summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile2
-rw-r--r--kernel/auditsc.c2
-rw-r--r--kernel/bpf/btf.c3
-rw-r--r--kernel/cfi.c22
-rw-r--r--kernel/dma/debug.c2
-rw-r--r--kernel/dma/swiotlb.c14
-rw-r--r--kernel/entry/kvm.c6
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/platform-feature.c27
-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.c89
-rw-r--r--kernel/trace/bpf_trace.c8
-rw-r--r--kernel/workqueue.c16
15 files changed, 177 insertions, 58 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 318789c728d3..a7e1f49ab2b3 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -7,7 +7,7 @@ obj-y = fork.o exec_domain.o panic.o \
cpu.o exit.o softirq.o resource.o \
sysctl.o capability.o ptrace.o user.o \
signal.o sys.o umh.o workqueue.o pid.o task_work.o \
- extable.o params.o \
+ extable.o params.o platform-feature.o \
kthread.o sys_ni.o nsproxy.o \
notifier.o ksysfs.o cred.o reboot.o \
async.o range.o smpboot.o ucount.o regset.o
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 7bccaa4646e5..63d0ac7dfe2f 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6054,6 +6054,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
struct bpf_reg_state *regs,
bool ptr_to_mem_ok)
{
+ enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
struct bpf_verifier_log *log = &env->log;
u32 i, nargs, ref_id, ref_obj_id = 0;
bool is_kfunc = btf_is_kernel(btf);
@@ -6171,7 +6172,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
return -EINVAL;
}
/* rest of the arguments can be anything, like normal kfunc */
- } else if (btf_get_prog_ctx_type(log, btf, t, env->prog->type, i)) {
+ } else 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.
*/
diff --git a/kernel/cfi.c b/kernel/cfi.c
index 9594cfd1cf2c..08102d19ec15 100644
--- a/kernel/cfi.c
+++ b/kernel/cfi.c
@@ -281,6 +281,8 @@ static inline cfi_check_fn find_module_check_fn(unsigned long ptr)
static inline cfi_check_fn find_check_fn(unsigned long ptr)
{
cfi_check_fn fn = NULL;
+ unsigned long flags;
+ bool rcu_idle;
if (is_kernel_text(ptr))
return __cfi_check;
@@ -290,13 +292,21 @@ static inline cfi_check_fn find_check_fn(unsigned long ptr)
* the shadow and __module_address use RCU, so we need to wake it
* up if necessary.
*/
- RCU_NONIDLE({
- if (IS_ENABLED(CONFIG_CFI_CLANG_SHADOW))
- fn = find_shadow_check_fn(ptr);
+ rcu_idle = !rcu_is_watching();
+ if (rcu_idle) {
+ local_irq_save(flags);
+ rcu_irq_enter();
+ }
+
+ if (IS_ENABLED(CONFIG_CFI_CLANG_SHADOW))
+ fn = find_shadow_check_fn(ptr);
+ if (!fn)
+ fn = find_module_check_fn(ptr);
- if (!fn)
- fn = find_module_check_fn(ptr);
- });
+ if (rcu_idle) {
+ rcu_irq_exit();
+ local_irq_restore(flags);
+ }
return fn;
}
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index ac740630c79c..2caafd13f8aa 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -564,7 +564,7 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
rc = active_cacheline_insert(entry);
if (rc == -ENOMEM) {
- pr_err("cacheline tracking ENOMEM, dma-debug disabled\n");
+ pr_err_once("cacheline tracking ENOMEM, dma-debug disabled\n");
global_disable = true;
} else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
err_printk(entry->dev, entry,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index dfa1de89dc94..cb50f8d38360 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -192,7 +192,7 @@ void __init swiotlb_update_mem_attributes(void)
}
static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
- unsigned long nslabs, bool late_alloc)
+ unsigned long nslabs, unsigned int flags, bool late_alloc)
{
void *vaddr = phys_to_virt(start);
unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
@@ -203,8 +203,7 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
mem->index = 0;
mem->late_alloc = late_alloc;
- if (swiotlb_force_bounce)
- mem->force_bounce = true;
+ mem->force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE);
spin_lock_init(&mem->lock);
for (i = 0; i < mem->nslabs; i++) {
@@ -275,8 +274,7 @@ retry:
panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
__func__, alloc_size, PAGE_SIZE);
- swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false);
- mem->force_bounce = flags & SWIOTLB_FORCE;
+ swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false);
if (flags & SWIOTLB_VERBOSE)
swiotlb_print_info();
@@ -348,7 +346,7 @@ retry:
set_memory_decrypted((unsigned long)vstart,
(nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
- swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, true);
+ swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true);
swiotlb_print_info();
return 0;
@@ -835,8 +833,8 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
rmem->size >> PAGE_SHIFT);
- swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false);
- mem->force_bounce = true;
+ swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, SWIOTLB_FORCE,
+ false);
mem->for_alloc = true;
rmem->priv = mem;
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index 9d09f489b60e..2e0f75bcb7fd 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -9,12 +9,6 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
int ret;
if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
- clear_notify_signal();
- if (task_work_pending(current))
- task_work_run();
- }
-
- if (ti_work & _TIF_SIGPENDING) {
kvm_handle_signal_exit(vcpu);
return -EINTR;
}
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/platform-feature.c b/kernel/platform-feature.c
new file mode 100644
index 000000000000..cb6a6c3e4fed
--- /dev/null
+++ b/kernel/platform-feature.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitops.h>
+#include <linux/cache.h>
+#include <linux/export.h>
+#include <linux/platform-feature.h>
+
+#define PLATFORM_FEAT_ARRAY_SZ BITS_TO_LONGS(PLATFORM_FEAT_N)
+static unsigned long __read_mostly platform_features[PLATFORM_FEAT_ARRAY_SZ];
+
+void platform_set(unsigned int feature)
+{
+ set_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_set);
+
+void platform_clear(unsigned int feature)
+{
+ clear_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_clear);
+
+bool platform_has(unsigned int feature)
+{
+ return test_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_has);
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 a091145ee710..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();
}
@@ -315,6 +317,43 @@ static int sys_off_notify(struct notifier_block *nb,
return handler->sys_off_cb(&data);
}
+static struct sys_off_handler platform_sys_off_handler;
+
+static struct sys_off_handler *alloc_sys_off_handler(int priority)
+{
+ struct sys_off_handler *handler;
+ gfp_t flags;
+
+ /*
+ * Platforms like m68k can't allocate sys_off handler dynamically
+ * at the early boot time because memory allocator isn't available yet.
+ */
+ if (priority == SYS_OFF_PRIO_PLATFORM) {
+ handler = &platform_sys_off_handler;
+ if (handler->cb_data)
+ return ERR_PTR(-EBUSY);
+ } else {
+ if (system_state > SYSTEM_RUNNING)
+ flags = GFP_ATOMIC;
+ else
+ flags = GFP_KERNEL;
+
+ handler = kzalloc(sizeof(*handler), flags);
+ if (!handler)
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return handler;
+}
+
+static void free_sys_off_handler(struct sys_off_handler *handler)
+{
+ if (handler == &platform_sys_off_handler)
+ memset(handler, 0, sizeof(*handler));
+ else
+ kfree(handler);
+}
+
/**
* register_sys_off_handler - Register sys-off handler
* @mode: Sys-off mode
@@ -345,9 +384,9 @@ register_sys_off_handler(enum sys_off_mode mode,
struct sys_off_handler *handler;
int err;
- handler = kzalloc(sizeof(*handler), GFP_KERNEL);
- if (!handler)
- return ERR_PTR(-ENOMEM);
+ handler = alloc_sys_off_handler(priority);
+ if (IS_ERR(handler))
+ return handler;
switch (mode) {
case SYS_OFF_MODE_POWER_OFF_PREPARE:
@@ -364,7 +403,7 @@ register_sys_off_handler(enum sys_off_mode mode,
break;
default:
- kfree(handler);
+ free_sys_off_handler(handler);
return ERR_PTR(-EINVAL);
}
@@ -391,7 +430,7 @@ register_sys_off_handler(enum sys_off_mode mode,
}
if (err) {
- kfree(handler);
+ free_sys_off_handler(handler);
return ERR_PTR(err);
}
@@ -409,7 +448,7 @@ void unregister_sys_off_handler(struct sys_off_handler *handler)
{
int err;
- if (!handler)
+ if (IS_ERR_OR_NULL(handler))
return;
if (handler->blocking)
@@ -422,7 +461,7 @@ void unregister_sys_off_handler(struct sys_off_handler *handler)
/* sanity check, shall never happen */
WARN_ON(err);
- kfree(handler);
+ free_sys_off_handler(handler);
}
EXPORT_SYMBOL_GPL(unregister_sys_off_handler);
@@ -584,7 +623,23 @@ static void do_kernel_power_off_prepare(void)
*/
void do_kernel_power_off(void)
{
+ struct sys_off_handler *sys_off = NULL;
+
+ /*
+ * Register sys-off handlers for legacy PM callback. This allows
+ * legacy PM callbacks temporary co-exist with the new sys-off API.
+ *
+ * TODO: Remove legacy handlers once all legacy PM users will be
+ * switched to the sys-off based APIs.
+ */
+ if (pm_power_off)
+ sys_off = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+ SYS_OFF_PRIO_DEFAULT,
+ legacy_pm_power_off, NULL);
+
atomic_notifier_call_chain(&power_off_handler_list, 0, NULL);
+
+ unregister_sys_off_handler(sys_off);
}
/**
@@ -595,7 +650,8 @@ void do_kernel_power_off(void)
*/
bool kernel_can_power_off(void)
{
- return !atomic_notifier_call_chain_is_empty(&power_off_handler_list);
+ return !atomic_notifier_call_chain_is_empty(&power_off_handler_list) ||
+ pm_power_off;
}
EXPORT_SYMBOL_GPL(kernel_can_power_off);
@@ -630,7 +686,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
void __user *, arg)
{
struct pid_namespace *pid_ns = task_active_pid_ns(current);
- struct sys_off_handler *sys_off = NULL;
char buffer[256];
int ret = 0;
@@ -655,21 +710,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
if (ret)
return ret;
- /*
- * Register sys-off handlers for legacy PM callback. This allows
- * legacy PM callbacks temporary co-exist with the new sys-off API.
- *
- * TODO: Remove legacy handlers once all legacy PM users will be
- * switched to the sys-off based APIs.
- */
- if (pm_power_off) {
- sys_off = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
- SYS_OFF_PRIO_DEFAULT,
- legacy_pm_power_off, NULL);
- if (IS_ERR(sys_off))
- return PTR_ERR(sys_off);
- }
-
/* Instead of trying to make the power_off code look like
* halt when pm_power_off is not set do it the easy way.
*/
@@ -727,7 +767,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
break;
}
mutex_unlock(&system_transition_mutex);
- unregister_sys_off_handler(sys_off);
return ret;
}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 10b157a6d73e..7a13e6ac6327 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2263,11 +2263,11 @@ static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32
int err = -ENOMEM;
unsigned int i;
- syms = kvmalloc(cnt * sizeof(*syms), GFP_KERNEL);
+ syms = kvmalloc_array(cnt, sizeof(*syms), GFP_KERNEL);
if (!syms)
goto error;
- buf = kvmalloc(cnt * KSYM_NAME_LEN, GFP_KERNEL);
+ buf = kvmalloc_array(cnt, KSYM_NAME_LEN, GFP_KERNEL);
if (!buf)
goto error;
@@ -2464,7 +2464,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
return -EINVAL;
size = cnt * sizeof(*addrs);
- addrs = kvmalloc(size, GFP_KERNEL);
+ addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
if (!addrs)
return -ENOMEM;
@@ -2489,7 +2489,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
if (ucookies) {
- cookies = kvmalloc(size, GFP_KERNEL);
+ cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
if (!cookies) {
err = -ENOMEM;
goto error;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4056f2a3f9d5..1ea50f6be843 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2788,13 +2788,13 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
}
/**
- * flush_workqueue - ensure that any scheduled work has run to completion.
+ * __flush_workqueue - ensure that any scheduled work has run to completion.
* @wq: workqueue to flush
*
* This function sleeps until all work items which were queued on entry
* have finished execution, but it is not livelocked by new incoming ones.
*/
-void flush_workqueue(struct workqueue_struct *wq)
+void __flush_workqueue(struct workqueue_struct *wq)
{
struct wq_flusher this_flusher = {
.list = LIST_HEAD_INIT(this_flusher.list),
@@ -2943,7 +2943,7 @@ void flush_workqueue(struct workqueue_struct *wq)
out_unlock:
mutex_unlock(&wq->mutex);
}
-EXPORT_SYMBOL(flush_workqueue);
+EXPORT_SYMBOL(__flush_workqueue);
/**
* drain_workqueue - drain a workqueue
@@ -2971,7 +2971,7 @@ void drain_workqueue(struct workqueue_struct *wq)
wq->flags |= __WQ_DRAINING;
mutex_unlock(&wq->mutex);
reflush:
- flush_workqueue(wq);
+ __flush_workqueue(wq);
mutex_lock(&wq->mutex);
@@ -6111,3 +6111,11 @@ void __init workqueue_init(void)
wq_online = true;
wq_watchdog_init();
}
+
+/*
+ * Despite the naming, this is a no-op function which is here only for avoiding
+ * link error. Since compile-time warning may fail to catch, we will need to
+ * emit run-time warning from __flush_workqueue().
+ */
+void __warn_flushing_systemwide_wq(void) { }
+EXPORT_SYMBOL(__warn_flushing_systemwide_wq);
generated by cgit (git 2.34.1) at 2024-06-04 14:03:00 +0000