aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/acct.c2
-rw-r--r--kernel/bpf/Makefile2
-rw-r--r--kernel/bpf/cgroup.c15
-rw-r--r--kernel/bpf/core.c4
-rw-r--r--kernel/bpf/disasm.c65
-rw-r--r--kernel/bpf/disasm.h29
-rw-r--r--kernel/bpf/inode.c40
-rw-r--r--kernel/bpf/offload.c147
-rw-r--r--kernel/bpf/sockmap.c8
-rw-r--r--kernel/bpf/stackmap.c28
-rw-r--r--kernel/bpf/syscall.c114
-rw-r--r--kernel/bpf/verifier.c146
-rw-r--r--kernel/cgroup/cgroup-v1.c6
-rw-r--r--kernel/cgroup/cgroup.c20
-rw-r--r--kernel/cpu.c12
-rw-r--r--kernel/exit.c1
-rw-r--r--kernel/fork.c3
-rw-r--r--kernel/irq/debug.h5
-rw-r--r--kernel/irq/debugfs.c1
-rw-r--r--kernel/irq/generic-chip.c11
-rw-r--r--kernel/irq/internals.h2
-rw-r--r--kernel/irq/irqdomain.c13
-rw-r--r--kernel/irq/msi.c64
-rw-r--r--kernel/pid.c8
-rw-r--r--kernel/sched/cpufreq_schedutil.c2
-rw-r--r--kernel/time/Kconfig1
-rw-r--r--kernel/time/tick-sched.c32
-rw-r--r--kernel/time/timer.c35
-rw-r--r--kernel/trace/ring_buffer.c12
-rw-r--r--kernel/trace/trace.c13
30 files changed, 660 insertions, 181 deletions
diff --git a/kernel/acct.c b/kernel/acct.c
index d15c0ee4d955..addf7732fb56 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -102,7 +102,7 @@ static int check_free_space(struct bsd_acct_struct *acct)
{
struct kstatfs sbuf;
- if (time_is_before_jiffies(acct->needcheck))
+ if (time_is_after_jiffies(acct->needcheck))
goto out;
/* May block */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e691da0b3bab..a713fd23ec88 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -9,9 +9,11 @@ obj-$(CONFIG_BPF_SYSCALL) += devmap.o
obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
obj-$(CONFIG_BPF_SYSCALL) += offload.o
ifeq ($(CONFIG_STREAM_PARSER),y)
+ifeq ($(CONFIG_INET),y)
obj-$(CONFIG_BPF_SYSCALL) += sockmap.o
endif
endif
+endif
ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
endif
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index b789ab78d28f..c1c0b60d3f2f 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -568,6 +568,8 @@ static bool cgroup_dev_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
+ const int size_default = sizeof(__u32);
+
if (type == BPF_WRITE)
return false;
@@ -576,8 +578,17 @@ static bool cgroup_dev_is_valid_access(int off, int size,
/* The verifier guarantees that size > 0. */
if (off % size != 0)
return false;
- if (size != sizeof(__u32))
- return false;
+
+ switch (off) {
+ case bpf_ctx_range(struct bpf_cgroup_dev_ctx, access_type):
+ bpf_ctx_record_field_size(info, size_default);
+ if (!bpf_ctx_narrow_access_ok(off, size, size_default))
+ return false;
+ break;
+ default:
+ if (size != size_default)
+ return false;
+ }
return true;
}
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 768e0a02d8c8..70a534549cd3 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -771,7 +771,9 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
/* Base function for offset calculation. Needs to go into .text section,
* therefore keeping it non-static as well; will also be used by JITs
- * anyway later on, so do not let the compiler omit it.
+ * anyway later on, so do not let the compiler omit it. This also needs
+ * to go into kallsyms for correlation from e.g. bpftool, so naming
+ * must not change.
*/
noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 883f88fa5bfc..8740406df2cd 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -21,10 +21,39 @@ static const char * const func_id_str[] = {
};
#undef __BPF_FUNC_STR_FN
-const char *func_id_name(int id)
+static const char *__func_get_name(const struct bpf_insn_cbs *cbs,
+ const struct bpf_insn *insn,
+ char *buff, size_t len)
{
BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
+ if (insn->src_reg != BPF_PSEUDO_CALL &&
+ insn->imm >= 0 && insn->imm < __BPF_FUNC_MAX_ID &&
+ func_id_str[insn->imm])
+ return func_id_str[insn->imm];
+
+ if (cbs && cbs->cb_call)
+ return cbs->cb_call(cbs->private_data, insn);
+
+ if (insn->src_reg == BPF_PSEUDO_CALL)
+ snprintf(buff, len, "%+d", insn->imm);
+
+ return buff;
+}
+
+static const char *__func_imm_name(const struct bpf_insn_cbs *cbs,
+ const struct bpf_insn *insn,
+ u64 full_imm, char *buff, size_t len)
+{
+ if (cbs && cbs->cb_imm)
+ return cbs->cb_imm(cbs->private_data, insn, full_imm);
+
+ snprintf(buff, len, "0x%llx", (unsigned long long)full_imm);
+ return buff;
+}
+
+const char *func_id_name(int id)
+{
if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
return func_id_str[id];
else
@@ -83,7 +112,7 @@ static const char *const bpf_jmp_string[16] = {
[BPF_EXIT >> 4] = "exit",
};
-static void print_bpf_end_insn(bpf_insn_print_cb verbose,
+static void print_bpf_end_insn(bpf_insn_print_t verbose,
struct bpf_verifier_env *env,
const struct bpf_insn *insn)
{
@@ -92,9 +121,12 @@ static void print_bpf_end_insn(bpf_insn_print_cb verbose,
insn->imm, insn->dst_reg);
}
-void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
- const struct bpf_insn *insn, bool allow_ptr_leaks)
+void print_bpf_insn(const struct bpf_insn_cbs *cbs,
+ struct bpf_verifier_env *env,
+ const struct bpf_insn *insn,
+ bool allow_ptr_leaks)
{
+ const bpf_insn_print_t verbose = cbs->cb_print;
u8 class = BPF_CLASS(insn->code);
if (class == BPF_ALU || class == BPF_ALU64) {
@@ -175,12 +207,15 @@ void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
*/
u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+ char tmp[64];
if (map_ptr && !allow_ptr_leaks)
imm = 0;
- verbose(env, "(%02x) r%d = 0x%llx\n", insn->code,
- insn->dst_reg, (unsigned long long)imm);
+ verbose(env, "(%02x) r%d = %s\n",
+ insn->code, insn->dst_reg,
+ __func_imm_name(cbs, insn, imm,
+ tmp, sizeof(tmp)));
} else {
verbose(env, "BUG_ld_%02x\n", insn->code);
return;
@@ -189,12 +224,20 @@ void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
u8 opcode = BPF_OP(insn->code);
if (opcode == BPF_CALL) {
- if (insn->src_reg == BPF_PSEUDO_CALL)
- verbose(env, "(%02x) call pc%+d\n", insn->code,
- insn->imm);
- else
+ char tmp[64];
+
+ if (insn->src_reg == BPF_PSEUDO_CALL) {
+ verbose(env, "(%02x) call pc%s\n",
+ insn->code,
+ __func_get_name(cbs, insn,
+ tmp, sizeof(tmp)));
+ } else {
+ strcpy(tmp, "unknown");
verbose(env, "(%02x) call %s#%d\n", insn->code,
- func_id_name(insn->imm), insn->imm);
+ __func_get_name(cbs, insn,
+ tmp, sizeof(tmp)),
+ insn->imm);
+ }
} else if (insn->code == (BPF_JMP | BPF_JA)) {
verbose(env, "(%02x) goto pc%+d\n",
insn->code, insn->off);
diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h
index 8de977e420b6..e0857d016f89 100644
--- a/kernel/bpf/disasm.h
+++ b/kernel/bpf/disasm.h
@@ -17,16 +17,35 @@
#include <linux/bpf.h>
#include <linux/kernel.h>
#include <linux/stringify.h>
+#ifndef __KERNEL__
+#include <stdio.h>
+#include <string.h>
+#endif
+
+struct bpf_verifier_env;
extern const char *const bpf_alu_string[16];
extern const char *const bpf_class_string[8];
const char *func_id_name(int id);
-struct bpf_verifier_env;
-typedef void (*bpf_insn_print_cb)(struct bpf_verifier_env *env,
- const char *, ...);
-void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
- const struct bpf_insn *insn, bool allow_ptr_leaks);
+typedef void (*bpf_insn_print_t)(struct bpf_verifier_env *env,
+ const char *, ...);
+typedef const char *(*bpf_insn_revmap_call_t)(void *private_data,
+ const struct bpf_insn *insn);
+typedef const char *(*bpf_insn_print_imm_t)(void *private_data,
+ const struct bpf_insn *insn,
+ __u64 full_imm);
+
+struct bpf_insn_cbs {
+ bpf_insn_print_t cb_print;
+ bpf_insn_revmap_call_t cb_call;
+ bpf_insn_print_imm_t cb_imm;
+ void *private_data;
+};
+void print_bpf_insn(const struct bpf_insn_cbs *cbs,
+ struct bpf_verifier_env *env,
+ const struct bpf_insn *insn,
+ bool allow_ptr_leaks);
#endif
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 01aaef1a77c5..5bb5e49ef4c3 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -368,7 +368,45 @@ out:
putname(pname);
return ret;
}
-EXPORT_SYMBOL_GPL(bpf_obj_get_user);
+
+static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
+{
+ struct bpf_prog *prog;
+ int ret = inode_permission(inode, MAY_READ | MAY_WRITE);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (inode->i_op == &bpf_map_iops)
+ return ERR_PTR(-EINVAL);
+ if (inode->i_op != &bpf_prog_iops)
+ return ERR_PTR(-EACCES);
+
+ prog = inode->i_private;
+
+ ret = security_bpf_prog(prog);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
+ if (!bpf_prog_get_ok(prog, &type, false))
+ return ERR_PTR(-EINVAL);
+
+ return bpf_prog_inc(prog);
+}
+
+struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type)
+{
+ struct bpf_prog *prog;
+ struct path path;
+ int ret = kern_path(name, LOOKUP_FOLLOW, &path);
+ if (ret)
+ return ERR_PTR(ret);
+ prog = __get_prog_inode(d_backing_inode(path.dentry), type);
+ if (!IS_ERR(prog))
+ touch_atime(&path);
+ path_put(&path);
+ return prog;
+}
+EXPORT_SYMBOL(bpf_prog_get_type_path);
static void bpf_evict_inode(struct inode *inode)
{
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 8455b89d1bbf..040d4e0edf3f 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -16,17 +16,22 @@
#include <linux/bpf.h>
#include <linux/bpf_verifier.h>
#include <linux/bug.h>
+#include <linux/kdev_t.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/printk.h>
+#include <linux/proc_ns.h>
#include <linux/rtnetlink.h>
+#include <linux/rwsem.h>
-/* protected by RTNL */
+/* Protects bpf_prog_offload_devs and offload members of all progs.
+ * RTNL lock cannot be taken when holding this lock.
+ */
+static DECLARE_RWSEM(bpf_devs_lock);
static LIST_HEAD(bpf_prog_offload_devs);
int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
{
- struct net *net = current->nsproxy->net_ns;
struct bpf_dev_offload *offload;
if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
@@ -41,32 +46,40 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
return -ENOMEM;
offload->prog = prog;
- init_waitqueue_head(&offload->verifier_done);
- rtnl_lock();
- offload->netdev = __dev_get_by_index(net, attr->prog_ifindex);
- if (!offload->netdev) {
- rtnl_unlock();
- kfree(offload);
- return -EINVAL;
- }
+ offload->netdev = dev_get_by_index(current->nsproxy->net_ns,
+ attr->prog_ifindex);
+ if (!offload->netdev)
+ goto err_free;
+ down_write(&bpf_devs_lock);
+ if (offload->netdev->reg_state != NETREG_REGISTERED)
+ goto err_unlock;
prog->aux->offload = offload;
list_add_tail(&offload->offloads, &bpf_prog_offload_devs);
- rtnl_unlock();
+ dev_put(offload->netdev);
+ up_write(&bpf_devs_lock);
return 0;
+err_unlock:
+ up_write(&bpf_devs_lock);
+ dev_put(offload->netdev);
+err_free:
+ kfree(offload);
+ return -EINVAL;
}
static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
struct netdev_bpf *data)
{
- struct net_device *netdev = prog->aux->offload->netdev;
+ struct bpf_dev_offload *offload = prog->aux->offload;
+ struct net_device *netdev;
ASSERT_RTNL();
- if (!netdev)
+ if (!offload)
return -ENODEV;
+ netdev = offload->netdev;
if (!netdev->netdev_ops->ndo_bpf)
return -EOPNOTSUPP;
@@ -87,62 +100,63 @@ int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
if (err)
goto exit_unlock;
- env->dev_ops = data.verifier.ops;
-
+ env->prog->aux->offload->dev_ops = data.verifier.ops;
env->prog->aux->offload->dev_state = true;
- env->prog->aux->offload->verifier_running = true;
exit_unlock:
rtnl_unlock();
return err;
}
+int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
+ int insn_idx, int prev_insn_idx)
+{
+ struct bpf_dev_offload *offload;
+ int ret = -ENODEV;
+
+ down_read(&bpf_devs_lock);
+ offload = env->prog->aux->offload;
+ if (offload)
+ ret = offload->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
+ up_read(&bpf_devs_lock);
+
+ return ret;
+}
+
static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
{
struct bpf_dev_offload *offload = prog->aux->offload;
struct netdev_bpf data = {};
- /* Caution - if netdev is destroyed before the program, this function
- * will be called twice.
- */
-
data.offload.prog = prog;
- if (offload->verifier_running)
- wait_event(offload->verifier_done, !offload->verifier_running);
-
if (offload->dev_state)
WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data));
- offload->dev_state = false;
+ /* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
+ bpf_prog_free_id(prog, true);
+
list_del_init(&offload->offloads);
- offload->netdev = NULL;
+ kfree(offload);
+ prog->aux->offload = NULL;
}
void bpf_prog_offload_destroy(struct bpf_prog *prog)
{
- struct bpf_dev_offload *offload = prog->aux->offload;
-
- offload->verifier_running = false;
- wake_up(&offload->verifier_done);
-
rtnl_lock();
- __bpf_prog_offload_destroy(prog);
+ down_write(&bpf_devs_lock);
+ if (prog->aux->offload)
+ __bpf_prog_offload_destroy(prog);
+ up_write(&bpf_devs_lock);
rtnl_unlock();
-
- kfree(offload);
}
static int bpf_prog_offload_translate(struct bpf_prog *prog)
{
- struct bpf_dev_offload *offload = prog->aux->offload;
struct netdev_bpf data = {};
int ret;
data.offload.prog = prog;
- offload->verifier_running = false;
- wake_up(&offload->verifier_done);
-
rtnl_lock();
ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data);
rtnl_unlock();
@@ -164,6 +178,63 @@ int bpf_prog_offload_compile(struct bpf_prog *prog)
return bpf_prog_offload_translate(prog);
}
+struct ns_get_path_bpf_prog_args {
+ struct bpf_prog *prog;
+ struct bpf_prog_info *info;
+};
+
+static struct ns_common *bpf_prog_offload_info_fill_ns(void *private_data)
+{
+ struct ns_get_path_bpf_prog_args *args = private_data;
+ struct bpf_prog_aux *aux = args->prog->aux;
+ struct ns_common *ns;
+ struct net *net;
+
+ rtnl_lock();
+ down_read(&bpf_devs_lock);
+
+ if (aux->offload) {
+ args->info->ifindex = aux->offload->netdev->ifindex;
+ net = dev_net(aux->offload->netdev);
+ get_net(net);
+ ns = &net->ns;
+ } else {
+ args->info->ifindex = 0;
+ ns = NULL;
+ }
+
+ up_read(&bpf_devs_lock);
+ rtnl_unlock();
+
+ return ns;
+}
+
+int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
+ struct bpf_prog *prog)
+{
+ struct ns_get_path_bpf_prog_args args = {
+ .prog = prog,
+ .info = info,
+ };
+ struct inode *ns_inode;
+ struct path ns_path;
+ void *res;
+
+ res = ns_get_path_cb(&ns_path, bpf_prog_offload_info_fill_ns, &args);
+ if (IS_ERR(res)) {
+ if (!info->ifindex)
+ return -ENODEV;
+ return PTR_ERR(res);
+ }
+
+ ns_inode = ns_path.dentry->d_inode;
+ info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev);
+ info->netns_ino = ns_inode->i_ino;
+ path_put(&ns_path);
+
+ return 0;
+}
+
const struct bpf_prog_ops bpf_offload_prog_ops = {
};
@@ -181,11 +252,13 @@ static int bpf_offload_notification(struct notifier_block *notifier,
if (netdev->reg_state != NETREG_UNREGISTERING)
break;
+ down_write(&bpf_devs_lock);
list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs,
offloads) {
if (offload->netdev == netdev)
__bpf_prog_offload_destroy(offload->prog);
}
+ up_write(&bpf_devs_lock);
break;
default:
break;
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 5ee2e41893d9..3f662ee23a34 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -96,14 +96,6 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
return rcu_dereference_sk_user_data(sk);
}
-/* compute the linear packet data range [data, data_end) for skb when
- * sk_skb type programs are in use.
- */
-static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
-{
- TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
-}
-
enum __sk_action {
__SK_DROP = 0,
__SK_PASS,
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a15bc636cc98..6c63c2222ea8 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -226,9 +226,33 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
return 0;
}
-static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+static int stack_map_get_next_key(struct bpf_map *map, void *key,
+ void *next_key)
{
- return -EINVAL;
+ struct bpf_stack_map *smap = container_of(map,
+ struct bpf_stack_map, map);
+ u32 id;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ if (!key) {
+ id = 0;
+ } else {
+ id = *(u32 *)key;
+ if (id >= smap->n_buckets || !smap->buckets[id])
+ id = 0;
+ else
+ id++;
+ }
+
+ while (id < smap->n_buckets && !smap->buckets[id])
+ id++;
+
+ if (id >= smap->n_buckets)
+ return -ENOENT;
+
+ *(u32 *)next_key = id;
+ return 0;
}
static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e2e1c78ce1dc..2bac0dc8baba 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -905,9 +905,13 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog)
return id > 0 ? 0 : id;
}
-static void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
+void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
{
- /* cBPF to eBPF migrations are currently not in the idr store. */
+ /* cBPF to eBPF migrations are currently not in the idr store.
+ * Offloaded programs are removed from the store when their device
+ * disappears - even if someone grabs an fd to them they are unusable,
+ * simply waiting for refcnt to drop to be freed.
+ */
if (!prog->aux->id)
return;
@@ -917,6 +921,7 @@ static void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
__acquire(&prog_idr_lock);
idr_remove(&prog_idr, prog->aux->id);
+ prog->aux->id = 0;
if (do_idr_lock)
spin_unlock_bh(&prog_idr_lock);
@@ -937,10 +942,16 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
+ int i;
+
trace_bpf_prog_put_rcu(prog);
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
+
+ for (i = 0; i < prog->aux->func_cnt; i++)
+ bpf_prog_kallsyms_del(prog->aux->func[i]);
bpf_prog_kallsyms_del(prog);
+
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
}
@@ -1057,7 +1068,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
}
EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);
-static bool bpf_prog_get_ok(struct bpf_prog *prog,
+bool bpf_prog_get_ok(struct bpf_prog *prog,
enum bpf_prog_type *attach_type, bool attach_drv)
{
/* not an attachment, just a refcount inc, always allow */
@@ -1151,6 +1162,8 @@ static int bpf_prog_load(union bpf_attr *attr)
if (!prog)
return -ENOMEM;
+ prog->aux->offload_requested = !!attr->prog_ifindex;
+
err = security_bpf_prog_alloc(prog->aux);
if (err)
goto free_prog_nouncharge;
@@ -1172,7 +1185,7 @@ static int bpf_prog_load(union bpf_attr *attr)
atomic_set(&prog->aux->refcnt, 1);
prog->gpl_compatible = is_gpl ? 1 : 0;
- if (attr->prog_ifindex) {
+ if (bpf_prog_is_dev_bound(prog->aux)) {
err = bpf_prog_offload_init(prog, attr);
if (err)
goto free_prog;
@@ -1552,6 +1565,67 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
return fd;
}
+static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
+ unsigned long addr)
+{
+ int i;
+
+ for (i = 0; i < prog->aux->used_map_cnt; i++)
+ if (prog->aux->used_maps[i] == (void *)addr)
+ return prog->aux->used_maps[i];
+ return NULL;
+}
+
+static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
+{
+ const struct bpf_map *map;
+ struct bpf_insn *insns;
+ u64 imm;
+ int i;
+
+ insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog),
+ GFP_USER);
+ if (!insns)
+ return insns;
+
+ for (i = 0; i < prog->len; i++) {
+ if (insns[i].code == (BPF_JMP | BPF_TAIL_CALL)) {
+ insns[i].code = BPF_JMP | BPF_CALL;
+ insns[i].imm = BPF_FUNC_tail_call;
+ /* fall-through */
+ }
+ if (insns[i].code == (BPF_JMP | BPF_CALL) ||
+ insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) {
+ if (insns[i].code == (BPF_JMP | BPF_CALL_ARGS))
+ insns[i].code = BPF_JMP | BPF_CALL;
+ if (!bpf_dump_raw_ok())
+ insns[i].imm = 0;
+ continue;
+ }
+
+ if (insns[i].code != (BPF_LD | BPF_IMM | BPF_DW))
+ continue;
+
+ imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm;
+ map = bpf_map_from_imm(prog, imm);
+ if (map) {
+ insns[i].src_reg = BPF_PSEUDO_MAP_FD;
+ insns[i].imm = map->id;
+ insns[i + 1].imm = 0;
+ continue;
+ }
+
+ if (!bpf_dump_raw_ok() &&
+ imm == (unsigned long)prog->aux) {
+ insns[i].imm = 0;
+ insns[i + 1].imm = 0;
+ continue;
+ }
+ }
+
+ return insns;
+}
+
static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
@@ -1602,21 +1676,43 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
ulen = info.jited_prog_len;
info.jited_prog_len = prog->jited_len;
if (info.jited_prog_len && ulen) {
- uinsns = u64_to_user_ptr(info.jited_prog_insns);
- ulen = min_t(u32, info.jited_prog_len, ulen);
- if (copy_to_user(uinsns, prog->bpf_func, ulen))
- return -EFAULT;
+ if (bpf_dump_raw_ok()) {
+ uinsns = u64_to_user_ptr(info.jited_prog_insns);
+ ulen = min_t(u32, info.jited_prog_len, ulen);
+ if (copy_to_user(uinsns, prog->bpf_func, ulen))
+ return -EFAULT;
+ } else {
+ info.jited_prog_insns = 0;
+ }
}
ulen = info.xlated_prog_len;
info.xlated_prog_len = bpf_prog_insn_size(prog);
if (info.xlated_prog_len && ulen) {
+ struct bpf_insn *insns_sanitized;
+ bool fault;
+
+ if (prog->blinded && !bpf_dump_raw_ok()) {
+ info.xlated_prog_insns = 0;
+ goto done;
+ }
+ insns_sanitized = bpf_insn_prepare_dump(prog);
+ if (!insns_sanitized)
+ return -ENOMEM;
uinsns = u64_to_user_ptr(info.xlated_prog_insns);
ulen = min_t(u32, info.xlated_prog_len, ulen);
- if (copy_to_user(uinsns, prog->insnsi, ulen))
+ fault = copy_to_user(uinsns, insns_sanitized, ulen);
+ kfree(insns_sanitized);
+ if (fault)
return -EFAULT;
}
+ if (bpf_prog_is_dev_bound(prog->aux)) {
+ err = bpf_prog_offload_info_fill(&info, prog);
+ if (err)
+ return err;
+ }
+
done:
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1cd2c2d28fc3..a2b211262c25 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -772,7 +772,7 @@ static int check_subprogs(struct bpf_verifier_env *env)
return -EPERM;
}
if (bpf_prog_is_dev_bound(env->prog->aux)) {
- verbose(env, "funcation calls in offloaded programs are not supported yet\n");
+ verbose(env, "function calls in offloaded programs are not supported yet\n");
return -EINVAL;
}
ret = add_subprog(env, i + insn[i].imm + 1);
@@ -823,6 +823,7 @@ next:
return 0;
}
+static
struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env,
const struct bpf_verifier_state *state,
struct bpf_verifier_state *parent,
@@ -867,7 +868,7 @@ bug:
verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp);
verbose(env, "regno %d parent frame %d current frame %d\n",
regno, parent->curframe, state->curframe);
- return 0;
+ return NULL;
}
static int mark_reg_read(struct bpf_verifier_env *env,
@@ -1434,33 +1435,80 @@ static int update_stack_depth(struct bpf_verifier_env *env,
const struct bpf_func_state *func,
int off)
{
- u16 stack = env->subprog_stack_depth[func->subprogno], total = 0;
- struct bpf_verifier_state *cur = env->cur_state;
- int i;
+ u16 stack = env->subprog_stack_depth[func->subprogno];
if (stack >= -off)
return 0;
/* update known max for given subprogram */
env->subprog_stack_depth[func->subprogno] = -off;
+ return 0;
+}
- /* compute the total for current call chain */
- for (i = 0; i <= cur->curframe; i++) {
- u32 depth = env->subprog_stack_depth[cur->frame[i]->subprogno];
-
- /* round up to 32-bytes, since this is granularity
- * of interpreter stack sizes
- */
- depth = round_up(depth, 32);
- total += depth;
- }
+/* 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.
+ * Since recursion is prevented by check_cfg() this algorithm
+ * only needs a local stack of MAX_CALL_FRAMES to remember callsites
+ */
+static int check_max_stack_depth(struct bpf_verifier_env *env)
+{
+ int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end;
+ struct bpf_insn *insn = env->prog->insnsi;
+ int insn_cnt = env->prog->len;
+ int ret_insn[MAX_CALL_FRAMES];
+ int ret_prog[MAX_CALL_FRAMES];
- if (total > MAX_BPF_STACK) {
+process_func:
+ /* round up to 32-bytes, since this is granularity
+ * of interpreter stack size
+ */
+ depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
+ if (depth > MAX_BPF_STACK) {
verbose(env, "combined stack size of %d calls is %d. Too large\n",
- cur->curframe, total);
+ frame + 1, depth);
return -EACCES;
}
- return 0;
+continue_func:
+ if (env->subprog_cnt == subprog)
+ subprog_end = insn_cnt;
+ else
+ subprog_end = env->subprog_starts[subprog];
+ for (; i < subprog_end; i++) {
+ if (insn[i].code != (BPF_JMP | BPF_CALL))
+ continue;
+ if (insn[i].src_reg != BPF_PSEUDO_CALL)
+ continue;
+ /* remember insn and function to return to */
+ ret_insn[frame] = i + 1;
+ ret_prog[frame] = subprog;
+
+ /* find the callee */
+ i = i + insn[i].imm + 1;
+ subprog = find_subprog(env, i);
+ if (subprog < 0) {
+ WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
+ i);
+ return -EFAULT;
+ }
+ subprog++;
+ frame++;
+ if (frame >= MAX_CALL_FRAMES) {
+ WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
+ return -EFAULT;
+ }
+ goto process_func;
+ }
+ /* end of for() loop means the last insn of the 'subprog'
+ * was reached. Doesn't matter whether it was JA or EXIT
+ */
+ if (frame == 0)
+ return 0;
+ depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
+ frame--;
+ i = ret_insn[frame];
+ subprog = ret_prog[frame];
+ goto continue_func;
}
static int get_callee_stack_depth(struct bpf_verifier_env *env,
@@ -2105,9 +2153,9 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
struct bpf_func_state *caller, *callee;
int i, subprog, target_insn;
- if (state->curframe >= MAX_CALL_FRAMES) {
+ if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
- state->curframe);
+ state->curframe + 2);
return -E2BIG;
}
@@ -4155,7 +4203,7 @@ static bool stacksafe(struct bpf_func_state *old,
if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
/* explored state didn't use this */
- return true;
+ continue;
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
continue;
@@ -4390,15 +4438,6 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
return 0;
}
-static int ext_analyzer_insn_hook(struct bpf_verifier_env *env,
- int insn_idx, int prev_insn_idx)
-{
- if (env->dev_ops && env->dev_ops->insn_hook)
- return env->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
-
- return 0;
-}
-
static int do_check(struct bpf_verifier_env *env)
{
struct bpf_verifier_state *state;
@@ -4475,14 +4514,20 @@ static int do_check(struct bpf_verifier_env *env)
}
if (env->log.level) {
+ const struct bpf_insn_cbs cbs = {
+ .cb_print = verbose,
+ };
+
verbose(env, "%d: ", insn_idx);
- print_bpf_insn(verbose, env, insn,
- env->allow_ptr_leaks);
+ print_bpf_insn(&cbs, env, insn, env->allow_ptr_leaks);
}
- err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
- if (err)
- return err;
+ if (bpf_prog_is_dev_bound(env->prog->aux)) {
+ err = bpf_prog_offload_verify_insn(env, insn_idx,
+ prev_insn_idx);
+ if (err)
+ return err;
+ }
regs = cur_regs(env);
env->insn_aux_data[insn_idx].seen = true;
@@ -5065,14 +5110,14 @@ static int jit_subprogs(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog, **func, *tmp;
int i, j, subprog_start, subprog_end = 0, len, subprog;
- struct bpf_insn *insn = prog->insnsi;
+ struct bpf_insn *insn;
void *old_bpf_func;
int err = -ENOMEM;
if (env->subprog_cnt == 0)
return 0;
- for (i = 0; i < prog->len; i++, insn++) {
+ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
@@ -5111,7 +5156,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
goto out_free;
memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
len * sizeof(struct bpf_insn));
+ func[i]->type = prog->type;
func[i]->len = len;
+ if (bpf_prog_calc_tag(func[i]))
+ goto out_free;
func[i]->is_func = 1;
/* Use bpf_prog_F_tag to indicate functions in stack traces.
* Long term would need debug info to populate names
@@ -5161,6 +5209,25 @@ static int jit_subprogs(struct bpf_verifier_env *env)
bpf_prog_lock_ro(func[i]);
bpf_prog_kallsyms_add(func[i]);
}
+
+ /* Last step: make now unused interpreter insns from main
+ * prog consistent for later dump requests, so they can
+ * later look the same as if they were interpreted only.
+ */
+ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
+ unsigned long addr;
+
+ if (insn->code != (BPF_JMP | BPF_CALL) ||
+ insn->src_reg != BPF_PSEUDO_CALL)
+ continue;
+ insn->off = env->insn_aux_data[i].call_imm;
+ subprog = find_subprog(env, i + insn->off + 1);
+ addr = (unsigned long)func[subprog + 1]->bpf_func;
+ addr &= PAGE_MASK;
+ insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
+ addr - __bpf_call_base;
+ }
+
prog->jited = 1;
prog->bpf_func = func[0]->bpf_func;
prog->aux->func = func;
@@ -5390,7 +5457,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
- if (env->prog->aux->offload) {
+ if (bpf_prog_is_dev_bound(env->prog->aux)) {
ret = bpf_prog_offload_verifier_prep(env);
if (ret)
goto err_unlock;
@@ -5427,6 +5494,9 @@ skip_full_check:
sanitize_dead_code(env);
if (ret == 0)
+ ret = check_max_stack_depth(env);
+
+ if (ret == 0)
/* program is valid, convert *(u32*)(ctx + off) accesses */
ret = convert_ctx_accesses(env);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 024085daab1a..a2c05d2476ac 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -123,7 +123,11 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
*/
do {
css_task_iter_start(&from->self, 0, &it);
- task = css_task_iter_next(&it);
+
+ do {
+ task = css_task_iter_next(&it);
+ } while (task && (task->flags & PF_EXITING));
+
if (task)
get_task_struct(task);
css_task_iter_end(&it);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 0b1ffe147f24..2cf06c274e4c 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1397,7 +1397,7 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
cft->name);
else
- strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+ strlcpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
return buf;
}
@@ -1864,9 +1864,9 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
root->flags = opts->flags;
if (opts->release_agent)
- strcpy(root->release_agent_path, opts->release_agent);
+ strlcpy(root->release_agent_path, opts->release_agent, PATH_MAX);
if (opts->name)
- strcpy(root->name, opts->name);
+ strlcpy(root->name, opts->name, MAX_CGROUP_ROOT_NAMELEN);
if (opts->cpuset_clone_children)
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
}
@@ -4125,26 +4125,24 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
static void css_task_iter_advance(struct css_task_iter *it)
{
- struct list_head *l = it->task_pos;
+ struct list_head *next;
lockdep_assert_held(&css_set_lock);
- WARN_ON_ONCE(!l);
-
repeat:
/*
* Advance iterator to find next entry. cset->tasks is consumed
* first and then ->mg_tasks. After ->mg_tasks, we move onto the
* next cset.
*/
- l = l->next;
+ next = it->task_pos->next;
- if (l == it->tasks_head)
- l = it->mg_tasks_head->next;
+ if (next == it->tasks_head)
+ next = it->mg_tasks_head->next;
- if (l == it->mg_tasks_head)
+ if (next == it->mg_tasks_head)
css_task_iter_advance_css_set(it);
else
- it->task_pos = l;
+ it->task_pos = next;
/* if PROCS, skip over tasks which aren't group leaders */
if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 41376c3ac93b..53f7dc65f9a3 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -80,19 +80,19 @@ static struct lockdep_map cpuhp_state_down_map =
STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map);
-static void inline cpuhp_lock_acquire(bool bringup)
+static inline void cpuhp_lock_acquire(bool bringup)
{
lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
-static void inline cpuhp_lock_release(bool bringup)
+static inline void cpuhp_lock_release(bool bringup)
{
lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
#else
-static void inline cpuhp_lock_acquire(bool bringup) { }
-static void inline cpuhp_lock_release(bool bringup) { }
+static inline void cpuhp_lock_acquire(bool bringup) { }
+static inline void cpuhp_lock_release(bool bringup) { }
#endif
@@ -1277,9 +1277,9 @@ static struct cpuhp_step cpuhp_bp_states[] = {
* before blk_mq_queue_reinit_notify() from notify_dead(),
* otherwise a RCU stall occurs.
*/
- [CPUHP_TIMERS_DEAD] = {
+ [CPUHP_TIMERS_PREPARE] = {
.name = "timers:dead",
- .startup.single = NULL,
+ .startup.single = timers_prepare_cpu,
.teardown.single = timers_dead_cpu,
},
/* Kicks the plugged cpu into life */
diff --git a/kernel/exit.c b/kernel/exit.c
index df0c91d5606c..995453d9fb55 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1763,3 +1763,4 @@ __weak void abort(void)
/* if that doesn't kill us, halt */
panic("Oops failed to kill thread");
}
+EXPORT_SYMBOL(abort);
diff --git a/kernel/fork.c b/kernel/fork.c
index 432eadf6b58c..2295fc69717f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -721,8 +721,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
goto out;
}
/* a new mm has just been created */
- arch_dup_mmap(oldmm, mm);
- retval = 0;
+ retval = arch_dup_mmap(oldmm, mm);
out:
up_write(&mm->mmap_sem);
flush_tlb_mm(oldmm);
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
index 17f05ef8f575..e4d3819a91cc 100644
--- a/kernel/irq/debug.h
+++ b/kernel/irq/debug.h
@@ -12,6 +12,11 @@
static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
{
+ static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 5);
+
+ if (!__ratelimit(&ratelimit))
+ return;
+
printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n",
irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
printk("->handle_irq(): %p, ", desc->handle_irq);
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index 7f608ac39653..acfaaef8672a 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -113,6 +113,7 @@ static const struct irq_bit_descr irqdata_states[] = {
BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING),
BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED),
BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
+ BIT_MASK_DESCR(IRQD_CAN_RESERVE),
BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU),
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index c26c5bb6b491..508c03dfef25 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -364,10 +364,11 @@ irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq)
EXPORT_SYMBOL_GPL(irq_get_domain_generic_chip);
/*
- * Separate lockdep class for interrupt chip which can nest irq_desc
- * lock.
+ * Separate lockdep classes for interrupt chip which can nest irq_desc
+ * lock and request mutex.
*/
static struct lock_class_key irq_nested_lock_class;
+static struct lock_class_key irq_nested_request_class;
/*
* irq_map_generic_chip - Map a generic chip for an irq domain
@@ -409,7 +410,8 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
set_bit(idx, &gc->installed);
if (dgc->gc_flags & IRQ_GC_INIT_NESTED_LOCK)
- irq_set_lockdep_class(virq, &irq_nested_lock_class);
+ irq_set_lockdep_class(virq, &irq_nested_lock_class,
+ &irq_nested_request_class);
if (chip->irq_calc_mask)
chip->irq_calc_mask(data);
@@ -479,7 +481,8 @@ void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk,
continue;
if (flags & IRQ_GC_INIT_NESTED_LOCK)
- irq_set_lockdep_class(i, &irq_nested_lock_class);
+ irq_set_lockdep_class(i, &irq_nested_lock_class,
+ &irq_nested_request_class);
if (!(flags & IRQ_GC_NO_MASK)) {
struct irq_data *d = irq_get_irq_data(i);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 07d08ca701ec..ab19371eab9b 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -440,7 +440,7 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
#endif /* !CONFIG_GENERIC_PENDING_IRQ */
#if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
-static inline int irq_domain_activate_irq(struct irq_data *data, bool early)
+static inline int irq_domain_activate_irq(struct irq_data *data, bool reserve)
{
irqd_set_activated(data);
return 0;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 4f4f60015e8a..62068ad46930 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1693,7 +1693,7 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
}
}
-static int __irq_domain_activate_irq(struct irq_data *irqd, bool early)
+static int __irq_domain_activate_irq(struct irq_data *irqd, bool reserve)
{
int ret = 0;
@@ -1702,9 +1702,9 @@ static int __irq_domain_activate_irq(struct irq_data *irqd, bool early)
if (irqd->parent_data)
ret = __irq_domain_activate_irq(irqd->parent_data,
- early);
+ reserve);
if (!ret && domain->ops->activate) {
- ret = domain->ops->activate(domain, irqd, early);
+ ret = domain->ops->activate(domain, irqd, reserve);
/* Rollback in case of error */
if (ret && irqd->parent_data)
__irq_domain_deactivate_irq(irqd->parent_data);
@@ -1716,17 +1716,18 @@ static int __irq_domain_activate_irq(struct irq_data *irqd, bool early)
/**
* irq_domain_activate_irq - Call domain_ops->activate recursively to activate
* interrupt
- * @irq_data: outermost irq_data associated with interrupt
+ * @irq_data: Outermost irq_data associated with interrupt
+ * @reserve: If set only reserve an interrupt vector instead of assigning one
*
* This is the second step to call domain_ops->activate to program interrupt
* controllers, so the interrupt could actually get delivered.
*/
-int irq_domain_activate_irq(struct irq_data *irq_data, bool early)
+int irq_domain_activate_irq(struct irq_data *irq_data, bool reserve)
{
int ret = 0;
if (!irqd_is_activated(irq_data))
- ret = __irq_domain_activate_irq(irq_data, early);
+ ret = __irq_domain_activate_irq(irq_data, reserve);
if (!ret)
irqd_set_activated(irq_data);
return ret;
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index edb987b2c58d..2f3c4f5382cc 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -339,6 +339,40 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
return ret;
}
+/*
+ * Carefully check whether the device can use reservation mode. If
+ * reservation mode is enabled then the early activation will assign a
+ * dummy vector to the device. If the PCI/MSI device does not support
+ * masking of the entry then this can result in spurious interrupts when
+ * the device driver is not absolutely careful. But even then a malfunction
+ * of the hardware could result in a spurious interrupt on the dummy vector
+ * and render the device unusable. If the entry can be masked then the core
+ * logic will prevent the spurious interrupt and reservation mode can be
+ * used. For now reservation mode is restricted to PCI/MSI.
+ */
+static bool msi_check_reservation_mode(struct irq_domain *domain,
+ struct msi_domain_info *info,
+ struct device *dev)
+{
+ struct msi_desc *desc;
+
+ if (domain->bus_token != DOMAIN_BUS_PCI_MSI)
+ return false;
+
+ if (!(info->flags & MSI_FLAG_MUST_REACTIVATE))
+ return false;
+
+ if (IS_ENABLED(CONFIG_PCI_MSI) && pci_msi_ignore_mask)
+ return false;
+
+ /*
+ * Checking the first MSI descriptor is sufficient. MSIX supports
+ * masking and MSI does so when the maskbit is set.
+ */
+ desc = first_msi_entry(dev);
+ return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit;
+}
+
/**
* msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
* @domain: The domain to allocate from
@@ -353,9 +387,11 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
- msi_alloc_info_t arg;
+ struct irq_data *irq_data;
struct msi_desc *desc;
+ msi_alloc_info_t arg;
int i, ret, virq;
+ bool can_reserve;
ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
if (ret)
@@ -385,6 +421,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
if (ops->msi_finish)
ops->msi_finish(&arg, 0);
+ can_reserve = msi_check_reservation_mode(domain, info, dev);
+
for_each_msi_entry(desc, dev) {
virq = desc->irq;
if (desc->nvec_used == 1)
@@ -397,15 +435,25 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
* the MSI entries before the PCI layer enables MSI in the
* card. Otherwise the card latches a random msi message.
*/
- if (info->flags & MSI_FLAG_ACTIVATE_EARLY) {
- struct irq_data *irq_data;
+ if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY))
+ continue;
+ irq_data = irq_domain_get_irq_data(domain, desc->irq);
+ if (!can_reserve)
+ irqd_clr_can_reserve(irq_data);
+ ret = irq_domain_activate_irq(irq_data, can_reserve);
+ if (ret)
+ goto cleanup;
+ }
+
+ /*
+ * If these interrupts use reservation mode, clear the activated bit
+ * so request_irq() will assign the final vector.
+ */
+ if (can_reserve) {
+ for_each_msi_entry(desc, dev) {
irq_data = irq_domain_get_irq_data(domain, desc->irq);
- ret = irq_domain_activate_irq(irq_data, true);
- if (ret)
- goto cleanup;
- if (info->flags & MSI_FLAG_MUST_REACTIVATE)
- irqd_clr_activated(irq_data);
+ irqd_clr_activated(irq_data);
}
}
return 0;
diff --git a/kernel/pid.c b/kernel/pid.c
index b13b624e2c49..1e8bb6550ec4 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -193,10 +193,8 @@ struct pid *alloc_pid(struct pid_namespace *ns)
}
if (unlikely(is_child_reaper(pid))) {
- if (pid_ns_prepare_proc(ns)) {
- disable_pid_allocation(ns);
+ if (pid_ns_prepare_proc(ns))
goto out_free;
- }
}
get_pid_ns(ns);
@@ -226,6 +224,10 @@ out_free:
while (++i <= ns->level)
idr_remove(&ns->idr, (pid->numbers + i)->nr);
+ /* On failure to allocate the first pid, reset the state */
+ if (ns->pid_allocated == PIDNS_ADDING)
+ idr_set_cursor(&ns->idr, 0);
+
spin_unlock_irq(&pidmap_lock);
kmem_cache_free(ns->pid_cachep, pid);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 2f52ec0f1539..d6717a3331a1 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -244,7 +244,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
#ifdef CONFIG_NO_HZ_COMMON
static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
{
- unsigned long idle_calls = tick_nohz_get_idle_calls();
+ unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
bool ret = idle_calls == sg_cpu->saved_idle_calls;
sg_cpu->saved_idle_calls = idle_calls;
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index e776fc8cc1df..f6b5f19223d6 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -95,6 +95,7 @@ config NO_HZ_FULL
select RCU_NOCB_CPU
select VIRT_CPU_ACCOUNTING_GEN
select IRQ_WORK
+ select CPU_ISOLATION
help
Adaptively try to shutdown the tick whenever possible, even when
the CPU is running tasks. Typically this requires running a single
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 99578f06c8d4..f7cc7abfcf25 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -650,6 +650,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
ts->next_tick = 0;
}
+static inline bool local_timer_softirq_pending(void)
+{
+ return local_softirq_pending() & TIMER_SOFTIRQ;
+}
+
static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
ktime_t now, int cpu)
{
@@ -666,8 +671,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
} while (read_seqretry(&jiffies_lock, seq));
ts->last_jiffies = basejiff;
- if (rcu_needs_cpu(basemono, &next_rcu) ||
- arch_needs_cpu() || irq_work_needs_cpu()) {
+ /*
+ * Keep the periodic tick, when RCU, architecture or irq_work
+ * requests it.
+ * Aside of that check whether the local timer softirq is
+ * pending. If so its a bad idea to call get_next_timer_interrupt()
+ * because there is an already expired timer, so it will request
+ * immeditate expiry, which rearms the hardware timer with a
+ * minimal delta which brings us back to this place
+ * immediately. Lather, rinse and repeat...
+ */
+ if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+ irq_work_needs_cpu() || local_timer_softirq_pending()) {
next_tick = basemono + TICK_NSEC;
} else {
/*
@@ -986,6 +1001,19 @@ ktime_t tick_nohz_get_sleep_length(void)
}
/**
+ * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
+ * for a particular CPU.
+ *
+ * Called from the schedutil frequency scaling governor in scheduler context.
+ */
+unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
+{
+ struct tick_sched *ts = tick_get_tick_sched(cpu);
+
+ return ts->idle_calls;
+}
+
+/**
* tick_nohz_get_idle_calls - return the current idle calls counter value
*
* Called from the schedutil frequency scaling governor in scheduler context.
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ffebcf878fba..89a9e1b4264a 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -823,11 +823,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);
/*
- * If the timer is deferrable and nohz is active then we need to use
- * the deferrable base.
+ * If the timer is deferrable and NO_HZ_COMMON is set then we need
+ * to use the deferrable base.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
- (tflags & TIMER_DEFERRABLE))
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
return base;
}
@@ -837,11 +836,10 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
/*
- * If the timer is deferrable and nohz is active then we need to use
- * the deferrable base.
+ * If the timer is deferrable and NO_HZ_COMMON is set then we need
+ * to use the deferrable base.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
- (tflags & TIMER_DEFERRABLE))
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
base = this_cpu_ptr(&timer_bases[BASE_DEF]);
return base;
}
@@ -1009,8 +1007,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
if (!ret && (options & MOD_TIMER_PENDING_ONLY))
goto out_unlock;
- debug_activate(timer, expires);
-
new_base = get_target_base(base, timer->flags);
if (base != new_base) {
@@ -1034,6 +1030,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
}
}
+ debug_activate(timer, expires);
+
timer->expires = expires;
/*
* If 'idx' was calculated above and the base time did not advance
@@ -1684,7 +1682,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
base->must_forward_clk = false;
__run_timers(base);
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
}
@@ -1855,6 +1853,21 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h
}
}
+int timers_prepare_cpu(unsigned int cpu)
+{
+ struct timer_base *base;
+ int b;
+
+ for (b = 0; b < NR_BASES; b++) {
+ base = per_cpu_ptr(&timer_bases[b], cpu);
+ base->clk = jiffies;
+ base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+ base->is_idle = false;
+ base->must_forward_clk = true;
+ }
+ return 0;
+}
+
int timers_dead_cpu(unsigned int cpu)
{
struct timer_base *old_base;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c87766c1c204..9ab18995ff1e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
/* Missed count stored at end */
#define RB_MISSED_STORED (1 << 30)
+#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED)
+
struct buffer_data_page {
u64 time_stamp; /* page time stamp */
local_t commit; /* write committed index */
@@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
*/
size_t ring_buffer_page_len(void *page)
{
- return local_read(&((struct buffer_data_page *)page)->commit)
+ struct buffer_data_page *bpage = page;
+
+ return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
+ BUF_PAGE_HDR_SIZE;
}
@@ -4400,8 +4404,13 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
{
struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
struct buffer_data_page *bpage = data;
+ struct page *page = virt_to_page(bpage);
unsigned long flags;
+ /* If the page is still in use someplace else, we can't reuse it */
+ if (page_ref_count(page) > 1)
+ goto out;
+
local_irq_save(flags);
arch_spin_lock(&cpu_buffer->lock);
@@ -4413,6 +4422,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
arch_spin_unlock(&cpu_buffer->lock);
local_irq_restore(flags);
+ out:
free_page((unsigned long)bpage);
}
EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 59518b8126d0..2a8d8a294345 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6769,7 +6769,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int entries, size, i;
+ int entries, i;
ssize_t ret = 0;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -6823,14 +6823,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}
- /*
- * zero out any left over data, this is going to
- * user land.
- */
- size = ring_buffer_page_len(ref->page);
- if (size < PAGE_SIZE)
- memset(ref->page + size, 0, PAGE_SIZE - size);
-
page = virt_to_page(ref->page);
spd.pages[i] = page;
@@ -7588,6 +7580,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
buf->data = alloc_percpu(struct trace_array_cpu);
if (!buf->data) {
ring_buffer_free(buf->buffer);
+ buf->buffer = NULL;
return -ENOMEM;
}
@@ -7611,7 +7604,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
allocate_snapshot ? size : 1);
if (WARN_ON(ret)) {
ring_buffer_free(tr->trace_buffer.buffer);
+ tr->trace_buffer.buffer = NULL;
free_percpu(tr->trace_buffer.data);
+ tr->trace_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
Powered by cgit, Gruvboxed by Blaster4385.