summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/bpf/core.c9
-rw-r--r--kernel/bpf/inode.c2
-rw-r--r--kernel/bpf/syscall.c3
-rw-r--r--kernel/crash_core.c439
-rw-r--r--kernel/fork.c25
-rw-r--r--kernel/groups.c2
-rw-r--r--kernel/hung_task.c8
-rw-r--r--kernel/irq/manage.c15
-rw-r--r--kernel/kcov.c9
-rw-r--r--kernel/kexec_core.c431
-rw-r--r--kernel/kprobes.c32
-rw-r--r--kernel/ksysfs.c8
-rw-r--r--kernel/module.c5
-rw-r--r--kernel/pid.c4
-rw-r--r--kernel/pid_namespace.c34
-rw-r--r--kernel/power/snapshot.c3
-rw-r--r--kernel/printk/braille.c15
-rw-r--r--kernel/printk/braille.h13
-rw-r--r--kernel/printk/printk.c30
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/sys.c3
-rw-r--r--kernel/sysctl.c2
-rw-r--r--kernel/taskstats.c14
-rw-r--r--kernel/time/posix-cpu-timers.c2
-rw-r--r--kernel/trace/ftrace.c20
-rw-r--r--kernel/trace/trace.c2
-rw-r--r--kernel/trace/trace_entries.h6
-rw-r--r--kernel/trace/trace_hwlat.c14
-rw-r--r--kernel/trace/trace_output.c9
30 files changed, 645 insertions, 517 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index b302b4731d16..72aa080f91f0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_MODULE_SIG) += module_signing.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
+obj-$(CONFIG_CRASH_CORE) += crash_core.o
obj-$(CONFIG_KEXEC_CORE) += kexec_core.o
obj-$(CONFIG_KEXEC) += kexec.o
obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 6f81e0f5a0fa..dedf367f59bb 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -76,8 +76,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
- gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog_aux *aux;
struct bpf_prog *fp;
@@ -107,8 +106,7 @@ EXPORT_SYMBOL_GPL(bpf_prog_alloc);
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
- gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
u32 pages, delta;
int ret;
@@ -655,8 +653,7 @@ out:
static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,
gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
- gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index fddcae801724..9bbd33497d3d 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -429,7 +429,7 @@ static int bpf_parse_options(char *data, struct bpf_mount_opts *opts)
static int bpf_fill_super(struct super_block *sb, void *data, int silent)
{
- static struct tree_descr bpf_rfiles[] = { { "" } };
+ static const struct tree_descr bpf_rfiles[] = { { "" } };
struct bpf_mount_opts opts;
struct inode *inode;
int ret;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 13642c73dca0..fd2411fd6914 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -67,8 +67,7 @@ void *bpf_map_area_alloc(size_t size)
return area;
}
- return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags,
- PAGE_KERNEL);
+ return __vmalloc(size, GFP_KERNEL | flags, PAGE_KERNEL);
}
void bpf_map_area_free(void *area)
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
new file mode 100644
index 000000000000..fcbd568f1e95
--- /dev/null
+++ b/kernel/crash_core.c
@@ -0,0 +1,439 @@
+/*
+ * crash.c - kernel crash support code.
+ * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com>
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ */
+
+#include <linux/crash_core.h>
+#include <linux/utsname.h>
+#include <linux/vmalloc.h>
+
+#include <asm/page.h>
+#include <asm/sections.h>
+
+/* vmcoreinfo stuff */
+static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
+u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+size_t vmcoreinfo_size;
+size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+
+/*
+ * parsing the "crashkernel" commandline
+ *
+ * this code is intended to be called from architecture specific code
+ */
+
+
+/*
+ * This function parses command lines in the format
+ *
+ * crashkernel=ramsize-range:size[,...][@offset]
+ *
+ * The function returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_mem(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ char *cur = cmdline, *tmp;
+
+ /* for each entry of the comma-separated list */
+ do {
+ unsigned long long start, end = ULLONG_MAX, size;
+
+ /* get the start of the range */
+ start = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("crashkernel: Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (*cur != '-') {
+ pr_warn("crashkernel: '-' expected\n");
+ return -EINVAL;
+ }
+ cur++;
+
+ /* if no ':' is here, than we read the end */
+ if (*cur != ':') {
+ end = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("crashkernel: Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (end <= start) {
+ pr_warn("crashkernel: end <= start\n");
+ return -EINVAL;
+ }
+ }
+
+ if (*cur != ':') {
+ pr_warn("crashkernel: ':' expected\n");
+ return -EINVAL;
+ }
+ cur++;
+
+ size = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (size >= system_ram) {
+ pr_warn("crashkernel: invalid size\n");
+ return -EINVAL;
+ }
+
+ /* match ? */
+ if (system_ram >= start && system_ram < end) {
+ *crash_size = size;
+ break;
+ }
+ } while (*cur++ == ',');
+
+ if (*crash_size > 0) {
+ while (*cur && *cur != ' ' && *cur != '@')
+ cur++;
+ if (*cur == '@') {
+ cur++;
+ *crash_base = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("Memory value expected after '@'\n");
+ return -EINVAL;
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * That function parses "simple" (old) crashkernel command lines like
+ *
+ * crashkernel=size[@offset]
+ *
+ * It returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_simple(char *cmdline,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ char *cur = cmdline;
+
+ *crash_size = memparse(cmdline, &cur);
+ if (cmdline == cur) {
+ pr_warn("crashkernel: memory value expected\n");
+ return -EINVAL;
+ }
+
+ if (*cur == '@')
+ *crash_base = memparse(cur+1, &cur);
+ else if (*cur != ' ' && *cur != '\0') {
+ pr_warn("crashkernel: unrecognized char: %c\n", *cur);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+#define SUFFIX_HIGH 0
+#define SUFFIX_LOW 1
+#define SUFFIX_NULL 2
+static __initdata char *suffix_tbl[] = {
+ [SUFFIX_HIGH] = ",high",
+ [SUFFIX_LOW] = ",low",
+ [SUFFIX_NULL] = NULL,
+};
+
+/*
+ * That function parses "suffix" crashkernel command lines like
+ *
+ * crashkernel=size,[high|low]
+ *
+ * It returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_suffix(char *cmdline,
+ unsigned long long *crash_size,
+ const char *suffix)
+{
+ char *cur = cmdline;
+
+ *crash_size = memparse(cmdline, &cur);
+ if (cmdline == cur) {
+ pr_warn("crashkernel: memory value expected\n");
+ return -EINVAL;
+ }
+
+ /* check with suffix */
+ if (strncmp(cur, suffix, strlen(suffix))) {
+ pr_warn("crashkernel: unrecognized char: %c\n", *cur);
+ return -EINVAL;
+ }
+ cur += strlen(suffix);
+ if (*cur != ' ' && *cur != '\0') {
+ pr_warn("crashkernel: unrecognized char: %c\n", *cur);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static __init char *get_last_crashkernel(char *cmdline,
+ const char *name,
+ const char *suffix)
+{
+ char *p = cmdline, *ck_cmdline = NULL;
+
+ /* find crashkernel and use the last one if there are more */
+ p = strstr(p, name);
+ while (p) {
+ char *end_p = strchr(p, ' ');
+ char *q;
+
+ if (!end_p)
+ end_p = p + strlen(p);
+
+ if (!suffix) {
+ int i;
+
+ /* skip the one with any known suffix */
+ for (i = 0; suffix_tbl[i]; i++) {
+ q = end_p - strlen(suffix_tbl[i]);
+ if (!strncmp(q, suffix_tbl[i],
+ strlen(suffix_tbl[i])))
+ goto next;
+ }
+ ck_cmdline = p;
+ } else {
+ q = end_p - strlen(suffix);
+ if (!strncmp(q, suffix, strlen(suffix)))
+ ck_cmdline = p;
+ }
+next:
+ p = strstr(p+1, name);
+ }
+
+ if (!ck_cmdline)
+ return NULL;
+
+ return ck_cmdline;
+}
+
+static int __init __parse_crashkernel(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base,
+ const char *name,
+ const char *suffix)
+{
+ char *first_colon, *first_space;
+ char *ck_cmdline;
+
+ BUG_ON(!crash_size || !crash_base);
+ *crash_size = 0;
+ *crash_base = 0;
+
+ ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
+
+ if (!ck_cmdline)
+ return -EINVAL;
+
+ ck_cmdline += strlen(name);
+
+ if (suffix)
+ return parse_crashkernel_suffix(ck_cmdline, crash_size,
+ suffix);
+ /*
+ * if the commandline contains a ':', then that's the extended
+ * syntax -- if not, it must be the classic syntax
+ */
+ first_colon = strchr(ck_cmdline, ':');
+ first_space = strchr(ck_cmdline, ' ');
+ if (first_colon && (!first_space || first_colon < first_space))
+ return parse_crashkernel_mem(ck_cmdline, system_ram,
+ crash_size, crash_base);
+
+ return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
+}
+
+/*
+ * That function is the entry point for command line parsing and should be
+ * called from the arch-specific code.
+ */
+int __init parse_crashkernel(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", NULL);
+}
+
+int __init parse_crashkernel_high(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", suffix_tbl[SUFFIX_HIGH]);
+}
+
+int __init parse_crashkernel_low(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", suffix_tbl[SUFFIX_LOW]);
+}
+
+Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
+ void *data, size_t data_len)
+{
+ struct elf_note *note = (struct elf_note *)buf;
+
+ note->n_namesz = strlen(name) + 1;
+ note->n_descsz = data_len;
+ note->n_type = type;
+ buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word));
+ memcpy(buf, name, note->n_namesz);
+ buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word));
+ memcpy(buf, data, data_len);
+ buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word));
+
+ return buf;
+}
+
+void final_note(Elf_Word *buf)
+{
+ memset(buf, 0, sizeof(struct elf_note));
+}
+
+static void update_vmcoreinfo_note(void)
+{
+ u32 *buf = vmcoreinfo_note;
+
+ if (!vmcoreinfo_size)
+ return;
+ buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
+ vmcoreinfo_size);
+ final_note(buf);
+}
+
+void crash_save_vmcoreinfo(void)
+{
+ vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
+ update_vmcoreinfo_note();
+}
+
+void vmcoreinfo_append_str(const char *fmt, ...)
+{
+ va_list args;
+ char buf[0x50];
+ size_t r;
+
+ va_start(args, fmt);
+ r = vscnprintf(buf, sizeof(buf), fmt, args);
+ va_end(args);
+
+ r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+
+ memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
+
+ vmcoreinfo_size += r;
+}
+
+/*
+ * provide an empty default implementation here -- architecture
+ * code may override this
+ */
+void __weak arch_crash_save_vmcoreinfo(void)
+{}
+
+phys_addr_t __weak paddr_vmcoreinfo_note(void)
+{
+ return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+}
+
+static int __init crash_save_vmcoreinfo_init(void)
+{
+ VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+ VMCOREINFO_PAGESIZE(PAGE_SIZE);
+
+ VMCOREINFO_SYMBOL(init_uts_ns);
+ VMCOREINFO_SYMBOL(node_online_map);
+#ifdef CONFIG_MMU
+ VMCOREINFO_SYMBOL(swapper_pg_dir);
+#endif
+ VMCOREINFO_SYMBOL(_stext);
+ VMCOREINFO_SYMBOL(vmap_area_list);
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+ VMCOREINFO_SYMBOL(mem_map);
+ VMCOREINFO_SYMBOL(contig_page_data);
+#endif
+#ifdef CONFIG_SPARSEMEM
+ VMCOREINFO_SYMBOL(mem_section);
+ VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
+ VMCOREINFO_STRUCT_SIZE(mem_section);
+ VMCOREINFO_OFFSET(mem_section, section_mem_map);
+#endif
+ VMCOREINFO_STRUCT_SIZE(page);
+ VMCOREINFO_STRUCT_SIZE(pglist_data);
+ VMCOREINFO_STRUCT_SIZE(zone);
+ VMCOREINFO_STRUCT_SIZE(free_area);
+ VMCOREINFO_STRUCT_SIZE(list_head);
+ VMCOREINFO_SIZE(nodemask_t);
+ VMCOREINFO_OFFSET(page, flags);
+ VMCOREINFO_OFFSET(page, _refcount);
+ VMCOREINFO_OFFSET(page, mapping);
+ VMCOREINFO_OFFSET(page, lru);
+ VMCOREINFO_OFFSET(page, _mapcount);
+ VMCOREINFO_OFFSET(page, private);
+ VMCOREINFO_OFFSET(page, compound_dtor);
+ VMCOREINFO_OFFSET(page, compound_order);
+ VMCOREINFO_OFFSET(page, compound_head);
+ VMCOREINFO_OFFSET(pglist_data, node_zones);
+ VMCOREINFO_OFFSET(pglist_data, nr_zones);
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+ VMCOREINFO_OFFSET(pglist_data, node_mem_map);
+#endif
+ VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
+ VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
+ VMCOREINFO_OFFSET(pglist_data, node_id);
+ VMCOREINFO_OFFSET(zone, free_area);
+ VMCOREINFO_OFFSET(zone, vm_stat);
+ VMCOREINFO_OFFSET(zone, spanned_pages);
+ VMCOREINFO_OFFSET(free_area, free_list);
+ VMCOREINFO_OFFSET(list_head, next);
+ VMCOREINFO_OFFSET(list_head, prev);
+ VMCOREINFO_OFFSET(vmap_area, va_start);
+ VMCOREINFO_OFFSET(vmap_area, list);
+ VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
+ log_buf_vmcoreinfo_setup();
+ VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
+ VMCOREINFO_NUMBER(NR_FREE_PAGES);
+ VMCOREINFO_NUMBER(PG_lru);
+ VMCOREINFO_NUMBER(PG_private);
+ VMCOREINFO_NUMBER(PG_swapcache);
+ VMCOREINFO_NUMBER(PG_slab);
+#ifdef CONFIG_MEMORY_FAILURE
+ VMCOREINFO_NUMBER(PG_hwpoison);
+#endif
+ VMCOREINFO_NUMBER(PG_head_mask);
+ VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
+#ifdef CONFIG_HUGETLB_PAGE
+ VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
+#endif
+
+ arch_crash_save_vmcoreinfo();
+ update_vmcoreinfo_note();
+
+ return 0;
+}
+
+subsys_initcall(crash_save_vmcoreinfo_init);
diff --git a/kernel/fork.c b/kernel/fork.c
index dd5a371c392a..08ba696aa561 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -179,6 +179,24 @@ void __weak arch_release_thread_stack(unsigned long *stack)
*/
#define NR_CACHED_STACKS 2
static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
+
+static int free_vm_stack_cache(unsigned int cpu)
+{
+ struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
+ int i;
+
+ for (i = 0; i < NR_CACHED_STACKS; i++) {
+ struct vm_struct *vm_stack = cached_vm_stacks[i];
+
+ if (!vm_stack)
+ continue;
+
+ vfree(vm_stack->addr);
+ cached_vm_stacks[i] = NULL;
+ }
+
+ return 0;
+}
#endif
static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
@@ -203,7 +221,7 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
VMALLOC_START, VMALLOC_END,
- THREADINFO_GFP | __GFP_HIGHMEM,
+ THREADINFO_GFP,
PAGE_KERNEL,
0, node, __builtin_return_address(0));
@@ -467,6 +485,11 @@ void __init fork_init(void)
for (i = 0; i < UCOUNT_COUNTS; i++) {
init_user_ns.ucount_max[i] = max_threads/2;
}
+
+#ifdef CONFIG_VMAP_STACK
+ cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
+ NULL, free_vm_stack_cache);
+#endif
}
int __weak arch_dup_task_struct(struct task_struct *dst,
diff --git a/kernel/groups.c b/kernel/groups.c
index 8dd7a61b7115..d09727692a2a 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -18,7 +18,7 @@ struct group_info *groups_alloc(int gidsetsize)
len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize;
gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY);
if (!gi)
- gi = __vmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_HIGHMEM, PAGE_KERNEL);
+ gi = __vmalloc(len, GFP_KERNEL_ACCOUNT, PAGE_KERNEL);
if (!gi)
return NULL;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index f0f8e2a8496f..751593ed7c0b 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -43,6 +43,7 @@ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_
int __read_mostly sysctl_hung_task_warnings = 10;
static int __read_mostly did_panic;
+static bool hung_task_show_lock;
static struct task_struct *watchdog_task;
@@ -120,12 +121,14 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
" disables this message.\n");
sched_show_task(t);
- debug_show_all_locks();
+ hung_task_show_lock = true;
}
touch_nmi_watchdog();
if (sysctl_hung_task_panic) {
+ if (hung_task_show_lock)
+ debug_show_all_locks();
trigger_all_cpu_backtrace();
panic("hung_task: blocked tasks");
}
@@ -172,6 +175,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
if (test_taint(TAINT_DIE) || did_panic)
return;
+ hung_task_show_lock = false;
rcu_read_lock();
for_each_process_thread(g, t) {
if (!max_count--)
@@ -187,6 +191,8 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
}
unlock:
rcu_read_unlock();
+ if (hung_task_show_lock)
+ debug_show_all_locks();
}
static long hung_timeout_jiffies(unsigned long last_checked,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ae1c90f20381..070be980c37a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1559,7 +1559,7 @@ void remove_irq(unsigned int irq, struct irqaction *act)
struct irq_desc *desc = irq_to_desc(irq);
if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
- __free_irq(irq, act->dev_id);
+ __free_irq(irq, act->dev_id);
}
EXPORT_SYMBOL_GPL(remove_irq);
@@ -1576,20 +1576,27 @@ EXPORT_SYMBOL_GPL(remove_irq);
* have completed.
*
* This function must not be called from interrupt context.
+ *
+ * Returns the devname argument passed to request_irq.
*/
-void free_irq(unsigned int irq, void *dev_id)
+const void *free_irq(unsigned int irq, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
+ struct irqaction *action;
+ const char *devname;
if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
- return;
+ return NULL;
#ifdef CONFIG_SMP
if (WARN_ON(desc->affinity_notify))
desc->affinity_notify = NULL;
#endif
- kfree(__free_irq(irq, dev_id));
+ action = __free_irq(irq, dev_id);
+ devname = action->name;
+ kfree(action);
+ return devname;
}
EXPORT_SYMBOL(free_irq);
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 85e5546cd791..cd771993f96f 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -60,15 +60,8 @@ void notrace __sanitizer_cov_trace_pc(void)
/*
* We are interested in code coverage as a function of a syscall inputs,
* so we ignore code executed in interrupts.
- * The checks for whether we are in an interrupt are open-coded, because
- * 1. We can't use in_interrupt() here, since it also returns true
- * when we are inside local_bh_disable() section.
- * 2. We don't want to use (in_irq() | in_serving_softirq() | in_nmi()),
- * since that leads to slower generated code (three separate tests,
- * one for each of the flags).
*/
- if (!t || (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET
- | NMI_MASK)))
+ if (!t || !in_task())
return;
mode = READ_ONCE(t->kcov_mode);
if (mode == KCOV_MODE_TRACE) {
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index bfe62d5b3872..ae1a3ba24df5 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -51,12 +51,6 @@ DEFINE_MUTEX(kexec_mutex);
/* Per cpu memory for storing cpu states in case of system crash. */
note_buf_t __percpu *crash_notes;
-/* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
-size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
-
/* Flag to indicate we are going to kexec a new kernel */
bool kexec_in_progress = false;
@@ -996,34 +990,6 @@ unlock:
return ret;
}
-static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
- size_t data_len)
-{
- struct elf_note note;
-
- note.n_namesz = strlen(name) + 1;
- note.n_descsz = data_len;
- note.n_type = type;
- memcpy(buf, &note, sizeof(note));
- buf += (sizeof(note) + 3)/4;
- memcpy(buf, name, note.n_namesz);
- buf += (note.n_namesz + 3)/4;
- memcpy(buf, data, note.n_descsz);
- buf += (note.n_descsz + 3)/4;
-
- return buf;
-}
-
-static void final_note(u32 *buf)
-{
- struct elf_note note;
-
- note.n_namesz = 0;
- note.n_descsz = 0;
- note.n_type = 0;
- memcpy(buf, &note, sizeof(note));
-}
-
void crash_save_cpu(struct pt_regs *regs, int cpu)
{
struct elf_prstatus prstatus;
@@ -1085,403 +1051,6 @@ subsys_initcall(crash_notes_memory_init);
/*
- * parsing the "crashkernel" commandline
- *
- * this code is intended to be called from architecture specific code
- */
-
-
-/*
- * This function parses command lines in the format
- *
- * crashkernel=ramsize-range:size[,...][@offset]
- *
- * The function returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_mem(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- char *cur = cmdline, *tmp;
-
- /* for each entry of the comma-separated list */
- do {
- unsigned long long start, end = ULLONG_MAX, size;
-
- /* get the start of the range */
- start = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("crashkernel: Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (*cur != '-') {
- pr_warn("crashkernel: '-' expected\n");
- return -EINVAL;
- }
- cur++;
-
- /* if no ':' is here, than we read the end */
- if (*cur != ':') {
- end = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("crashkernel: Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (end <= start) {
- pr_warn("crashkernel: end <= start\n");
- return -EINVAL;
- }
- }
-
- if (*cur != ':') {
- pr_warn("crashkernel: ':' expected\n");
- return -EINVAL;
- }
- cur++;
-
- size = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (size >= system_ram) {
- pr_warn("crashkernel: invalid size\n");
- return -EINVAL;
- }
-
- /* match ? */
- if (system_ram >= start && system_ram < end) {
- *crash_size = size;
- break;
- }
- } while (*cur++ == ',');
-
- if (*crash_size > 0) {
- while (*cur && *cur != ' ' && *cur != '@')
- cur++;
- if (*cur == '@') {
- cur++;
- *crash_base = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("Memory value expected after '@'\n");
- return -EINVAL;
- }
- }
- }
-
- return 0;
-}
-
-/*
- * That function parses "simple" (old) crashkernel command lines like
- *
- * crashkernel=size[@offset]
- *
- * It returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_simple(char *cmdline,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- char *cur = cmdline;
-
- *crash_size = memparse(cmdline, &cur);
- if (cmdline == cur) {
- pr_warn("crashkernel: memory value expected\n");
- return -EINVAL;
- }
-
- if (*cur == '@')
- *crash_base = memparse(cur+1, &cur);
- else if (*cur != ' ' && *cur != '\0') {
- pr_warn("crashkernel: unrecognized char: %c\n", *cur);
- return -EINVAL;
- }
-
- return 0;
-}
-
-#define SUFFIX_HIGH 0
-#define SUFFIX_LOW 1
-#define SUFFIX_NULL 2
-static __initdata char *suffix_tbl[] = {
- [SUFFIX_HIGH] = ",high",
- [SUFFIX_LOW] = ",low",
- [SUFFIX_NULL] = NULL,
-};
-
-/*
- * That function parses "suffix" crashkernel command lines like
- *
- * crashkernel=size,[high|low]
- *
- * It returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_suffix(char *cmdline,
- unsigned long long *crash_size,
- const char *suffix)
-{
- char *cur = cmdline;
-
- *crash_size = memparse(cmdline, &cur);
- if (cmdline == cur) {
- pr_warn("crashkernel: memory value expected\n");
- return -EINVAL;
- }
-
- /* check with suffix */
- if (strncmp(cur, suffix, strlen(suffix))) {
- pr_warn("crashkernel: unrecognized char: %c\n", *cur);
- return -EINVAL;
- }
- cur += strlen(suffix);
- if (*cur != ' ' && *cur != '\0') {
- pr_warn("crashkernel: unrecognized char: %c\n", *cur);
- return -EINVAL;
- }
-
- return 0;
-}
-
-static __init char *get_last_crashkernel(char *cmdline,
- const char *name,
- const char *suffix)
-{
- char *p = cmdline, *ck_cmdline = NULL;
-
- /* find crashkernel and use the last one if there are more */
- p = strstr(p, name);
- while (p) {
- char *end_p = strchr(p, ' ');
- char *q;
-
- if (!end_p)
- end_p = p + strlen(p);
-
- if (!suffix) {
- int i;
-
- /* skip the one with any known suffix */
- for (i = 0; suffix_tbl[i]; i++) {
- q = end_p - strlen(suffix_tbl[i]);
- if (!strncmp(q, suffix_tbl[i],
- strlen(suffix_tbl[i])))
- goto next;
- }
- ck_cmdline = p;
- } else {
- q = end_p - strlen(suffix);
- if (!strncmp(q, suffix, strlen(suffix)))
- ck_cmdline = p;
- }
-next:
- p = strstr(p+1, name);
- }
-
- if (!ck_cmdline)
- return NULL;
-
- return ck_cmdline;
-}
-
-static int __init __parse_crashkernel(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base,
- const char *name,
- const char *suffix)
-{
- char *first_colon, *first_space;
- char *ck_cmdline;
-
- BUG_ON(!crash_size || !crash_base);
- *crash_size = 0;
- *crash_base = 0;
-
- ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
-
- if (!ck_cmdline)
- return -EINVAL;
-
- ck_cmdline += strlen(name);
-
- if (suffix)
- return parse_crashkernel_suffix(ck_cmdline, crash_size,
- suffix);
- /*
- * if the commandline contains a ':', then that's the extended
- * syntax -- if not, it must be the classic syntax
- */
- first_colon = strchr(ck_cmdline, ':');
- first_space = strchr(ck_cmdline, ' ');
- if (first_colon && (!first_space || first_colon < first_space))
- return parse_crashkernel_mem(ck_cmdline, system_ram,
- crash_size, crash_base);
-
- return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
-}
-
-/*
- * That function is the entry point for command line parsing and should be
- * called from the arch-specific code.
- */
-int __init parse_crashkernel(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", NULL);
-}
-
-int __init parse_crashkernel_high(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", suffix_tbl[SUFFIX_HIGH]);
-}
-
-int __init parse_crashkernel_low(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
-{
- return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
- "crashkernel=", suffix_tbl[SUFFIX_LOW]);
-}
-
-static void update_vmcoreinfo_note(void)
-{
- u32 *buf = vmcoreinfo_note;
-
- if (!vmcoreinfo_size)
- return;
- buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
- vmcoreinfo_size);
- final_note(buf);
-}
-
-void crash_save_vmcoreinfo(void)
-{
- vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
- update_vmcoreinfo_note();
-}
-
-void vmcoreinfo_append_str(const char *fmt, ...)
-{
- va_list args;
- char buf[0x50];
- size_t r;
-
- va_start(args, fmt);
- r = vscnprintf(buf, sizeof(buf), fmt, args);
- va_end(args);
-
- r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
-
- memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
-
- vmcoreinfo_size += r;
-}
-
-/*
- * provide an empty default implementation here -- architecture
- * code may override this
- */
-void __weak arch_crash_save_vmcoreinfo(void)
-{}
-
-phys_addr_t __weak paddr_vmcoreinfo_note(void)
-{
- return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
-}
-
-static int __init crash_save_vmcoreinfo_init(void)
-{
- VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
- VMCOREINFO_PAGESIZE(PAGE_SIZE);
-
- VMCOREINFO_SYMBOL(init_uts_ns);
- VMCOREINFO_SYMBOL(node_online_map);
-#ifdef CONFIG_MMU
- VMCOREINFO_SYMBOL(swapper_pg_dir);
-#endif
- VMCOREINFO_SYMBOL(_stext);
- VMCOREINFO_SYMBOL(vmap_area_list);
-
-#ifndef CONFIG_NEED_MULTIPLE_NODES
- VMCOREINFO_SYMBOL(mem_map);
- VMCOREINFO_SYMBOL(contig_page_data);
-#endif
-#ifdef CONFIG_SPARSEMEM
- VMCOREINFO_SYMBOL(mem_section);
- VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
- VMCOREINFO_STRUCT_SIZE(mem_section);
- VMCOREINFO_OFFSET(mem_section, section_mem_map);
-#endif
- VMCOREINFO_STRUCT_SIZE(page);
- VMCOREINFO_STRUCT_SIZE(pglist_data);
- VMCOREINFO_STRUCT_SIZE(zone);
- VMCOREINFO_STRUCT_SIZE(free_area);
- VMCOREINFO_STRUCT_SIZE(list_head);
- VMCOREINFO_SIZE(nodemask_t);
- VMCOREINFO_OFFSET(page, flags);
- VMCOREINFO_OFFSET(page, _refcount);
- VMCOREINFO_OFFSET(page, mapping);
- VMCOREINFO_OFFSET(page, lru);
- VMCOREINFO_OFFSET(page, _mapcount);
- VMCOREINFO_OFFSET(page, private);
- VMCOREINFO_OFFSET(page, compound_dtor);
- VMCOREINFO_OFFSET(page, compound_order);
- VMCOREINFO_OFFSET(page, compound_head);
- VMCOREINFO_OFFSET(pglist_data, node_zones);
- VMCOREINFO_OFFSET(pglist_data, nr_zones);
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
- VMCOREINFO_OFFSET(pglist_data, node_mem_map);
-#endif
- VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
- VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
- VMCOREINFO_OFFSET(pglist_data, node_id);
- VMCOREINFO_OFFSET(zone, free_area);
- VMCOREINFO_OFFSET(zone, vm_stat);
- VMCOREINFO_OFFSET(zone, spanned_pages);
- VMCOREINFO_OFFSET(free_area, free_list);
- VMCOREINFO_OFFSET(list_head, next);
- VMCOREINFO_OFFSET(list_head, prev);
- VMCOREINFO_OFFSET(vmap_area, va_start);
- VMCOREINFO_OFFSET(vmap_area, list);
- VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
- log_buf_kexec_setup();
- VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
- VMCOREINFO_NUMBER(NR_FREE_PAGES);
- VMCOREINFO_NUMBER(PG_lru);
- VMCOREINFO_NUMBER(PG_private);
- VMCOREINFO_NUMBER(PG_swapcache);
- VMCOREINFO_NUMBER(PG_slab);
-#ifdef CONFIG_MEMORY_FAILURE
- VMCOREINFO_NUMBER(PG_hwpoison);
-#endif
- VMCOREINFO_NUMBER(PG_head_mask);
- VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
-#ifdef CONFIG_HUGETLB_PAGE
- VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
-#endif
-
- arch_crash_save_vmcoreinfo();
- update_vmcoreinfo_note();
-
- return 0;
-}
-
-subsys_initcall(crash_save_vmcoreinfo_init);
-
-/*
* Move into place and start executing a preloaded standalone
* executable. If nothing was preloaded return an error.
*/
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d733479a10ee..7367e0ec6f81 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -58,15 +58,6 @@
#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
-/*
- * Some oddball architectures like 64bit powerpc have function descriptors
- * so this must be overridable.
- */
-#ifndef kprobe_lookup_name
-#define kprobe_lookup_name(name, addr) \
- addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name)))
-#endif
-
static int kprobes_initialized;
static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
@@ -81,6 +72,12 @@ static struct {
raw_spinlock_t lock ____cacheline_aligned_in_smp;
} kretprobe_table_locks[KPROBE_TABLE_SIZE];
+kprobe_opcode_t * __weak kprobe_lookup_name(const char *name,
+ unsigned int __unused)
+{
+ return ((kprobe_opcode_t *)(kallsyms_lookup_name(name)));
+}
+
static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
{
return &(kretprobe_table_locks[hash].lock);
@@ -746,13 +743,20 @@ static void kill_optimized_kprobe(struct kprobe *p)
arch_remove_optimized_kprobe(op);
}
+static inline
+void __prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
+{
+ if (!kprobe_ftrace(p))
+ arch_prepare_optimized_kprobe(op, p);
+}
+
/* Try to prepare optimized instructions */
static void prepare_optimized_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
- arch_prepare_optimized_kprobe(op, p);
+ __prepare_optimized_kprobe(op, p);
}
/* Allocate new optimized_kprobe and try to prepare optimized instructions */
@@ -766,7 +770,7 @@ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
INIT_LIST_HEAD(&op->list);
op->kp.addr = p->addr;
- arch_prepare_optimized_kprobe(op, p);
+ __prepare_optimized_kprobe(op, p);
return &op->kp;
}
@@ -1398,7 +1402,7 @@ static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr,
goto invalid;
if (symbol_name) {
- kprobe_lookup_name(symbol_name, addr);
+ addr = kprobe_lookup_name(symbol_name, offset);
if (!addr)
return ERR_PTR(-ENOENT);
}
@@ -2218,8 +2222,8 @@ static int __init init_kprobes(void)
if (kretprobe_blacklist_size) {
/* lookup the function address from its name */
for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
- kprobe_lookup_name(kretprobe_blacklist[i].name,
- kretprobe_blacklist[i].addr);
+ kretprobe_blacklist[i].addr =
+ kprobe_lookup_name(kretprobe_blacklist[i].name, 0);
if (!kretprobe_blacklist[i].addr)
printk("kretprobe: lookup failed: %s\n",
kretprobe_blacklist[i].name);
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 0999679d6f26..23cd70651238 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -125,6 +125,10 @@ static ssize_t kexec_crash_size_store(struct kobject *kobj,
}
KERNEL_ATTR_RW(kexec_crash_size);
+#endif /* CONFIG_KEXEC_CORE */
+
+#ifdef CONFIG_CRASH_CORE
+
static ssize_t vmcoreinfo_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
@@ -134,7 +138,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
}
KERNEL_ATTR_RO(vmcoreinfo);
-#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_CRASH_CORE */
/* whether file capabilities are enabled */
static ssize_t fscaps_show(struct kobject *kobj,
@@ -219,6 +223,8 @@ static struct attribute * kernel_attrs[] = {
&kexec_loaded_attr.attr,
&kexec_crash_loaded_attr.attr,
&kexec_crash_size_attr.attr,
+#endif
+#ifdef CONFIG_CRASH_CORE
&vmcoreinfo_attr.attr,
#endif
#ifndef CONFIG_TINY_RCU
diff --git a/kernel/module.c b/kernel/module.c
index f37308b733d8..4a3665f8f837 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -49,6 +49,9 @@
#include <linux/rculist.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
+#ifdef CONFIG_STRICT_MODULE_RWX
+#include <asm/set_memory.h>
+#endif
#include <asm/mmu_context.h>
#include <linux/license.h>
#include <asm/sections.h>
@@ -2864,7 +2867,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
/* Suck in entire file: we'll want most of it. */
info->hdr = __vmalloc(info->len,
- GFP_KERNEL | __GFP_HIGHMEM | __GFP_NOWARN, PAGE_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN, PAGE_KERNEL);
if (!info->hdr)
return -ENOMEM;
diff --git a/kernel/pid.c b/kernel/pid.c
index 0143ac0ddceb..fd1cde1e4576 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -321,8 +321,10 @@ struct pid *alloc_pid(struct pid_namespace *ns)
}
if (unlikely(is_child_reaper(pid))) {
- if (pid_ns_prepare_proc(ns))
+ if (pid_ns_prepare_proc(ns)) {
+ disable_pid_allocation(ns);
goto out_free;
+ }
}
get_pid_ns(ns);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index de461aa0bf9a..d1f3e9f558b8 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -374,6 +374,29 @@ static struct ns_common *pidns_get(struct task_struct *task)
return ns ? &ns->ns : NULL;
}
+static struct ns_common *pidns_for_children_get(struct task_struct *task)
+{
+ struct pid_namespace *ns = NULL;
+
+ task_lock(task);
+ if (task->nsproxy) {
+ ns = task->nsproxy->pid_ns_for_children;
+ get_pid_ns(ns);
+ }
+ task_unlock(task);
+
+ if (ns) {
+ read_lock(&tasklist_lock);
+ if (!ns->child_reaper) {
+ put_pid_ns(ns);
+ ns = NULL;
+ }
+ read_unlock(&tasklist_lock);
+ }
+
+ return ns ? &ns->ns : NULL;
+}
+
static void pidns_put(struct ns_common *ns)
{
put_pid_ns(to_pid_ns(ns));
@@ -443,6 +466,17 @@ const struct proc_ns_operations pidns_operations = {
.get_parent = pidns_get_parent,
};
+const struct proc_ns_operations pidns_for_children_operations = {
+ .name = "pid_for_children",
+ .real_ns_name = "pid",
+ .type = CLONE_NEWPID,
+ .get = pidns_for_children_get,
+ .put = pidns_put,
+ .install = pidns_install,
+ .owner = pidns_owner,
+ .get_parent = pidns_get_parent,
+};
+
static __init int pid_namespaces_init(void)
{
pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index d79a38de425a..3b1e0f3ad07f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -36,6 +36,9 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
+#ifdef CONFIG_STRICT_KERNEL_RWX
+#include <asm/set_memory.h>
+#endif
#include "power.h"
diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c
index d5760c42f042..61d41ca41844 100644
--- a/kernel/printk/braille.c
+++ b/kernel/printk/braille.c
@@ -2,12 +2,13 @@
#include <linux/kernel.h>
#include <linux/console.h>
+#include <linux/errno.h>
#include <linux/string.h>
#include "console_cmdline.h"
#include "braille.h"
-char *_braille_console_setup(char **str, char **brl_options)
+int _braille_console_setup(char **str, char **brl_options)
{
if (!strncmp(*str, "brl,", 4)) {
*brl_options = "";
@@ -15,14 +16,14 @@ char *_braille_console_setup(char **str, char **brl_options)
} else if (!strncmp(*str, "brl=", 4)) {
*brl_options = *str + 4;
*str = strchr(*brl_options, ',');
- if (!*str)
+ if (!*str) {
pr_err("need port name after brl=\n");
- else
- *((*str)++) = 0;
- } else
- return NULL;
+ return -EINVAL;
+ }
+ *((*str)++) = 0;
+ }
- return *str;
+ return 0;
}
int
diff --git a/kernel/printk/braille.h b/kernel/printk/braille.h
index 769d771145c8..749a6756843a 100644
--- a/kernel/printk/braille.h
+++ b/kernel/printk/braille.h
@@ -9,7 +9,14 @@ braille_set_options(struct console_cmdline *c, char *brl_options)
c->brl_options = brl_options;
}
-char *
+/*
+ * Setup console according to braille options.
+ * Return -EINVAL on syntax error, 0 on success (or no braille option was
+ * actually given).
+ * Modifies str to point to the serial options
+ * Sets brl_options to the parsed braille options.
+ */
+int
_braille_console_setup(char **str, char **brl_options);
int
@@ -25,10 +32,10 @@ braille_set_options(struct console_cmdline *c, char *brl_options)
{
}
-static inline char *
+static inline int
_braille_console_setup(char **str, char **brl_options)
{
- return NULL;
+ return 0;
}
static inline int
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 779479ac9f57..a1aecf44ab07 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -32,7 +32,7 @@
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/syscalls.h>
-#include <linux/kexec.h>
+#include <linux/crash_core.h>
#include <linux/kdb.h>
#include <linux/ratelimit.h>
#include <linux/kmsg_dump.h>
@@ -1002,7 +1002,7 @@ const struct file_operations kmsg_fops = {
.release = devkmsg_release,
};
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_CORE
/*
* This appends the listed symbols to /proc/vmcore
*
@@ -1011,7 +1011,7 @@ const struct file_operations kmsg_fops = {
* symbols are specifically used so that utilities can access and extract the
* dmesg log from a vmcore file after a crash.
*/
-void log_buf_kexec_setup(void)
+void log_buf_vmcoreinfo_setup(void)
{
VMCOREINFO_SYMBOL(log_buf);
VMCOREINFO_SYMBOL(log_buf_len);
@@ -2642,6 +2642,30 @@ int unregister_console(struct console *console)
EXPORT_SYMBOL(unregister_console);
/*
+ * Initialize the console device. This is called *early*, so
+ * we can't necessarily depend on lots of kernel help here.
+ * Just do some early initializations, and do the complex setup
+ * later.
+ */
+void __init console_init(void)
+{
+ initcall_t *call;
+
+ /* Setup the default TTY line discipline. */
+ n_tty_init();
+
+ /*
+ * set up the console device so that later boot sequences can
+ * inform about problems etc..
+ */
+ call = __con_initcall_start;
+ while (call < __con_initcall_end) {
+ (*call)();
+ call++;
+ }
+}
+
+/*
* Some boot consoles access data that is in the init section and which will
* be discarded after the initcalls have been run. To make sure that no code
* will access this data, unregister the boot consoles in a late initcall.
diff --git a/kernel/signal.c b/kernel/signal.c
index 7e59ebc2c25e..a8c54f384553 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1318,7 +1318,7 @@ int kill_pid_info(int sig, struct siginfo *info, struct pid *pid)
}
}
-int kill_proc_info(int sig, struct siginfo *info, pid_t pid)
+static int kill_proc_info(int sig, struct siginfo *info, pid_t pid)
{
int error;
rcu_read_lock();
diff --git a/kernel/sys.c b/kernel/sys.c
index 196c7134bee6..8a94b4eabcaa 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1396,8 +1396,7 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource,
!capable(CAP_SYS_RESOURCE))
retval = -EPERM;
if (!retval)
- retval = security_task_setrlimit(tsk->group_leader,
- resource, new_rlim);
+ retval = security_task_setrlimit(tsk, resource, new_rlim);
if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) {
/*
* The caller is asking for an immediate RLIMIT_CPU
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 21343d110296..4dfba1a76cc3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2576,7 +2576,7 @@ static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
int write, void *data)
{
if (write) {
- if (*lvalp > LONG_MAX / HZ)
+ if (*lvalp > INT_MAX / HZ)
return 1;
*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
} else {
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 8a5e44236f78..4559e914452b 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -30,6 +30,7 @@
#include <linux/pid_namespace.h>
#include <net/genetlink.h>
#include <linux/atomic.h>
+#include <linux/sched/cputime.h>
/*
* Maximum length of a cpumask that can be specified in
@@ -210,6 +211,8 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
struct task_struct *tsk, *first;
unsigned long flags;
int rc = -ESRCH;
+ u64 delta, utime, stime;
+ u64 start_time;
/*
* Add additional stats from live tasks except zombie thread group
@@ -227,6 +230,7 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
memset(stats, 0, sizeof(*stats));
tsk = first;
+ start_time = ktime_get_ns();
do {
if (tsk->exit_state)
continue;
@@ -238,6 +242,16 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
*/
delayacct_add_tsk(stats, tsk);
+ /* calculate task elapsed time in nsec */
+ delta = start_time - tsk->start_time;
+ /* Convert to micro seconds */
+ do_div(delta, NSEC_PER_USEC);
+ stats->ac_etime += delta;
+
+ task_cputime(tsk, &utime, &stime);
+ stats->ac_utime += div_u64(utime, NSEC_PER_USEC);
+ stats->ac_stime += div_u64(stime, NSEC_PER_USEC);
+
stats->nvcsw += tsk->nvcsw;
stats->nivcsw += tsk->nivcsw;
} while_each_thread(first, tsk);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 949e434d3536..1370f067fb51 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1318,7 +1318,7 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
*/
if (CPUCLOCK_PERTHREAD(which_clock) &&
(CPUCLOCK_PID(which_clock) == 0 ||
- CPUCLOCK_PID(which_clock) == current->pid))
+ CPUCLOCK_PID(which_clock) == task_pid_vnr(current)))
return -EINVAL;
error = do_cpu_nanosleep(which_clock, flags, rqtp, &it);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 00077a57b746..39dca4e86a94 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3631,22 +3631,20 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
/* blank module name to match all modules */
if (!mod_g->len) {
/* blank module globbing: modname xor exclude_mod */
- if ((!exclude_mod) != (!modname))
+ if (!exclude_mod != !modname)
goto func_match;
return 0;
}
- /* not matching the module */
- if (!modname || !mod_matches) {
- if (exclude_mod)
- goto func_match;
- else
- return 0;
- }
-
- if (mod_matches && exclude_mod)
+ /*
+ * exclude_mod is set to trace everything but the given
+ * module. If it is set and the module matches, then
+ * return 0. If it is not set, and the module doesn't match
+ * also return 0. Otherwise, check the function to see if
+ * that matches.
+ */
+ if (!mod_matches == !exclude_mod)
return 0;
-
func_match:
/* blank search means to match all funcs in the mod */
if (!func_g->len)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 80eda7d254ed..4ad4420b33d6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1976,7 +1976,7 @@ static void __trace_find_cmdline(int pid, char comm[])
map = savedcmd->map_pid_to_cmdline[pid];
if (map != NO_CMDLINE_MAP)
- strcpy(comm, get_saved_cmdlines(map));
+ strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
else
strcpy(comm, "<...>");
}
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index c203ac4df791..adcdbbeae010 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -348,14 +348,14 @@ FTRACE_ENTRY(hwlat, hwlat_entry,
__field( u64, duration )
__field( u64, outer_duration )
__field( u64, nmi_total_ts )
- __field_struct( struct timespec, timestamp )
- __field_desc( long, timestamp, tv_sec )
+ __field_struct( struct timespec64, timestamp )
+ __field_desc( s64, timestamp, tv_sec )
__field_desc( long, timestamp, tv_nsec )
__field( unsigned int, nmi_count )
__field( unsigned int, seqnum )
),
- F_printk("cnt:%u\tts:%010lu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
+ F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
__entry->seqnum,
__entry->tv_sec,
__entry->tv_nsec,
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 21ea6ae77d93..d7c8e4ec3d9d 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -79,12 +79,12 @@ static u64 last_tracing_thresh = DEFAULT_LAT_THRESHOLD * NSEC_PER_USEC;
/* Individual latency samples are stored here when detected. */
struct hwlat_sample {
- u64 seqnum; /* unique sequence */
- u64 duration; /* delta */
- u64 outer_duration; /* delta (outer loop) */
- u64 nmi_total_ts; /* Total time spent in NMIs */
- struct timespec timestamp; /* wall time */
- int nmi_count; /* # NMIs during this sample */
+ u64 seqnum; /* unique sequence */
+ u64 duration; /* delta */
+ u64 outer_duration; /* delta (outer loop) */
+ u64 nmi_total_ts; /* Total time spent in NMIs */
+ struct timespec64 timestamp; /* wall time */
+ int nmi_count; /* # NMIs during this sample */
};
/* keep the global state somewhere. */
@@ -250,7 +250,7 @@ static int get_sample(void)
s.seqnum = hwlat_data.count;
s.duration = sample;
s.outer_duration = outer_sample;
- s.timestamp = CURRENT_TIME;
+ ktime_get_real_ts64(&s.timestamp);
s.nmi_total_ts = nmi_total_ts;
s.nmi_count = nmi_count;
trace_hwlat_sample(&s);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 02a4aeb22c47..08f9bab8089e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -4,7 +4,6 @@
* Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
*/
-
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/ftrace.h>
@@ -1161,11 +1160,11 @@ trace_hwlat_print(struct trace_iterator *iter, int flags,
trace_assign_type(field, entry);
- trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%ld.%09ld",
+ trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld",
field->seqnum,
field->duration,
field->outer_duration,
- field->timestamp.tv_sec,
+ (long long)field->timestamp.tv_sec,
field->timestamp.tv_nsec);
if (field->nmi_count) {
@@ -1195,10 +1194,10 @@ trace_hwlat_raw(struct trace_iterator *iter, int flags,
trace_assign_type(field, iter->ent);
- trace_seq_printf(s, "%llu %lld %ld %09ld %u\n",
+ trace_seq_printf(s, "%llu %lld %lld %09ld %u\n",
field->duration,
field->outer_duration,
- field->timestamp.tv_sec,
+ (long long)field->timestamp.tv_sec,
field->timestamp.tv_nsec,
field->seqnum);