aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cpu.c2
-rw-r--r--kernel/cpuset.c130
-rw-r--r--kernel/events/uprobes.c213
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/fork.c46
-rw-r--r--kernel/irq/handle.c7
-rw-r--r--kernel/irq/manage.c17
-rw-r--r--kernel/kexec.c2
-rw-r--r--kernel/kmod.c37
-rw-r--r--kernel/panic.c8
-rw-r--r--kernel/power/suspend.c3
-rw-r--r--kernel/printk.c191
-rw-r--r--kernel/resource.c24
-rw-r--r--kernel/sched/core.c94
-rw-r--r--kernel/sched/fair.c113
-rw-r--r--kernel/sched/sched.h23
-rw-r--r--kernel/softirq.c9
-rw-r--r--kernel/sys.c57
-rw-r--r--kernel/sysctl.c51
-rw-r--r--kernel/sysctl_binary.c2
-rw-r--r--kernel/taskstats.c5
-rw-r--r--kernel/trace/trace.c7
-rw-r--r--kernel/trace/trace_functions.c36
-rw-r--r--kernel/watchdog.c21
24 files changed, 742 insertions, 358 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a4eb5227a19e..14d32588cccd 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -416,7 +416,7 @@ int __cpuinit cpu_up(unsigned int cpu)
if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
mutex_lock(&zonelists_mutex);
- build_all_zonelists(NULL);
+ build_all_zonelists(NULL, NULL);
mutex_unlock(&zonelists_mutex);
}
#endif
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 8c8bd652dd12..f33c7153b6d7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -147,6 +147,12 @@ typedef enum {
CS_SPREAD_SLAB,
} cpuset_flagbits_t;
+/* the type of hotplug event */
+enum hotplug_event {
+ CPUSET_CPU_OFFLINE,
+ CPUSET_MEM_OFFLINE,
+};
+
/* convenient tests for these bits */
static inline int is_cpu_exclusive(const struct cpuset *cs)
{
@@ -1990,8 +1996,36 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
}
/*
- * Walk the specified cpuset subtree and look for empty cpusets.
- * The tasks of such cpuset must be moved to a parent cpuset.
+ * Helper function to traverse cpusets.
+ * It can be used to walk the cpuset tree from top to bottom, completing
+ * one layer before dropping down to the next (thus always processing a
+ * node before any of its children).
+ */
+static struct cpuset *cpuset_next(struct list_head *queue)
+{
+ struct cpuset *cp;
+ struct cpuset *child; /* scans child cpusets of cp */
+ struct cgroup *cont;
+
+ if (list_empty(queue))
+ return NULL;
+
+ cp = list_first_entry(queue, struct cpuset, stack_list);
+ list_del(queue->next);
+ list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
+ child = cgroup_cs(cont);
+ list_add_tail(&child->stack_list, queue);
+ }
+
+ return cp;
+}
+
+
+/*
+ * Walk the specified cpuset subtree upon a hotplug operation (CPU/Memory
+ * online/offline) and update the cpusets accordingly.
+ * For regular CPU/Mem hotplug, look for empty cpusets; the tasks of such
+ * cpuset must be moved to a parent cpuset.
*
* Called with cgroup_mutex held. We take callback_mutex to modify
* cpus_allowed and mems_allowed.
@@ -2000,50 +2034,61 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
* before dropping down to the next. It always processes a node before
* any of its children.
*
- * For now, since we lack memory hot unplug, we'll never see a cpuset
- * that has tasks along with an empty 'mems'. But if we did see such
- * a cpuset, we'd handle it just like we do if its 'cpus' was empty.
+ * In the case of memory hot-unplug, it will remove nodes from N_HIGH_MEMORY
+ * if all present pages from a node are offlined.
*/
-static void scan_for_empty_cpusets(struct cpuset *root)
+static void
+scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
{
LIST_HEAD(queue);
- struct cpuset *cp; /* scans cpusets being updated */
- struct cpuset *child; /* scans child cpusets of cp */
- struct cgroup *cont;
+ struct cpuset *cp; /* scans cpusets being updated */
static nodemask_t oldmems; /* protected by cgroup_mutex */
list_add_tail((struct list_head *)&root->stack_list, &queue);
- while (!list_empty(&queue)) {
- cp = list_first_entry(&queue, struct cpuset, stack_list);
- list_del(queue.next);
- list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
- child = cgroup_cs(cont);
- list_add_tail(&child->stack_list, &queue);
+ switch (event) {
+ case CPUSET_CPU_OFFLINE:
+ while ((cp = cpuset_next(&queue)) != NULL) {
+
+ /* Continue past cpusets with all cpus online */
+ if (cpumask_subset(cp->cpus_allowed, cpu_active_mask))
+ continue;
+
+ /* Remove offline cpus from this cpuset. */
+ mutex_lock(&callback_mutex);
+ cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
+ cpu_active_mask);
+ mutex_unlock(&callback_mutex);
+
+ /* Move tasks from the empty cpuset to a parent */
+ if (cpumask_empty(cp->cpus_allowed))
+ remove_tasks_in_empty_cpuset(cp);
+ else
+ update_tasks_cpumask(cp, NULL);
}
+ break;
- /* Continue past cpusets with all cpus, mems online */
- if (cpumask_subset(cp->cpus_allowed, cpu_active_mask) &&
- nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
- continue;
+ case CPUSET_MEM_OFFLINE:
+ while ((cp = cpuset_next(&queue)) != NULL) {
- oldmems = cp->mems_allowed;
+ /* Continue past cpusets with all mems online */
+ if (nodes_subset(cp->mems_allowed,
+ node_states[N_HIGH_MEMORY]))
+ continue;
- /* Remove offline cpus and mems from this cpuset. */
- mutex_lock(&callback_mutex);
- cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
- cpu_active_mask);
- nodes_and(cp->mems_allowed, cp->mems_allowed,
+ oldmems = cp->mems_allowed;
+
+ /* Remove offline mems from this cpuset. */
+ mutex_lock(&callback_mutex);
+ nodes_and(cp->mems_allowed, cp->mems_allowed,
node_states[N_HIGH_MEMORY]);
- mutex_unlock(&callback_mutex);
+ mutex_unlock(&callback_mutex);
- /* Move tasks from the empty cpuset to a parent */
- if (cpumask_empty(cp->cpus_allowed) ||
- nodes_empty(cp->mems_allowed))
- remove_tasks_in_empty_cpuset(cp);
- else {
- update_tasks_cpumask(cp, NULL);
- update_tasks_nodemask(cp, &oldmems, NULL);
+ /* Move tasks from the empty cpuset to a parent */
+ if (nodes_empty(cp->mems_allowed))
+ remove_tasks_in_empty_cpuset(cp);
+ else
+ update_tasks_nodemask(cp, &oldmems, NULL);
}
}
}
@@ -2054,13 +2099,19 @@ static void scan_for_empty_cpusets(struct cpuset *root)
* (of no affect) on systems that are actively using CPU hotplug
* but making no active use of cpusets.
*
+ * The only exception to this is suspend/resume, where we don't
+ * modify cpusets at all.
+ *
* This routine ensures that top_cpuset.cpus_allowed tracks
* cpu_active_mask on each CPU hotplug (cpuhp) event.
*
* Called within get_online_cpus(). Needs to call cgroup_lock()
* before calling generate_sched_domains().
+ *
+ * @cpu_online: Indicates whether this is a CPU online event (true) or
+ * a CPU offline event (false).
*/
-void cpuset_update_active_cpus(void)
+void cpuset_update_active_cpus(bool cpu_online)
{
struct sched_domain_attr *attr;
cpumask_var_t *doms;
@@ -2070,7 +2121,10 @@ void cpuset_update_active_cpus(void)
mutex_lock(&callback_mutex);
cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
mutex_unlock(&callback_mutex);
- scan_for_empty_cpusets(&top_cpuset);
+
+ if (!cpu_online)
+ scan_cpusets_upon_hotplug(&top_cpuset, CPUSET_CPU_OFFLINE);
+
ndoms = generate_sched_domains(&doms, &attr);
cgroup_unlock();
@@ -2082,7 +2136,7 @@ void cpuset_update_active_cpus(void)
/*
* Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
* Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
- * See also the previous routine cpuset_track_online_cpus().
+ * See cpuset_update_active_cpus() for CPU hotplug handling.
*/
static int cpuset_track_online_nodes(struct notifier_block *self,
unsigned long action, void *arg)
@@ -2101,9 +2155,9 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
case MEM_OFFLINE:
/*
* needn't update top_cpuset.mems_allowed explicitly because
- * scan_for_empty_cpusets() will update it.
+ * scan_cpusets_upon_hotplug() will update it.
*/
- scan_for_empty_cpusets(&top_cpuset);
+ scan_cpusets_upon_hotplug(&top_cpuset, CPUSET_MEM_OFFLINE);
break;
default:
break;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f93532748bca..c08a22d02f72 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -32,6 +32,7 @@
#include <linux/swap.h> /* try_to_free_swap */
#include <linux/ptrace.h> /* user_enable_single_step */
#include <linux/kdebug.h> /* notifier mechanism */
+#include "../../mm/internal.h" /* munlock_vma_page */
#include <linux/uprobes.h>
@@ -112,14 +113,14 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register)
return false;
}
-static loff_t vma_address(struct vm_area_struct *vma, loff_t offset)
+static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset)
{
- loff_t vaddr;
-
- vaddr = vma->vm_start + offset;
- vaddr -= vma->vm_pgoff << PAGE_SHIFT;
+ return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+}
- return vaddr;
+static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
+{
+ return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start);
}
/**
@@ -127,25 +128,27 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset)
* based on replace_page in mm/ksm.c
*
* @vma: vma that holds the pte pointing to page
+ * @addr: address the old @page is mapped at
* @page: the cowed page we are replacing by kpage
* @kpage: the modified page we replace page by
*
* Returns 0 on success, -EFAULT on failure.
*/
-static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage)
+static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
+ struct page *page, struct page *kpage)
{
struct mm_struct *mm = vma->vm_mm;
- unsigned long addr;
spinlock_t *ptl;
pte_t *ptep;
+ int err;
- addr = page_address_in_vma(page, vma);
- if (addr == -EFAULT)
- return -EFAULT;
+ /* For try_to_free_swap() and munlock_vma_page() below */
+ lock_page(page);
+ err = -EAGAIN;
ptep = page_check_address(page, mm, addr, &ptl, 0);
if (!ptep)
- return -EAGAIN;
+ goto unlock;
get_page(kpage);
page_add_new_anon_rmap(kpage, vma, addr);
@@ -162,10 +165,16 @@ static int __replace_page(struct vm_area_struct *vma, struct page *page, struct
page_remove_rmap(page);
if (!page_mapped(page))
try_to_free_swap(page);
- put_page(page);
pte_unmap_unlock(ptep, ptl);
- return 0;
+ if (vma->vm_flags & VM_LOCKED)
+ munlock_vma_page(page);
+ put_page(page);
+
+ err = 0;
+ unlock:
+ unlock_page(page);
+ return err;
}
/**
@@ -206,45 +215,23 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
unsigned long vaddr, uprobe_opcode_t opcode)
{
struct page *old_page, *new_page;
- struct address_space *mapping;
void *vaddr_old, *vaddr_new;
struct vm_area_struct *vma;
- struct uprobe *uprobe;
int ret;
+
retry:
/* Read the page with vaddr into memory */
ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma);
if (ret <= 0)
return ret;
- ret = -EINVAL;
-
- /*
- * We are interested in text pages only. Our pages of interest
- * should be mapped for read and execute only. We desist from
- * adding probes in write mapped pages since the breakpoints
- * might end up in the file copy.
- */
- if (!valid_vma(vma, is_swbp_insn(&opcode)))
- goto put_out;
-
- uprobe = container_of(auprobe, struct uprobe, arch);
- mapping = uprobe->inode->i_mapping;
- if (mapping != vma->vm_file->f_mapping)
- goto put_out;
-
ret = -ENOMEM;
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
if (!new_page)
- goto put_out;
+ goto put_old;
__SetPageUptodate(new_page);
- /*
- * lock page will serialize against do_wp_page()'s
- * PageAnon() handling
- */
- lock_page(old_page);
/* copy the page now that we've got it stable */
vaddr_old = kmap_atomic(old_page);
vaddr_new = kmap_atomic(new_page);
@@ -257,17 +244,13 @@ retry:
ret = anon_vma_prepare(vma);
if (ret)
- goto unlock_out;
+ goto put_new;
- lock_page(new_page);
- ret = __replace_page(vma, old_page, new_page);
- unlock_page(new_page);
+ ret = __replace_page(vma, vaddr, old_page, new_page);
-unlock_out:
- unlock_page(old_page);
+put_new:
page_cache_release(new_page);
-
-put_out:
+put_old:
put_page(old_page);
if (unlikely(ret == -EAGAIN))
@@ -791,7 +774,7 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
curr = info;
info->mm = vma->vm_mm;
- info->vaddr = vma_address(vma, offset);
+ info->vaddr = offset_to_vaddr(vma, offset);
}
mutex_unlock(&mapping->i_mmap_mutex);
@@ -839,12 +822,13 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
goto free;
down_write(&mm->mmap_sem);
- vma = find_vma(mm, (unsigned long)info->vaddr);
- if (!vma || !valid_vma(vma, is_register))
+ vma = find_vma(mm, info->vaddr);
+ if (!vma || !valid_vma(vma, is_register) ||
+ vma->vm_file->f_mapping->host != uprobe->inode)
goto unlock;
- if (vma->vm_file->f_mapping->host != uprobe->inode ||
- vma_address(vma, uprobe->offset) != info->vaddr)
+ if (vma->vm_start > info->vaddr ||
+ vaddr_to_offset(vma, info->vaddr) != uprobe->offset)
goto unlock;
if (is_register) {
@@ -960,59 +944,66 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume
put_uprobe(uprobe);
}
-/*
- * Of all the nodes that correspond to the given inode, return the node
- * with the least offset.
- */
-static struct rb_node *find_least_offset_node(struct inode *inode)
+static struct rb_node *
+find_node_in_range(struct inode *inode, loff_t min, loff_t max)
{
- struct uprobe u = { .inode = inode, .offset = 0};
struct rb_node *n = uprobes_tree.rb_node;
- struct rb_node *close_node = NULL;
- struct uprobe *uprobe;
- int match;
while (n) {
- uprobe = rb_entry(n, struct uprobe, rb_node);
- match = match_uprobe(&u, uprobe);
-
- if (uprobe->inode == inode)
- close_node = n;
-
- if (!match)
- return close_node;
+ struct uprobe *u = rb_entry(n, struct uprobe, rb_node);
- if (match < 0)
+ if (inode < u->inode) {
n = n->rb_left;
- else
+ } else if (inode > u->inode) {
n = n->rb_right;
+ } else {
+ if (max < u->offset)
+ n = n->rb_left;
+ else if (min > u->offset)
+ n = n->rb_right;
+ else
+ break;
+ }
}
- return close_node;
+ return n;
}
/*
- * For a given inode, build a list of probes that need to be inserted.
+ * For a given range in vma, build a list of probes that need to be inserted.
*/
-static void build_probe_list(struct inode *inode, struct list_head *head)
+static void build_probe_list(struct inode *inode,
+ struct vm_area_struct *vma,
+ unsigned long start, unsigned long end,
+ struct list_head *head)
{
- struct uprobe *uprobe;
+ loff_t min, max;
unsigned long flags;
- struct rb_node *n;
-
- spin_lock_irqsave(&uprobes_treelock, flags);
-
- n = find_least_offset_node(inode);
+ struct rb_node *n, *t;
+ struct uprobe *u;
- for (; n; n = rb_next(n)) {
- uprobe = rb_entry(n, struct uprobe, rb_node);
- if (uprobe->inode != inode)
- break;
+ INIT_LIST_HEAD(head);
+ min = vaddr_to_offset(vma, start);
+ max = min + (end - start) - 1;
- list_add(&uprobe->pending_list, head);
- atomic_inc(&uprobe->ref);
+ spin_lock_irqsave(&uprobes_treelock, flags);
+ n = find_node_in_range(inode, min, max);
+ if (n) {
+ for (t = n; t; t = rb_prev(t)) {
+ u = rb_entry(t, struct uprobe, rb_node);
+ if (u->inode != inode || u->offset < min)
+ break;
+ list_add(&u->pending_list, head);
+ atomic_inc(&u->ref);
+ }
+ for (t = n; (t = rb_next(t)); ) {
+ u = rb_entry(t, struct uprobe, rb_node);
+ if (u->inode != inode || u->offset > max)
+ break;
+ list_add(&u->pending_list, head);
+ atomic_inc(&u->ref);
+ }
}
-
spin_unlock_irqrestore(&uprobes_treelock, flags);
}
@@ -1031,7 +1022,7 @@ static void build_probe_list(struct inode *inode, struct list_head *head)
int uprobe_mmap(struct vm_area_struct *vma)
{
struct list_head tmp_list;
- struct uprobe *uprobe;
+ struct uprobe *uprobe, *u;
struct inode *inode;
int ret, count;
@@ -1042,21 +1033,15 @@ int uprobe_mmap(struct vm_area_struct *vma)
if (!inode)
return 0;
- INIT_LIST_HEAD(&tmp_list);
mutex_lock(uprobes_mmap_hash(inode));
- build_probe_list(inode, &tmp_list);
+ build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list);
ret = 0;
count = 0;
- list_for_each_entry(uprobe, &tmp_list, pending_list) {
+ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
if (!ret) {
- loff_t vaddr = vma_address(vma, uprobe->offset);
-
- if (vaddr < vma->vm_start || vaddr >= vma->vm_end) {
- put_uprobe(uprobe);
- continue;
- }
+ unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
/*
@@ -1097,12 +1082,15 @@ int uprobe_mmap(struct vm_area_struct *vma)
void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
struct list_head tmp_list;
- struct uprobe *uprobe;
+ struct uprobe *uprobe, *u;
struct inode *inode;
if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
return;
+ if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
+ return;
+
if (!atomic_read(&vma->vm_mm->uprobes_state.count))
return;
@@ -1110,21 +1098,17 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon
if (!inode)
return;
- INIT_LIST_HEAD(&tmp_list);
mutex_lock(uprobes_mmap_hash(inode));
- build_probe_list(inode, &tmp_list);
-
- list_for_each_entry(uprobe, &tmp_list, pending_list) {
- loff_t vaddr = vma_address(vma, uprobe->offset);
-
- if (vaddr >= start && vaddr < end) {
- /*
- * An unregister could have removed the probe before
- * unmap. So check before we decrement the count.
- */
- if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1)
- atomic_dec(&vma->vm_mm->uprobes_state.count);
- }
+ build_probe_list(inode, vma, start, end, &tmp_list);
+
+ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
+ unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
+ /*
+ * An unregister could have removed the probe before
+ * unmap. So check before we decrement the count.
+ */
+ if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1)
+ atomic_dec(&vma->vm_mm->uprobes_state.count);
put_uprobe(uprobe);
}
mutex_unlock(uprobes_mmap_hash(inode));
@@ -1463,12 +1447,9 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
vma = find_vma(mm, bp_vaddr);
if (vma && vma->vm_start <= bp_vaddr) {
if (valid_vma(vma, false)) {
- struct inode *inode;
- loff_t offset;
+ struct inode *inode = vma->vm_file->f_mapping->host;
+ loff_t offset = vaddr_to_offset(vma, bp_vaddr);
- inode = vma->vm_file->f_mapping->host;
- offset = bp_vaddr - vma->vm_start;
- offset += (vma->vm_pgoff << PAGE_SHIFT);
uprobe = find_uprobe(inode, offset);
}
diff --git a/kernel/exit.c b/kernel/exit.c
index d17f6c4ddfa9..f65345f9e5bb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -483,7 +483,7 @@ static void close_files(struct files_struct * files)
rcu_read_unlock();
for (;;) {
unsigned long set;
- i = j * __NFDBITS;
+ i = j * BITS_PER_LONG;
if (i >= fdt->max_fds)
break;
set = fdt->open_fds[j++];
diff --git a/kernel/fork.c b/kernel/fork.c
index ff1cad3b7bdc..3bd2280d79f6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -114,6 +114,10 @@ int nr_processes(void)
return total;
}
+void __weak arch_release_task_struct(struct task_struct *tsk)
+{
+}
+
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static struct kmem_cache *task_struct_cachep;
@@ -122,17 +126,17 @@ static inline struct task_struct *alloc_task_struct_node(int node)
return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);
}
-void __weak arch_release_task_struct(struct task_struct *tsk) { }
-
static inline void free_task_struct(struct task_struct *tsk)
{
- arch_release_task_struct(tsk);
kmem_cache_free(task_struct_cachep, tsk);
}
#endif
+void __weak arch_release_thread_info(struct thread_info *ti)
+{
+}
+
#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
-void __weak arch_release_thread_info(struct thread_info *ti) { }
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
@@ -150,7 +154,6 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
static inline void free_thread_info(struct thread_info *ti)
{
- arch_release_thread_info(ti);
free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
}
# else
@@ -164,7 +167,6 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
static void free_thread_info(struct thread_info *ti)
{
- arch_release_thread_info(ti);
kmem_cache_free(thread_info_cache, ti);
}
@@ -205,10 +207,12 @@ static void account_kernel_stack(struct thread_info *ti, int account)
void free_task(struct task_struct *tsk)
{
account_kernel_stack(tsk->stack, -1);
+ arch_release_thread_info(tsk->stack);
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
put_seccomp_filter(tsk);
+ arch_release_task_struct(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
@@ -298,23 +302,16 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
return NULL;
ti = alloc_thread_info_node(tsk, node);
- if (!ti) {
- free_task_struct(tsk);
- return NULL;
- }
+ if (!ti)
+ goto free_tsk;
err = arch_dup_task_struct(tsk, orig);
+ if (err)
+ goto free_ti;
- /*
- * We defer looking at err, because we will need this setup
- * for the clean up path to work correctly.
- */
tsk->stack = ti;
- setup_thread_stack(tsk, orig);
-
- if (err)
- goto out;
+ setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
clear_tsk_need_resched(tsk);
stackend = end_of_stack(tsk);
@@ -338,8 +335,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
return tsk;
-out:
+free_ti:
free_thread_info(ti);
+free_tsk:
free_task_struct(tsk);
return NULL;
}
@@ -383,16 +381,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
- long pages = vma_pages(mpnt);
- mm->total_vm -= pages;
vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
- -pages);
+ -vma_pages(mpnt));
continue;
}
charge = 0;
if (mpnt->vm_flags & VM_ACCOUNT) {
- unsigned long len;
- len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
+ unsigned long len = vma_pages(mpnt);
+
if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
goto fail_nomem;
charge = len;
@@ -1310,7 +1306,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
p->memcg_batch.do_batch = 0;
p->memcg_batch.memcg = NULL;
#endif
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index bdb180325551..131ca176b497 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -133,7 +133,7 @@ irqreturn_t
handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
{
irqreturn_t retval = IRQ_NONE;
- unsigned int random = 0, irq = desc->irq_data.irq;
+ unsigned int flags = 0, irq = desc->irq_data.irq;
do {
irqreturn_t res;
@@ -161,7 +161,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
/* Fall through to add to randomness */
case IRQ_HANDLED:
- random |= action->flags;
+ flags |= action->flags;
break;
default:
@@ -172,8 +172,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
action = action->next;
} while (action);
- if (random & IRQF_SAMPLE_RANDOM)
- add_interrupt_randomness(irq);
+ add_interrupt_randomness(irq, flags);
if (!noirqdebug)
note_interrupt(irq, desc, retval);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 814c9ef6bba1..0a8e8f059627 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -893,22 +893,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
return -ENOSYS;
if (!try_module_get(desc->owner))
return -ENODEV;
- /*
- * Some drivers like serial.c use request_irq() heavily,
- * so we have to be careful not to interfere with a
- * running system.
- */
- if (new->flags & IRQF_SAMPLE_RANDOM) {
- /*
- * This function might sleep, we want to call it first,
- * outside of the atomic block.
- * Yes, this might clear the entropy pool if the wrong
- * driver is attempted to be loaded, without actually
- * installing a new handler, but is this really a problem,
- * only the sysadmin is able to do this.
- */
- rand_initialize_irq(irq);
- }
/*
* Check whether the interrupt nests into another interrupt
@@ -1354,7 +1338,6 @@ EXPORT_SYMBOL(free_irq);
* Flags:
*
* IRQF_SHARED Interrupt is shared
- * IRQF_SAMPLE_RANDOM The interrupt can be used for entropy
* IRQF_TRIGGER_* Specify active edge(s) or level
*
*/
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 4e2e472f6aeb..0668d58d6413 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1424,7 +1424,7 @@ static void update_vmcoreinfo_note(void)
void crash_save_vmcoreinfo(void)
{
- vmcoreinfo_append_str("CRASHTIME=%ld", get_seconds());
+ vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
update_vmcoreinfo_note();
}
diff --git a/kernel/kmod.c b/kernel/kmod.c
index ff2c7cb86d77..6f99aead66c6 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -45,6 +45,13 @@ extern int max_threads;
static struct workqueue_struct *khelper_wq;
+/*
+ * kmod_thread_locker is used for deadlock avoidance. There is no explicit
+ * locking to protect this global - it is private to the singleton khelper
+ * thread and should only ever be modified by that thread.
+ */
+static const struct task_struct *kmod_thread_locker;
+
#define CAP_BSET (void *)1
#define CAP_PI (void *)2
@@ -221,6 +228,13 @@ fail:
return 0;
}
+static int call_helper(void *data)
+{
+ /* Worker thread started blocking khelper thread. */
+ kmod_thread_locker = current;
+ return ____call_usermodehelper(data);
+}
+
static void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
if (info->cleanup)
@@ -295,9 +309,12 @@ static void __call_usermodehelper(struct work_struct *work)
if (wait == UMH_WAIT_PROC)
pid = kernel_thread(wait_for_helper, sub_info,
CLONE_FS | CLONE_FILES | SIGCHLD);
- else
- pid = kernel_thread(____call_usermodehelper, sub_info,
+ else {
+ pid = kernel_thread(call_helper, sub_info,
CLONE_VFORK | SIGCHLD);
+ /* Worker thread stopped blocking khelper thread. */
+ kmod_thread_locker = NULL;
+ }
switch (wait) {
case UMH_NO_WAIT:
@@ -548,6 +565,16 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
retval = -EBUSY;
goto out;
}
+ /*
+ * Worker thread must not wait for khelper thread at below
+ * wait_for_completion() if the thread was created with CLONE_VFORK
+ * flag, for khelper thread is already waiting for the thread at
+ * wait_for_completion() in do_fork().
+ */
+ if (wait != UMH_NO_WAIT && current == kmod_thread_locker) {
+ retval = -EBUSY;
+ goto out;
+ }
sub_info->complete = &done;
sub_info->wait = wait;
@@ -577,6 +604,12 @@ unlock:
return retval;
}
+/*
+ * call_usermodehelper_fns() will not run the caller-provided cleanup function
+ * if a memory allocation failure is experienced. So the caller might need to
+ * check the call_usermodehelper_fns() return value: if it is -ENOMEM, perform
+ * the necessaary cleanup within the caller.
+ */
int call_usermodehelper_fns(
char *path, char **argv, char **envp, int wait,
int (*init)(struct subprocess_info *info, struct cred *new),
diff --git a/kernel/panic.c b/kernel/panic.c
index d2a5f4ecc6dd..e1b2822fff97 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -75,6 +75,14 @@ void panic(const char *fmt, ...)
int state = 0;
/*
+ * Disable local interrupts. This will prevent panic_smp_self_stop
+ * from deadlocking the first cpu that invokes the panic, since
+ * there is nothing to prevent an interrupt handler (that runs
+ * after the panic_lock is acquired) from invoking panic again.
+ */
+ local_irq_disable();
+
+ /*
* It's possible to come here directly from a panic-assertion and
* not have preempt disabled. Some functions called from here want
* preempt to be disabled. No point enabling it later though...
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index c8b7446b27df..1da39ea248fd 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -178,6 +178,9 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
+ /* Kick the lockup detector */
+ lockup_detector_bootcpu_resume();
+
Enable_cpus:
enable_nonboot_cpus();
diff --git a/kernel/printk.c b/kernel/printk.c
index ac4bc9e79465..6a76ab9d4476 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -216,6 +216,7 @@ struct log {
*/
static DEFINE_RAW_SPINLOCK(logbuf_lock);
+#ifdef CONFIG_PRINTK
/* the next printk record to read by syslog(READ) or /proc/kmsg */
static u64 syslog_seq;
static u32 syslog_idx;
@@ -228,14 +229,19 @@ static u32 log_first_idx;
/* index and sequence number of the next record to store in the buffer */
static u64 log_next_seq;
-#ifdef CONFIG_PRINTK
static u32 log_next_idx;
+/* the next printk record to write to the console */
+static u64 console_seq;
+static u32 console_idx;
+static enum log_flags console_prev;
+
/* the next printk record to read after the last 'clear' command */
static u64 clear_seq;
static u32 clear_idx;
-#define LOG_LINE_MAX 1024
+#define PREFIX_MAX 32
+#define LOG_LINE_MAX 1024 - PREFIX_MAX
/* record buffer */
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
@@ -360,6 +366,7 @@ static void log_store(int facility, int level,
struct devkmsg_user {
u64 seq;
u32 idx;
+ enum log_flags prev;
struct mutex lock;
char buf[8192];
};
@@ -382,8 +389,10 @@ static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv,
line = buf;
for (i = 0; i < count; i++) {
- if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len))
+ if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len)) {
+ ret = -EFAULT;
goto out;
+ }
line += iv[i].iov_len;
}
@@ -425,6 +434,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
struct log *msg;
u64 ts_usec;
size_t i;
+ char cont = '-';
size_t len;
ssize_t ret;
@@ -462,8 +472,25 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
msg = log_from_idx(user->idx);
ts_usec = msg->ts_nsec;
do_div(ts_usec, 1000);
- len = sprintf(user->buf, "%u,%llu,%llu;",
- (msg->facility << 3) | msg->level, user->seq, ts_usec);
+
+ /*
+ * If we couldn't merge continuation line fragments during the print,
+ * export the stored flags to allow an optional external merge of the
+ * records. Merging the records isn't always neccessarily correct, like
+ * when we hit a race during printing. In most cases though, it produces
+ * better readable output. 'c' in the record flags mark the first
+ * fragment of a line, '+' the following.
+ */
+ if (msg->flags & LOG_CONT && !(user->prev & LOG_CONT))
+ cont = 'c';
+ else if ((msg->flags & LOG_CONT) ||
+ ((user->prev & LOG_CONT) && !(msg->flags & LOG_PREFIX)))
+ cont = '+';
+
+ len = sprintf(user->buf, "%u,%llu,%llu,%c;",
+ (msg->facility << 3) | msg->level,
+ user->seq, ts_usec, cont);
+ user->prev = msg->flags;
/* escape non-printable characters */
for (i = 0; i < msg->text_len; i++) {
@@ -646,6 +673,15 @@ void log_buf_kexec_setup(void)
VMCOREINFO_SYMBOL(log_buf_len);
VMCOREINFO_SYMBOL(log_first_idx);
VMCOREINFO_SYMBOL(log_next_idx);
+ /*
+ * Export struct log size and field offsets. User space tools can
+ * parse it and detect any changes to structure down the line.
+ */
+ VMCOREINFO_STRUCT_SIZE(log);
+ VMCOREINFO_OFFSET(log, ts_nsec);
+ VMCOREINFO_OFFSET(log, len);
+ VMCOREINFO_OFFSET(log, text_len);
+ VMCOREINFO_OFFSET(log, dict_len);
}
#endif
@@ -876,7 +912,7 @@ static size_t msg_print_text(const struct log *msg, enum log_flags prev,
if (buf) {
if (print_prefix(msg, syslog, NULL) +
- text_len + 1>= size - len)
+ text_len + 1 >= size - len)
break;
if (prefix)
@@ -907,7 +943,7 @@ static int syslog_print(char __user *buf, int size)
struct log *msg;
int len = 0;
- text = kmalloc(LOG_LINE_MAX, GFP_KERNEL);
+ text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
if (!text)
return -ENOMEM;
@@ -930,7 +966,8 @@ static int syslog_print(char __user *buf, int size)
skip = syslog_partial;
msg = log_from_idx(syslog_idx);
- n = msg_print_text(msg, syslog_prev, true, text, LOG_LINE_MAX);
+ n = msg_print_text(msg, syslog_prev, true, text,
+ LOG_LINE_MAX + PREFIX_MAX);
if (n - syslog_partial <= size) {
/* message fits into buffer, move forward */
syslog_idx = log_next(syslog_idx);
@@ -969,7 +1006,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
char *text;
int len = 0;
- text = kmalloc(LOG_LINE_MAX, GFP_KERNEL);
+ text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
if (!text)
return -ENOMEM;
@@ -1022,7 +1059,8 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
struct log *msg = log_from_idx(idx);
int textlen;
- textlen = msg_print_text(msg, prev, true, text, LOG_LINE_MAX);
+ textlen = msg_print_text(msg, prev, true, text,
+ LOG_LINE_MAX + PREFIX_MAX);
if (textlen < 0) {
len = textlen;
break;
@@ -1349,20 +1387,36 @@ static struct cont {
u64 ts_nsec; /* time of first print */
u8 level; /* log level of first message */
u8 facility; /* log level of first message */
+ enum log_flags flags; /* prefix, newline flags */
bool flushed:1; /* buffer sealed and committed */
} cont;
-static void cont_flush(void)
+static void cont_flush(enum log_flags flags)
{
if (cont.flushed)
return;
if (cont.len == 0)
return;
- log_store(cont.facility, cont.level, LOG_NOCONS, cont.ts_nsec,
- NULL, 0, cont.buf, cont.len);
-
- cont.flushed = true;
+ if (cont.cons) {
+ /*
+ * If a fragment of this line was directly flushed to the
+ * console; wait for the console to pick up the rest of the
+ * line. LOG_NOCONS suppresses a duplicated output.
+ */
+ log_store(cont.facility, cont.level, flags | LOG_NOCONS,
+ cont.ts_nsec, NULL, 0, cont.buf, cont.len);
+ cont.flags = flags;
+ cont.flushed = true;
+ } else {
+ /*
+ * If no fragment of this line ever reached the console,
+ * just submit it to the store and free the buffer.
+ */
+ log_store(cont.facility, cont.level, flags, 0,
+ NULL, 0, cont.buf, cont.len);
+ cont.len = 0;
+ }
}
static bool cont_add(int facility, int level, const char *text, size_t len)
@@ -1371,7 +1425,8 @@ static bool cont_add(int facility, int level, const char *text, size_t len)
return false;
if (cont.len + len > sizeof(cont.buf)) {
- cont_flush();
+ /* the line gets too long, split it up in separate records */
+ cont_flush(LOG_CONT);
return false;
}
@@ -1380,12 +1435,17 @@ static bool cont_add(int facility, int level, const char *text, size_t len)
cont.level = level;
cont.owner = current;
cont.ts_nsec = local_clock();
+ cont.flags = 0;
cont.cons = 0;
cont.flushed = false;
}
memcpy(cont.buf + cont.len, text, len);
cont.len += len;
+
+ if (cont.len > (sizeof(cont.buf) * 80) / 100)
+ cont_flush(LOG_CONT);
+
return true;
}
@@ -1394,7 +1454,7 @@ static size_t cont_print_text(char *text, size_t size)
size_t textlen = 0;
size_t len;
- if (cont.cons == 0) {
+ if (cont.cons == 0 && (console_prev & LOG_NEWLINE)) {
textlen += print_time(cont.ts_nsec, text);
size -= textlen;
}
@@ -1409,7 +1469,8 @@ static size_t cont_print_text(char *text, size_t size)
}
if (cont.flushed) {
- text[textlen++] = '\n';
+ if (cont.flags & LOG_NEWLINE)
+ text[textlen++] = '\n';
/* got everything, release buffer */
cont.len = 0;
}
@@ -1481,17 +1542,23 @@ asmlinkage int vprintk_emit(int facility, int level,
lflags |= LOG_NEWLINE;
}
- /* strip syslog prefix and extract log level or control flags */
- if (text[0] == '<' && text[1] && text[2] == '>') {
- switch (text[1]) {
- case '0' ... '7':
- if (level == -1)
- level = text[1] - '0';
- case 'd': /* KERN_DEFAULT */
- lflags |= LOG_PREFIX;
- case 'c': /* KERN_CONT */
- text += 3;
- text_len -= 3;
+ /* strip kernel syslog prefix and extract log level or control flags */
+ if (facility == 0) {
+ int kern_level = printk_get_level(text);
+
+ if (kern_level) {
+ const char *end_of_header = printk_skip_level(text);
+ switch (kern_level) {
+ case '0' ... '7':
+ if (level == -1)
+ level = kern_level - '0';
+ case 'd': /* KERN_DEFAULT */
+ lflags |= LOG_PREFIX;
+ case 'c': /* KERN_CONT */
+ break;
+ }
+ text_len -= end_of_header - text;
+ text = (char *)end_of_header;
}
}
@@ -1507,7 +1574,7 @@ asmlinkage int vprintk_emit(int facility, int level,
* or another task also prints continuation lines.
*/
if (cont.len && (lflags & LOG_PREFIX || cont.owner != current))
- cont_flush();
+ cont_flush(LOG_NEWLINE);
/* buffer line if possible, otherwise store it right away */
if (!cont_add(facility, level, text, text_len))
@@ -1525,7 +1592,7 @@ asmlinkage int vprintk_emit(int facility, int level,
if (cont.len && cont.owner == current) {
if (!(lflags & LOG_PREFIX))
stored = cont_add(facility, level, text, text_len);
- cont_flush();
+ cont_flush(LOG_NEWLINE);
}
if (!stored)
@@ -1616,9 +1683,20 @@ asmlinkage int printk(const char *fmt, ...)
}
EXPORT_SYMBOL(printk);
-#else
+#else /* CONFIG_PRINTK */
+#define LOG_LINE_MAX 0
+#define PREFIX_MAX 0
#define LOG_LINE_MAX 0
+static u64 syslog_seq;
+static u32 syslog_idx;
+static u64 console_seq;
+static u32 console_idx;
+static enum log_flags syslog_prev;
+static u64 log_first_seq;
+static u32 log_first_idx;
+static u64 log_next_seq;
+static enum log_flags console_prev;
static struct cont {
size_t len;
size_t cons;
@@ -1902,10 +1980,34 @@ void wake_up_klogd(void)
this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
}
-/* the next printk record to write to the console */
-static u64 console_seq;
-static u32 console_idx;
-static enum log_flags console_prev;
+static void console_cont_flush(char *text, size_t size)
+{
+ unsigned long flags;
+ size_t len;
+
+ raw_spin_lock_irqsave(&logbuf_lock, flags);
+
+ if (!cont.len)
+ goto out;
+
+ /*
+ * We still queue earlier records, likely because the console was
+ * busy. The earlier ones need to be printed before this one, we
+ * did not flush any fragment so far, so just let it queue up.
+ */
+ if (console_seq < log_next_seq && !cont.cons)
+ goto out;
+
+ len = cont_print_text(text, size);
+ raw_spin_unlock(&logbuf_lock);
+ stop_critical_timings();
+ call_console_drivers(cont.level, text, len);
+ start_critical_timings();
+ local_irq_restore(flags);
+ return;
+out:
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+}
/**
* console_unlock - unlock the console system
@@ -1923,7 +2025,7 @@ static enum log_flags console_prev;
*/
void console_unlock(void)
{
- static char text[LOG_LINE_MAX];
+ static char text[LOG_LINE_MAX + PREFIX_MAX];
static u64 seen_seq;
unsigned long flags;
bool wake_klogd = false;
@@ -1937,19 +2039,7 @@ void console_unlock(void)
console_may_schedule = 0;
/* flush buffered message fragment immediately to console */
- raw_spin_lock_irqsave(&logbuf_lock, flags);
- if (cont.len && (cont.cons < cont.len || cont.flushed)) {
- size_t len;
-
- len = cont_print_text(text, sizeof(text));
- raw_spin_unlock(&logbuf_lock);
- stop_critical_timings();
- call_console_drivers(cont.level, text, len);
- start_critical_timings();
- local_irq_restore(flags);
- } else
- raw_spin_unlock_irqrestore(&logbuf_lock, flags);
-
+ console_cont_flush(text, sizeof(text));
again:
for (;;) {
struct log *msg;
@@ -1986,6 +2076,7 @@ skip:
* will properly dump everything later.
*/
msg->flags &= ~LOG_NOCONS;
+ console_prev = msg->flags;
goto skip;
}
diff --git a/kernel/resource.c b/kernel/resource.c
index dc8b47764443..34d45886ee84 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -7,6 +7,8 @@
* Arbitrary resource management.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/export.h>
#include <linux/errno.h>
#include <linux/ioport.h>
@@ -791,8 +793,28 @@ void __init reserve_region_with_split(struct resource *root,
resource_size_t start, resource_size_t end,
const char *name)
{
+ int abort = 0;
+
write_lock(&resource_lock);
- __reserve_region_with_split(root, start, end, name);
+ if (root->start > start || root->end < end) {
+ pr_err("requested range [0x%llx-0x%llx] not in root %pr\n",
+ (unsigned long long)start, (unsigned long long)end,
+ root);
+ if (start > root->end || end < root->start)
+ abort = 1;
+ else {
+ if (end > root->end)
+ end = root->end;
+ if (start < root->start)
+ start = root->start;
+ pr_err("fixing request to [0x%llx-0x%llx]\n",
+ (unsigned long long)start,
+ (unsigned long long)end);
+ }
+ dump_stack();
+ }
+ if (!abort)
+ __reserve_region_with_split(root, start, end, name);
write_unlock(&resource_lock);
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 468bdd44c1ba..d325c4b2dcbb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1096,7 +1096,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
* a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
*
* sched_move_task() holds both and thus holding either pins the cgroup,
- * see set_task_rq().
+ * see task_group().
*
* Furthermore, all task_rq users should acquire both locks, see
* task_rq_lock().
@@ -1910,12 +1910,12 @@ static inline void
prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
+ trace_sched_switch(prev, next);
sched_info_switch(prev, next);
perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
prepare_lock_switch(rq, next);
prepare_arch_switch(next);
- trace_sched_switch(prev, next);
}
/**
@@ -6024,6 +6024,11 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
* SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
* allows us to avoid some pointer chasing select_idle_sibling().
*
+ * Iterate domains and sched_groups downward, assigning CPUs to be
+ * select_idle_sibling() hw buddy. Cross-wiring hw makes bouncing
+ * due to random perturbation self canceling, ie sw buddies pull
+ * their counterpart to their CPU's hw counterpart.
+ *
* Also keep a unique ID per domain (we use the first cpu number in
* the cpumask of the domain), this allows us to quickly tell if
* two cpus are in the same cache domain, see cpus_share_cache().
@@ -6037,8 +6042,40 @@ static void update_top_cache_domain(int cpu)
int id = cpu;
sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
- if (sd)
+ if (sd) {
+ struct sched_domain *tmp = sd;
+ struct sched_group *sg, *prev;
+ bool right;
+
+ /*
+ * Traverse to first CPU in group, and count hops
+ * to cpu from there, switching direction on each
+ * hop, never ever pointing the last CPU rightward.
+ */
+ do {
+ id = cpumask_first(sched_domain_span(tmp));
+ prev = sg = tmp->groups;
+ right = 1;
+
+ while (cpumask_first(sched_group_cpus(sg)) != id)
+ sg = sg->next;
+
+ while (!cpumask_test_cpu(cpu, sched_group_cpus(sg))) {
+ prev = sg;
+ sg = sg->next;
+ right = !right;
+ }
+
+ /* A CPU went down, never point back to domain start. */
+ if (right && cpumask_first(sched_group_cpus(sg->next)) == id)
+ right = false;
+
+ sg = right ? sg->next : prev;
+ tmp->idle_buddy = cpumask_first(sched_group_cpus(sg));
+ } while ((tmp = tmp->child));
+
id = cpumask_first(sched_domain_span(sd));
+ }
rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
per_cpu(sd_llc_id, cpu) = id;
@@ -7097,34 +7134,66 @@ match2:
mutex_unlock(&sched_domains_mutex);
}
+static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */
+
/*
* Update cpusets according to cpu_active mask. If cpusets are
* disabled, cpuset_update_active_cpus() becomes a simple wrapper
* around partition_sched_domains().
+ *
+ * If we come here as part of a suspend/resume, don't touch cpusets because we
+ * want to restore it back to its original state upon resume anyway.
*/
static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
- switch (action & ~CPU_TASKS_FROZEN) {
+ switch (action) {
+ case CPU_ONLINE_FROZEN:
+ case CPU_DOWN_FAILED_FROZEN:
+
+ /*
+ * num_cpus_frozen tracks how many CPUs are involved in suspend
+ * resume sequence. As long as this is not the last online
+ * operation in the resume sequence, just build a single sched
+ * domain, ignoring cpusets.
+ */
+ num_cpus_frozen--;
+ if (likely(num_cpus_frozen)) {
+ partition_sched_domains(1, NULL, NULL);
+ break;
+ }
+
+ /*
+ * This is the last CPU online operation. So fall through and
+ * restore the original sched domains by considering the
+ * cpuset configurations.
+ */
+
case CPU_ONLINE:
case CPU_DOWN_FAILED:
- cpuset_update_active_cpus();
- return NOTIFY_OK;
+ cpuset_update_active_cpus(true);
+ break;
default:
return NOTIFY_DONE;
}
+ return NOTIFY_OK;
}
static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
- switch (action & ~CPU_TASKS_FROZEN) {
+ switch (action) {
case CPU_DOWN_PREPARE:
- cpuset_update_active_cpus();
- return NOTIFY_OK;
+ cpuset_update_active_cpus(false);
+ break;
+ case CPU_DOWN_PREPARE_FROZEN:
+ num_cpus_frozen++;
+ partition_sched_domains(1, NULL, NULL);
+ break;
default:
return NOTIFY_DONE;
}
+ return NOTIFY_OK;
}
void __init sched_init_smp(void)
@@ -7589,6 +7658,7 @@ void sched_destroy_group(struct task_group *tg)
*/
void sched_move_task(struct task_struct *tsk)
{
+ struct task_group *tg;
int on_rq, running;
unsigned long flags;
struct rq *rq;
@@ -7603,6 +7673,12 @@ void sched_move_task(struct task_struct *tsk)
if (unlikely(running))
tsk->sched_class->put_prev_task(rq, tsk);
+ tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id,
+ lockdep_is_held(&tsk->sighand->siglock)),
+ struct task_group, css);
+ tg = autogroup_task_group(tsk, tg);
+ tsk->sched_task_group = tg;
+
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->task_move_group)
tsk->sched_class->task_move_group(tsk, on_rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c099cc6eebe3..22321db64952 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2637,8 +2637,6 @@ static int select_idle_sibling(struct task_struct *p, int target)
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
struct sched_domain *sd;
- struct sched_group *sg;
- int i;
/*
* If the task is going to be woken-up on this cpu and if it is
@@ -2655,29 +2653,17 @@ static int select_idle_sibling(struct task_struct *p, int target)
return prev_cpu;
/*
- * Otherwise, iterate the domains and find an elegible idle cpu.
+ * Otherwise, check assigned siblings to find an elegible idle cpu.
*/
sd = rcu_dereference(per_cpu(sd_llc, target));
- for_each_lower_domain(sd) {
- sg = sd->groups;
- do {
- if (!cpumask_intersects(sched_group_cpus(sg),
- tsk_cpus_allowed(p)))
- goto next;
-
- for_each_cpu(i, sched_group_cpus(sg)) {
- if (!idle_cpu(i))
- goto next;
- }
- target = cpumask_first_and(sched_group_cpus(sg),
- tsk_cpus_allowed(p));
- goto done;
-next:
- sg = sg->next;
- } while (sg != sd->groups);
+ for_each_lower_domain(sd) {
+ if (!cpumask_test_cpu(sd->idle_buddy, tsk_cpus_allowed(p)))
+ continue;
+ if (idle_cpu(sd->idle_buddy))
+ return sd->idle_buddy;
}
-done:
+
return target;
}
@@ -3068,16 +3054,19 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
#define LBF_ALL_PINNED 0x01
#define LBF_NEED_BREAK 0x02
+#define LBF_SOME_PINNED 0x04
struct lb_env {
struct sched_domain *sd;
- int src_cpu;
struct rq *src_rq;
+ int src_cpu;
int dst_cpu;
struct rq *dst_rq;
+ struct cpumask *dst_grpmask;
+ int new_dst_cpu;
enum cpu_idle_type idle;
long imbalance;
unsigned int flags;
@@ -3145,9 +3134,31 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
* 3) are cache-hot on their current CPU.
*/
if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
+ int new_dst_cpu;
+
schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
+
+ /*
+ * Remember if this task can be migrated to any other cpu in
+ * our sched_group. We may want to revisit it if we couldn't
+ * meet load balance goals by pulling other tasks on src_cpu.
+ *
+ * Also avoid computing new_dst_cpu if we have already computed
+ * one in current iteration.
+ */
+ if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED))
+ return 0;
+
+ new_dst_cpu = cpumask_first_and(env->dst_grpmask,
+ tsk_cpus_allowed(p));
+ if (new_dst_cpu < nr_cpu_ids) {
+ env->flags |= LBF_SOME_PINNED;
+ env->new_dst_cpu = new_dst_cpu;
+ }
return 0;
}
+
+ /* Record that we found atleast one task that could run on dst_cpu */
env->flags &= ~LBF_ALL_PINNED;
if (task_running(env->src_rq, p)) {
@@ -4227,7 +4238,8 @@ static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
- int ld_moved, active_balance = 0;
+ int ld_moved, cur_ld_moved, active_balance = 0;
+ int lb_iterations, max_lb_iterations;
struct sched_group *group;
struct rq *busiest;
unsigned long flags;
@@ -4237,11 +4249,13 @@ static int load_balance(int this_cpu, struct rq *this_rq,
.sd = sd,
.dst_cpu = this_cpu,
.dst_rq = this_rq,
+ .dst_grpmask = sched_group_cpus(sd->groups),
.idle = idle,
.loop_break = sched_nr_migrate_break,
};
cpumask_copy(cpus, cpu_active_mask);
+ max_lb_iterations = cpumask_weight(env.dst_grpmask);
schedstat_inc(sd, lb_count[idle]);
@@ -4267,6 +4281,7 @@ redo:
schedstat_add(sd, lb_imbalance[idle], env.imbalance);
ld_moved = 0;
+ lb_iterations = 1;
if (busiest->nr_running > 1) {
/*
* Attempt to move tasks. If find_busiest_group has found
@@ -4284,7 +4299,13 @@ more_balance:
double_rq_lock(this_rq, busiest);
if (!env.loop)
update_h_load(env.src_cpu);
- ld_moved += move_tasks(&env);
+
+ /*
+ * cur_ld_moved - load moved in current iteration
+ * ld_moved - cumulative load moved across iterations
+ */
+ cur_ld_moved = move_tasks(&env);
+ ld_moved += cur_ld_moved;
double_rq_unlock(this_rq, busiest);
local_irq_restore(flags);
@@ -4296,14 +4317,52 @@ more_balance:
/*
* some other cpu did the load balance for us.
*/
- if (ld_moved && this_cpu != smp_processor_id())
- resched_cpu(this_cpu);
+ if (cur_ld_moved && env.dst_cpu != smp_processor_id())
+ resched_cpu(env.dst_cpu);
+
+ /*
+ * Revisit (affine) tasks on src_cpu that couldn't be moved to
+ * us and move them to an alternate dst_cpu in our sched_group
+ * where they can run. The upper limit on how many times we
+ * iterate on same src_cpu is dependent on number of cpus in our
+ * sched_group.
+ *
+ * This changes load balance semantics a bit on who can move
+ * load to a given_cpu. In addition to the given_cpu itself
+ * (or a ilb_cpu acting on its behalf where given_cpu is
+ * nohz-idle), we now have balance_cpu in a position to move
+ * load to given_cpu. In rare situations, this may cause
+ * conflicts (balance_cpu and given_cpu/ilb_cpu deciding
+ * _independently_ and at _same_ time to move some load to
+ * given_cpu) causing exceess load to be moved to given_cpu.
+ * This however should not happen so much in practice and
+ * moreover subsequent load balance cycles should correct the
+ * excess load moved.
+ */
+ if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 &&
+ lb_iterations++ < max_lb_iterations) {
+
+ this_rq = cpu_rq(env.new_dst_cpu);
+ env.dst_rq = this_rq;
+ env.dst_cpu = env.new_dst_cpu;
+ env.flags &= ~LBF_SOME_PINNED;
+ env.loop = 0;
+ env.loop_break = sched_nr_migrate_break;
+ /*
+ * Go back to "more_balance" rather than "redo" since we
+ * need to continue with same src_cpu.
+ */
+ goto more_balance;
+ }
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(env.flags & LBF_ALL_PINNED)) {
cpumask_clear_cpu(cpu_of(busiest), cpus);
- if (!cpumask_empty(cpus))
+ if (!cpumask_empty(cpus)) {
+ env.loop = 0;
+ env.loop_break = sched_nr_migrate_break;
goto redo;
+ }
goto out_balanced;
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 55844f24435a..c35a1a7dd4d6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -538,22 +538,19 @@ extern int group_balance_cpu(struct sched_group *sg);
/*
* Return the group to which this tasks belongs.
*
- * We use task_subsys_state_check() and extend the RCU verification with
- * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
- * task it moves into the cgroup. Therefore by holding either of those locks,
- * we pin the task to the current cgroup.
+ * We cannot use task_subsys_state() and friends because the cgroup
+ * subsystem changes that value before the cgroup_subsys::attach() method
+ * is called, therefore we cannot pin it and might observe the wrong value.
+ *
+ * The same is true for autogroup's p->signal->autogroup->tg, the autogroup
+ * core changes this before calling sched_move_task().
+ *
+ * Instead we use a 'copy' which is updated from sched_move_task() while
+ * holding both task_struct::pi_lock and rq::lock.
*/
static inline struct task_group *task_group(struct task_struct *p)
{
- struct task_group *tg;
- struct cgroup_subsys_state *css;
-
- css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
- lockdep_is_held(&p->pi_lock) ||
- lockdep_is_held(&task_rq(p)->lock));
- tg = container_of(css, struct task_group, css);
-
- return autogroup_task_group(p, tg);
+ return p->sched_task_group;
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 671f9594e368..b73e681df09e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -210,6 +210,14 @@ asmlinkage void __do_softirq(void)
__u32 pending;
int max_restart = MAX_SOFTIRQ_RESTART;
int cpu;
+ unsigned long old_flags = current->flags;
+
+ /*
+ * Mask out PF_MEMALLOC s current task context is borrowed for the
+ * softirq. A softirq handled such as network RX might set PF_MEMALLOC
+ * again if the socket is related to swap
+ */
+ current->flags &= ~PF_MEMALLOC;
pending = local_softirq_pending();
account_system_vtime(current);
@@ -265,6 +273,7 @@ restart:
account_system_vtime(current);
__local_bh_enable(SOFTIRQ_OFFSET);
+ tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
#ifndef __ARCH_HAS_DO_SOFTIRQ
diff --git a/kernel/sys.c b/kernel/sys.c
index 2d39a84cd857..241507f23eca 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2015,7 +2015,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
break;
}
me->pdeath_signal = arg2;
- error = 0;
break;
case PR_GET_PDEATHSIG:
error = put_user(me->pdeath_signal, (int __user *)arg2);
@@ -2029,7 +2028,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
break;
}
set_dumpable(me->mm, arg2);
- error = 0;
break;
case PR_SET_UNALIGN:
@@ -2056,10 +2054,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_SET_TIMING:
if (arg2 != PR_TIMING_STATISTICAL)
error = -EINVAL;
- else
- error = 0;
break;
-
case PR_SET_NAME:
comm[sizeof(me->comm)-1] = 0;
if (strncpy_from_user(comm, (char __user *)arg2,
@@ -2067,20 +2062,19 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EFAULT;
set_task_comm(me, comm);
proc_comm_connector(me);
- return 0;
+ break;
case PR_GET_NAME:
get_task_comm(comm, me);
if (copy_to_user((char __user *)arg2, comm,
sizeof(comm)))
return -EFAULT;
- return 0;
+ break;
case PR_GET_ENDIAN:
error = GET_ENDIAN(me, arg2);
break;
case PR_SET_ENDIAN:
error = SET_ENDIAN(me, arg2);
break;
-
case PR_GET_SECCOMP:
error = prctl_get_seccomp();
break;
@@ -2108,7 +2102,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
current->default_timer_slack_ns;
else
current->timer_slack_ns = arg2;
- error = 0;
break;
case PR_MCE_KILL:
if (arg4 | arg5)
@@ -2134,7 +2127,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
default:
return -EINVAL;
}
- error = 0;
break;
case PR_MCE_KILL_GET:
if (arg2 | arg3 | arg4 | arg5)
@@ -2153,7 +2145,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
break;
case PR_SET_CHILD_SUBREAPER:
me->signal->is_child_subreaper = !!arg2;
- error = 0;
break;
case PR_GET_CHILD_SUBREAPER:
error = put_user(me->signal->is_child_subreaper,
@@ -2195,46 +2186,52 @@ static void argv_cleanup(struct subprocess_info *info)
argv_free(info->argv);
}
-/**
- * orderly_poweroff - Trigger an orderly system poweroff
- * @force: force poweroff if command execution fails
- *
- * This may be called from any context to trigger a system shutdown.
- * If the orderly shutdown fails, it will force an immediate shutdown.
- */
-int orderly_poweroff(bool force)
+static int __orderly_poweroff(void)
{
int argc;
- char **argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
+ char **argv;
static char *envp[] = {
"HOME=/",
"PATH=/sbin:/bin:/usr/sbin:/usr/bin",
NULL
};
- int ret = -ENOMEM;
+ int ret;
+ argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
if (argv == NULL) {
printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
__func__, poweroff_cmd);
- goto out;
+ return -ENOMEM;
}
ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_NO_WAIT,
NULL, argv_cleanup, NULL);
-out:
- if (likely(!ret))
- return 0;
-
if (ret == -ENOMEM)
argv_free(argv);
- if (force) {
+ return ret;
+}
+
+/**
+ * orderly_poweroff - Trigger an orderly system poweroff
+ * @force: force poweroff if command execution fails
+ *
+ * This may be called from any context to trigger a system shutdown.
+ * If the orderly shutdown fails, it will force an immediate shutdown.
+ */
+int orderly_poweroff(bool force)
+{
+ int ret = __orderly_poweroff();
+
+ if (ret && force) {
printk(KERN_WARNING "Failed to start orderly shutdown: "
"forcing the issue\n");
- /* I guess this should try to kick off some daemon to
- sync and poweroff asap. Or not even bother syncing
- if we're doing an emergency shutdown? */
+ /*
+ * I guess this should try to kick off some daemon to sync and
+ * poweroff asap. Or not even bother syncing if we're doing an
+ * emergency shutdown?
+ */
emergency_sync();
kernel_power_off();
}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4ab11879aeb4..6502d35a25ba 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -30,6 +30,7 @@
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/kmemcheck.h>
+#include <linux/kmemleak.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
@@ -174,6 +175,11 @@ static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
+static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
+static int proc_dostring_coredump(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
+
#ifdef CONFIG_MAGIC_SYSRQ
/* Note: sysrq code uses it's own private copy */
static int __sysrq_enabled = SYSRQ_DEFAULT_ENABLE;
@@ -410,7 +416,7 @@ static struct ctl_table kern_table[] = {
.data = core_pattern,
.maxlen = CORENAME_MAX_SIZE,
.mode = 0644,
- .proc_handler = proc_dostring,
+ .proc_handler = proc_dostring_coredump,
},
{
.procname = "core_pipe_limit",
@@ -1095,11 +1101,9 @@ static struct ctl_table vm_table[] = {
.extra1 = &zero,
},
{
- .procname = "nr_pdflush_threads",
- .data = &nr_pdflush_threads,
- .maxlen = sizeof nr_pdflush_threads,
- .mode = 0444 /* read-only*/,
- .proc_handler = proc_dointvec,
+ .procname = "nr_pdflush_threads",
+ .mode = 0444 /* read-only */,
+ .proc_handler = pdflush_proc_obsolete,
},
{
.procname = "swappiness",
@@ -1498,7 +1502,7 @@ static struct ctl_table fs_table[] = {
.data = &suid_dumpable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_dointvec_minmax_coredump,
.extra1 = &zero,
.extra2 = &two,
},
@@ -1551,7 +1555,10 @@ static struct ctl_table dev_table[] = {
int __init sysctl_init(void)
{
- register_sysctl_table(sysctl_base_table);
+ struct ctl_table_header *hdr;
+
+ hdr = register_sysctl_table(sysctl_base_table);
+ kmemleak_not_leak(hdr);
return 0;
}
@@ -2009,6 +2016,34 @@ int proc_dointvec_minmax(struct ctl_table *table, int write,
do_proc_dointvec_minmax_conv, &param);
}
+static void validate_coredump_safety(void)
+{
+ if (suid_dumpable == SUID_DUMPABLE_SAFE &&
+ core_pattern[0] != '/' && core_pattern[0] != '|') {
+ printk(KERN_WARNING "Unsafe core_pattern used with "\
+ "suid_dumpable=2. Pipe handler or fully qualified "\
+ "core dump path required.\n");
+ }
+}
+
+static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (!error)
+ validate_coredump_safety();
+ return error;
+}
+
+static int proc_dostring_coredump(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int error = proc_dostring(table, write, buffer, lenp, ppos);
+ if (!error)
+ validate_coredump_safety();
+ return error;
+}
+
static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos,
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index a650694883a1..65bdcf198d4e 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -147,7 +147,7 @@ static const struct bin_table bin_vm_table[] = {
{ CTL_INT, VM_DIRTY_RATIO, "dirty_ratio" },
/* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */
/* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */
- { CTL_INT, VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" },
+ /* VM_NR_PDFLUSH_THREADS "nr_pdflush_threads" no longer used */
{ CTL_INT, VM_OVERCOMMIT_RATIO, "overcommit_ratio" },
/* VM_PAGEBUF unused */
/* VM_HUGETLB_PAGES "nr_hugepages" no longer used */
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index e66046456f4f..d0a32796550f 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -436,6 +436,11 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS,
sizeof(struct cgroupstats));
+ if (na == NULL) {
+ rc = -EMSGSIZE;
+ goto err;
+ }
+
stats = nla_data(na);
memset(stats, 0, sizeof(*stats));
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a120f98c4112..5c38c81496ce 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3187,10 +3187,10 @@ static int tracing_set_tracer(const char *buf)
}
destroy_trace_option_files(topts);
- current_trace = t;
+ current_trace = &nop_trace;
- topts = create_trace_option_files(current_trace);
- if (current_trace->use_max_tr) {
+ topts = create_trace_option_files(t);
+ if (t->use_max_tr) {
int cpu;
/* we need to make per cpu buffer sizes equivalent */
for_each_tracing_cpu(cpu) {
@@ -3210,6 +3210,7 @@ static int tracing_set_tracer(const char *buf)
goto out;
}
+ current_trace = t;
trace_branch_enable(tr);
out:
mutex_unlock(&trace_types_lock);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index c7b0c6a7db09..a426f410c060 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -13,6 +13,7 @@
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
+#include <linux/pstore.h>
#include <linux/fs.h>
#include "trace.h"
@@ -74,6 +75,14 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
preempt_enable_notrace();
}
+/* Our two options */
+enum {
+ TRACE_FUNC_OPT_STACK = 0x1,
+ TRACE_FUNC_OPT_PSTORE = 0x2,
+};
+
+static struct tracer_flags func_flags;
+
static void
function_trace_call(unsigned long ip, unsigned long parent_ip)
{
@@ -97,6 +106,12 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
+ /*
+ * So far tracing doesn't support multiple buffers, so
+ * we make an explicit call for now.
+ */
+ if (unlikely(func_flags.val & TRACE_FUNC_OPT_PSTORE))
+ pstore_ftrace_call(ip, parent_ip);
pc = preempt_count();
trace_function(tr, ip, parent_ip, flags, pc);
}
@@ -158,15 +173,13 @@ static struct ftrace_ops trace_stack_ops __read_mostly =
.flags = FTRACE_OPS_FL_GLOBAL,
};
-/* Our two options */
-enum {
- TRACE_FUNC_OPT_STACK = 0x1,
-};
-
static struct tracer_opt func_opts[] = {
#ifdef CONFIG_STACKTRACE
{ TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) },
#endif
+#ifdef CONFIG_PSTORE_FTRACE
+ { TRACER_OPT(func_pstore, TRACE_FUNC_OPT_PSTORE) },
+#endif
{ } /* Always set a last empty entry */
};
@@ -204,10 +217,11 @@ static void tracing_stop_function_trace(void)
static int func_set_flag(u32 old_flags, u32 bit, int set)
{
- if (bit == TRACE_FUNC_OPT_STACK) {
+ switch (bit) {
+ case TRACE_FUNC_OPT_STACK:
/* do nothing if already set */
if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
- return 0;
+ break;
if (set) {
unregister_ftrace_function(&trace_ops);
@@ -217,10 +231,14 @@ static int func_set_flag(u32 old_flags, u32 bit, int set)
register_ftrace_function(&trace_ops);
}
- return 0;
+ break;
+ case TRACE_FUNC_OPT_PSTORE:
+ break;
+ default:
+ return -EINVAL;
}
- return -EINVAL;
+ return 0;
}
static struct tracer function_trace __read_mostly =
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4b1dfba70f7c..69add8a9da68 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -575,7 +575,7 @@ out:
/*
* Create/destroy watchdog threads as CPUs come and go:
*/
-static int __cpuinit
+static int
cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
int hotcpu = (unsigned long)hcpu;
@@ -610,10 +610,27 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
return NOTIFY_OK;
}
-static struct notifier_block __cpuinitdata cpu_nfb = {
+static struct notifier_block cpu_nfb = {
.notifier_call = cpu_callback
};
+#ifdef CONFIG_SUSPEND
+/*
+ * On exit from suspend we force an offline->online transition on the boot CPU
+ * so that the PMU state that was lost while in suspended state gets set up
+ * properly for the boot CPU. This information is required for restarting the
+ * NMI watchdog.
+ */
+void lockup_detector_bootcpu_resume(void)
+{
+ void *cpu = (void *)(long)smp_processor_id();
+
+ cpu_callback(&cpu_nfb, CPU_DEAD_FROZEN, cpu);
+ cpu_callback(&cpu_nfb, CPU_UP_PREPARE_FROZEN, cpu);
+ cpu_callback(&cpu_nfb, CPU_ONLINE_FROZEN, cpu);
+}
+#endif
+
void __init lockup_detector_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.