summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile4
-rw-r--r--kernel/bpf/stackmap.c3
-rw-r--r--kernel/bpf/verifier.c41
-rw-r--r--kernel/events/callchain.c36
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/events/uprobes.c7
-rw-r--r--kernel/exit.c32
-rw-r--r--kernel/fork.c23
-rw-r--r--kernel/gcov/Kconfig1
-rw-r--r--kernel/irq/ipi.c2
-rw-r--r--kernel/kexec.c109
-rw-r--r--kernel/kexec_core.c9
-rw-r--r--kernel/kexec_file.c8
-rw-r--r--kernel/locking/percpu-rwsem.c1
-rw-r--r--kernel/locking/rwsem.c16
-rw-r--r--kernel/pid.c2
-rw-r--r--kernel/relay.c1
-rw-r--r--kernel/sched/core.c18
-rw-r--r--kernel/sched/cpufreq_schedutil.c4
-rw-r--r--kernel/sched/idle.c2
-rw-r--r--kernel/signal.c10
-rw-r--r--kernel/sys.c3
-rw-r--r--kernel/sysctl.c11
-rw-r--r--kernel/time/hrtimer.c1
-rw-r--r--kernel/trace/bpf_trace.c14
25 files changed, 213 insertions, 147 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index f0c40bf49d9f..e2ec54e2b952 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -91,9 +91,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
obj-$(CONFIG_LATENCYTOP) += latencytop.o
-obj-$(CONFIG_BINFMT_ELF) += elfcore.o
-obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o
-obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o
+obj-$(CONFIG_ELFCORE) += elfcore.o
obj-$(CONFIG_FUNCTION_TRACER) += trace/
obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_TRACE_CLOCK) += trace/
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index c8ee35287bfe..080a2dfb5800 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -136,7 +136,8 @@ u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
return -EINVAL;
- trace = get_perf_callchain(regs, init_nr, kernel, user, false, false);
+ trace = get_perf_callchain(regs, init_nr, kernel, user,
+ sysctl_perf_event_max_stack, false, false);
if (unlikely(!trace))
/* couldn't fetch the stack trace */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 668e07903c8f..eec9f90ba030 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -126,31 +126,6 @@
* are set to NOT_INIT to indicate that they are no longer readable.
*/
-/* types of values stored in eBPF registers */
-enum bpf_reg_type {
- NOT_INIT = 0, /* nothing was written into register */
- UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */
- PTR_TO_CTX, /* reg points to bpf_context */
- CONST_PTR_TO_MAP, /* reg points to struct bpf_map */
- PTR_TO_MAP_VALUE, /* reg points to map element value */
- PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
- FRAME_PTR, /* reg == frame_pointer */
- PTR_TO_STACK, /* reg == frame_pointer + imm */
- CONST_IMM, /* constant integer value */
-
- /* PTR_TO_PACKET represents:
- * skb->data
- * skb->data + imm
- * skb->data + (u16) var
- * skb->data + (u16) var + imm
- * if (range > 0) then [ptr, ptr + range - off) is safe to access
- * if (id > 0) means that some 'var' was added
- * if (off > 0) menas that 'imm' was added
- */
- PTR_TO_PACKET,
- PTR_TO_PACKET_END, /* skb->data + headlen */
-};
-
struct reg_state {
enum bpf_reg_type type;
union {
@@ -695,10 +670,10 @@ static int check_packet_access(struct verifier_env *env, u32 regno, int off,
/* check access to 'struct bpf_context' fields */
static int check_ctx_access(struct verifier_env *env, int off, int size,
- enum bpf_access_type t)
+ enum bpf_access_type t, enum bpf_reg_type *reg_type)
{
if (env->prog->aux->ops->is_valid_access &&
- env->prog->aux->ops->is_valid_access(off, size, t)) {
+ env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) {
/* remember the offset of last byte accessed in ctx */
if (env->prog->aux->max_ctx_offset < off + size)
env->prog->aux->max_ctx_offset = off + size;
@@ -798,21 +773,19 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
mark_reg_unknown_value(state->regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
+ enum bpf_reg_type reg_type = UNKNOWN_VALUE;
+
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose("R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
- err = check_ctx_access(env, off, size, t);
+ err = check_ctx_access(env, off, size, t, &reg_type);
if (!err && t == BPF_READ && value_regno >= 0) {
mark_reg_unknown_value(state->regs, value_regno);
- if (off == offsetof(struct __sk_buff, data) &&
- env->allow_ptr_leaks)
+ if (env->allow_ptr_leaks)
/* note that reg.[id|off|range] == 0 */
- state->regs[value_regno].type = PTR_TO_PACKET;
- else if (off == offsetof(struct __sk_buff, data_end) &&
- env->allow_ptr_leaks)
- state->regs[value_regno].type = PTR_TO_PACKET_END;
+ state->regs[value_regno].type = reg_type;
}
} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index b9325e7dcba1..179ef4640964 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -19,11 +19,13 @@ struct callchain_cpus_entries {
};
int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK;
static inline size_t perf_callchain_entry__sizeof(void)
{
return (sizeof(struct perf_callchain_entry) +
- sizeof(__u64) * sysctl_perf_event_max_stack);
+ sizeof(__u64) * (sysctl_perf_event_max_stack +
+ sysctl_perf_event_max_contexts_per_stack));
}
static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
@@ -32,12 +34,12 @@ static DEFINE_MUTEX(callchain_mutex);
static struct callchain_cpus_entries *callchain_cpus_entries;
-__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+__weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
-__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+__weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
@@ -176,14 +178,15 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
if (!kernel && !user)
return NULL;
- return get_perf_callchain(regs, 0, kernel, user, crosstask, true);
+ return get_perf_callchain(regs, 0, kernel, user, sysctl_perf_event_max_stack, crosstask, true);
}
struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
- bool crosstask, bool add_mark)
+ u32 max_stack, bool crosstask, bool add_mark)
{
struct perf_callchain_entry *entry;
+ struct perf_callchain_entry_ctx ctx;
int rctx;
entry = get_callchain_entry(&rctx);
@@ -193,12 +196,16 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
if (!entry)
goto exit_put;
- entry->nr = init_nr;
+ ctx.entry = entry;
+ ctx.max_stack = max_stack;
+ ctx.nr = entry->nr = init_nr;
+ ctx.contexts = 0;
+ ctx.contexts_maxed = false;
if (kernel && !user_mode(regs)) {
if (add_mark)
- perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
- perf_callchain_kernel(entry, regs);
+ perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL);
+ perf_callchain_kernel(&ctx, regs);
}
if (user) {
@@ -214,8 +221,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
goto exit_put;
if (add_mark)
- perf_callchain_store(entry, PERF_CONTEXT_USER);
- perf_callchain_user(entry, regs);
+ perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
+ perf_callchain_user(&ctx, regs);
}
}
@@ -225,10 +232,15 @@ exit_put:
return entry;
}
+/*
+ * Used for sysctl_perf_event_max_stack and
+ * sysctl_perf_event_max_contexts_per_stack.
+ */
int perf_event_max_stack_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- int new_value = sysctl_perf_event_max_stack, ret;
+ int *value = table->data;
+ int new_value = *value, ret;
struct ctl_table new_table = *table;
new_table.data = &new_value;
@@ -240,7 +252,7 @@ int perf_event_max_stack_handler(struct ctl_table *table, int write,
if (atomic_read(&nr_callchain_events))
ret = -EBUSY;
else
- sysctl_perf_event_max_stack = new_value;
+ *value = new_value;
mutex_unlock(&callchain_mutex);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 274450efea90..d00c47b67a97 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7531,7 +7531,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
prog = event->tp_event->prog;
if (prog) {
event->tp_event->prog = NULL;
- bpf_prog_put(prog);
+ bpf_prog_put_rcu(prog);
}
}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index c01f733ff2e1..b7a525ab2083 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1130,7 +1130,9 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
struct vm_area_struct *vma;
int ret;
- down_write(&mm->mmap_sem);
+ if (down_write_killable(&mm->mmap_sem))
+ return -EINTR;
+
if (mm->uprobes_state.xol_area) {
ret = -EALREADY;
goto fail;
@@ -1469,7 +1471,8 @@ static void dup_xol_work(struct callback_head *work)
if (current->flags & PF_EXITING)
return;
- if (!__create_xol_area(current->utask->dup_xol_addr))
+ if (!__create_xol_area(current->utask->dup_xol_addr) &&
+ !fatal_signal_pending(current))
uprobe_warn(current, "dup xol area");
}
diff --git a/kernel/exit.c b/kernel/exit.c
index 75b34fe835b2..9e6e1356e6bb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -918,17 +918,28 @@ static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
task_pid_type(p, wo->wo_type) == wo->wo_pid;
}
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int
+eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p)
{
if (!eligible_pid(wo, p))
return 0;
- /* Wait for all children (clone and not) if __WALL is set;
- * otherwise, wait for clone children *only* if __WCLONE is
- * set; otherwise, wait for non-clone children *only*. (Note:
- * A "clone" child here is one that reports to its parent
- * using a signal other than SIGCHLD.) */
- if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
- && !(wo->wo_flags & __WALL))
+
+ /*
+ * Wait for all children (clone and not) if __WALL is set or
+ * if it is traced by us.
+ */
+ if (ptrace || (wo->wo_flags & __WALL))
+ return 1;
+
+ /*
+ * Otherwise, wait for clone children *only* if __WCLONE is set;
+ * otherwise, wait for non-clone children *only*.
+ *
+ * Note: a "clone" child here is one that reports to its parent
+ * using a signal other than SIGCHLD, or a non-leader thread which
+ * we can only see if it is traced by us.
+ */
+ if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
return 0;
return 1;
@@ -1300,7 +1311,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
if (unlikely(exit_state == EXIT_DEAD))
return 0;
- ret = eligible_child(wo, p);
+ ret = eligible_child(wo, ptrace, p);
if (!ret)
return ret;
@@ -1524,7 +1535,8 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
enum pid_type type;
long ret;
- if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED))
+ if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
+ __WNOTHREAD|__WCLONE|__WALL))
return -EINVAL;
if (!(options & (WEXITED|WSTOPPED|WCONTINUED)))
return -EINVAL;
diff --git a/kernel/fork.c b/kernel/fork.c
index 103d78fd8f75..5c2c355aa97f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -340,13 +340,14 @@ void set_task_stack_end_magic(struct task_struct *tsk)
*stackend = STACK_END_MAGIC; /* for overflow detection */
}
-static struct task_struct *dup_task_struct(struct task_struct *orig)
+static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
struct thread_info *ti;
- int node = tsk_fork_get_node(orig);
int err;
+ if (node == NUMA_NO_NODE)
+ node = tsk_fork_get_node(orig);
tsk = alloc_task_struct_node(node);
if (!tsk)
return NULL;
@@ -413,7 +414,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
unsigned long charge;
uprobe_start_dup_mmap();
- down_write(&oldmm->mmap_sem);
+ if (down_write_killable(&oldmm->mmap_sem)) {
+ retval = -EINTR;
+ goto fail_uprobe_end;
+ }
flush_cache_dup_mm(oldmm);
uprobe_dup_mmap(oldmm, mm);
/*
@@ -525,6 +529,7 @@ out:
up_write(&mm->mmap_sem);
flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
+fail_uprobe_end:
uprobe_end_dup_mmap();
return retval;
fail_nomem_anon_vma_fork:
@@ -731,6 +736,7 @@ void mmput(struct mm_struct *mm)
}
EXPORT_SYMBOL_GPL(mmput);
+#ifdef CONFIG_MMU
static void mmput_async_fn(struct work_struct *work)
{
struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
@@ -744,6 +750,7 @@ void mmput_async(struct mm_struct *mm)
schedule_work(&mm->async_put_work);
}
}
+#endif
/**
* set_mm_exe_file - change a reference to the mm's executable file
@@ -1276,7 +1283,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
int __user *child_tidptr,
struct pid *pid,
int trace,
- unsigned long tls)
+ unsigned long tls,
+ int node)
{
int retval;
struct task_struct *p;
@@ -1328,7 +1336,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto fork_out;
retval = -ENOMEM;
- p = dup_task_struct(current);
+ p = dup_task_struct(current, node);
if (!p)
goto fork_out;
@@ -1706,7 +1714,8 @@ static inline void init_idle_pids(struct pid_link *links)
struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
- task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0);
+ task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+ cpu_to_node(cpu));
if (!IS_ERR(task)) {
init_idle_pids(task->pids);
init_idle(task, cpu);
@@ -1751,7 +1760,7 @@ long _do_fork(unsigned long clone_flags,
}
p = copy_process(clone_flags, stack_start, stack_size,
- child_tidptr, NULL, trace, tls);
+ child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index c92e44855ddd..1276aabaab55 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -37,6 +37,7 @@ config ARCH_HAS_GCOV_PROFILE_ALL
config GCOV_PROFILE_ALL
bool "Profile entire Kernel"
+ depends on !COMPILE_TEST
depends on GCOV_KERNEL
depends on ARCH_HAS_GCOV_PROFILE_ALL
default n
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index c42742208e5e..89b49f6773f0 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -125,7 +125,7 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest)
domain = data->domain;
if (WARN_ON(domain == NULL))
- return;
+ return -EINVAL;
if (!irq_domain_is_ipi(domain)) {
pr_warn("Trying to destroy a non IPI domain!\n");
diff --git a/kernel/kexec.c b/kernel/kexec.c
index ee70aef5cd81..4384672d3245 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -103,6 +103,65 @@ out_free_image:
return ret;
}
+static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
+ struct kexec_segment __user *segments, unsigned long flags)
+{
+ struct kimage **dest_image, *image;
+ unsigned long i;
+ int ret;
+
+ if (flags & KEXEC_ON_CRASH) {
+ dest_image = &kexec_crash_image;
+ if (kexec_crash_image)
+ arch_kexec_unprotect_crashkres();
+ } else {
+ dest_image = &kexec_image;
+ }
+
+ if (nr_segments == 0) {
+ /* Uninstall image */
+ kimage_free(xchg(dest_image, NULL));
+ return 0;
+ }
+ if (flags & KEXEC_ON_CRASH) {
+ /*
+ * Loading another kernel to switch to if this one
+ * crashes. Free any current crash dump kernel before
+ * we corrupt it.
+ */
+ kimage_free(xchg(&kexec_crash_image, NULL));
+ }
+
+ ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags);
+ if (ret)
+ return ret;
+
+ if (flags & KEXEC_PRESERVE_CONTEXT)
+ image->preserve_context = 1;
+
+ ret = machine_kexec_prepare(image);
+ if (ret)
+ goto out;
+
+ for (i = 0; i < nr_segments; i++) {
+ ret = kimage_load_segment(image, &image->segment[i]);
+ if (ret)
+ goto out;
+ }
+
+ kimage_terminate(image);
+
+ /* Install the new kernel and uninstall the old */
+ image = xchg(dest_image, image);
+
+out:
+ if ((flags & KEXEC_ON_CRASH) && kexec_crash_image)
+ arch_kexec_protect_crashkres();
+
+ kimage_free(image);
+ return ret;
+}
+
/*
* Exec Kernel system call: for obvious reasons only root may call it.
*
@@ -127,7 +186,6 @@ out_free_image:
SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
struct kexec_segment __user *, segments, unsigned long, flags)
{
- struct kimage **dest_image, *image;
int result;
/* We only trust the superuser with rebooting the system. */
@@ -152,9 +210,6 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
if (nr_segments > KEXEC_SEGMENT_MAX)
return -EINVAL;
- image = NULL;
- result = 0;
-
/* Because we write directly to the reserved memory
* region when loading crash kernels we need a mutex here to
* prevent multiple crash kernels from attempting to load
@@ -166,53 +221,9 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
if (!mutex_trylock(&kexec_mutex))
return -EBUSY;
- dest_image = &kexec_image;
- if (flags & KEXEC_ON_CRASH)
- dest_image = &kexec_crash_image;
- if (nr_segments > 0) {
- unsigned long i;
-
- if (flags & KEXEC_ON_CRASH) {
- /*
- * Loading another kernel to switch to if this one
- * crashes. Free any current crash dump kernel before
- * we corrupt it.
- */
-
- kimage_free(xchg(&kexec_crash_image, NULL));
- result = kimage_alloc_init(&image, entry, nr_segments,
- segments, flags);
- crash_map_reserved_pages();
- } else {
- /* Loading another kernel to reboot into. */
-
- result = kimage_alloc_init(&image, entry, nr_segments,
- segments, flags);
- }
- if (result)
- goto out;
-
- if (flags & KEXEC_PRESERVE_CONTEXT)
- image->preserve_context = 1;
- result = machine_kexec_prepare(image);
- if (result)
- goto out;
-
- for (i = 0; i < nr_segments; i++) {
- result = kimage_load_segment(image, &image->segment[i]);
- if (result)
- goto out;
- }
- kimage_terminate(image);
- if (flags & KEXEC_ON_CRASH)
- crash_unmap_reserved_pages();
- }
- /* Install the new kernel, and Uninstall the old */
- image = xchg(dest_image, image);
+ result = do_kexec_load(entry, nr_segments, segments, flags);
-out:
mutex_unlock(&kexec_mutex);
- kimage_free(image);
return result;
}
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index d5d408252992..56b3ed0927b0 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -954,7 +954,6 @@ int crash_shrink_memory(unsigned long new_size)
start = roundup(start, KEXEC_CRASH_MEM_ALIGN);
end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN);
- crash_map_reserved_pages();
crash_free_reserved_phys_range(end, crashk_res.end);
if ((start == end) && (crashk_res.parent != NULL))
@@ -968,7 +967,6 @@ int crash_shrink_memory(unsigned long new_size)
crashk_res.end = end - 1;
insert_resource(&iomem_resource, ram_res);
- crash_unmap_reserved_pages();
unlock:
mutex_unlock(&kexec_mutex);
@@ -1553,13 +1551,14 @@ int kernel_kexec(void)
}
/*
- * Add and remove page tables for crashkernel memory
+ * Protection mechanism for crashkernel reserved memory after
+ * the kdump kernel is loaded.
*
* Provide an empty default implementation here -- architecture
* code may override this
*/
-void __weak crash_map_reserved_pages(void)
+void __weak arch_kexec_protect_crashkres(void)
{}
-void __weak crash_unmap_reserved_pages(void)
+void __weak arch_kexec_unprotect_crashkres(void)
{}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index c72d2ff5896e..503bc2d348e5 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -274,8 +274,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
return -EBUSY;
dest_image = &kexec_image;
- if (flags & KEXEC_FILE_ON_CRASH)
+ if (flags & KEXEC_FILE_ON_CRASH) {
dest_image = &kexec_crash_image;
+ if (kexec_crash_image)
+ arch_kexec_unprotect_crashkres();
+ }
if (flags & KEXEC_FILE_UNLOAD)
goto exchange;
@@ -324,6 +327,9 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
exchange:
image = xchg(dest_image, image);
out:
+ if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
+ arch_kexec_protect_crashkres();
+
mutex_unlock(&kexec_mutex);
kimage_free(image);
return ret;
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index f231e0bb311c..bec0b647f9cc 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -37,6 +37,7 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
free_percpu(brw->fast_read_ctr);
brw->fast_read_ctr = NULL; /* catch use after free bugs */
}
+EXPORT_SYMBOL_GPL(percpu_free_rwsem);
/*
* This is the fast-path for down_read/up_read. If it succeeds we rely
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index c817216c1615..2e853ad93a3a 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -173,6 +173,22 @@ void down_write_nested(struct rw_semaphore *sem, int subclass)
EXPORT_SYMBOL(down_write_nested);
+int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
+{
+ might_sleep();
+ rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
+
+ if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
+ rwsem_release(&sem->dep_map, 1, _RET_IP_);
+ return -EINTR;
+ }
+
+ rwsem_set_owner(sem);
+ return 0;
+}
+
+EXPORT_SYMBOL(down_write_killable_nested);
+
void up_read_non_owner(struct rw_semaphore *sem)
{
__up_read(sem);
diff --git a/kernel/pid.c b/kernel/pid.c
index 4d73a834c7e6..f66162f2359b 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -311,7 +311,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
pid->level = ns->level;
for (i = ns->level; i >= 0; i--) {
nr = alloc_pidmap(tmp);
- if (IS_ERR_VALUE(nr)) {
+ if (nr < 0) {
retval = nr;
goto out_free;
}
diff --git a/kernel/relay.c b/kernel/relay.c
index 074994bcfa9b..04d7cf3ef8cf 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -614,6 +614,7 @@ free_bufs:
kref_put(&chan->kref, relay_destroy_channel);
mutex_unlock(&relay_channels_mutex);
+ kfree(chan);
return NULL;
}
EXPORT_SYMBOL_GPL(relay_open);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 404c0784b1fc..7f2cae4620c7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1768,13 +1768,15 @@ void sched_ttwu_pending(void)
cookie = lockdep_pin_lock(&rq->lock);
while (llist) {
+ int wake_flags = 0;
+
p = llist_entry(llist, struct task_struct, wake_entry);
llist = llist_next(llist);
- /*
- * See ttwu_queue(); we only call ttwu_queue_remote() when
- * its a x-cpu wakeup.
- */
- ttwu_do_activate(rq, p, WF_MIGRATED, cookie);
+
+ if (p->sched_remote_wakeup)
+ wake_flags = WF_MIGRATED;
+
+ ttwu_do_activate(rq, p, wake_flags, cookie);
}
lockdep_unpin_lock(&rq->lock, cookie);
@@ -1819,10 +1821,12 @@ void scheduler_ipi(void)
irq_exit();
}
-static void ttwu_queue_remote(struct task_struct *p, int cpu)
+static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq = cpu_rq(cpu);
+ p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
+
if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
if (!set_nr_if_polling(rq->idle))
smp_send_reschedule(cpu);
@@ -1869,7 +1873,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
#if defined(CONFIG_SMP)
if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
sched_clock_cpu(cpu); /* sync clocks x-cpu */
- ttwu_queue_remote(p, cpu);
+ ttwu_queue_remote(p, cpu, wake_flags);
return;
}
#endif
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 154ae3a51e86..14c4aa25cc45 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -9,6 +9,8 @@
* published by the Free Software Foundation.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/cpufreq.h>
#include <linux/module.h>
#include <linux/slab.h>
@@ -388,7 +390,7 @@ static int sugov_init(struct cpufreq_policy *policy)
mutex_unlock(&global_tunables_lock);
sugov_policy_free(sg_policy);
- pr_err("cpufreq: schedutil governor initialization failed (error %d)\n", ret);
+ pr_err("initialization failed (error %d)\n", ret);
return ret;
}
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index bd12c6c714ec..c5aeedf4e93a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -127,7 +127,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
*/
static void cpuidle_idle_call(void)
{
- struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+ struct cpuidle_device *dev = cpuidle_get_device();
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
diff --git a/kernel/signal.c b/kernel/signal.c
index ab122a2cee41..96e9bc40667f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -224,7 +224,7 @@ static inline void print_dropped_signal(int sig)
if (!__ratelimit(&ratelimit_state))
return;
- printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n",
+ pr_info("%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n",
current->comm, current->pid, sig);
}
@@ -1089,10 +1089,10 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
static void print_fatal_signal(int signr)
{
struct pt_regs *regs = signal_pt_regs();
- printk(KERN_INFO "potentially unexpected fatal signal %d.\n", signr);
+ pr_info("potentially unexpected fatal signal %d.\n", signr);
#if defined(__i386__) && !defined(__arch_um__)
- printk(KERN_INFO "code at %08lx: ", regs->ip);
+ pr_info("code at %08lx: ", regs->ip);
{
int i;
for (i = 0; i < 16; i++) {
@@ -1100,10 +1100,10 @@ static void print_fatal_signal(int signr)
if (get_user(insn, (unsigned char *)(regs->ip + i)))
break;
- printk(KERN_CONT "%02x ", insn);
+ pr_cont("%02x ", insn);
}
}
- printk(KERN_CONT "\n");
+ pr_cont("\n");
#endif
preempt_disable();
show_regs(regs);
diff --git a/kernel/sys.c b/kernel/sys.c
index cf8ba545c7d3..89d5be418157 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2246,7 +2246,8 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_SET_THP_DISABLE:
if (arg3 || arg4 || arg5)
return -EINVAL;
- down_write(&me->mm->mmap_sem);
+ if (down_write_killable(&me->mm->mmap_sem))
+ return -EINTR;
if (arg2)
me->mm->def_flags |= VM_NOHUGEPAGE;
else
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2effd84d83e3..87b2fc38398b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1149,13 +1149,22 @@ static struct ctl_table kern_table[] = {
},
{
.procname = "perf_event_max_stack",
- .data = NULL, /* filled in by handler */
+ .data = &sysctl_perf_event_max_stack,
.maxlen = sizeof(sysctl_perf_event_max_stack),
.mode = 0644,
.proc_handler = perf_event_max_stack_handler,
.extra1 = &zero,
.extra2 = &six_hundred_forty_kb,
},
+ {
+ .procname = "perf_event_max_contexts_per_stack",
+ .data = &sysctl_perf_event_max_contexts_per_stack,
+ .maxlen = sizeof(sysctl_perf_event_max_contexts_per_stack),
+ .mode = 0644,
+ .proc_handler = perf_event_max_stack_handler,
+ .extra1 = &zero,
+ .extra2 = &one_thousand,
+ },
#endif
#ifdef CONFIG_KMEMCHECK
{
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 8c7392c4fdbd..e99df0ff1d42 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -425,6 +425,7 @@ void destroy_hrtimer_on_stack(struct hrtimer *timer)
{
debug_object_free(timer, &hrtimer_debug_descr);
}
+EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack);
#else
static inline void debug_hrtimer_init(struct hrtimer *timer) { }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 780bcbe1d4de..26f603da7e26 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -198,7 +198,7 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
- file = (struct file *)array->ptrs[index];
+ file = READ_ONCE(array->ptrs[index]);
if (unlikely(!file))
return -ENOENT;
@@ -209,6 +209,10 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
event->pmu->count)
return -EINVAL;
+ if (unlikely(event->attr.type != PERF_TYPE_HARDWARE &&
+ event->attr.type != PERF_TYPE_RAW))
+ return -EINVAL;
+
/*
* we don't know if the function is run successfully by the
* return value. It can be judged in other places, such as
@@ -247,7 +251,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
- file = (struct file *)array->ptrs[index];
+ file = READ_ONCE(array->ptrs[index]);
if (unlikely(!file))
return -ENOENT;
@@ -349,7 +353,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
}
/* bpf+kprobe programs can access fields of 'struct pt_regs' */
-static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
{
/* check bounds */
if (off < 0 || off >= sizeof(struct pt_regs))
@@ -427,7 +432,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
}
}
-static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
{
if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
return false;
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-20 00:13:28 +0000