aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile2
-rw-r--r--kernel/crash_core.c44
-rw-r--r--kernel/fork.c22
-rw-r--r--kernel/kcmp.c57
-rw-r--r--kernel/kexec.c8
-rw-r--r--kernel/kexec_core.c39
-rw-r--r--kernel/kexec_file.c15
-rw-r--r--kernel/kexec_internal.h2
-rw-r--r--kernel/ksysfs.c2
-rw-r--r--kernel/sysctl.c335
-rw-r--r--kernel/sysctl_binary.c2
-rw-r--r--kernel/watchdog.c287
-rw-r--r--kernel/watchdog_hld.c37
13 files changed, 654 insertions, 198 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 72aa080f91f0..4cb8e8b23c6e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -82,7 +82,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += debug/
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
-obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RELAY) += relay.o
obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index fcbd568f1e95..6db80fc0810b 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -14,10 +14,12 @@
#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);
+static unsigned char *vmcoreinfo_data;
+static size_t vmcoreinfo_size;
+u32 *vmcoreinfo_note;
+
+/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */
+static unsigned char *vmcoreinfo_data_safecopy;
/*
* parsing the "crashkernel" commandline
@@ -324,8 +326,23 @@ static void update_vmcoreinfo_note(void)
final_note(buf);
}
+void crash_update_vmcoreinfo_safecopy(void *ptr)
+{
+ if (ptr)
+ memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size);
+
+ vmcoreinfo_data_safecopy = ptr;
+}
+
void crash_save_vmcoreinfo(void)
{
+ if (!vmcoreinfo_note)
+ return;
+
+ /* Use the safe copy to generate vmcoreinfo note if have */
+ if (vmcoreinfo_data_safecopy)
+ vmcoreinfo_data = vmcoreinfo_data_safecopy;
+
vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
update_vmcoreinfo_note();
}
@@ -340,7 +357,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
r = vscnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
- r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+ r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size);
memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
@@ -356,11 +373,26 @@ void __weak arch_crash_save_vmcoreinfo(void)
phys_addr_t __weak paddr_vmcoreinfo_note(void)
{
- return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+ return __pa(vmcoreinfo_note);
}
static int __init crash_save_vmcoreinfo_init(void)
{
+ vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+ if (!vmcoreinfo_data) {
+ pr_warn("Memory allocation for vmcoreinfo_data failed\n");
+ return -ENOMEM;
+ }
+
+ vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE,
+ GFP_KERNEL | __GFP_ZERO);
+ if (!vmcoreinfo_note) {
+ free_page((unsigned long)vmcoreinfo_data);
+ vmcoreinfo_data = NULL;
+ pr_warn("Memory allocation for vmcoreinfo_note failed\n");
+ return -ENOMEM;
+ }
+
VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
VMCOREINFO_PAGESIZE(PAGE_SIZE);
diff --git a/kernel/fork.c b/kernel/fork.c
index 0f69a3e5281e..17921b0390b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -205,19 +205,17 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
void *stack;
int i;
- local_irq_disable();
for (i = 0; i < NR_CACHED_STACKS; i++) {
- struct vm_struct *s = this_cpu_read(cached_stacks[i]);
+ struct vm_struct *s;
+
+ s = this_cpu_xchg(cached_stacks[i], NULL);
if (!s)
continue;
- this_cpu_write(cached_stacks[i], NULL);
tsk->stack_vm_area = s;
- local_irq_enable();
return s->addr;
}
- local_irq_enable();
stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
VMALLOC_START, VMALLOC_END,
@@ -245,19 +243,15 @@ static inline void free_thread_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
if (task_stack_vm_area(tsk)) {
- unsigned long flags;
int i;
- local_irq_save(flags);
for (i = 0; i < NR_CACHED_STACKS; i++) {
- if (this_cpu_read(cached_stacks[i]))
+ if (this_cpu_cmpxchg(cached_stacks[i],
+ NULL, tsk->stack_vm_area) != NULL)
continue;
- this_cpu_write(cached_stacks[i], tsk->stack_vm_area);
- local_irq_restore(flags);
return;
}
- local_irq_restore(flags);
vfree_atomic(tsk->stack);
return;
@@ -560,7 +554,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
set_task_stack_end_magic(tsk);
#ifdef CONFIG_CC_STACKPROTECTOR
- tsk->stack_canary = get_random_long();
+ tsk->stack_canary = get_random_canary();
#endif
/*
@@ -579,6 +573,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
kcov_task_init(tsk);
+#ifdef CONFIG_FAULT_INJECTION
+ tsk->fail_nth = 0;
+#endif
+
return tsk;
free_stack:
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 3a47fa998fe0..ea34ed8bb952 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -11,6 +11,10 @@
#include <linux/bug.h>
#include <linux/err.h>
#include <linux/kcmp.h>
+#include <linux/capability.h>
+#include <linux/list.h>
+#include <linux/eventpoll.h>
+#include <linux/file.h>
#include <asm/unistd.h>
@@ -94,6 +98,56 @@ static int kcmp_lock(struct mutex *m1, struct mutex *m2)
return err;
}
+#ifdef CONFIG_EPOLL
+static int kcmp_epoll_target(struct task_struct *task1,
+ struct task_struct *task2,
+ unsigned long idx1,
+ struct kcmp_epoll_slot __user *uslot)
+{
+ struct file *filp, *filp_epoll, *filp_tgt;
+ struct kcmp_epoll_slot slot;
+ struct files_struct *files;
+
+ if (copy_from_user(&slot, uslot, sizeof(slot)))
+ return -EFAULT;
+
+ filp = get_file_raw_ptr(task1, idx1);
+ if (!filp)
+ return -EBADF;
+
+ files = get_files_struct(task2);
+ if (!files)
+ return -EBADF;
+
+ spin_lock(&files->file_lock);
+ filp_epoll = fcheck_files(files, slot.efd);
+ if (filp_epoll)
+ get_file(filp_epoll);
+ else
+ filp_tgt = ERR_PTR(-EBADF);
+ spin_unlock(&files->file_lock);
+ put_files_struct(files);
+
+ if (filp_epoll) {
+ filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff);
+ fput(filp_epoll);
+ } else
+
+ if (IS_ERR(filp_tgt))
+ return PTR_ERR(filp_tgt);
+
+ return kcmp_ptr(filp, filp_tgt, KCMP_FILE);
+}
+#else
+static int kcmp_epoll_target(struct task_struct *task1,
+ struct task_struct *task2,
+ unsigned long idx1,
+ struct kcmp_epoll_slot __user *uslot)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
unsigned long, idx1, unsigned long, idx2)
{
@@ -165,6 +219,9 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
ret = -EOPNOTSUPP;
#endif
break;
+ case KCMP_EPOLL_TFD:
+ ret = kcmp_epoll_target(task1, task2, idx1, (void *)idx2);
+ break;
default:
ret = -EINVAL;
break;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 980936a90ee6..e62ec4dc6620 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -144,6 +144,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
if (ret)
goto out;
+ /*
+ * Some architecture(like S390) may touch the crash memory before
+ * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+ */
+ ret = kimage_crash_copy_vmcoreinfo(image);
+ if (ret)
+ goto out;
+
for (i = 0; i < nr_segments; i++) {
ret = kimage_load_segment(image, &image->segment[i]);
if (ret)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 154ffb489b93..1ae7c41c33c1 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -482,6 +482,40 @@ struct page *kimage_alloc_control_pages(struct kimage *image,
return pages;
}
+int kimage_crash_copy_vmcoreinfo(struct kimage *image)
+{
+ struct page *vmcoreinfo_page;
+ void *safecopy;
+
+ if (image->type != KEXEC_TYPE_CRASH)
+ return 0;
+
+ /*
+ * For kdump, allocate one vmcoreinfo safe copy from the
+ * crash memory. as we have arch_kexec_protect_crashkres()
+ * after kexec syscall, we naturally protect it from write
+ * (even read) access under kernel direct mapping. But on
+ * the other hand, we still need to operate it when crash
+ * happens to generate vmcoreinfo note, hereby we rely on
+ * vmap for this purpose.
+ */
+ vmcoreinfo_page = kimage_alloc_control_pages(image, 0);
+ if (!vmcoreinfo_page) {
+ pr_warn("Could not allocate vmcoreinfo buffer\n");
+ return -ENOMEM;
+ }
+ safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL);
+ if (!safecopy) {
+ pr_warn("Could not vmap vmcoreinfo buffer\n");
+ return -ENOMEM;
+ }
+
+ image->vmcoreinfo_data_copy = safecopy;
+ crash_update_vmcoreinfo_safecopy(safecopy);
+
+ return 0;
+}
+
static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
{
if (*image->entry != 0)
@@ -569,6 +603,11 @@ void kimage_free(struct kimage *image)
if (!image)
return;
+ if (image->vmcoreinfo_data_copy) {
+ crash_update_vmcoreinfo_safecopy(NULL);
+ vunmap(image->vmcoreinfo_data_copy);
+ }
+
kimage_free_extra_pages(image);
for_each_kimage_entry(image, ptr, entry) {
if (entry & IND_INDIRECTION) {
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 766e7e4d3ad9..9f48f4412297 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -26,13 +26,6 @@
#include <linux/vmalloc.h>
#include "kexec_internal.h"
-/*
- * Declare these symbols weak so that if architecture provides a purgatory,
- * these will be overridden.
- */
-char __weak kexec_purgatory[0];
-size_t __weak kexec_purgatory_size = 0;
-
static int kexec_calculate_store_digests(struct kimage *image);
/* Architectures can provide this probe function */
@@ -298,6 +291,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
if (ret)
goto out;
+ /*
+ * Some architecture(like S390) may touch the crash memory before
+ * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+ */
+ ret = kimage_crash_copy_vmcoreinfo(image);
+ if (ret)
+ goto out;
+
ret = kexec_calculate_store_digests(image);
if (ret)
goto out;
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 799a8a452187..50dfcb039a41 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -17,6 +17,8 @@ extern struct mutex kexec_mutex;
#ifdef CONFIG_KEXEC_FILE
#include <linux/purgatory.h>
void kimage_file_post_load_cleanup(struct kimage *image);
+extern char kexec_purgatory[];
+extern size_t kexec_purgatory_size;
#else /* CONFIG_KEXEC_FILE */
static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
#endif /* CONFIG_KEXEC_FILE */
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index df1a9aa602a0..46ba853656f6 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
{
phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
return sprintf(buf, "%pa %x\n", &vmcore_base,
- (unsigned int)sizeof(vmcoreinfo_note));
+ (unsigned int)VMCOREINFO_NOTE_SIZE);
}
KERNEL_ATTR_RO(vmcoreinfo);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4dfba1a76cc3..6648fbbb8157 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -174,11 +174,32 @@ extern int no_unaligned_warning;
#ifdef CONFIG_PROC_SYSCTL
-#define SYSCTL_WRITES_LEGACY -1
-#define SYSCTL_WRITES_WARN 0
-#define SYSCTL_WRITES_STRICT 1
+/**
+ * enum sysctl_writes_mode - supported sysctl write modes
+ *
+ * @SYSCTL_WRITES_LEGACY: each write syscall must fully contain the sysctl value
+ * to be written, and multiple writes on the same sysctl file descriptor
+ * will rewrite the sysctl value, regardless of file position. No warning
+ * is issued when the initial position is not 0.
+ * @SYSCTL_WRITES_WARN: same as above but warn when the initial file position is
+ * not 0.
+ * @SYSCTL_WRITES_STRICT: writes to numeric sysctl entries must always be at
+ * file position 0 and the value must be fully contained in the buffer
+ * sent to the write syscall. If dealing with strings respect the file
+ * position, but restrict this to the max length of the buffer, anything
+ * passed the max lenght will be ignored. Multiple writes will append
+ * to the buffer.
+ *
+ * These write modes control how current file position affects the behavior of
+ * updating sysctl values through the proc interface on each write.
+ */
+enum sysctl_writes_mode {
+ SYSCTL_WRITES_LEGACY = -1,
+ SYSCTL_WRITES_WARN = 0,
+ SYSCTL_WRITES_STRICT = 1,
+};
-static int sysctl_writes_strict = SYSCTL_WRITES_STRICT;
+static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT;
static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
@@ -880,6 +901,14 @@ static struct ctl_table kern_table[] = {
#endif
},
{
+ .procname = "watchdog_cpumask",
+ .data = &watchdog_cpumask_bits,
+ .maxlen = NR_CPUS,
+ .mode = 0644,
+ .proc_handler = proc_watchdog_cpumask,
+ },
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
+ {
.procname = "soft_watchdog",
.data = &soft_watchdog_enabled,
.maxlen = sizeof (int),
@@ -889,13 +918,6 @@ static struct ctl_table kern_table[] = {
.extra2 = &one,
},
{
- .procname = "watchdog_cpumask",
- .data = &watchdog_cpumask_bits,
- .maxlen = NR_CPUS,
- .mode = 0644,
- .proc_handler = proc_watchdog_cpumask,
- },
- {
.procname = "softlockup_panic",
.data = &softlockup_panic,
.maxlen = sizeof(int),
@@ -904,27 +926,29 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &one,
},
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_SMP
{
- .procname = "hardlockup_panic",
- .data = &hardlockup_panic,
+ .procname = "softlockup_all_cpu_backtrace",
+ .data = &sysctl_softlockup_all_cpu_backtrace,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
+#endif /* CONFIG_SMP */
#endif
-#ifdef CONFIG_SMP
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
{
- .procname = "softlockup_all_cpu_backtrace",
- .data = &sysctl_softlockup_all_cpu_backtrace,
+ .procname = "hardlockup_panic",
+ .data = &hardlockup_panic,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
+#ifdef CONFIG_SMP
{
.procname = "hardlockup_all_cpu_backtrace",
.data = &sysctl_hardlockup_all_cpu_backtrace,
@@ -936,6 +960,8 @@ static struct ctl_table kern_table[] = {
},
#endif /* CONFIG_SMP */
#endif
+#endif
+
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
{
.procname = "unknown_nmi_panic",
@@ -1950,6 +1976,32 @@ static void warn_sysctl_write(struct ctl_table *table)
}
/**
+ * proc_first_pos_non_zero_ignore - check if firs position is allowed
+ * @ppos: file position
+ * @table: the sysctl table
+ *
+ * Returns true if the first position is non-zero and the sysctl_writes_strict
+ * mode indicates this is not allowed for numeric input types. String proc
+ * hadlers can ignore the return value.
+ */
+static bool proc_first_pos_non_zero_ignore(loff_t *ppos,
+ struct ctl_table *table)
+{
+ if (!*ppos)
+ return false;
+
+ switch (sysctl_writes_strict) {
+ case SYSCTL_WRITES_STRICT:
+ return true;
+ case SYSCTL_WRITES_WARN:
+ warn_sysctl_write(table);
+ return false;
+ default:
+ return false;
+ }
+}
+
+/**
* proc_dostring - read a string sysctl
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
@@ -1969,8 +2021,8 @@ static void warn_sysctl_write(struct ctl_table *table)
int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN)
- warn_sysctl_write(table);
+ if (write)
+ proc_first_pos_non_zero_ignore(ppos, table);
return _proc_do_string((char *)(table->data), table->maxlen, write,
(char __user *)buffer, lenp, ppos);
@@ -2128,19 +2180,18 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
return 0;
}
-static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
- int *valp,
- int write, void *data)
+static int do_proc_douintvec_conv(unsigned long *lvalp,
+ unsigned int *valp,
+ int write, void *data)
{
if (write) {
- if (*negp)
+ if (*lvalp > UINT_MAX)
return -EINVAL;
if (*lvalp > UINT_MAX)
return -EINVAL;
*valp = *lvalp;
} else {
unsigned int val = *valp;
- *negp = false;
*lvalp = (unsigned long)val;
}
return 0;
@@ -2172,17 +2223,8 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
conv = do_proc_dointvec_conv;
if (write) {
- if (*ppos) {
- switch (sysctl_writes_strict) {
- case SYSCTL_WRITES_STRICT:
- goto out;
- case SYSCTL_WRITES_WARN:
- warn_sysctl_write(table);
- break;
- default:
- break;
- }
- }
+ if (proc_first_pos_non_zero_ignore(ppos, table))
+ goto out;
if (left > PAGE_SIZE - 1)
left = PAGE_SIZE - 1;
@@ -2249,6 +2291,146 @@ static int do_proc_dointvec(struct ctl_table *table, int write,
buffer, lenp, ppos, conv, data);
}
+static int do_proc_douintvec_w(unsigned int *tbl_data,
+ struct ctl_table *table,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos,
+ int (*conv)(unsigned long *lvalp,
+ unsigned int *valp,
+ int write, void *data),
+ void *data)
+{
+ unsigned long lval;
+ int err = 0;
+ size_t left;
+ bool neg;
+ char *kbuf = NULL, *p;
+
+ left = *lenp;
+
+ if (proc_first_pos_non_zero_ignore(ppos, table))
+ goto bail_early;
+
+ if (left > PAGE_SIZE - 1)
+ left = PAGE_SIZE - 1;
+
+ p = kbuf = memdup_user_nul(buffer, left);
+ if (IS_ERR(kbuf))
+ return -EINVAL;
+
+ left -= proc_skip_spaces(&p);
+ if (!left) {
+ err = -EINVAL;
+ goto out_free;
+ }
+
+ err = proc_get_long(&p, &left, &lval, &neg,
+ proc_wspace_sep,
+ sizeof(proc_wspace_sep), NULL);
+ if (err || neg) {
+ err = -EINVAL;
+ goto out_free;
+ }
+
+ if (conv(&lval, tbl_data, 1, data)) {
+ err = -EINVAL;
+ goto out_free;
+ }
+
+ if (!err && left)
+ left -= proc_skip_spaces(&p);
+
+out_free:
+ kfree(kbuf);
+ if (err)
+ return -EINVAL;
+
+ return 0;
+
+ /* This is in keeping with old __do_proc_dointvec() */
+bail_early:
+ *ppos += *lenp;
+ return err;
+}
+
+static int do_proc_douintvec_r(unsigned int *tbl_data, void __user *buffer,
+ size_t *lenp, loff_t *ppos,
+ int (*conv)(unsigned long *lvalp,
+ unsigned int *valp,
+ int write, void *data),
+ void *data)
+{
+ unsigned long lval;
+ int err = 0;
+ size_t left;
+
+ left = *lenp;
+
+ if (conv(&lval, tbl_data, 0, data)) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = proc_put_long(&buffer, &left, lval, false);
+ if (err || !left)
+ goto out;
+
+ err = proc_put_char(&buffer, &left, '\n');
+
+out:
+ *lenp -= left;
+ *ppos += *lenp;
+
+ return err;
+}
+
+static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table,
+ int write, void __user *buffer,
+ size_t *lenp, loff_t *ppos,
+ int (*conv)(unsigned long *lvalp,
+ unsigned int *valp,
+ int write, void *data),
+ void *data)
+{
+ unsigned int *i, vleft;
+
+ if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
+ *lenp = 0;
+ return 0;
+ }
+
+ i = (unsigned int *) tbl_data;
+ vleft = table->maxlen / sizeof(*i);
+
+ /*
+ * Arrays are not supported, keep this simple. *Do not* add
+ * support for them.
+ */
+ if (vleft != 1) {
+ *lenp = 0;
+ return -EINVAL;
+ }
+
+ if (!conv)
+ conv = do_proc_douintvec_conv;
+
+ if (write)
+ return do_proc_douintvec_w(i, table, buffer, lenp, ppos,
+ conv, data);
+ return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data);
+}
+
+static int do_proc_douintvec(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos,
+ int (*conv)(unsigned long *lvalp,
+ unsigned int *valp,
+ int write, void *data),
+ void *data)
+{
+ return __do_proc_douintvec(table->data, table, write,
+ buffer, lenp, ppos, conv, data);
+}
+
/**
* proc_dointvec - read a vector of integers
* @table: the sysctl table
@@ -2284,8 +2466,8 @@ int proc_dointvec(struct ctl_table *table, int write,
int proc_douintvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table, write, buffer, lenp, ppos,
- do_proc_douintvec_conv, NULL);
+ return do_proc_douintvec(table, write, buffer, lenp, ppos,
+ do_proc_douintvec_conv, NULL);
}
/*
@@ -2390,6 +2572,65 @@ int proc_dointvec_minmax(struct ctl_table *table, int write,
do_proc_dointvec_minmax_conv, &param);
}
+struct do_proc_douintvec_minmax_conv_param {
+ unsigned int *min;
+ unsigned int *max;
+};
+
+static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
+ unsigned int *valp,
+ int write, void *data)
+{
+ struct do_proc_douintvec_minmax_conv_param *param = data;
+
+ if (write) {
+ unsigned int val = *lvalp;
+
+ if ((param->min && *param->min > val) ||
+ (param->max && *param->max < val))
+ return -ERANGE;
+
+ if (*lvalp > UINT_MAX)
+ return -EINVAL;
+ *valp = val;
+ } else {
+ unsigned int val = *valp;
+ *lvalp = (unsigned long) val;
+ }
+
+ return 0;
+}
+
+/**
+ * proc_douintvec_minmax - read a vector of unsigned ints with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string. Negative
+ * strings are not allowed.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max). There is a final sanity
+ * check for UINT_MAX to avoid having to support wrap around uses from
+ * userspace.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec_minmax(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct do_proc_douintvec_minmax_conv_param param = {
+ .min = (unsigned int *) table->extra1,
+ .max = (unsigned int *) table->extra2,
+ };
+ return do_proc_douintvec(table, write, buffer, lenp, ppos,
+ do_proc_douintvec_minmax_conv, &param);
+}
+
static void validate_coredump_safety(void)
{
#ifdef CONFIG_COREDUMP
@@ -2447,17 +2688,8 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
left = *lenp;
if (write) {
- if (*ppos) {
- switch (sysctl_writes_strict) {
- case SYSCTL_WRITES_STRICT:
- goto out;
- case SYSCTL_WRITES_WARN:
- warn_sysctl_write(table);
- break;
- default:
- break;
- }
- }
+ if (proc_first_pos_non_zero_ignore(ppos, table))
+ goto out;
if (left > PAGE_SIZE - 1)
left = PAGE_SIZE - 1;
@@ -2898,6 +3130,12 @@ int proc_dointvec_minmax(struct ctl_table *table, int write,
return -ENOSYS;
}
+int proc_douintvec_minmax(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+
int proc_dointvec_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -2940,6 +3178,7 @@ EXPORT_SYMBOL(proc_dointvec);
EXPORT_SYMBOL(proc_douintvec);
EXPORT_SYMBOL(proc_dointvec_jiffies);
EXPORT_SYMBOL(proc_dointvec_minmax);
+EXPORT_SYMBOL_GPL(proc_douintvec_minmax);
EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
EXPORT_SYMBOL(proc_dostring);
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 939a158eab11..02e1859f2ca8 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1346,7 +1346,7 @@ static void deprecated_sysctl_warning(const int *name, int nlen)
* CTL_KERN/KERN_VERSION is used by older glibc and cannot
* ever go away.
*/
- if (name[0] == CTL_KERN && name[1] == KERN_VERSION)
+ if (nlen >= 2 && name[0] == CTL_KERN && name[1] == KERN_VERSION)
return;
if (printk_ratelimit()) {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 03e0b69bb5bf..cabe3e9fb620 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -29,15 +29,58 @@
#include <linux/kvm_para.h>
#include <linux/kthread.h>
+/* Watchdog configuration */
static DEFINE_MUTEX(watchdog_proc_mutex);
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
+int __read_mostly nmi_watchdog_enabled;
+
+#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
+unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED |
+ NMI_WATCHDOG_ENABLED;
#else
unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
#endif
-int __read_mostly nmi_watchdog_enabled;
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+/* boot commands */
+/*
+ * Should we panic when a soft-lockup or hard-lockup occurs:
+ */
+unsigned int __read_mostly hardlockup_panic =
+ CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
+/*
+ * We may not want to enable hard lockup detection by default in all cases,
+ * for example when running the kernel as a guest on a hypervisor. In these
+ * cases this function can be called to disable hard lockup detection. This
+ * function should only be executed once by the boot processor before the
+ * kernel command line parameters are parsed, because otherwise it is not
+ * possible to override this in hardlockup_panic_setup().
+ */
+void hardlockup_detector_disable(void)
+{
+ watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+}
+
+static int __init hardlockup_panic_setup(char *str)
+{
+ if (!strncmp(str, "panic", 5))
+ hardlockup_panic = 1;
+ else if (!strncmp(str, "nopanic", 7))
+ hardlockup_panic = 0;
+ else if (!strncmp(str, "0", 1))
+ watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+ else if (!strncmp(str, "1", 1))
+ watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+ return 1;
+}
+__setup("nmi_watchdog=", hardlockup_panic_setup);
+
+#endif
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
int __read_mostly soft_watchdog_enabled;
+#endif
+
int __read_mostly watchdog_user_enabled;
int __read_mostly watchdog_thresh = 10;
@@ -45,15 +88,9 @@ int __read_mostly watchdog_thresh = 10;
int __read_mostly sysctl_softlockup_all_cpu_backtrace;
int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
#endif
-static struct cpumask watchdog_cpumask __read_mostly;
+struct cpumask watchdog_cpumask __read_mostly;
unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
-/* Helper for online, unparked cpus. */
-#define for_each_watchdog_cpu(cpu) \
- for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
-
-atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
-
/*
* The 'watchdog_running' variable is set to 1 when the watchdog threads
* are registered/started and is set to 0 when the watchdog threads are
@@ -72,7 +109,47 @@ static int __read_mostly watchdog_running;
* of 'watchdog_running' cannot change while the watchdog is deactivated
* temporarily (see related code in 'proc' handlers).
*/
-static int __read_mostly watchdog_suspended;
+int __read_mostly watchdog_suspended;
+
+/*
+ * These functions can be overridden if an architecture implements its
+ * own hardlockup detector.
+ *
+ * watchdog_nmi_enable/disable can be implemented to start and stop when
+ * softlockup watchdog threads start and stop. The arch must select the
+ * SOFTLOCKUP_DETECTOR Kconfig.
+ */
+int __weak watchdog_nmi_enable(unsigned int cpu)
+{
+ return 0;
+}
+void __weak watchdog_nmi_disable(unsigned int cpu)
+{
+}
+
+/*
+ * watchdog_nmi_reconfigure can be implemented to be notified after any
+ * watchdog configuration change. The arch hardlockup watchdog should
+ * respond to the following variables:
+ * - nmi_watchdog_enabled
+ * - watchdog_thresh
+ * - watchdog_cpumask
+ * - sysctl_hardlockup_all_cpu_backtrace
+ * - hardlockup_panic
+ * - watchdog_suspended
+ */
+void __weak watchdog_nmi_reconfigure(void)
+{
+}
+
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
+
+/* Helper for online, unparked cpus. */
+#define for_each_watchdog_cpu(cpu) \
+ for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
+
+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
static u64 __read_mostly sample_period;
@@ -120,6 +197,7 @@ static int __init softlockup_all_cpu_backtrace_setup(char *str)
return 1;
}
__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
static int __init hardlockup_all_cpu_backtrace_setup(char *str)
{
sysctl_hardlockup_all_cpu_backtrace =
@@ -128,6 +206,7 @@ static int __init hardlockup_all_cpu_backtrace_setup(char *str)
}
__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
#endif
+#endif
/*
* Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -213,18 +292,6 @@ void touch_softlockup_watchdog_sync(void)
__this_cpu_write(watchdog_touch_ts, 0);
}
-/* watchdog detector functions */
-bool is_hardlockup(void)
-{
- unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
-
- if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
- return true;
-
- __this_cpu_write(hrtimer_interrupts_saved, hrint);
- return false;
-}
-
static int is_softlockup(unsigned long touch_ts)
{
unsigned long now = get_timestamp();
@@ -237,21 +304,21 @@ static int is_softlockup(unsigned long touch_ts)
return 0;
}
-static void watchdog_interrupt_count(void)
+/* watchdog detector functions */
+bool is_hardlockup(void)
{
- __this_cpu_inc(hrtimer_interrupts);
-}
+ unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
-/*
- * These two functions are mostly architecture specific
- * defining them as weak here.
- */
-int __weak watchdog_nmi_enable(unsigned int cpu)
-{
- return 0;
+ if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
+ return true;
+
+ __this_cpu_write(hrtimer_interrupts_saved, hrint);
+ return false;
}
-void __weak watchdog_nmi_disable(unsigned int cpu)
+
+static void watchdog_interrupt_count(void)
{
+ __this_cpu_inc(hrtimer_interrupts);
}
static int watchdog_enable_all_cpus(void);
@@ -502,57 +569,6 @@ static void watchdog_unpark_threads(void)
kthread_unpark(per_cpu(softlockup_watchdog, cpu));
}
-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
- */
-int lockup_detector_suspend(void)
-{
- int ret = 0;
-
- get_online_cpus();
- mutex_lock(&watchdog_proc_mutex);
- /*
- * Multiple suspend requests can be active in parallel (counted by
- * the 'watchdog_suspended' variable). If the watchdog threads are
- * running, the first caller takes care that they will be parked.
- * The state of 'watchdog_running' cannot change while a suspend
- * request is active (see related code in 'proc' handlers).
- */
- if (watchdog_running && !watchdog_suspended)
- ret = watchdog_park_threads();
-
- if (ret == 0)
- watchdog_suspended++;
- else {
- watchdog_disable_all_cpus();
- pr_err("Failed to suspend lockup detectors, disabled\n");
- watchdog_enabled = 0;
- }
-
- mutex_unlock(&watchdog_proc_mutex);
-
- return ret;
-}
-
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
- */
-void lockup_detector_resume(void)
-{
- mutex_lock(&watchdog_proc_mutex);
-
- watchdog_suspended--;
- /*
- * The watchdog threads are unparked if they were previously running
- * and if there is no more active suspend request.
- */
- if (watchdog_running && !watchdog_suspended)
- watchdog_unpark_threads();
-
- mutex_unlock(&watchdog_proc_mutex);
- put_online_cpus();
-}
-
static int update_watchdog_all_cpus(void)
{
int ret;
@@ -605,6 +621,100 @@ static void watchdog_disable_all_cpus(void)
}
#ifdef CONFIG_SYSCTL
+static int watchdog_update_cpus(void)
+{
+ return smpboot_update_cpumask_percpu_thread(
+ &watchdog_threads, &watchdog_cpumask);
+}
+#endif
+
+#else /* SOFTLOCKUP */
+static int watchdog_park_threads(void)
+{
+ return 0;
+}
+
+static void watchdog_unpark_threads(void)
+{
+}
+
+static int watchdog_enable_all_cpus(void)
+{
+ return 0;
+}
+
+static void watchdog_disable_all_cpus(void)
+{
+}
+
+#ifdef CONFIG_SYSCTL
+static int watchdog_update_cpus(void)
+{
+ return 0;
+}
+#endif
+
+static void set_sample_period(void)
+{
+}
+#endif /* SOFTLOCKUP */
+
+/*
+ * Suspend the hard and soft lockup detector by parking the watchdog threads.
+ */
+int lockup_detector_suspend(void)
+{
+ int ret = 0;
+
+ get_online_cpus();
+ mutex_lock(&watchdog_proc_mutex);
+ /*
+ * Multiple suspend requests can be active in parallel (counted by
+ * the 'watchdog_suspended' variable). If the watchdog threads are
+ * running, the first caller takes care that they will be parked.
+ * The state of 'watchdog_running' cannot change while a suspend
+ * request is active (see related code in 'proc' handlers).
+ */
+ if (watchdog_running && !watchdog_suspended)
+ ret = watchdog_park_threads();
+
+ if (ret == 0)
+ watchdog_suspended++;
+ else {
+ watchdog_disable_all_cpus();
+ pr_err("Failed to suspend lockup detectors, disabled\n");
+ watchdog_enabled = 0;
+ }
+
+ watchdog_nmi_reconfigure();
+
+ mutex_unlock(&watchdog_proc_mutex);
+
+ return ret;
+}
+
+/*
+ * Resume the hard and soft lockup detector by unparking the watchdog threads.
+ */
+void lockup_detector_resume(void)
+{
+ mutex_lock(&watchdog_proc_mutex);
+
+ watchdog_suspended--;
+ /*
+ * The watchdog threads are unparked if they were previously running
+ * and if there is no more active suspend request.
+ */
+ if (watchdog_running && !watchdog_suspended)
+ watchdog_unpark_threads();
+
+ watchdog_nmi_reconfigure();
+
+ mutex_unlock(&watchdog_proc_mutex);
+ put_online_cpus();
+}
+
+#ifdef CONFIG_SYSCTL
/*
* Update the run state of the lockup detectors.
@@ -625,6 +735,8 @@ static int proc_watchdog_update(void)
else
watchdog_disable_all_cpus();
+ watchdog_nmi_reconfigure();
+
return err;
}
@@ -810,10 +922,11 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
* a temporary cpumask, so we are likely not in a
* position to do much else to make things better.
*/
- if (smpboot_update_cpumask_percpu_thread(
- &watchdog_threads, &watchdog_cpumask) != 0)
+ if (watchdog_update_cpus() != 0)
pr_err("cpumask update failed\n");
}
+
+ watchdog_nmi_reconfigure();
}
out:
mutex_unlock(&watchdog_proc_mutex);
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 54a427d1f344..295a0d84934c 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -22,41 +22,9 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
-/* boot commands */
-/*
- * Should we panic when a soft-lockup or hard-lockup occurs:
- */
-unsigned int __read_mostly hardlockup_panic =
- CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
static unsigned long hardlockup_allcpu_dumped;
-/*
- * We may not want to enable hard lockup detection by default in all cases,
- * for example when running the kernel as a guest on a hypervisor. In these
- * cases this function can be called to disable hard lockup detection. This
- * function should only be executed once by the boot processor before the
- * kernel command line parameters are parsed, because otherwise it is not
- * possible to override this in hardlockup_panic_setup().
- */
-void hardlockup_detector_disable(void)
-{
- watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-}
-
-static int __init hardlockup_panic_setup(char *str)
-{
- if (!strncmp(str, "panic", 5))
- hardlockup_panic = 1;
- else if (!strncmp(str, "nopanic", 7))
- hardlockup_panic = 0;
- else if (!strncmp(str, "0", 1))
- watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
- else if (!strncmp(str, "1", 1))
- watchdog_enabled |= NMI_WATCHDOG_ENABLED;
- return 1;
-}
-__setup("nmi_watchdog=", hardlockup_panic_setup);
-void touch_nmi_watchdog(void)
+void arch_touch_nmi_watchdog(void)
{
/*
* Using __raw here because some code paths have
@@ -66,9 +34,8 @@ void touch_nmi_watchdog(void)
* going off.
*/
raw_cpu_write(watchdog_nmi_touch, true);
- touch_softlockup_watchdog();
}
-EXPORT_SYMBOL(touch_nmi_watchdog);
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
static struct perf_event_attr wd_hw_attr = {
.type = PERF_TYPE_HARDWARE,
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-12 06:40:54 +0000