unsigned int, enqueued, _task_util_est(p));
- WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+ WRITE_ONCE(cfs_rq->avg.util_est, enqueued);
trace_sched_util_est_cfs_tp(cfs_rq);
}
#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100)
-/*
- * Check if a (signed) value is within a specified (unsigned) margin,
- * based on the observation that:
- *
- * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1)
- *
- * NOTE: this only works when value + margin < INT_MAX.
- */
-static inline bool within_margin(int value, int margin)
-{
- return ((unsigned int)(value + margin - 1) < (2 * margin - 1));
-}
-
static inline void util_est_update(struct cfs_rq *cfs_rq,
struct task_struct *p,
bool task_sleep)
{
- long last_ewma_diff, last_enqueued_diff;
- struct util_est ue;
+ unsigned int ewma, dequeued, last_ewma_diff;
if (!sched_feat(UTIL_EST))
return;
@@ -4846,71 +4888,73 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
if (!task_sleep)
return;
+ /* Get current estimate of utilization */
+ ewma = READ_ONCE(p->se.avg.util_est);
+
/*
* If the PELT values haven't changed since enqueue time,
* skip the util_est update.
*/
- ue = p->se.avg.util_est;
- if (ue.enqueued & UTIL_AVG_UNCHANGED)
+ if (ewma & UTIL_AVG_UNCHANGED)
return;
- last_enqueued_diff = ue.enqueued;
+ /* Get utilization at dequeue */
+ dequeued = task_util(p);
/*
* Reset EWMA on utilization increases, the moving average is used only
* to smooth utilization decreases.
*/
- ue.enqueued = task_util(p);
- if (sched_feat(UTIL_EST_FASTUP)) {
- if (ue.ewma < ue.enqueued) {
- ue.ewma = ue.enqueued;
- goto done;
- }
+ if (ewma <= dequeued) {
+ ewma = dequeued;
+ goto done;
}
/*
* Skip update of task's estimated utilization when its members are
* already ~1% close to its last activation value.
*/
- last_ewma_diff = ue.enqueued - ue.ewma;
- last_enqueued_diff -= ue.enqueued;
- if (within_margin(last_ewma_diff, UTIL_EST_MARGIN)) {
- if (!within_margin(last_enqueued_diff, UTIL_EST_MARGIN))
- goto done;
-
- return;
- }
+ last_ewma_diff = ewma - dequeued;
+ if (last_ewma_diff < UTIL_EST_MARGIN)
+ goto done;
/*
* To avoid overestimation of actual task utilization, skip updates if
* we cannot grant there is idle time in this CPU.
*/
- if (task_util(p) > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
+ if (dequeued > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
return;
/*
+ * To avoid underestimate of task utilization, skip updates of EWMA if
+ * we cannot grant that thread got all CPU time it wanted.
+ */
+ if ((dequeued + UTIL_EST_MARGIN) < task_runnable(p))
+ goto done;
+
+
+ /*
* Update Task's estimated utilization
*
* When *p completes an activation we can consolidate another sample
- * of the task size. This is done by storing the current PELT value
- * as ue.enqueued and by using this value to update the Exponential
- * Weighted Moving Average (EWMA):
+ * of the task size. This is done by using this value to update the
+ * Exponential Weighted Moving Average (EWMA):
*
* ewma(t) = w * task_util(p) + (1-w) * ewma(t-1)
* = w * task_util(p) + ewma(t-1) - w * ewma(t-1)
* = w * (task_util(p) - ewma(t-1)) + ewma(t-1)
- * = w * ( last_ewma_diff ) + ewma(t-1)
- * = w * (last_ewma_diff + ewma(t-1) / w)
+ * = w * ( -last_ewma_diff ) + ewma(t-1)
+ * = w * (-last_ewma_diff + ewma(t-1) / w)
*
* Where 'w' is the weight of new samples, which is configured to be
* 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT)
*/
- ue.ewma <<= UTIL_EST_WEIGHT_SHIFT;
- ue.ewma += last_ewma_diff;
- ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
+ ewma <<= UTIL_EST_WEIGHT_SHIFT;
+ ewma -= last_ewma_diff;
+ ewma >>= UTIL_EST_WEIGHT_SHIFT;
done:
- ue.enqueued |= UTIL_AVG_UNCHANGED;
- WRITE_ONCE(p->se.avg.util_est, ue);
+ ewma |= UTIL_AVG_UNCHANGED;
+ WRITE_ONCE(p->se.avg.util_est, ewma);
trace_sched_util_est_se_tp(&p->se);
}
@@ -7638,16 +7682,16 @@ cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost)
if (sched_feat(UTIL_EST)) {
unsigned long util_est;
- util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
+ util_est = READ_ONCE(cfs_rq->avg.util_est);
/*
* During wake-up @p isn't enqueued yet and doesn't contribute
- * to any cpu_rq(cpu)->cfs.avg.util_est.enqueued.
+ * to any cpu_rq(cpu)->cfs.avg.util_est.
* If @dst_cpu == @cpu add it to "simulate" cpu_util after @p
* has been enqueued.
*
* During exec (@dst_cpu = -1) @p is enqueued and does
- * contribute to cpu_rq(cpu)->cfs.util_est.enqueued.
+ * contribute to cpu_rq(cpu)->cfs.util_est.
* Remove it to "simulate" cpu_util without @p's contribution.
*
* Despite the task_on_rq_queued(@p) check there is still a
@@ -7776,7 +7820,7 @@ static inline void eenv_pd_busy_time(struct energy_env *eenv,
for_each_cpu(cpu, pd_cpus) {
unsigned long util = cpu_util(cpu, p, -1, 0);
- busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL);
+ busy_time += effective_cpu_util(cpu, util, NULL, NULL);
}
eenv->pd_busy_time = min(eenv->pd_cap, busy_time);
@@ -7799,7 +7843,7 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
for_each_cpu(cpu, pd_cpus) {
struct task_struct *tsk = (cpu == dst_cpu) ? p : NULL;
unsigned long util = cpu_util(cpu, p, dst_cpu, 1);
- unsigned long eff_util;
+ unsigned long eff_util, min, max;
/*
* Performance domain frequency: utilization clamping
@@ -7808,7 +7852,23 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
* NOTE: in case RT tasks are running, by default the
* FREQUENCY_UTIL's utilization can be max OPP.
*/
- eff_util = effective_cpu_util(cpu, util, FREQUENCY_UTIL, tsk);
+ eff_util = effective_cpu_util(cpu, util, &min, &max);
+
+ /* Task's uclamp can modify min and max value */
+ if (tsk && uclamp_is_used()) {
+ min = max(min, uclamp_eff_value(p, UCLAMP_MIN));
+
+ /*
+ * If there is no active max uclamp constraint,
+ * directly use task's one, otherwise keep max.
+ */
+ if (uclamp_rq_is_idle(cpu_rq(cpu)))
+ max = uclamp_eff_value(p, UCLAMP_MAX);
+ else
+ max = max(max, uclamp_eff_value(p, UCLAMP_MAX));
+ }
+
+ eff_util = sugov_effective_cpu_perf(cpu, eff_util, min, max);
max_util = max(max_util, eff_util);
}
@@ -8210,7 +8270,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
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 next_buddy_marked = 0;
int cse_is_idle, pse_is_idle;
if (unlikely(se == pse))
@@ -8227,7 +8286,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) {
set_next_buddy(pse);
- next_buddy_marked = 1;
}
/*
@@ -9060,7 +9118,7 @@ static int detach_tasks(struct lb_env *env)
case migrate_util:
util = task_util_est(p);
- if (util > env->imbalance)
+ if (shr_bound(util, env->sd->nr_balance_failed) > env->imbalance)
goto next;
env->imbalance -= util;
@@ -12413,6 +12471,9 @@ static void rq_offline_fair(struct rq *rq)
/* Ensure any throttled groups are reachable by pick_next_task */
unthrottle_offline_cfs_rqs(rq);
+
+ /* Ensure that we remove rq contribution to group share: */
+ clear_tg_offline_cfs_rqs(rq);
}
#endif /* CONFIG_SMP */
@@ -13036,19 +13097,6 @@ next_cpu:
return 0;
}
-#else /* CONFIG_FAIR_GROUP_SCHED */
-
-void free_fair_sched_group(struct task_group *tg) { }
-
-int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
-{
- return 1;
-}
-
-void online_fair_sched_group(struct task_group *tg) { }
-
-void unregister_fair_sched_group(struct task_group *tg) { }
-
#endif /* CONFIG_FAIR_GROUP_SCHED */
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index a3ddf84de430..143f55df890b 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -83,7 +83,6 @@ SCHED_FEAT(WA_BIAS, true)
* UtilEstimation. Use estimated CPU utilization.
*/
SCHED_FEAT(UTIL_EST, true)
-SCHED_FEAT(UTIL_EST_FASTUP, true)
SCHED_FEAT(LATENCY_WARN, false)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 565f8374ddbb..31231925f1ec 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -258,6 +258,36 @@ static void do_idle(void)
while (!need_resched()) {
rmb();
+ /*
+ * Interrupts shouldn't be re-enabled from that point on until
+ * the CPU sleeping instruction is reached. Otherwise an interrupt
+ * may fire and queue a timer that would be ignored until the CPU
+ * wakes from the sleeping instruction. And testing need_resched()
+ * doesn't tell about pending needed timer reprogram.
+ *
+ * Several cases to consider:
+ *
+ * - SLEEP-UNTIL-PENDING-INTERRUPT based instructions such as
+ * "wfi" or "mwait" are fine because they can be entered with
+ * interrupt disabled.
+ *
+ * - sti;mwait() couple is fine because the interrupts are
+ * re-enabled only upon the execution of mwait, leaving no gap
+ * in-between.
+ *
+ * - ROLLBACK based idle handlers with the sleeping instruction
+ * called with interrupts enabled are NOT fine. In this scheme
+ * when the interrupt detects it has interrupted an idle handler,
+ * it rolls back to its beginning which performs the
+ * need_resched() check before re-executing the sleeping
+ * instruction. This can leak a pending needed timer reprogram.
+ * If such a scheme is really mandatory due to the lack of an
+ * appropriate CPU sleeping instruction, then a FAST-FORWARD
+ * must instead be applied: when the interrupt detects it has
+ * interrupted an idle handler, it must resume to the end of
+ * this idle handler so that the generic idle loop is iterated
+ * again to reprogram the tick.
+ */
local_irq_disable();
if (cpu_is_offline(cpu)) {
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 3a0e0dc28721..9e1083465fbc 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -52,13 +52,13 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
return;
/* Avoid store if the flag has been already reset */
- enqueued = avg->util_est.enqueued;
+ enqueued = avg->util_est;
if (!(enqueued & UTIL_AVG_UNCHANGED))
return;
/* Reset flag to report util_avg has been updated */
enqueued &= ~UTIL_AVG_UNCHANGED;
- WRITE_ONCE(avg->util_est.enqueued, enqueued);
+ WRITE_ONCE(avg->util_est, enqueued);
}
static inline u64 rq_clock_pelt(struct rq *rq)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 6aaf0a3d6081..3261b067b67e 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1002,24 +1002,15 @@ static void update_curr_rt(struct rq *rq)
{
struct task_struct *curr = rq->curr;
struct sched_rt_entity *rt_se = &curr->rt;
- u64 delta_exec;
- u64 now;
+ s64 delta_exec;
if (curr->sched_class != &rt_sched_class)
return;
- now = rq_clock_task(rq);
- delta_exec = now - curr->se.exec_start;
- if (unlikely((s64)delta_exec <= 0))
+ delta_exec = update_curr_common(rq);
+ if (unlikely(delta_exec <= 0))
return;
- schedstat_set(curr->stats.exec_max,
- max(curr->stats.exec_max, delta_exec));
-
- trace_sched_stat_runtime(curr, delta_exec, 0);
-
- update_current_exec_runtime(curr, now, delta_exec);
-
if (!rt_bandwidth_enabled())
return;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2e5a95486a42..001fe047bd5d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -273,8 +273,6 @@ struct rt_bandwidth {
unsigned int rt_period_active;
};
-void __dl_clear_params(struct task_struct *p);
-
static inline int dl_bandwidth_enabled(void)
{
return sysctl_sched_rt_runtime >= 0;
@@ -315,6 +313,33 @@ extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *att
extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
extern int dl_bw_check_overflow(int cpu);
+/*
+ * SCHED_DEADLINE supports servers (nested scheduling) with the following
+ * interface:
+ *
+ * dl_se::rq -- runqueue we belong to.
+ *
+ * dl_se::server_has_tasks() -- used on bandwidth enforcement; we 'stop' the
+ * server when it runs out of tasks to run.
+ *
+ * dl_se::server_pick() -- nested pick_next_task(); we yield the period if this
+ * returns NULL.
+ *
+ * dl_server_update() -- called from update_curr_common(), propagates runtime
+ * to the server.
+ *
+ * dl_server_start()
+ * dl_server_stop() -- start/stop the server when it has (no) tasks.
+ *
+ * dl_server_init() -- initializes the server.
+ */
+extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
+extern void dl_server_start(struct sched_dl_entity *dl_se);
+extern void dl_server_stop(struct sched_dl_entity *dl_se);
+extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
+ dl_server_has_tasks_f has_tasks,
+ dl_server_pick_f pick);
+
#ifdef CONFIG_CGROUP_SCHED
struct cfs_rq;
@@ -436,10 +461,21 @@ static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
extern int tg_nop(struct task_group *tg, void *data);
+#ifdef CONFIG_FAIR_GROUP_SCHED
extern void free_fair_sched_group(struct task_group *tg);
extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
extern void online_fair_sched_group(struct task_group *tg);
extern void unregister_fair_sched_group(struct task_group *tg);
+#else
+static inline void free_fair_sched_group(struct task_group *tg) { }
+static inline int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
+{
+ return 1;
+}
+static inline void online_fair_sched_group(struct task_group *tg) { }
+static inline void unregister_fair_sched_group(struct task_group *tg) { }
+#endif
+
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);
@@ -2179,6 +2215,10 @@ extern const u32 sched_prio_to_wmult[40];
* MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location
* in the runqueue.
*
+ * NOCLOCK - skip the update_rq_clock() (avoids double updates)
+ *
+ * MIGRATION - p->on_rq == TASK_ON_RQ_MIGRATING (used for DEADLINE)
+ *
* ENQUEUE_HEAD - place at front of runqueue (tail if not specified)
* ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
* ENQUEUE_MIGRATED - the task was migrated during wakeup
@@ -2189,6 +2229,7 @@ extern const u32 sched_prio_to_wmult[40];
#define DEQUEUE_SAVE 0x02 /* Matches ENQUEUE_RESTORE */
#define DEQUEUE_MOVE 0x04 /* Matches ENQUEUE_MOVE */
#define DEQUEUE_NOCLOCK 0x08 /* Matches ENQUEUE_NOCLOCK */
+#define DEQUEUE_MIGRATING 0x100 /* Matches ENQUEUE_MIGRATING */
#define ENQUEUE_WAKEUP 0x01
#define ENQUEUE_RESTORE 0x02
@@ -2203,6 +2244,7 @@ extern const u32 sched_prio_to_wmult[40];
#define ENQUEUE_MIGRATED 0x00
#endif
#define ENQUEUE_INITIAL 0x80
+#define ENQUEUE_MIGRATING 0x100
#define RETRY_TASK ((void *)-1UL)
@@ -2212,6 +2254,8 @@ struct affinity_context {
unsigned int flags;
};
+extern s64 update_curr_common(struct rq *rq);
+
struct sched_class {
#ifdef CONFIG_UCLAMP_TASK
@@ -2425,8 +2469,7 @@ extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
-extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
-extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_entity(struct sched_dl_entity *dl_se);
#define BW_SHIFT 20
#define BW_UNIT (1 << BW_SHIFT)
@@ -2822,6 +2865,7 @@ 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_root_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
@@ -2961,24 +3005,14 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif
#ifdef CONFIG_SMP
-/**
- * enum cpu_util_type - CPU utilization type
- * @FREQUENCY_UTIL: Utilization used to select frequency
- * @ENERGY_UTIL: Utilization used during energy calculation
- *
- * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
- * need to be aggregated differently depending on the usage made of them. This
- * enum is used within effective_cpu_util() to differentiate the types of
- * utilization expected by the callers, and adjust the aggregation accordingly.
- */
-enum cpu_util_type {
- FREQUENCY_UTIL,
- ENERGY_UTIL,
-};
-
unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
- enum cpu_util_type type,
- struct task_struct *p);
+ unsigned long *min,
+ unsigned long *max);
+
+unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
+ unsigned long min,
+ unsigned long max);
+
/*
* Verify the fitness of task @p to run on @cpu taking into account the
@@ -3035,59 +3069,6 @@ static inline bool uclamp_rq_is_idle(struct rq *rq)
return rq->uclamp_flags & UCLAMP_FLAG_IDLE;
}
-/**
- * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
- * @rq: The rq to clamp against. Must not be NULL.
- * @util: The util value to clamp.
- * @p: The task to clamp against. Can be NULL if you want to clamp
- * against @rq only.
- *
- * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
- *
- * If sched_uclamp_used static key is disabled, then just return the util
- * without any clamping since uclamp aggregation at the rq level in the fast
- * path is disabled, rendering this operation a NOP.
- *
- * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
- * will return the correct effective uclamp value of the task even if the
- * static key is disabled.
- */
-static __always_inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
- struct task_struct *p)
-{
- unsigned long min_util = 0;
- unsigned long max_util = 0;
-
- if (!static_branch_likely(&sched_uclamp_used))
- return util;
-
- if (p) {
- min_util = uclamp_eff_value(p, UCLAMP_MIN);
- max_util = uclamp_eff_value(p, UCLAMP_MAX);
-
- /*
- * Ignore last runnable task's max clamp, as this task will
- * reset it. Similarly, no need to read the rq's min clamp.
- */
- if (uclamp_rq_is_idle(rq))
- goto out;
- }
-
- min_util = max_t(unsigned long, min_util, uclamp_rq_get(rq, UCLAMP_MIN));
- max_util = max_t(unsigned long, max_util, uclamp_rq_get(rq, UCLAMP_MAX));
-out:
- /*
- * Since CPU's {min,max}_util clamps are MAX aggregated considering
- * RUNNABLE tasks with _different_ clamps, we can end up with an
- * inversion. Fix it now when the clamps are applied.
- */
- if (unlikely(min_util >= max_util))
- return min_util;
-
- return clamp(util, min_util, max_util);
-}
-
/* Is the rq being capped/throttled by uclamp_max? */
static inline bool uclamp_rq_is_capped(struct rq *rq)
{
@@ -3125,13 +3106,6 @@ static inline unsigned long uclamp_eff_value(struct task_struct *p,
return SCHED_CAPACITY_SCALE;
}
-static inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
- struct task_struct *p)
-{
- return util;
-}
-
static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
static inline bool uclamp_is_used(void)
@@ -3261,16 +3235,6 @@ extern int sched_dynamic_mode(const char *str);
extern void sched_dynamic_update(int mode);
#endif
-static inline void update_current_exec_runtime(struct task_struct *curr,
- u64 now, u64 delta_exec)
-{
- curr->se.sum_exec_runtime += delta_exec;
- account_group_exec_runtime(curr, delta_exec);
-
- curr->se.exec_start = now;
- cgroup_account_cputime(curr, delta_exec);
-}
-
#ifdef CONFIG_SCHED_MM_CID
#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 6cf7304e6449..b1b8fe61c532 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -70,18 +70,7 @@ static void yield_task_stop(struct rq *rq)
static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
{
- struct task_struct *curr = rq->curr;
- u64 now, delta_exec;
-
- now = rq_clock_task(rq);
- delta_exec = now - curr->se.exec_start;
- if (unlikely((s64)delta_exec < 0))
- delta_exec = 0;
-
- schedstat_set(curr->stats.exec_max,
- max(curr->stats.exec_max, delta_exec));
-
- update_current_exec_runtime(curr, now, delta_exec);
+ update_curr_common(rq);
}
/*
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 255999ba9190..aca7b437882e 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1072,7 +1072,7 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn
*/
list_del_init(&addfd->list);
if (!addfd->setfd)
- fd = receive_fd(addfd->file, addfd->flags);
+ fd = receive_fd(addfd->file, NULL, addfd->flags);
else
fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags);
addfd->ret = fd;
diff --git a/kernel/signal.c b/kernel/signal.c
index 47a7602dfe8d..c9c57d053ce4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -171,16 +171,6 @@ static bool recalc_sigpending_tsk(struct task_struct *t)
return false;
}
-/*
- * After recalculating TIF_SIGPENDING, we need to make sure the task wakes up.
- * This is superfluous when called on current, the wakeup is a harmless no-op.
- */
-void recalc_sigpending_and_wake(struct task_struct *t)
-{
- if (recalc_sigpending_tsk(t))
- signal_wake_up(t, 0);
-}
-
void recalc_sigpending(void)
{
if (!recalc_sigpending_tsk(current) && !freezing(current))
@@ -1348,10 +1338,8 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
action->sa.sa_handler = SIG_DFL;
if (handler == HANDLER_EXIT)
action->sa.sa_flags |= SA_IMMUTABLE;
- if (blocked) {
+ if (blocked)
sigdelset(&t->blocked, sig);
- recalc_sigpending_and_wake(t);
- }
}
/*
* Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect
@@ -1361,6 +1349,9 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
(!t->ptrace || (handler == HANDLER_EXIT)))
t->signal->flags &= ~SIGNAL_UNKILLABLE;
ret = send_signal_locked(sig, info, t, PIDTYPE_PID);
+ /* This can happen if the signal was already pending and blocked */
+ if (!task_sigpending(t))
+ signal_wake_up(t, 0);
spin_unlock_irqrestore(&t->sighand->siglock, flags);
return ret;
@@ -1376,12 +1367,12 @@ int force_sig_info(struct kernel_siginfo *info)
*/
int zap_other_threads(struct task_struct *p)
{
- struct task_struct *t = p;
+ struct task_struct *t;
int count = 0;
p->signal->group_stop_count = 0;
- while_each_thread(p, t) {
+ for_other_threads(p, t) {
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
/* Don't require de_thread to wait for the vhost_worker */
if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)
@@ -2465,12 +2456,10 @@ static bool do_signal_stop(int signr)
sig->group_exit_code = signr;
sig->group_stop_count = 0;
-
if (task_set_jobctl_pending(current, signr | gstop))
sig->group_stop_count++;
- t = current;
- while_each_thread(current, t) {
+ for_other_threads(current, t) {
/*
* Setting state to TASK_STOPPED for a group
* stop is always done with the siglock held,
@@ -2966,8 +2955,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
if (sigisemptyset(&retarget))
return;
- t = tsk;
- while_each_thread(tsk, t) {
+ for_other_threads(tsk, t) {
if (t->flags & PF_EXITING)
continue;
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 4f65824879ab..afb3c116da91 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -126,7 +126,7 @@ EXPORT_SYMBOL_GPL(stack_trace_save);
/**
* stack_trace_save_tsk - Save a task stack trace into a storage array
- * @task: The task to examine
+ * @tsk: The task to examine
* @store: Pointer to storage array
* @size: Size of the storage array
* @skipnr: Number of entries to skip at the start of the stack trace
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e1a6e3c675c0..faad00cce269 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -171,6 +171,9 @@ COND_SYSCALL(landlock_add_rule);
COND_SYSCALL(landlock_restrict_self);
COND_SYSCALL(fadvise64_64);
COND_SYSCALL_COMPAT(fadvise64_64);
+COND_SYSCALL(lsm_get_self_attr);
+COND_SYSCALL(lsm_set_self_attr);
+COND_SYSCALL(lsm_list_modules);
/* CONFIG_MMU only */
COND_SYSCALL(swapon);
@@ -201,6 +204,20 @@ 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
*/
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-internal.h b/kernel/time/tick-internal.h
index 649f2b48e8f0..481b7ab65e2c 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -56,7 +56,6 @@ extern int clockevents_program_event(struct clock_event_device *dev,
ktime_t expires, bool force);
extern void clockevents_handle_noop(struct clock_event_device *dev);
extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
-extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
/* Broadcasting support */
# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
@@ -197,3 +196,5 @@ void hrtimers_resume_local(void);
#else
#define JIFFIES_SHIFT 8
#endif
+
+extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index be77b021e5d6..a17d26002831 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -839,6 +839,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
ts->next_timer = next_tick;
}
+ /* Make sure next_tick is never before basemono! */
+ if (WARN_ON_ONCE(basemono > next_tick))
+ next_tick = basemono;
+
/*
* If the tick is due in the next period, keep it ticking or
* force prod the timer.
@@ -887,7 +891,6 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
u64 basemono = ts->timer_expires_base;
u64 expires = ts->timer_expires;
- ktime_t tick = expires;
/* Make sure we won't be trying to stop it twice in a row. */
ts->timer_expires_base = 0;
@@ -910,7 +913,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
/* 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))
+ if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
return;
WARN_ON_ONCE(1);
@@ -920,11 +923,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
}
/*
- * 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().
+ * tick_nohz_stop_tick() can be called several times before
+ * tick_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 tick_nohz_restart_sched_tick().
*/
if (!ts->tick_stopped) {
calc_load_nohz_start();
@@ -935,7 +938,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
trace_tick_stop(1, TICK_DEP_MASK_NONE);
}
- ts->next_tick = tick;
+ ts->next_tick = expires;
/*
* If the expiration time == KTIME_MAX, then we simply stop
@@ -950,11 +953,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
}
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
- hrtimer_start(&ts->sched_timer, tick,
+ hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS_PINNED_HARD);
} else {
- hrtimer_set_expires(&ts->sched_timer, tick);
- tick_program_event(tick, 1);
+ hrtimer_set_expires(&ts->sched_timer, expires);
+ tick_program_event(expires, 1);
}
}
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 63a8ce7177dd..352b161113cd 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -571,18 +571,15 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk,
static void
trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
{
- if (!is_timers_nohz_active())
- return;
-
/*
- * TODO: This wants some optimizing similar to the code below, but we
- * will do that when we switch from push to pull for deferrable timers.
+ * Deferrable timers do not prevent the CPU from entering dynticks and
+ * are not taken into account on the idle/nohz_full path. An IPI when a
+ * new deferrable timer is enqueued will wake up the remote CPU but
+ * nothing will be done with the deferrable timer base. Therefore skip
+ * the remote IPI for deferrable timers completely.
*/
- if (timer->flags & TIMER_DEFERRABLE) {
- if (tick_nohz_full_cpu(base->cpu))
- wake_up_nohz_cpu(base->cpu);
+ if (!is_timers_nohz_active() || timer->flags & TIMER_DEFERRABLE)
return;
- }
/*
* We might have to IPI the remote CPU if the base is idle and the
@@ -606,7 +603,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
__set_bit(idx, base->pending_map);
timer_set_idx(timer, idx);
- trace_timer_start(timer, timer->expires, timer->flags);
+ trace_timer_start(timer, bucket_expiry);
/*
* Check whether this is the new first expiring timer. The
@@ -942,31 +939,34 @@ get_target_base(struct timer_base *base, unsigned tflags)
return get_timer_this_cpu_base(tflags);
}
-static inline void forward_timer_base(struct timer_base *base)
+static inline void __forward_timer_base(struct timer_base *base,
+ unsigned long basej)
{
- unsigned long jnow = READ_ONCE(jiffies);
-
/*
- * No need to forward if we are close enough below jiffies.
- * Also while executing timers, base->clk is 1 offset ahead
- * of jiffies to avoid endless requeuing to current jiffies.
+ * Check whether we can forward the base. We can only do that when
+ * @basej is past base->clk otherwise we might rewind base->clk.
*/
- if ((long)(jnow - base->clk) < 1)
+ if (time_before_eq(basej, base->clk))
return;
/*
* If the next expiry value is > jiffies, then we fast forward to
* jiffies otherwise we forward to the next expiry value.
*/
- if (time_after(base->next_expiry, jnow)) {
- base->clk = jnow;
+ if (time_after(base->next_expiry, basej)) {
+ base->clk = basej;
} else {
if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk)))
return;
base->clk = base->next_expiry;
}
+
}
+static inline void forward_timer_base(struct timer_base *base)
+{
+ __forward_timer_base(base, READ_ONCE(jiffies));
+}
/*
* We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
@@ -1803,8 +1803,10 @@ static int next_pending_bucket(struct timer_base *base, unsigned offset,
/*
* Search the first expiring timer in the various clock levels. Caller must
* hold base->lock.
+ *
+ * Store next expiry time in base->next_expiry.
*/
-static unsigned long __next_timer_interrupt(struct timer_base *base)
+static void next_expiry_recalc(struct timer_base *base)
{
unsigned long clk, next, adj;
unsigned lvl, offset = 0;
@@ -1870,10 +1872,9 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
clk += adj;
}
+ base->next_expiry = next;
base->next_expiry_recalc = false;
base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
-
- return next;
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -1921,8 +1922,9 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
{
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+ unsigned long nextevt = basej + NEXT_TIMER_MAX_DELTA;
u64 expires = KTIME_MAX;
- unsigned long nextevt;
+ bool was_idle;
/*
* Pretend that there is no timer pending if the cpu is offline.
@@ -1933,37 +1935,44 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
raw_spin_lock(&base->lock);
if (base->next_expiry_recalc)
- base->next_expiry = __next_timer_interrupt(base);
- nextevt = base->next_expiry;
+ next_expiry_recalc(base);
/*
* We have a fresh next event. Check whether we can forward the
- * base. We can only do that when @basej is past base->clk
- * otherwise we might rewind base->clk.
+ * base.
*/
- if (time_after(basej, base->clk)) {
- if (time_after(nextevt, basej))
- base->clk = basej;
- else if (time_after(nextevt, base->clk))
- base->clk = nextevt;
- }
+ __forward_timer_base(base, basej);
- if (time_before_eq(nextevt, basej)) {
- expires = basem;
- base->is_idle = false;
+ if (base->timers_pending) {
+ nextevt = base->next_expiry;
+
+ /* If we missed a tick already, force 0 delta */
+ if (time_before(nextevt, basej))
+ nextevt = basej;
+ expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
} else {
- if (base->timers_pending)
- expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
/*
- * If we expect to sleep more than a tick, mark the base idle.
- * Also the tick is stopped so any added timer must forward
- * the base clk itself to keep granularity small. This idle
- * logic is only maintained for the BASE_STD base, deferrable
- * timers may still see large granularity skew (by design).
+ * Move next_expiry for the empty base into the future to
+ * prevent a unnecessary raise of the timer softirq when the
+ * next_expiry value will be reached even if there is no timer
+ * pending.
*/
- if ((expires - basem) > TICK_NSEC)
- base->is_idle = true;
+ base->next_expiry = nextevt;
}
+
+ /*
+ * Base is idle if the next event is more than a tick away.
+ *
+ * If the base is marked idle then any timer add operation must forward
+ * the base clk itself to keep granularity small. This idle logic is
+ * only maintained for the BASE_STD base, deferrable timers may still
+ * see large granularity skew (by design).
+ */
+ was_idle = base->is_idle;
+ base->is_idle = time_after(nextevt, basej + 1);
+ if (was_idle != base->is_idle)
+ trace_timer_base_idle(base->is_idle, base->cpu);
+
raw_spin_unlock(&base->lock);
return cmp_next_hrtimer_event(basem, expires);
@@ -1984,7 +1993,10 @@ void timer_clear_idle(void)
* sending the IPI a few instructions smaller for the cost of taking
* the lock in the exit from idle path.
*/
- base->is_idle = false;
+ if (base->is_idle) {
+ base->is_idle = false;
+ trace_timer_base_idle(false, smp_processor_id());
+ }
}
#endif
@@ -2015,8 +2027,12 @@ static inline void __run_timers(struct timer_base *base)
*/
WARN_ON_ONCE(!levels && !base->next_expiry_recalc
&& base->timers_pending);
+ /*
+ * While executing timers, base->clk is set 1 offset ahead of
+ * jiffies to avoid endless requeuing to current jiffies.
+ */
base->clk++;
- base->next_expiry = __next_timer_interrupt(base);
+ next_expiry_recalc(base);
while (levels--)
expire_timers(base, heads + levels);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 84e8a0f6e4e0..7ac6c52b25eb 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -24,6 +24,7 @@
#include <linux/key.h>
#include <linux/verification.h>
#include <linux/namei.h>
+#include <linux/fileattr.h>
#include <net/bpf_sk_storage.h>
@@ -41,6 +42,9 @@
#define bpf_event_rcu_dereference(p) \
rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))
+#define MAX_UPROBE_MULTI_CNT (1U << 20)
+#define MAX_KPROBE_MULTI_CNT (1U << 20)
+
#ifdef CONFIG_MODULES
struct bpf_trace_module {
struct module *module;
@@ -1376,6 +1380,8 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
struct bpf_dynptr_kern *sig_ptr,
struct bpf_key *trusted_keyring)
{
+ const void *data, *sig;
+ u32 data_len, sig_len;
int ret;
if (trusted_keyring->has_ref) {
@@ -1392,10 +1398,12 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
return ret;
}
- return verify_pkcs7_signature(data_ptr->data,
- __bpf_dynptr_size(data_ptr),
- sig_ptr->data,
- __bpf_dynptr_size(sig_ptr),
+ data_len = __bpf_dynptr_size(data_ptr);
+ data = __bpf_dynptr_data(data_ptr, data_len);
+ sig_len = __bpf_dynptr_size(sig_ptr);
+ sig = __bpf_dynptr_data(sig_ptr, sig_len);
+
+ return verify_pkcs7_signature(data, data_len, sig, sig_len,
trusted_keyring->key,
VERIFYING_UNSPECIFIED_SIGNATURE, NULL,
NULL);
@@ -1427,6 +1435,72 @@ static int __init bpf_key_sig_kfuncs_init(void)
late_initcall(bpf_key_sig_kfuncs_init);
#endif /* CONFIG_KEYS */
+/* filesystem kfuncs */
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_get_file_xattr - get xattr of a file
+ * @file: file to get xattr from
+ * @name__str: name of the xattr
+ * @value_ptr: output buffer of the xattr value
+ *
+ * Get xattr *name__str* of *file* and store the output in *value_ptr*.
+ *
+ * For security reasons, only *name__str* with prefix "user." is allowed.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str,
+ struct bpf_dynptr_kern *value_ptr)
+{
+ struct dentry *dentry;
+ u32 value_len;
+ void *value;
+ int ret;
+
+ if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+ return -EPERM;
+
+ value_len = __bpf_dynptr_size(value_ptr);
+ value = __bpf_dynptr_data_rw(value_ptr, value_len);
+ if (!value)
+ return -EINVAL;
+
+ dentry = file_dentry(file);
+ ret = inode_permission(&nop_mnt_idmap, dentry->d_inode, MAY_READ);
+ if (ret)
+ return ret;
+ return __vfs_getxattr(dentry, dentry->d_inode, name__str, value, value_len);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(fs_kfunc_set_ids)
+BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+BTF_SET8_END(fs_kfunc_set_ids)
+
+static int bpf_get_file_xattr_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+ if (!btf_id_set8_contains(&fs_kfunc_set_ids, kfunc_id))
+ return 0;
+
+ /* Only allow to attach from LSM hooks, to avoid recursion */
+ return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0;
+}
+
+static const struct btf_kfunc_id_set bpf_fs_kfunc_set = {
+ .owner = THIS_MODULE,
+ .set = &fs_kfunc_set_ids,
+ .filter = bpf_get_file_xattr_filter,
+};
+
+static int __init bpf_fs_kfuncs_init(void)
+{
+ return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set);
+}
+
+late_initcall(bpf_fs_kfuncs_init);
+
static const struct bpf_func_proto *
bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -2899,6 +2973,8 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
cnt = attr->link_create.kprobe_multi.cnt;
if (!cnt)
return -EINVAL;
+ if (cnt > MAX_KPROBE_MULTI_CNT)
+ return -E2BIG;
size = cnt * sizeof(*addrs);
addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
@@ -3029,6 +3105,7 @@ struct bpf_uprobe_multi_link;
struct bpf_uprobe {
struct bpf_uprobe_multi_link *link;
loff_t offset;
+ unsigned long ref_ctr_offset;
u64 cookie;
struct uprobe_consumer consumer;
};
@@ -3037,6 +3114,7 @@ struct bpf_uprobe_multi_link {
struct path path;
struct bpf_link link;
u32 cnt;
+ u32 flags;
struct bpf_uprobe *uprobes;
struct task_struct *task;
};
@@ -3078,9 +3156,79 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
kfree(umulti_link);
}
+static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
+ struct bpf_link_info *info)
+{
+ u64 __user *uref_ctr_offsets = u64_to_user_ptr(info->uprobe_multi.ref_ctr_offsets);
+ u64 __user *ucookies = u64_to_user_ptr(info->uprobe_multi.cookies);
+ u64 __user *uoffsets = u64_to_user_ptr(info->uprobe_multi.offsets);
+ u64 __user *upath = u64_to_user_ptr(info->uprobe_multi.path);
+ u32 upath_size = info->uprobe_multi.path_size;
+ struct bpf_uprobe_multi_link *umulti_link;
+ u32 ucount = info->uprobe_multi.count;
+ int err = 0, i;
+ long left;
+
+ if (!upath ^ !upath_size)
+ return -EINVAL;
+
+ if ((uoffsets || uref_ctr_offsets || ucookies) && !ucount)
+ return -EINVAL;
+
+ umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+ info->uprobe_multi.count = umulti_link->cnt;
+ info->uprobe_multi.flags = umulti_link->flags;
+ info->uprobe_multi.pid = umulti_link->task ?
+ task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0;
+
+ if (upath) {
+ char *p, *buf;
+
+ upath_size = min_t(u32, upath_size, PATH_MAX);
+
+ buf = kmalloc(upath_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+ p = d_path(&umulti_link->path, buf, upath_size);
+ if (IS_ERR(p)) {
+ kfree(buf);
+ return PTR_ERR(p);
+ }
+ upath_size = buf + upath_size - p;
+ left = copy_to_user(upath, p, upath_size);
+ kfree(buf);
+ if (left)
+ return -EFAULT;
+ info->uprobe_multi.path_size = upath_size;
+ }
+
+ if (!uoffsets && !ucookies && !uref_ctr_offsets)
+ return 0;
+
+ if (ucount < umulti_link->cnt)
+ err = -ENOSPC;
+ else
+ ucount = umulti_link->cnt;
+
+ for (i = 0; i < ucount; i++) {
+ if (uoffsets &&
+ put_user(umulti_link->uprobes[i].offset, uoffsets + i))
+ return -EFAULT;
+ if (uref_ctr_offsets &&
+ put_user(umulti_link->uprobes[i].ref_ctr_offset, uref_ctr_offsets + i))
+ return -EFAULT;
+ if (ucookies &&
+ put_user(umulti_link->uprobes[i].cookie, ucookies + i))
+ return -EFAULT;
+ }
+
+ return err;
+}
+
static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
.release = bpf_uprobe_multi_link_release,
.dealloc = bpf_uprobe_multi_link_dealloc,
+ .fill_link_info = bpf_uprobe_multi_link_fill_link_info,
};
static int uprobe_prog_run(struct bpf_uprobe *uprobe,
@@ -3168,7 +3316,6 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
{
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;
@@ -3202,6 +3349,8 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
if (!upath || !uoffsets || !cnt)
return -EINVAL;
+ if (cnt > MAX_UPROBE_MULTI_CNT)
+ return -E2BIG;
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);
@@ -3241,22 +3390,20 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
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)) {
+ if (__get_user(uprobes[i].offset, uoffsets + i)) {
err = -EFAULT;
goto error_free;
}
- if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) {
+ if (uprobes[i].offset < 0) {
+ err = -EINVAL;
+ goto error_free;
+ }
+ if (uref_ctr_offsets && __get_user(uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) {
err = -EFAULT;
goto error_free;
}
- if (__get_user(uprobes[i].offset, uoffsets + i)) {
+ if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) {
err = -EFAULT;
goto error_free;
}
@@ -3276,6 +3423,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
link->uprobes = uprobes;
link->path = path;
link->task = task;
+ link->flags = flags;
bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
&bpf_uprobe_multi_link_lops, prog);
@@ -3283,7 +3431,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
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].ref_ctr_offset,
&uprobes[i].consumer);
if (err) {
bpf_uprobe_unregister(&path, uprobes, i);
@@ -3295,11 +3443,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
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)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8de8bec5f366..b01ae7d36021 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1183,18 +1183,19 @@ static void __add_hash_entry(struct ftrace_hash *hash,
hash->count++;
}
-static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
+static struct ftrace_func_entry *
+add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
{
struct ftrace_func_entry *entry;
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
- return -ENOMEM;
+ return NULL;
entry->ip = ip;
__add_hash_entry(hash, entry);
- return 0;
+ return entry;
}
static void
@@ -1349,7 +1350,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
struct ftrace_func_entry *entry;
struct ftrace_hash *new_hash;
int size;
- int ret;
int i;
new_hash = alloc_ftrace_hash(size_bits);
@@ -1366,8 +1366,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
size = 1 << hash->size_bits;
for (i = 0; i < size; i++) {
hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
- ret = add_hash_entry(new_hash, entry->ip);
- if (ret < 0)
+ if (add_hash_entry(new_hash, entry->ip) == NULL)
goto free_hash;
}
}
@@ -2536,7 +2535,7 @@ ftrace_find_unique_ops(struct dyn_ftrace *rec)
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
/* Protected by rcu_tasks for reading, and direct_mutex for writing */
-static struct ftrace_hash *direct_functions = EMPTY_HASH;
+static struct ftrace_hash __rcu *direct_functions = EMPTY_HASH;
static DEFINE_MUTEX(direct_mutex);
int ftrace_direct_func_count;
@@ -2555,39 +2554,6 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
return entry->direct;
}
-static struct ftrace_func_entry*
-ftrace_add_rec_direct(unsigned long ip, unsigned long addr,
- struct ftrace_hash **free_hash)
-{
- struct ftrace_func_entry *entry;
-
- if (ftrace_hash_empty(direct_functions) ||
- direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
- struct ftrace_hash *new_hash;
- int size = ftrace_hash_empty(direct_functions) ? 0 :
- direct_functions->count + 1;
-
- if (size < 32)
- size = 32;
-
- new_hash = dup_hash(direct_functions, size);
- if (!new_hash)
- return NULL;
-
- *free_hash = direct_functions;
- direct_functions = new_hash;
- }
-
- entry = kmalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry)
- return NULL;
-
- entry->ip = ip;
- entry->direct = addr;
- __add_hash_entry(direct_functions, entry);
- return entry;
-}
-
static void call_direct_funcs(unsigned long ip, unsigned long pip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
@@ -4223,8 +4189,8 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int clear_filter)
/* Do nothing if it exists */
if (entry)
return 0;
-
- ret = add_hash_entry(hash, rec->ip);
+ if (add_hash_entry(hash, rec->ip) == NULL)
+ ret = -ENOMEM;
}
return ret;
}
@@ -5266,7 +5232,8 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
return 0;
}
- return add_hash_entry(hash, ip);
+ entry = add_hash_entry(hash, ip);
+ return entry ? 0 : -ENOMEM;
}
static int
@@ -5410,7 +5377,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long
*/
int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
{
- struct ftrace_hash *hash, *free_hash = NULL;
+ struct ftrace_hash *hash, *new_hash = NULL, *free_hash = NULL;
struct ftrace_func_entry *entry, *new;
int err = -EBUSY, size, i;
@@ -5436,17 +5403,44 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
}
}
- /* ... and insert them to direct_functions hash. */
err = -ENOMEM;
+
+ /* Make a copy hash to place the new and the old entries in */
+ size = hash->count + direct_functions->count;
+ if (size > 32)
+ size = 32;
+ new_hash = alloc_ftrace_hash(fls(size));
+ if (!new_hash)
+ goto out_unlock;
+
+ /* Now copy over the existing direct entries */
+ size = 1 << direct_functions->size_bits;
+ for (i = 0; i < size; i++) {
+ hlist_for_each_entry(entry, &direct_functions->buckets[i], hlist) {
+ new = add_hash_entry(new_hash, entry->ip);
+ if (!new)
+ goto out_unlock;
+ new->direct = entry->direct;
+ }
+ }
+
+ /* ... and add the new entries */
+ size = 1 << hash->size_bits;
for (i = 0; i < size; i++) {
hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
- new = ftrace_add_rec_direct(entry->ip, addr, &free_hash);
+ new = add_hash_entry(new_hash, entry->ip);
if (!new)
- goto out_remove;
+ goto out_unlock;
+ /* Update both the copy and the hash entry */
+ new->direct = addr;
entry->direct = addr;
}
}
+ free_hash = direct_functions;
+ rcu_assign_pointer(direct_functions, new_hash);
+ new_hash = NULL;
+
ops->func = call_direct_funcs;
ops->flags = MULTI_FLAGS;
ops->trampoline = FTRACE_REGS_ADDR;
@@ -5454,17 +5448,17 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
err = register_ftrace_function_nolock(ops);
- out_remove:
- if (err)
- remove_direct_functions_hash(hash, addr);
-
out_unlock:
mutex_unlock(&direct_mutex);
- if (free_hash) {
+ if (free_hash && free_hash != EMPTY_HASH) {
synchronize_rcu_tasks();
free_ftrace_hash(free_hash);
}
+
+ if (new_hash)
+ free_ftrace_hash(new_hash);
+
return err;
}
EXPORT_SYMBOL_GPL(register_ftrace_direct);
@@ -6309,7 +6303,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
if (entry)
continue;
- if (add_hash_entry(hash, rec->ip) < 0)
+ if (add_hash_entry(hash, rec->ip) == NULL)
goto out;
} else {
if (entry) {
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 6fd7d4ecbbc6..fa03094e9e69 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -48,7 +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);
}
/**
@@ -63,7 +63,7 @@ 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);
}
@@ -82,6 +82,12 @@ static int rethook_fini_pool(struct objpool_head *head, void *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.
@@ -107,7 +113,7 @@ struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
return ERR_PTR(-ENOMEM);
rh->data = data;
- rh->handler = handler;
+ rcu_assign_pointer(rh->handler, handler);
/* initialize the objpool for rethook nodes */
if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
@@ -135,9 +141,10 @@ 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)))
+ handler = rethook_get_handler(node->rethook);
+ if (likely(handler))
objpool_push(node, &node->rethook->pool);
else
call_rcu(&node->rcu, free_rethook_node_rcu);
@@ -153,9 +160,7 @@ NOKPROBE_SYMBOL(rethook_recycle);
*/
struct rethook_node *rethook_try_get(struct rethook *rh)
{
- rethook_handler_t handler = READ_ONCE(rh->handler);
-
- lockdep_assert_preemption_disabled();
+ rethook_handler_t handler = rethook_get_handler(rh);
/* Check whether @rh is going to be freed. */
if (unlikely(!handler))
@@ -300,7 +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 43cc47d7faaf..9286f88fcd32 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -644,8 +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 */
@@ -700,44 +700,6 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
return local_try_cmpxchg(l, &expect, set);
}
-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;
-}
-
#else /* 64 bits */
/* local64_t always succeeds */
@@ -751,11 +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)
-{
- return local64_try_cmpxchg(&t->time, &expect, set);
-}
#endif
/*
@@ -924,9 +881,14 @@ static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int f
if (!nr_pages || !full)
return true;
- dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+ /*
+ * Add one as dirty will never equal nr_pages, as the sub-buffer
+ * that the writer is on is not counted as dirty.
+ * This is needed if "buffer_percent" is set to 100.
+ */
+ dirty = ring_buffer_nr_dirty_pages(buffer, cpu) + 1;
- return (dirty * 100) > (full * nr_pages);
+ return (dirty * 100) >= (full * nr_pages);
}
/*
@@ -987,7 +949,8 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
/* make sure the waiters see the new index */
smp_wmb();
- rb_wake_up_waiters(&rbwork->work);
+ /* This can be called in any context */
+ irq_work_queue(&rbwork->work);
}
/**
@@ -1787,6 +1750,8 @@ 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);
}
@@ -2407,7 +2372,7 @@ 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;
@@ -2981,25 +2946,6 @@ 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)
@@ -3007,8 +2953,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long new_index, old_index;
struct buffer_page *bpage;
unsigned long addr;
- u64 write_stamp;
- u64 delta;
new_index = rb_event_index(event);
old_index = new_index + rb_event_ts_length(event);
@@ -3017,41 +2961,34 @@ 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.
*/
/*
@@ -3488,7 +3425,7 @@ 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;
@@ -3582,7 +3519,10 @@ __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 {
@@ -3605,26 +3545,19 @@ __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 */
@@ -3632,41 +3565,40 @@ __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*/ 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 */
+ /*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();
+ /*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
@@ -3717,6 +3649,12 @@ 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 */
@@ -3740,6 +3678,8 @@ 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;
}
@@ -5121,7 +5061,8 @@ 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;
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 9aebf904ff97..a0defe156b57 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1894,6 +1894,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
__update_max_tr(tr, tsk, cpu);
arch_spin_unlock(&tr->max_lock);
+
+ /* Any waiters on the old snapshot buffer need to wake up */
+ ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS);
}
/**
@@ -1945,12 +1948,23 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
static int wait_on_pipe(struct trace_iterator *iter, int full)
{
+ int ret;
+
/* Iterators are static, they should be filled or empty */
if (trace_buffer_iter(iter, iter->cpu_file))
return 0;
- return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file,
- full);
+ ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ /*
+ * Make sure this is still the snapshot buffer, as if a snapshot were
+ * to happen, this would now be the main buffer.
+ */
+ if (iter->snapshot)
+ iter->array_buffer = &iter->tr->max_buffer;
+#endif
+ return ret;
}
#ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -2360,13 +2374,7 @@ 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;
@@ -2374,119 +2382,83 @@ 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)
@@ -2770,8 +2742,11 @@ 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));
@@ -2785,10 +2760,6 @@ 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)
@@ -2823,11 +2794,9 @@ 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();
@@ -2836,17 +2805,19 @@ 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;
@@ -4765,7 +4736,11 @@ 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
@@ -5007,6 +4982,12 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp)
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);
@@ -6387,13 +6368,15 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
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);
@@ -6418,7 +6401,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
WARN_ON(1);
tracing_disabled = 1;
}
- return ret;
+ goto out_start;
}
update_buffer_entries(&tr->max_buffer, cpu);
@@ -6427,7 +6410,8 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
#endif /* CONFIG_TRACER_MAX_TRACE */
update_buffer_entries(&tr->array_buffer, cpu);
-
+ out_start:
+ tracing_start_tr(tr);
return ret;
}
@@ -8547,7 +8531,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
wait_index = READ_ONCE(iter->wait_index);
- ret = wait_on_pipe(iter, iter->tr->buffer_percent);
+ ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent);
if (ret)
goto out;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b7f4ea25a194..0489e72c8169 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -617,6 +617,7 @@ 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);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1abc07fba1b9..5ecf3c8bde20 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5623,10 +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);
}
@@ -5634,7 +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
@@ -5900,10 +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);
}
@@ -5911,7 +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_synth.c b/kernel/trace/trace_events_synth.c
index 846e02c0fb59..e7af286af4f1 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -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 9365ce407426..e76f5e1efdf2 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -2177,14 +2177,12 @@ static int user_events_open(struct inode *node, struct file *file)
static ssize_t user_events_write(struct file *file, const char __user *ubuf,
size_t count, loff_t *ppos)
{
- struct iovec iov;
struct iov_iter i;
if (unlikely(*ppos != 0))
return -EFAULT;
- if (unlikely(import_single_range(ITER_SOURCE, (char __user *)ubuf,
- count, &iov, &i)))
+ if (unlikely(import_ubuf(ITER_SOURCE, (char __user *)ubuf, count, &i)))
return -EFAULT;
return user_events_write_core(file, &i);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index d8b302d01083..3e7fa44dc2b2 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -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_uprobe.c b/kernel/trace/trace_uprobe.c
index 99c051de412a..a84b85d8aac1 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -151,7 +151,7 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
return -ENOMEM;
if (addr == FETCH_TOKEN_COMM)
- ret = strlcpy(dst, current->comm, maxlen);
+ ret = strscpy(dst, current->comm, maxlen);
else
ret = strncpy_from_user(dst, src, maxlen);
if (ret >= 0) {
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index eabe8bcc7042..ce4d99df5f0e 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -231,7 +231,7 @@ void __put_user_ns(struct user_namespace *ns)
}
EXPORT_SYMBOL(__put_user_ns);
-/**
+/*
* struct idmap_key - holds the information necessary to find an idmapping in a
* sorted idmap array. It is passed to cmp_map_id() as first argument.
*/
@@ -241,7 +241,7 @@ struct idmap_key {
u32 count; /* == 0 unless used with map_id_range_down() */
};
-/**
+/*
* cmp_map_id - Function to be passed to bsearch() to find the requested
* idmapping. Expects struct idmap_key to be passed via @k.
*/
@@ -271,7 +271,7 @@ static int cmp_map_id(const void *k, const void *e)
return 1;
}
-/**
+/*
* map_id_range_down_max - Find idmap via binary search in ordered idmap array.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
@@ -288,7 +288,7 @@ map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 cou
sizeof(struct uid_gid_extent), cmp_map_id);
}
-/**
+/*
* map_id_range_down_base - Find idmap via binary search in static extent array.
* Can only be called if number of mappings is equal or less than
* UID_GID_MAP_MAX_BASE_EXTENTS.
@@ -332,12 +332,12 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
return id;
}
-static u32 map_id_down(struct uid_gid_map *map, u32 id)
+u32 map_id_down(struct uid_gid_map *map, u32 id)
{
return map_id_range_down(map, id, 1);
}
-/**
+/*
* map_id_up_base - Find idmap via binary search in static extent array.
* Can only be called if number of mappings is equal or less than
* UID_GID_MAP_MAX_BASE_EXTENTS.
@@ -358,7 +358,7 @@ map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id)
return NULL;
}
-/**
+/*
* map_id_up_max - Find idmap via binary search in ordered idmap array.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
@@ -375,7 +375,7 @@ map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id)
sizeof(struct uid_gid_extent), cmp_map_id);
}
-static u32 map_id_up(struct uid_gid_map *map, u32 id)
+u32 map_id_up(struct uid_gid_map *map, u32 id)
{
struct uid_gid_extent *extent;
unsigned extents = map->nr_extents;
@@ -770,7 +770,7 @@ static bool mappings_overlap(struct uid_gid_map *new_map,
return false;
}
-/**
+/*
* insert_extent - Safely insert a new idmap extent into struct uid_gid_map.
* Takes care to allocate a 4K block of memory if the number of mappings exceeds
* UID_GID_MAP_MAX_BASE_EXTENTS.
@@ -839,7 +839,7 @@ static int cmp_extents_reverse(const void *a, const void *b)
return 0;
}
-/**
+/*
* sort_idmaps - Sorts an array of idmap entries.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index 778b4056700f..03b90d7d2175 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -270,7 +270,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
goto error;
ret = -ENOMEM;
- pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
+ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
if (!pages)
goto error;
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 5cd6d4e26915..81a8862295d6 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -91,7 +91,7 @@ static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts);
static DEFINE_PER_CPU(int, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned);
static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched);
-static unsigned long watchdog_hardlockup_all_cpu_dumped;
+static unsigned long hard_lockup_nmi_warn;
notrace void arch_touch_nmi_watchdog(void)
{
@@ -151,12 +151,32 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
*/
if (is_hardlockup(cpu)) {
unsigned int this_cpu = smp_processor_id();
+ unsigned long flags;
/* Only print hardlockups once. */
if (per_cpu(watchdog_hardlockup_warned, cpu))
return;
+ /*
+ * Prevent multiple hard-lockup reports if one cpu is already
+ * engaged in dumping all cpu back traces.
+ */
+ if (sysctl_hardlockup_all_cpu_backtrace) {
+ if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn))
+ return;
+ }
+
+ /*
+ * NOTE: we call printk_cpu_sync_get_irqsave() after printing
+ * the lockup message. While it would be nice to serialize
+ * that printout, we really want to make sure that if some
+ * other CPU somehow locked up while holding the lock associated
+ * with printk_cpu_sync_get_irqsave() that we can still at least
+ * get the message about the lockup out.
+ */
pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", cpu);
+ printk_cpu_sync_get_irqsave(flags);
+
print_modules();
print_irqtrace_events(current);
if (cpu == this_cpu) {
@@ -164,17 +184,17 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
show_regs(regs);
else
dump_stack();
+ printk_cpu_sync_put_irqrestore(flags);
} else {
+ printk_cpu_sync_put_irqrestore(flags);
trigger_single_cpu_backtrace(cpu);
}
- /*
- * Perform multi-CPU dump only once to avoid multiple
- * hardlockups generating interleaving traces
- */
- if (sysctl_hardlockup_all_cpu_backtrace &&
- !test_and_set_bit(0, &watchdog_hardlockup_all_cpu_dumped))
+ if (sysctl_hardlockup_all_cpu_backtrace) {
trigger_allbutcpu_cpu_backtrace(cpu);
+ if (!hardlockup_panic)
+ clear_bit_unlock(0, &hard_lockup_nmi_warn);
+ }
if (hardlockup_panic)
nmi_panic(regs, "Hard LOCKUP");
@@ -448,6 +468,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
struct pt_regs *regs = get_irq_regs();
int duration;
int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
+ unsigned long flags;
if (!watchdog_enabled)
return HRTIMER_NORESTART;
@@ -514,6 +535,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
/* Start period for the next softlockup warning. */
update_report_ts();
+ printk_cpu_sync_get_irqsave(flags);
pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
smp_processor_id(), duration,
current->comm, task_pid_nr(current));
@@ -523,10 +545,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
show_regs(regs);
else
dump_stack();
+ printk_cpu_sync_put_irqrestore(flags);
if (softlockup_all_cpu_backtrace) {
trigger_allbutcpu_cpu_backtrace(smp_processor_id());
- clear_bit_unlock(0, &soft_lockup_nmi_warn);
+ if (!softlockup_panic)
+ clear_bit_unlock(0, &soft_lockup_nmi_warn);
}
add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 6e578f576a6f..76e60faed892 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -381,6 +381,12 @@ 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;
+/* PL: user requested unbound cpumask via sysfs */
+static cpumask_var_t wq_requested_unbound_cpumask;
+
+/* PL: isolated cpumask to be excluded from unbound cpumask */
+static cpumask_var_t wq_isolated_cpumask;
+
/* for further constrain wq_unbound_cpumask by cmdline parameter*/
static struct cpumask wq_cmdline_cpumask __initdata;
@@ -1684,9 +1690,6 @@ 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)) {
@@ -4411,19 +4414,6 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
mutex_unlock(&ctx->wq->mutex);
}
-static void apply_wqattrs_lock(void)
-{
- /* CPUs should stay stable across pwq creations and installations */
- cpus_read_lock();
- mutex_lock(&wq_pool_mutex);
-}
-
-static void apply_wqattrs_unlock(void)
-{
- mutex_unlock(&wq_pool_mutex);
- cpus_read_unlock();
-}
-
static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs)
{
@@ -5828,39 +5818,40 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
}
/**
- * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask
- * @cpumask: the cpumask to set
- *
- * The low-level workqueues cpumask is a global cpumask that limits
- * the affinity of all unbound workqueues. This function check the @cpumask
- * and apply it to all unbound workqueues and updates all pwqs of them.
+ * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask
+ * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask
*
- * Return: 0 - Success
- * -EINVAL - Invalid @cpumask
- * -ENOMEM - Failed to allocate memory for attrs or pwqs.
+ * This function can be called from cpuset code to provide a set of isolated
+ * CPUs that should be excluded from wq_unbound_cpumask. The caller must hold
+ * either cpus_read_lock or cpus_write_lock.
*/
-int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
+int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask)
{
- int ret = -EINVAL;
+ cpumask_var_t cpumask;
+ int ret = 0;
+
+ if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL))
+ return -ENOMEM;
+
+ lockdep_assert_cpus_held();
+ mutex_lock(&wq_pool_mutex);
+
+ /* Save the current isolated cpumask & export it via sysfs */
+ cpumask_copy(wq_isolated_cpumask, exclude_cpumask);
/*
- * Not excluding isolated cpus on purpose.
- * If the user wishes to include them, we allow that.
+ * If the operation fails, it will fall back to
+ * wq_requested_unbound_cpumask which is initially set to
+ * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten
+ * by any subsequent write to workqueue/cpumask sysfs file.
*/
- cpumask_and(cpumask, cpumask, cpu_possible_mask);
- if (!cpumask_empty(cpumask)) {
- apply_wqattrs_lock();
- if (cpumask_equal(cpumask, wq_unbound_cpumask)) {
- ret = 0;
- goto out_unlock;
- }
-
+ if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask))
+ cpumask_copy(cpumask, wq_requested_unbound_cpumask);
+ if (!cpumask_equal(cpumask, wq_unbound_cpumask))
ret = workqueue_apply_unbound_cpumask(cpumask);
-out_unlock:
- apply_wqattrs_unlock();
- }
-
+ mutex_unlock(&wq_pool_mutex);
+ free_cpumask_var(cpumask);
return ret;
}
@@ -5982,6 +5973,19 @@ static struct attribute *wq_sysfs_attrs[] = {
};
ATTRIBUTE_GROUPS(wq_sysfs);
+static void apply_wqattrs_lock(void)
+{
+ /* CPUs should stay stable across pwq creations and installations */
+ cpus_read_lock();
+ mutex_lock(&wq_pool_mutex);
+}
+
+static void apply_wqattrs_unlock(void)
+{
+ mutex_unlock(&wq_pool_mutex);
+ cpus_read_unlock();
+}
+
static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -6158,19 +6162,74 @@ static struct bus_type wq_subsys = {
.dev_groups = wq_sysfs_groups,
};
-static ssize_t wq_unbound_cpumask_show(struct device *dev,
- struct device_attribute *attr, char *buf)
+/**
+ * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask
+ * @cpumask: the cpumask to set
+ *
+ * The low-level workqueues cpumask is a global cpumask that limits
+ * the affinity of all unbound workqueues. This function check the @cpumask
+ * and apply it to all unbound workqueues and updates all pwqs of them.
+ *
+ * Return: 0 - Success
+ * -EINVAL - Invalid @cpumask
+ * -ENOMEM - Failed to allocate memory for attrs or pwqs.
+ */
+static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
+{
+ int ret = -EINVAL;
+
+ /*
+ * Not excluding isolated cpus on purpose.
+ * If the user wishes to include them, we allow that.
+ */
+ cpumask_and(cpumask, cpumask, cpu_possible_mask);
+ if (!cpumask_empty(cpumask)) {
+ apply_wqattrs_lock();
+ cpumask_copy(wq_requested_unbound_cpumask, cpumask);
+ if (cpumask_equal(cpumask, wq_unbound_cpumask)) {
+ ret = 0;
+ goto out_unlock;
+ }
+
+ ret = workqueue_apply_unbound_cpumask(cpumask);
+
+out_unlock:
+ apply_wqattrs_unlock();
+ }
+
+ return ret;
+}
+
+static ssize_t __wq_cpumask_show(struct device *dev,
+ struct device_attribute *attr, char *buf, cpumask_var_t mask)
{
int written;
mutex_lock(&wq_pool_mutex);
- written = scnprintf(buf, PAGE_SIZE, "%*pb\n",
- cpumask_pr_args(wq_unbound_cpumask));
+ written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
mutex_unlock(&wq_pool_mutex);
return written;
}
+static ssize_t wq_unbound_cpumask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask);
+}
+
+static ssize_t wq_requested_cpumask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask);
+}
+
+static ssize_t wq_isolated_cpumask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask);
+}
+
static ssize_t wq_unbound_cpumask_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
@@ -6188,9 +6247,13 @@ static ssize_t wq_unbound_cpumask_store(struct device *dev,
return ret ? ret : count;
}
-static struct device_attribute wq_sysfs_cpumask_attr =
+static struct device_attribute wq_sysfs_cpumask_attrs[] = {
__ATTR(cpumask, 0644, wq_unbound_cpumask_show,
- wq_unbound_cpumask_store);
+ wq_unbound_cpumask_store),
+ __ATTR(cpumask_requested, 0444, wq_requested_cpumask_show, NULL),
+ __ATTR(cpumask_isolated, 0444, wq_isolated_cpumask_show, NULL),
+ __ATTR_NULL,
+};
static int __init wq_sysfs_init(void)
{
@@ -6203,7 +6266,13 @@ static int __init wq_sysfs_init(void)
dev_root = bus_get_dev_root(&wq_subsys);
if (dev_root) {
- err = device_create_file(dev_root, &wq_sysfs_cpumask_attr);
+ struct device_attribute *attr;
+
+ for (attr = wq_sysfs_cpumask_attrs; attr->attr.name; attr++) {
+ err = device_create_file(dev_root, attr);
+ if (err)
+ break;
+ }
put_device(dev_root);
}
return err;
@@ -6515,6 +6584,17 @@ static inline void wq_watchdog_init(void) { }
#endif /* CONFIG_WQ_WATCHDOG */
+static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask)
+{
+ 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;
+ }
+
+ cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask);
+}
+
/**
* workqueue_init_early - early init for workqueue subsystem
*
@@ -6534,11 +6614,16 @@ void __init workqueue_init_early(void)
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));
+ BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL));
+ BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL));
+ 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))
- cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, &wq_cmdline_cpumask);
+ restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
+
+ cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask);
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);