summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile3
-rw-r--r--kernel/bpf/cgroup.c2
-rw-r--r--kernel/bpf/syscall.c1
-rw-r--r--kernel/bpf/verifier.c11
-rw-r--r--kernel/capability.c2
-rw-r--r--kernel/dma/remap.c2
-rw-r--r--kernel/entry/common.c1
-rw-r--r--kernel/entry/kvm.c4
-rw-r--r--kernel/events/uprobes.c2
-rw-r--r--kernel/groups.c2
-rw-r--r--kernel/irq/manage.c2
-rw-r--r--kernel/module.c23
-rw-r--r--kernel/sched/core.c2
-rw-r--r--kernel/sched/cpufreq_schedutil.c5
-rw-r--r--kernel/sched/fair.c2
-rw-r--r--kernel/sched/sched.h15
-rw-r--r--kernel/sys.c10
-rw-r--r--kernel/task_work.c30
-rw-r--r--kernel/time/timer.c9
-rw-r--r--kernel/trace/ring_buffer.c10
20 files changed, 71 insertions, 67 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 2044ef02763b..af601b9bda0e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -38,9 +38,6 @@ KASAN_SANITIZE_kcov.o := n
KCSAN_SANITIZE_kcov.o := n
CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack) -fno-stack-protector
-# cond_syscall is currently not LTO compatible
-CFLAGS_sys_ni.o = $(DISABLE_LTO)
-
obj-y += sched/
obj-y += locking/
obj-y += power/
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index e21de4f1754c..6ec088a96302 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1226,7 +1226,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
*/
int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
struct ctl_table *table, int write,
- void **buf, size_t *pcount, loff_t *ppos,
+ char **buf, size_t *pcount, loff_t *ppos,
enum bpf_attach_type type)
{
struct bpf_sysctl_kern ctx = {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1110ecd7d1f3..8f50c9c19f1b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2913,7 +2913,6 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
return BPF_PROG_TYPE_CGROUP_SKB;
- break;
case BPF_CGROUP_INET_SOCK_CREATE:
case BPF_CGROUP_INET_SOCK_RELEASE:
case BPF_CGROUP_INET4_POST_BIND:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 39d7f44e7c92..6200519582a6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5133,24 +5133,19 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
regs[BPF_REG_0].id = ++env->id_gen;
} else {
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
- regs[BPF_REG_0].id = ++env->id_gen;
}
} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
- regs[BPF_REG_0].id = ++env->id_gen;
} else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
- regs[BPF_REG_0].id = ++env->id_gen;
} else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
- regs[BPF_REG_0].id = ++env->id_gen;
} else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
- regs[BPF_REG_0].id = ++env->id_gen;
regs[BPF_REG_0].mem_size = meta.mem_size;
} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
@@ -5199,6 +5194,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return -EINVAL;
}
+ if (reg_type_may_be_null(regs[BPF_REG_0].type))
+ regs[BPF_REG_0].id = ++env->id_gen;
+
if (is_ptr_cast_function(func_id)) {
/* For release_reference() */
regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
@@ -7212,7 +7210,8 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
struct bpf_reg_state *reg, u32 id,
bool is_null)
{
- if (reg_type_may_be_null(reg->type) && reg->id == id) {
+ if (reg_type_may_be_null(reg->type) && reg->id == id &&
+ !WARN_ON_ONCE(!reg->id)) {
/* Old offset (both fixed and variable parts) should
* have been known-zero, because we don't allow pointer
* arithmetic on pointers that might be NULL.
diff --git a/kernel/capability.c b/kernel/capability.c
index 7c59b096c98a..de7eac903a2a 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -418,7 +418,7 @@ EXPORT_SYMBOL(ns_capable_noaudit);
/**
* ns_capable_setid - Determine if the current task has a superior capability
* in effect, while signalling that this check is being done from within a
- * setid syscall.
+ * setid or setgroups syscall.
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 78b23f089cf1..905c3fa005f1 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -2,7 +2,7 @@
/*
* Copyright (c) 2014 The Linux Foundation
*/
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 0a1e20f8d4e8..2b8366693d5c 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -161,7 +161,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
arch_do_signal(regs);
if (ti_work & _TIF_NOTIFY_RESUME) {
- clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
rseq_handle_notify_resume(NULL, regs);
}
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index eb1a8a4c867c..b6678a5e3cf6 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -16,10 +16,8 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
if (ti_work & _TIF_NEED_RESCHED)
schedule();
- if (ti_work & _TIF_NOTIFY_RESUME) {
- clear_thread_flag(TIF_NOTIFY_RESUME);
+ if (ti_work & _TIF_NOTIFY_RESUME)
tracehook_notify_resume(NULL);
- }
ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
if (ret)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 0e18aaf23a7b..00b0358739ab 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1823,7 +1823,7 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
t->utask->dup_xol_addr = area->vaddr;
init_task_work(&t->utask->dup_xol_work, dup_xol_work);
- task_work_add(t, &t->utask->dup_xol_work, true);
+ task_work_add(t, &t->utask->dup_xol_work, TWA_RESUME);
}
/*
diff --git a/kernel/groups.c b/kernel/groups.c
index 6ee6691f6839..fe7e6385530e 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -178,7 +178,7 @@ bool may_setgroups(void)
{
struct user_namespace *user_ns = current_user_ns();
- return ns_capable(user_ns, CAP_SETGID) &&
+ return ns_capable_setid(user_ns, CAP_SETGID) &&
userns_may_setgroups(user_ns);
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 5df903fccb60..c460e0496006 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1162,7 +1162,7 @@ static int irq_thread(void *data)
handler_fn = irq_thread_fn;
init_task_work(&on_exit_work, irq_thread_dtor);
- task_work_add(current, &on_exit_work, false);
+ task_work_add(current, &on_exit_work, TWA_NONE);
irq_thread_check_affinity(desc, action);
diff --git a/kernel/module.c b/kernel/module.c
index 9d9f2400d94e..a4fa44a652a7 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -92,8 +92,9 @@ EXPORT_SYMBOL_GPL(module_mutex);
static LIST_HEAD(modules);
/* Work queue for freeing init sections in success case */
-static struct work_struct init_free_wq;
-static struct llist_head init_free_list;
+static void do_free_init(struct work_struct *w);
+static DECLARE_WORK(init_free_wq, do_free_init);
+static LLIST_HEAD(init_free_list);
#ifdef CONFIG_MODULES_TREE_LOOKUP
@@ -2097,8 +2098,11 @@ static int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
int i;
for (i = 0; i < hdr->e_shnum; i++) {
- if ((sechdrs[i].sh_flags & shf_wx) == shf_wx)
+ if ((sechdrs[i].sh_flags & shf_wx) == shf_wx) {
+ pr_err("%s: section %s (index %d) has invalid WRITE|EXEC flags\n",
+ mod->name, secstrings + sechdrs[i].sh_name, i);
return -ENOEXEC;
+ }
}
return 0;
@@ -3591,14 +3595,6 @@ static void do_free_init(struct work_struct *w)
}
}
-static int __init modules_wq_init(void)
-{
- INIT_WORK(&init_free_wq, do_free_init);
- init_llist_head(&init_free_list);
- return 0;
-}
-module_init(modules_wq_init);
-
/*
* This is where the real work happens.
*
@@ -3841,8 +3837,10 @@ static int load_module(struct load_info *info, const char __user *uargs,
char *after_dashes;
err = elf_header_check(info);
- if (err)
+ if (err) {
+ pr_err("Module has invalid ELF header\n");
goto free_copy;
+ }
err = setup_load_info(info, flags);
if (err)
@@ -3850,6 +3848,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
if (blacklisted(info->name)) {
err = -EPERM;
+ pr_err("Module %s is blacklisted\n", info->name);
goto free_copy;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8160ab5263f8..d2003a7d5ab5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -44,7 +44,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
+#ifdef CONFIG_SCHED_DEBUG
/*
* Debugging: various feature bits
*
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 5ae7b4e6e8d6..e254745a82cb 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -441,6 +441,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
unsigned long util, max;
unsigned int next_f;
bool busy;
+ unsigned int cached_freq = sg_policy->cached_raw_freq;
sugov_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
@@ -464,8 +465,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
if (busy && next_f < sg_policy->next_freq) {
next_f = sg_policy->next_freq;
- /* Reset cached freq as next_freq has changed */
- sg_policy->cached_raw_freq = 0;
+ /* Restore cached freq as next_freq has changed */
+ sg_policy->cached_raw_freq = cached_freq;
}
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aa4c6227cd6d..e17012be4d14 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2928,7 +2928,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
curr->node_stamp += period;
if (!time_before(jiffies, curr->mm->numa_next_scan))
- task_work_add(curr, work, true);
+ task_work_add(curr, work, TWA_RESUME);
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 28709f6b0975..df80bfcea92e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1471,7 +1471,7 @@ struct sched_group_capacity {
int id;
#endif
- unsigned long cpumask[0]; /* Balance mask */
+ unsigned long cpumask[]; /* Balance mask */
};
struct sched_group {
@@ -1629,7 +1629,7 @@ enum {
#undef SCHED_FEAT
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
+#ifdef CONFIG_SCHED_DEBUG
/*
* To support run-time toggling of sched features, all the translation units
@@ -1637,6 +1637,7 @@ enum {
*/
extern const_debug unsigned int sysctl_sched_features;
+#ifdef CONFIG_JUMP_LABEL
#define SCHED_FEAT(name, enabled) \
static __always_inline bool static_branch_##name(struct static_key *key) \
{ \
@@ -1649,7 +1650,13 @@ static __always_inline bool static_branch_##name(struct static_key *key) \
extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
-#else /* !(SCHED_DEBUG && CONFIG_JUMP_LABEL) */
+#else /* !CONFIG_JUMP_LABEL */
+
+#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
+
+#endif /* CONFIG_JUMP_LABEL */
+
+#else /* !SCHED_DEBUG */
/*
* Each translation unit has its own copy of sysctl_sched_features to allow
@@ -1665,7 +1672,7 @@ static const_debug __maybe_unused unsigned int sysctl_sched_features =
#define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
-#endif /* SCHED_DEBUG && CONFIG_JUMP_LABEL */
+#endif /* SCHED_DEBUG */
extern struct static_key_false sched_numa_balancing;
extern struct static_key_false sched_schedstats;
diff --git a/kernel/sys.c b/kernel/sys.c
index 6401880dff74..84594bcd886e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -373,7 +373,7 @@ long __sys_setregid(gid_t rgid, gid_t egid)
if (rgid != (gid_t) -1) {
if (gid_eq(old->gid, krgid) ||
gid_eq(old->egid, krgid) ||
- ns_capable(old->user_ns, CAP_SETGID))
+ ns_capable_setid(old->user_ns, CAP_SETGID))
new->gid = krgid;
else
goto error;
@@ -382,7 +382,7 @@ long __sys_setregid(gid_t rgid, gid_t egid)
if (gid_eq(old->gid, kegid) ||
gid_eq(old->egid, kegid) ||
gid_eq(old->sgid, kegid) ||
- ns_capable(old->user_ns, CAP_SETGID))
+ ns_capable_setid(old->user_ns, CAP_SETGID))
new->egid = kegid;
else
goto error;
@@ -432,7 +432,7 @@ long __sys_setgid(gid_t gid)
old = current_cred();
retval = -EPERM;
- if (ns_capable(old->user_ns, CAP_SETGID))
+ if (ns_capable_setid(old->user_ns, CAP_SETGID))
new->gid = new->egid = new->sgid = new->fsgid = kgid;
else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid))
new->egid = new->fsgid = kgid;
@@ -744,7 +744,7 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
old = current_cred();
retval = -EPERM;
- if (!ns_capable(old->user_ns, CAP_SETGID)) {
+ if (!ns_capable_setid(old->user_ns, CAP_SETGID)) {
if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) &&
!gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
goto error;
@@ -871,7 +871,7 @@ long __sys_setfsgid(gid_t gid)
if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) ||
gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) ||
- ns_capable(old->user_ns, CAP_SETGID)) {
+ ns_capable_setid(old->user_ns, CAP_SETGID)) {
if (!gid_eq(kgid, old->fsgid)) {
new->fsgid = kgid;
if (security_task_fix_setgid(new,old,LSM_SETID_FS) == 0)
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 613b2d634af8..8d6e1217c451 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -9,23 +9,28 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
* task_work_add - ask the @task to execute @work->func()
* @task: the task which should run the callback
* @work: the callback to run
- * @notify: send the notification if true
+ * @notify: how to notify the targeted task
*
- * Queue @work for task_work_run() below and notify the @task if @notify.
- * Fails if the @task is exiting/exited and thus it can't process this @work.
- * Otherwise @work->func() will be called when the @task returns from kernel
- * mode or exits.
+ * Queue @work for task_work_run() below and notify the @task if @notify
+ * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the
+ * it will interrupt the targeted task and run the task_work. @TWA_RESUME
+ * work is run only when the task exits the kernel and returns to user mode,
+ * or before entering guest mode. Fails if the @task is exiting/exited and thus
+ * it can't process this @work. Otherwise @work->func() will be called when the
+ * @task goes through one of the aforementioned transitions, or exits.
*
- * This is like the signal handler which runs in kernel mode, but it doesn't
- * try to wake up the @task.
+ * If the targeted task is exiting, then an error is returned and the work item
+ * is not queued. It's up to the caller to arrange for an alternative mechanism
+ * in that case.
*
- * Note: there is no ordering guarantee on works queued here.
+ * Note: there is no ordering guarantee on works queued here. The task_work
+ * list is LIFO.
*
* RETURNS:
* 0 if succeeds or -ESRCH.
*/
-int
-task_work_add(struct task_struct *task, struct callback_head *work, int notify)
+int task_work_add(struct task_struct *task, struct callback_head *work,
+ enum task_work_notify_mode notify)
{
struct callback_head *head;
unsigned long flags;
@@ -38,6 +43,8 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
} while (cmpxchg(&task->task_works, head, work) != head);
switch (notify) {
+ case TWA_NONE:
+ break;
case TWA_RESUME:
set_notify_resume(task);
break;
@@ -54,6 +61,9 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
unlock_task_sighand(task, &flags);
}
break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
}
return 0;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index dda05f4b7a1f..de37e33a868d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1706,6 +1706,8 @@ void update_process_times(int user_tick)
{
struct task_struct *p = current;
+ PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0);
+
/* Note: this timer irq context must be accounted for as well. */
account_process_tick(p, user_tick);
run_local_timers();
@@ -1717,13 +1719,6 @@ void update_process_times(int user_tick)
scheduler_tick();
if (IS_ENABLED(CONFIG_POSIX_TIMERS))
run_posix_cpu_timers();
-
- /* The current CPU might make use of net randoms without receiving IRQs
- * to renew them often enough. Let's update the net_rand_state from a
- * non-constant value that's not affine to the number of calls to make
- * sure it's updated when there's some activity (we don't care in idle).
- */
- this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
}
/**
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 15bf28b13e50..7f45fd9d5a45 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -793,7 +793,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
* ring_buffer_wait - wait for input to the ring buffer
* @buffer: buffer to wait on
* @cpu: the cpu buffer to wait on
- * @full: wait until a full page is available, if @cpu != RING_BUFFER_ALL_CPUS
+ * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS
*
* If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
* as data is added to any of the @buffer's cpu buffers. Otherwise
@@ -1952,18 +1952,18 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
{
struct ring_buffer_per_cpu *cpu_buffer;
unsigned long nr_pages;
- int cpu, err = 0;
+ int cpu, err;
/*
* Always succeed at resizing a non-existent buffer:
*/
if (!buffer)
- return size;
+ return 0;
/* Make sure the requested buffer exists */
if (cpu_id != RING_BUFFER_ALL_CPUS &&
!cpumask_test_cpu(cpu_id, buffer->cpumask))
- return size;
+ return 0;
nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
@@ -2119,7 +2119,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
}
mutex_unlock(&buffer->mutex);
- return size;
+ return 0;
out_err:
for_each_buffer_cpu(buffer, cpu) {
generated by cgit (git 2.34.1) at 2024-06-09 15:22:13 +0000