summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/auditsc.c2
-rw-r--r--kernel/bpf/btf.c5
-rw-r--r--kernel/irq/chip.c5
-rw-r--r--kernel/locking/lockdep.c2
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/printk/internal.h2
-rw-r--r--kernel/printk/printk.c8
-rw-r--r--kernel/printk/printk_safe.c32
-rw-r--r--kernel/reboot.c2
-rw-r--r--kernel/sched/core.c36
-rw-r--r--kernel/sched/sched.h5
-rw-r--r--kernel/trace/bpf_trace.c60
-rw-r--r--kernel/trace/ftrace.c13
-rw-r--r--kernel/trace/rethook.c9
14 files changed, 159 insertions, 24 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index f3a2abd6d1a1..3a8c9d744800 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1014,10 +1014,10 @@ static void audit_reset_context(struct audit_context *ctx)
ctx->target_comm[0] = '\0';
unroll_tree_refs(ctx, NULL, 0);
WARN_ON(!list_empty(&ctx->killed_trees));
- ctx->type = 0;
audit_free_module(ctx);
ctx->fds[0] = -1;
audit_proctitle_free(ctx);
+ ctx->type = 0; /* reset last for audit_free_*() */
}
static inline struct audit_context *audit_alloc_context(enum audit_state state)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f08037c31dd7..d003d4d8242a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4928,6 +4928,7 @@ static int btf_check_type_tags(struct btf_verifier_env *env,
n = btf_nr_types(btf);
for (i = start_id; i < n; i++) {
const struct btf_type *t;
+ int chain_limit = 32;
u32 cur_id = i;
t = btf_type_by_id(btf, i);
@@ -4940,6 +4941,10 @@ static int btf_check_type_tags(struct btf_verifier_env *env,
in_tags = btf_type_is_type_tag(t);
while (btf_type_is_modifier(t)) {
+ if (!chain_limit--) {
+ btf_verifier_log(env, "Max chain length or cycle detected");
+ return -ELOOP;
+ }
if (btf_type_is_type_tag(t)) {
if (!in_tags) {
btf_verifier_log(env, "Type tags don't precede modifiers");
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index e6b8e564b37f..886789dcee43 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -1006,8 +1006,10 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
if (desc->irq_data.chip != &no_irq_chip)
mask_ack_irq(desc);
irq_state_set_disabled(desc);
- if (is_chained)
+ if (is_chained) {
desc->action = NULL;
+ WARN_ON(irq_chip_pm_put(irq_desc_get_irq_data(desc)));
+ }
desc->depth = 1;
}
desc->handle_irq = handle;
@@ -1033,6 +1035,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
irq_settings_set_norequest(desc);
irq_settings_set_nothread(desc);
desc->action = &chained_action;
+ WARN_ON(irq_chip_pm_get(irq_desc_get_irq_data(desc)));
irq_activate_and_startup(desc, IRQ_RESEND);
}
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 81e87280513e..f06b91ca6482 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -5432,7 +5432,7 @@ static struct pin_cookie __lock_pin_lock(struct lockdep_map *lock)
* be guessable and still allows some pin nesting in
* our u32 pin_count.
*/
- cookie.val = 1 + (prandom_u32() >> 16);
+ cookie.val = 1 + (sched_clock() & 0xffff);
hlock->pin_count += cookie.val;
return cookie;
}
diff --git a/kernel/panic.c b/kernel/panic.c
index a3c758dba15a..4cf13c37bd08 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -297,6 +297,7 @@ void panic(const char *fmt, ...)
* unfortunately means it may not be hardened to work in a
* panic situation.
*/
+ try_block_console_kthreads(10000);
smp_send_stop();
} else {
/*
@@ -304,6 +305,7 @@ void panic(const char *fmt, ...)
* kmsg_dump, we will need architecture dependent extra
* works in addition to stopping other CPUs.
*/
+ try_block_console_kthreads(10000);
crash_smp_send_stop();
}
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index d947ca6c84f9..e7d8578860ad 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -20,6 +20,8 @@ enum printk_info_flags {
LOG_CONT = 8, /* text is a fragment of a continuation line */
};
+extern bool block_console_kthreads;
+
__printf(4, 0)
int vprintk_store(int facility, int level,
const struct dev_printk_info *dev_info,
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ea3dd55709e7..b095fb5f5f61 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -250,6 +250,9 @@ static atomic_t console_kthreads_active = ATOMIC_INIT(0);
#define console_kthread_printing_exit() \
atomic_dec(&console_kthreads_active)
+/* Block console kthreads to avoid processing new messages. */
+bool block_console_kthreads;
+
/*
* Helper macros to handle lockdep when locking/unlocking console_sem. We use
* macros instead of functions so that _RET_IP_ contains useful information.
@@ -3729,7 +3732,10 @@ static bool printer_should_wake(struct console *con, u64 seq)
return true;
if (con->blocked ||
- console_kthreads_atomically_blocked()) {
+ console_kthreads_atomically_blocked() ||
+ block_console_kthreads ||
+ system_state > SYSTEM_RUNNING ||
+ oops_in_progress) {
return false;
}
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index ef0f9a2044da..caac4de1ea59 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -8,7 +8,9 @@
#include <linux/smp.h>
#include <linux/cpumask.h>
#include <linux/printk.h>
+#include <linux/console.h>
#include <linux/kprobes.h>
+#include <linux/delay.h>
#include "internal.h"
@@ -50,3 +52,33 @@ asmlinkage int vprintk(const char *fmt, va_list args)
return vprintk_default(fmt, args);
}
EXPORT_SYMBOL(vprintk);
+
+/**
+ * try_block_console_kthreads() - Try to block console kthreads and
+ * make the global console_lock() avaialble
+ *
+ * @timeout_ms: The maximum time (in ms) to wait.
+ *
+ * Prevent console kthreads from starting processing new messages. Wait
+ * until the global console_lock() become available.
+ *
+ * Context: Can be called in any context.
+ */
+void try_block_console_kthreads(int timeout_ms)
+{
+ block_console_kthreads = true;
+
+ /* Do not wait when the console lock could not be safely taken. */
+ if (this_cpu_read(printk_context) || in_nmi())
+ return;
+
+ while (timeout_ms > 0) {
+ if (console_trylock()) {
+ console_unlock();
+ return;
+ }
+
+ udelay(1000);
+ timeout_ms -= 1;
+ }
+}
diff --git a/kernel/reboot.c b/kernel/reboot.c
index b5a71d1ff603..80564ffafabf 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -82,6 +82,7 @@ void kernel_restart_prepare(char *cmd)
{
blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
+ try_block_console_kthreads(10000);
usermodehelper_disable();
device_shutdown();
}
@@ -270,6 +271,7 @@ static void kernel_shutdown_prepare(enum system_states state)
blocking_notifier_call_chain(&reboot_notifier_list,
(state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL);
system_state = state;
+ try_block_console_kthreads(10000);
usermodehelper_disable();
device_shutdown();
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bfa7452ca92e..da0bf6fe9ecd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4798,25 +4798,55 @@ static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
static void balance_push(struct rq *rq);
+/*
+ * balance_push_callback is a right abuse of the callback interface and plays
+ * by significantly different rules.
+ *
+ * Where the normal balance_callback's purpose is to be ran in the same context
+ * that queued it (only later, when it's safe to drop rq->lock again),
+ * balance_push_callback is specifically targeted at __schedule().
+ *
+ * This abuse is tolerated because it places all the unlikely/odd cases behind
+ * a single test, namely: rq->balance_callback == NULL.
+ */
struct callback_head balance_push_callback = {
.next = NULL,
.func = (void (*)(struct callback_head *))balance_push,
};
-static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+static inline struct callback_head *
+__splice_balance_callbacks(struct rq *rq, bool split)
{
struct callback_head *head = rq->balance_callback;
+ if (likely(!head))
+ return NULL;
+
lockdep_assert_rq_held(rq);
- if (head)
+ /*
+ * Must not take balance_push_callback off the list when
+ * splice_balance_callbacks() and balance_callbacks() are not
+ * in the same rq->lock section.
+ *
+ * In that case it would be possible for __schedule() to interleave
+ * and observe the list empty.
+ */
+ if (split && head == &balance_push_callback)
+ head = NULL;
+ else
rq->balance_callback = NULL;
return head;
}
+static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+{
+ return __splice_balance_callbacks(rq, true);
+}
+
static void __balance_callbacks(struct rq *rq)
{
- do_balance_callbacks(rq, splice_balance_callbacks(rq));
+ do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
}
static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 01259611beb9..47b89a0fc6e5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1693,6 +1693,11 @@ queue_balance_callback(struct rq *rq,
{
lockdep_assert_rq_held(rq);
+ /*
+ * Don't (re)queue an already queued item; nor queue anything when
+ * balance_push() is active, see the comment with
+ * balance_push_callback.
+ */
if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
return;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4be976cf7d63..68e5cdd24cef 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2423,7 +2423,7 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip,
kprobe_multi_link_prog_run(link, entry_ip, regs);
}
-static int symbols_cmp(const void *a, const void *b)
+static int symbols_cmp_r(const void *a, const void *b, const void *priv)
{
const char **str_a = (const char **) a;
const char **str_b = (const char **) b;
@@ -2431,6 +2431,28 @@ static int symbols_cmp(const void *a, const void *b)
return strcmp(*str_a, *str_b);
}
+struct multi_symbols_sort {
+ const char **funcs;
+ u64 *cookies;
+};
+
+static void symbols_swap_r(void *a, void *b, int size, const void *priv)
+{
+ const struct multi_symbols_sort *data = priv;
+ const char **name_a = a, **name_b = b;
+
+ swap(*name_a, *name_b);
+
+ /* If defined, swap also related cookies. */
+ if (data->cookies) {
+ u64 *cookie_a, *cookie_b;
+
+ cookie_a = data->cookies + (name_a - data->funcs);
+ cookie_b = data->cookies + (name_b - data->funcs);
+ swap(*cookie_a, *cookie_b);
+ }
+}
+
int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_kprobe_multi_link *link = NULL;
@@ -2468,38 +2490,46 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
if (!addrs)
return -ENOMEM;
+ ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
+ if (ucookies) {
+ cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
+ if (!cookies) {
+ err = -ENOMEM;
+ goto error;
+ }
+ if (copy_from_user(cookies, ucookies, size)) {
+ err = -EFAULT;
+ goto error;
+ }
+ }
+
if (uaddrs) {
if (copy_from_user(addrs, uaddrs, size)) {
err = -EFAULT;
goto error;
}
} else {
+ struct multi_symbols_sort data = {
+ .cookies = cookies,
+ };
struct user_syms us;
err = copy_user_syms(&us, usyms, cnt);
if (err)
goto error;
- sort(us.syms, cnt, sizeof(*us.syms), symbols_cmp, NULL);
+ if (cookies)
+ data.funcs = us.syms;
+
+ sort_r(us.syms, cnt, sizeof(*us.syms), symbols_cmp_r,
+ symbols_swap_r, &data);
+
err = ftrace_lookup_symbols(us.syms, cnt, addrs);
free_user_syms(&us);
if (err)
goto error;
}
- ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
- if (ucookies) {
- cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
- if (!cookies) {
- err = -ENOMEM;
- goto error;
- }
- if (copy_from_user(cookies, ucookies, size)) {
- err = -EFAULT;
- goto error;
- }
- }
-
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
err = -ENOMEM;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e750fe141a60..601ccf1b2f09 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8029,15 +8029,23 @@ static int kallsyms_callback(void *data, const char *name,
struct module *mod, unsigned long addr)
{
struct kallsyms_data *args = data;
+ const char **sym;
+ int idx;
- if (!bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp))
+ sym = bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp);
+ if (!sym)
+ return 0;
+
+ idx = sym - args->syms;
+ if (args->addrs[idx])
return 0;
addr = ftrace_location(addr);
if (!addr)
return 0;
- args->addrs[args->found++] = addr;
+ args->addrs[idx] = addr;
+ args->found++;
return args->found == args->cnt ? 1 : 0;
}
@@ -8062,6 +8070,7 @@ int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *a
struct kallsyms_data args;
int err;
+ memset(addrs, 0, sizeof(*addrs) * cnt);
args.addrs = addrs;
args.syms = sorted_syms;
args.cnt = cnt;
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index b56833700d23..c69d82273ce7 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -154,6 +154,15 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
if (unlikely(!handler))
return NULL;
+ /*
+ * This expects the caller will set up a rethook on a function entry.
+ * When the function returns, the rethook will eventually be reclaimed
+ * or released in the rethook_recycle() with call_rcu().
+ * This means the caller must be run in the RCU-availabe context.
+ */
+ if (unlikely(!rcu_is_watching()))
+ return NULL;
+
fn = freelist_try_get(&rh->pool);
if (!fn)
return NULL;
generated by cgit (git 2.34.1) at 2024-06-12 15:32:28 +0000