summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/async.c1
-rw-r--r--kernel/audit.c19
-rw-r--r--kernel/audit.h2
-rw-r--r--kernel/auditsc.c6
-rw-r--r--kernel/cpu.c64
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/events/uprobes.c11
-rw-r--r--kernel/exit.c5
-rw-r--r--kernel/futex.c67
-rw-r--r--kernel/futex_compat.c2
-rw-r--r--kernel/irq/irqdomain.c1
-rw-r--r--kernel/irq/msi.c8
-rw-r--r--kernel/kcmp.c4
-rw-r--r--kernel/kexec.c10
-rw-r--r--kernel/kexec_core.c7
-rw-r--r--kernel/kexec_file.c2
-rw-r--r--kernel/kexec_internal.h21
-rw-r--r--kernel/memremap.c219
-rw-r--r--kernel/panic.c3
-rw-r--r--kernel/printk/printk.c77
-rw-r--r--kernel/ptrace.c49
-rw-r--r--kernel/sched/idle.c6
-rw-r--r--kernel/stop_machine.c4
-rw-r--r--kernel/sys.c20
-rw-r--r--kernel/sysctl.c2
-rw-r--r--kernel/time/tick-sched.c2
26 files changed, 418 insertions, 196 deletions
diff --git a/kernel/async.c b/kernel/async.c
index 4c3773c0bf63..d2edd6efec56 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -326,3 +326,4 @@ bool current_is_async(void)
return worker && worker->current_func == async_run_entry_fn;
}
+EXPORT_SYMBOL_GPL(current_is_async);
diff --git a/kernel/audit.c b/kernel/audit.c
index 5ffcbd354a52..3a3e5deeda8d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -110,7 +110,6 @@ static u32 audit_backlog_limit = 64;
#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
static u32 audit_backlog_wait_time_master = AUDIT_BACKLOG_WAIT_TIME;
static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
-static u32 audit_backlog_wait_overflow = 0;
/* The identity of the user shutting down the audit system. */
kuid_t audit_sig_uid = INVALID_UID;
@@ -509,8 +508,7 @@ static void flush_hold_queue(void)
* if auditd just disappeared but we
* dequeued an skb we need to drop ref
*/
- if (skb)
- consume_skb(skb);
+ consume_skb(skb);
}
static int kauditd_thread(void *dummy)
@@ -524,7 +522,8 @@ static int kauditd_thread(void *dummy)
skb = skb_dequeue(&audit_skb_queue);
if (skb) {
- if (skb_queue_len(&audit_skb_queue) <= audit_backlog_limit)
+ if (!audit_backlog_limit ||
+ (skb_queue_len(&audit_skb_queue) <= audit_backlog_limit))
wake_up(&audit_backlog_wait);
if (audit_pid)
kauditd_send_skb(skb);
@@ -1232,9 +1231,7 @@ static void audit_buffer_free(struct audit_buffer *ab)
if (!ab)
return;
- if (ab->skb)
- kfree_skb(ab->skb);
-
+ kfree_skb(ab->skb);
spin_lock_irqsave(&audit_freelist_lock, flags);
if (audit_freelist_count > AUDIT_MAXFREE)
kfree(ab);
@@ -1372,7 +1369,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
return NULL;
if (gfp_mask & __GFP_DIRECT_RECLAIM) {
- if (audit_pid && audit_pid == current->pid)
+ if (audit_pid && audit_pid == current->tgid)
gfp_mask &= ~__GFP_DIRECT_RECLAIM;
else
reserve = 0;
@@ -1395,12 +1392,12 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
skb_queue_len(&audit_skb_queue),
audit_backlog_limit);
audit_log_lost("backlog limit exceeded");
- audit_backlog_wait_time = audit_backlog_wait_overflow;
+ audit_backlog_wait_time = 0;
wake_up(&audit_backlog_wait);
return NULL;
}
- if (!reserve)
+ if (!reserve && !audit_backlog_wait_time)
audit_backlog_wait_time = audit_backlog_wait_time_master;
ab = audit_buffer_alloc(ctx, gfp_mask, type);
@@ -1722,7 +1719,7 @@ static inline int audit_copy_fcaps(struct audit_names *name,
/* Copy inode data into an audit_names. */
void audit_copy_inode(struct audit_names *name, const struct dentry *dentry,
- const struct inode *inode)
+ struct inode *inode)
{
name->ino = inode->i_ino;
name->dev = inode->i_sb->s_dev;
diff --git a/kernel/audit.h b/kernel/audit.h
index de6cbb7cf547..cbbe6bb6496e 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -207,7 +207,7 @@ extern u32 audit_ever_enabled;
extern void audit_copy_inode(struct audit_names *name,
const struct dentry *dentry,
- const struct inode *inode);
+ struct inode *inode);
extern void audit_log_cap(struct audit_buffer *ab, char *prefix,
kernel_cap_t *cap);
extern void audit_log_name(struct audit_context *context,
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index b86cc04959de..195ffaee50b9 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1754,7 +1754,7 @@ void __audit_inode(struct filename *name, const struct dentry *dentry,
unsigned int flags)
{
struct audit_context *context = current->audit_context;
- const struct inode *inode = d_backing_inode(dentry);
+ struct inode *inode = d_backing_inode(dentry);
struct audit_names *n;
bool parent = flags & AUDIT_INODE_PARENT;
@@ -1848,12 +1848,12 @@ void __audit_file(const struct file *file)
* must be hooked prior, in order to capture the target inode during
* unsuccessful attempts.
*/
-void __audit_inode_child(const struct inode *parent,
+void __audit_inode_child(struct inode *parent,
const struct dentry *dentry,
const unsigned char type)
{
struct audit_context *context = current->audit_context;
- const struct inode *inode = d_backing_inode(dentry);
+ struct inode *inode = d_backing_inode(dentry);
const char *dname = dentry->d_name.name;
struct audit_names *n, *found_parent = NULL, *found_child = NULL;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 85ff5e26e23b..5b9d39633ce9 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -759,71 +759,33 @@ const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
EXPORT_SYMBOL(cpu_all_bits);
#ifdef CONFIG_INIT_ALL_POSSIBLE
-static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly
- = CPU_BITS_ALL;
+struct cpumask __cpu_possible_mask __read_mostly
+ = {CPU_BITS_ALL};
#else
-static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly;
+struct cpumask __cpu_possible_mask __read_mostly;
#endif
-const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits);
-EXPORT_SYMBOL(cpu_possible_mask);
+EXPORT_SYMBOL(__cpu_possible_mask);
-static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly;
-const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits);
-EXPORT_SYMBOL(cpu_online_mask);
+struct cpumask __cpu_online_mask __read_mostly;
+EXPORT_SYMBOL(__cpu_online_mask);
-static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly;
-const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits);
-EXPORT_SYMBOL(cpu_present_mask);
+struct cpumask __cpu_present_mask __read_mostly;
+EXPORT_SYMBOL(__cpu_present_mask);
-static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
-const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
-EXPORT_SYMBOL(cpu_active_mask);
-
-void set_cpu_possible(unsigned int cpu, bool possible)
-{
- if (possible)
- cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits));
- else
- cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits));
-}
-
-void set_cpu_present(unsigned int cpu, bool present)
-{
- if (present)
- cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits));
- else
- cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits));
-}
-
-void set_cpu_online(unsigned int cpu, bool online)
-{
- if (online) {
- cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
- cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
- } else {
- cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
- }
-}
-
-void set_cpu_active(unsigned int cpu, bool active)
-{
- if (active)
- cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
- else
- cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits));
-}
+struct cpumask __cpu_active_mask __read_mostly;
+EXPORT_SYMBOL(__cpu_active_mask);
void init_cpu_present(const struct cpumask *src)
{
- cpumask_copy(to_cpumask(cpu_present_bits), src);
+ cpumask_copy(&__cpu_present_mask, src);
}
void init_cpu_possible(const struct cpumask *src)
{
- cpumask_copy(to_cpumask(cpu_possible_bits), src);
+ cpumask_copy(&__cpu_possible_mask, src);
}
void init_cpu_online(const struct cpumask *src)
{
- cpumask_copy(to_cpumask(cpu_online_bits), src);
+ cpumask_copy(&__cpu_online_mask, src);
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bf8244190d0f..c0957416b32e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3376,7 +3376,7 @@ find_lively_task_by_vpid(pid_t vpid)
/* Reuse ptrace permission checks for now. */
err = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
goto errout;
return task;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index bb0669169716..0167679182c0 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -161,7 +161,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
const unsigned long mmun_end = addr + PAGE_SIZE;
struct mem_cgroup *memcg;
- err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg);
+ err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg,
+ false);
if (err)
return err;
@@ -175,8 +176,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
goto unlock;
get_page(kpage);
- page_add_new_anon_rmap(kpage, vma, addr);
- mem_cgroup_commit_charge(kpage, memcg, false);
+ page_add_new_anon_rmap(kpage, vma, addr, false);
+ mem_cgroup_commit_charge(kpage, memcg, false, false);
lru_cache_add_active_or_unevictable(kpage, vma);
if (!PageAnon(page)) {
@@ -188,7 +189,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
ptep_clear_flush_notify(vma, addr, ptep);
set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
- page_remove_rmap(page);
+ page_remove_rmap(page, false);
if (!page_mapped(page))
try_to_free_swap(page);
pte_unmap_unlock(ptep, ptl);
@@ -199,7 +200,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
err = 0;
unlock:
- mem_cgroup_cancel_charge(kpage, memcg);
+ mem_cgroup_cancel_charge(kpage, memcg, false);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
unlock_page(page);
return err;
diff --git a/kernel/exit.c b/kernel/exit.c
index 07110c6020a0..10e088237fed 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -59,8 +59,6 @@
#include <asm/pgtable.h>
#include <asm/mmu_context.h>
-static void exit_mm(struct task_struct *tsk);
-
static void __unhash_process(struct task_struct *p, bool group_dead)
{
nr_threads--;
@@ -1120,8 +1118,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
static int *task_stopped_code(struct task_struct *p, bool ptrace)
{
if (ptrace) {
- if (task_is_stopped_or_traced(p) &&
- !(p->jobctl & JOBCTL_LISTENING))
+ if (task_is_traced(p) && !(p->jobctl & JOBCTL_LISTENING))
return &p->exit_code;
} else {
if (p->signal->flags & SIGNAL_STOP_STOPPED)
diff --git a/kernel/futex.c b/kernel/futex.c
index 8a310e240cda..0773f2b23b10 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -469,7 +469,8 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
{
unsigned long address = (unsigned long)uaddr;
struct mm_struct *mm = current->mm;
- struct page *page, *page_head;
+ struct page *page;
+ struct address_space *mapping;
int err, ro = 0;
/*
@@ -519,46 +520,9 @@ again:
else
err = 0;
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- page_head = page;
- if (unlikely(PageTail(page))) {
- put_page(page);
- /* serialize against __split_huge_page_splitting() */
- local_irq_disable();
- if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) {
- page_head = compound_head(page);
- /*
- * page_head is valid pointer but we must pin
- * it before taking the PG_lock and/or
- * PG_compound_lock. The moment we re-enable
- * irqs __split_huge_page_splitting() can
- * return and the head page can be freed from
- * under us. We can't take the PG_lock and/or
- * PG_compound_lock on a page that could be
- * freed from under us.
- */
- if (page != page_head) {
- get_page(page_head);
- put_page(page);
- }
- local_irq_enable();
- } else {
- local_irq_enable();
- goto again;
- }
- }
-#else
- page_head = compound_head(page);
- if (page != page_head) {
- get_page(page_head);
- put_page(page);
- }
-#endif
-
- lock_page(page_head);
-
+ lock_page(page);
/*
- * If page_head->mapping is NULL, then it cannot be a PageAnon
+ * If page->mapping is NULL, then it cannot be a PageAnon
* page; but it might be the ZERO_PAGE or in the gate area or
* in a special mapping (all cases which we are happy to fail);
* or it may have been a good file page when get_user_pages_fast
@@ -570,12 +534,13 @@ again:
*
* The case we do have to guard against is when memory pressure made
* shmem_writepage move it from filecache to swapcache beneath us:
- * an unlikely race, but we do need to retry for page_head->mapping.
+ * an unlikely race, but we do need to retry for page->mapping.
*/
- if (!page_head->mapping) {
- int shmem_swizzled = PageSwapCache(page_head);
- unlock_page(page_head);
- put_page(page_head);
+ mapping = compound_head(page)->mapping;
+ if (!mapping) {
+ int shmem_swizzled = PageSwapCache(page);
+ unlock_page(page);
+ put_page(page);
if (shmem_swizzled)
goto again;
return -EFAULT;
@@ -588,7 +553,7 @@ again:
* it's a read-only handle, it's expected that futexes attach to
* the object not the particular process.
*/
- if (PageAnon(page_head)) {
+ if (PageAnon(page)) {
/*
* A RO anonymous page will never change and thus doesn't make
* sense for futex operations.
@@ -603,15 +568,15 @@ again:
key->private.address = address;
} else {
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
- key->shared.inode = page_head->mapping->host;
+ key->shared.inode = mapping->host;
key->shared.pgoff = basepage_index(page);
}
get_futex_key_refs(key); /* implies MB (B) */
out:
- unlock_page(page_head);
- put_page(page_head);
+ unlock_page(page);
+ put_page(page);
return err;
}
@@ -639,7 +604,7 @@ static int fault_in_user_writeable(u32 __user *uaddr)
down_read(&mm->mmap_sem);
ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
- FAULT_FLAG_WRITE);
+ FAULT_FLAG_WRITE, NULL);
up_read(&mm->mmap_sem);
return ret < 0 ? ret : 0;
@@ -2919,7 +2884,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
}
ret = -EPERM;
- if (!ptrace_may_access(p, PTRACE_MODE_READ))
+ if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
head = p->robust_list;
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 55c8c9349cfe..4ae3232e7a28 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -155,7 +155,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
}
ret = -EPERM;
- if (!ptrace_may_access(p, PTRACE_MODE_READ))
+ if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
head = p->compat_robust_list;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 8cf95de1ab3f..6e655f7acd3b 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1061,6 +1061,7 @@ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
__irq_set_handler(virq, handler, 0, handler_name);
irq_set_handler_data(virq, handler_data);
}
+EXPORT_SYMBOL(irq_domain_set_info);
/**
* irq_domain_reset_irq_data - Clear hwirq, chip and chip_data in @irq_data
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 15b249e7c673..38e89ce7b071 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -109,9 +109,11 @@ static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
if (irq_find_mapping(domain, hwirq) > 0)
return -EEXIST;
- ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
- if (ret < 0)
- return ret;
+ if (domain->parent) {
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+ if (ret < 0)
+ return ret;
+ }
for (i = 0; i < nr_irqs; i++) {
ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg);
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 0aa69ea1d8fd..3a47fa998fe0 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -122,8 +122,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
&task2->signal->cred_guard_mutex);
if (ret)
goto err;
- if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
- !ptrace_may_access(task2, PTRACE_MODE_READ)) {
+ if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) ||
+ !ptrace_may_access(task2, PTRACE_MODE_READ_REALCREDS)) {
ret = -EPERM;
goto err_unlock;
}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index d873b64fbddc..ee70aef5cd81 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -63,16 +63,16 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
if (ret)
goto out_free_image;
- ret = sanity_check_segment_list(image);
- if (ret)
- goto out_free_image;
-
- /* Enable the special crash kernel control page allocation policy. */
if (kexec_on_panic) {
+ /* Enable special crash kernel control page alloc policy. */
image->control_page = crashk_res.start;
image->type = KEXEC_TYPE_CRASH;
}
+ ret = sanity_check_segment_list(image);
+ if (ret)
+ goto out_free_image;
+
/*
* Find a location for the control code buffer, and add it
* the vector of segments so that it's pages will also be
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index c823f3001e12..8dc659144869 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -310,12 +310,9 @@ static void kimage_free_pages(struct page *page)
void kimage_free_page_list(struct list_head *list)
{
- struct list_head *pos, *next;
+ struct page *page, *next;
- list_for_each_safe(pos, next, list) {
- struct page *page;
-
- page = list_entry(pos, struct page, lru);
+ list_for_each_entry_safe(page, next, list, lru) {
list_del(&page->lru);
kimage_free_pages(page);
}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b70ada0028d2..007b791f676d 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -109,11 +109,13 @@ int __weak arch_kimage_file_post_load_cleanup(struct kimage *image)
return -EINVAL;
}
+#ifdef CONFIG_KEXEC_VERIFY_SIG
int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
unsigned long buf_len)
{
return -EKEYREJECTED;
}
+#endif
/* Apply relocations of type RELA */
int __weak
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index e4392a698ad4..0a52315d9c62 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -15,6 +15,27 @@ int kimage_is_destination_range(struct kimage *image,
extern struct mutex kexec_mutex;
#ifdef CONFIG_KEXEC_FILE
+struct kexec_sha_region {
+ unsigned long start;
+ unsigned long len;
+};
+
+/*
+ * Keeps track of buffer parameters as provided by caller for requesting
+ * memory placement of buffer.
+ */
+struct kexec_buf {
+ struct kimage *image;
+ char *buffer;
+ unsigned long bufsz;
+ unsigned long mem;
+ unsigned long memsz;
+ unsigned long buf_align;
+ unsigned long buf_min;
+ unsigned long buf_max;
+ bool top_down; /* allocate from top of memory hole */
+};
+
void kimage_file_post_load_cleanup(struct kimage *image);
#else /* CONFIG_KEXEC_FILE */
static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 7658d32c5c78..e517a16cb426 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -10,8 +10,11 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
+#include <linux/radix-tree.h>
+#include <linux/memremap.h>
#include <linux/device.h>
#include <linux/types.h>
+#include <linux/pfn_t.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/memory_hotplug.h>
@@ -147,24 +150,127 @@ void devm_memunmap(struct device *dev, void *addr)
}
EXPORT_SYMBOL(devm_memunmap);
+pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags)
+{
+ return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
+}
+EXPORT_SYMBOL(phys_to_pfn_t);
+
#ifdef CONFIG_ZONE_DEVICE
+static DEFINE_MUTEX(pgmap_lock);
+static RADIX_TREE(pgmap_radix, GFP_KERNEL);
+#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
+#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
+
struct page_map {
struct resource res;
+ struct percpu_ref *ref;
+ struct dev_pagemap pgmap;
+ struct vmem_altmap altmap;
};
-static void devm_memremap_pages_release(struct device *dev, void *res)
+void get_zone_device_page(struct page *page)
+{
+ percpu_ref_get(page->pgmap->ref);
+}
+EXPORT_SYMBOL(get_zone_device_page);
+
+void put_zone_device_page(struct page *page)
+{
+ put_dev_pagemap(page->pgmap);
+}
+EXPORT_SYMBOL(put_zone_device_page);
+
+static void pgmap_radix_release(struct resource *res)
+{
+ resource_size_t key;
+
+ mutex_lock(&pgmap_lock);
+ for (key = res->start; key <= res->end; key += SECTION_SIZE)
+ radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT);
+ mutex_unlock(&pgmap_lock);
+}
+
+static unsigned long pfn_first(struct page_map *page_map)
+{
+ struct dev_pagemap *pgmap = &page_map->pgmap;
+ const struct resource *res = &page_map->res;
+ struct vmem_altmap *altmap = pgmap->altmap;
+ unsigned long pfn;
+
+ pfn = res->start >> PAGE_SHIFT;
+ if (altmap)
+ pfn += vmem_altmap_offset(altmap);
+ return pfn;
+}
+
+static unsigned long pfn_end(struct page_map *page_map)
+{
+ const struct resource *res = &page_map->res;
+
+ return (res->start + resource_size(res)) >> PAGE_SHIFT;
+}
+
+#define for_each_device_pfn(pfn, map) \
+ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++)
+
+static void devm_memremap_pages_release(struct device *dev, void *data)
{
- struct page_map *page_map = res;
+ struct page_map *page_map = data;
+ struct resource *res = &page_map->res;
+ resource_size_t align_start, align_size;
+ struct dev_pagemap *pgmap = &page_map->pgmap;
+
+ if (percpu_ref_tryget_live(pgmap->ref)) {
+ dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
+ percpu_ref_put(pgmap->ref);
+ }
+
+ pgmap_radix_release(res);
/* pages are dead and unused, undo the arch mapping */
- arch_remove_memory(page_map->res.start, resource_size(&page_map->res));
+ align_start = res->start & ~(SECTION_SIZE - 1);
+ align_size = ALIGN(resource_size(res), SECTION_SIZE);
+ arch_remove_memory(align_start, align_size);
+ dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
+ "%s: failed to free all reserved pages\n", __func__);
+}
+
+/* assumes rcu_read_lock() held at entry */
+struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
+{
+ struct page_map *page_map;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT);
+ return page_map ? &page_map->pgmap : NULL;
}
-void *devm_memremap_pages(struct device *dev, struct resource *res)
+/**
+ * devm_memremap_pages - remap and provide memmap backing for the given resource
+ * @dev: hosting device for @res
+ * @res: "host memory" address range
+ * @ref: a live per-cpu reference count
+ * @altmap: optional descriptor for allocating the memmap from @res
+ *
+ * Notes:
+ * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time
+ * (or devm release event).
+ *
+ * 2/ @res is expected to be a host memory range that could feasibly be
+ * treated as a "System RAM" range, i.e. not a device mmio range, but
+ * this is not enforced.
+ */
+void *devm_memremap_pages(struct device *dev, struct resource *res,
+ struct percpu_ref *ref, struct vmem_altmap *altmap)
{
int is_ram = region_intersects(res->start, resource_size(res),
"System RAM");
+ resource_size_t key, align_start, align_size;
+ struct dev_pagemap *pgmap;
struct page_map *page_map;
+ unsigned long pfn;
int error, nid;
if (is_ram == REGION_MIXED) {
@@ -176,25 +282,120 @@ void *devm_memremap_pages(struct device *dev, struct resource *res)
if (is_ram == REGION_INTERSECTS)
return __va(res->start);
+ if (altmap && !IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) {
+ dev_err(dev, "%s: altmap requires CONFIG_SPARSEMEM_VMEMMAP=y\n",
+ __func__);
+ return ERR_PTR(-ENXIO);
+ }
+
+ if (!ref)
+ return ERR_PTR(-EINVAL);
+
page_map = devres_alloc_node(devm_memremap_pages_release,
sizeof(*page_map), GFP_KERNEL, dev_to_node(dev));
if (!page_map)
return ERR_PTR(-ENOMEM);
+ pgmap = &page_map->pgmap;
memcpy(&page_map->res, res, sizeof(*res));
+ pgmap->dev = dev;
+ if (altmap) {
+ memcpy(&page_map->altmap, altmap, sizeof(*altmap));
+ pgmap->altmap = &page_map->altmap;
+ }
+ pgmap->ref = ref;
+ pgmap->res = &page_map->res;
+
+ mutex_lock(&pgmap_lock);
+ error = 0;
+ for (key = res->start; key <= res->end; key += SECTION_SIZE) {
+ struct dev_pagemap *dup;
+
+ rcu_read_lock();
+ dup = find_dev_pagemap(key);
+ rcu_read_unlock();
+ if (dup) {
+ dev_err(dev, "%s: %pr collides with mapping for %s\n",
+ __func__, res, dev_name(dup->dev));
+ error = -EBUSY;
+ break;
+ }
+ error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT,
+ page_map);
+ if (error) {
+ dev_err(dev, "%s: failed: %d\n", __func__, error);
+ break;
+ }
+ }
+ mutex_unlock(&pgmap_lock);
+ if (error)
+ goto err_radix;
+
nid = dev_to_node(dev);
if (nid < 0)
nid = numa_mem_id();
- error = arch_add_memory(nid, res->start, resource_size(res), true);
- if (error) {
- devres_free(page_map);
- return ERR_PTR(error);
- }
+ align_start = res->start & ~(SECTION_SIZE - 1);
+ align_size = ALIGN(resource_size(res), SECTION_SIZE);
+ error = arch_add_memory(nid, align_start, align_size, true);
+ if (error)
+ goto err_add_memory;
+ for_each_device_pfn(pfn, page_map) {
+ struct page *page = pfn_to_page(pfn);
+
+ /* ZONE_DEVICE pages must never appear on a slab lru */
+ list_force_poison(&page->lru);
+ page->pgmap = pgmap;
+ }
devres_add(dev, page_map);
return __va(res->start);
+
+ err_add_memory:
+ err_radix:
+ pgmap_radix_release(res);
+ devres_free(page_map);
+ return ERR_PTR(error);
}
EXPORT_SYMBOL(devm_memremap_pages);
+
+unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
+{
+ /* number of pfns from base where pfn_to_page() is valid */
+ return altmap->reserve + altmap->free;
+}
+
+void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
+{
+ altmap->alloc -= nr_pfns;
+}
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
+{
+ /*
+ * 'memmap_start' is the virtual address for the first "struct
+ * page" in this range of the vmemmap array. In the case of
+ * CONFIG_SPARSE_VMEMMAP a page_to_pfn conversion is simple
+ * pointer arithmetic, so we can perform this to_vmem_altmap()
+ * conversion without concern for the initialization state of
+ * the struct page fields.
+ */
+ struct page *page = (struct page *) memmap_start;
+ struct dev_pagemap *pgmap;
+
+ /*
+ * Uncoditionally retrieve a dev_pagemap associated with the
+ * given physical address, this is only for use in the
+ * arch_{add|remove}_memory() for setting up and tearing down
+ * the memmap.
+ */
+ rcu_read_lock();
+ pgmap = find_dev_pagemap(__pfn_to_phys(page_to_pfn(page)));
+ rcu_read_unlock();
+
+ return pgmap ? pgmap->altmap : NULL;
+}
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
#endif /* CONFIG_ZONE_DEVICE */
diff --git a/kernel/panic.c b/kernel/panic.c
index b333380c6bb2..d96469de72dc 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -180,8 +180,7 @@ void panic(const char *fmt, ...)
* panic() is not being callled from OOPS.
*/
debug_locks_off();
- console_trylock();
- console_unlock();
+ console_flush_on_panic();
if (!panic_blink)
panic_blink = no_blink;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 2ce8826f1053..c963ba534a78 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -48,6 +48,7 @@
#include <linux/uio.h>
#include <asm/uaccess.h>
+#include <asm-generic/sections.h>
#define CREATE_TRACE_POINTS
#include <trace/events/printk.h>
@@ -232,7 +233,11 @@ struct printk_log {
u8 facility; /* syslog facility */
u8 flags:5; /* internal record flags */
u8 level:3; /* syslog level */
-};
+}
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+__packed __aligned(4)
+#endif
+;
/*
* The logbuf_lock protects kmsg buffer, indices, counters. This can be taken
@@ -273,11 +278,7 @@ static u32 clear_idx;
#define LOG_FACILITY(v) ((v) >> 3 & 0xff)
/* record buffer */
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-#define LOG_ALIGN 4
-#else
#define LOG_ALIGN __alignof__(struct printk_log)
-#endif
#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
static char *log_buf = __log_buf;
@@ -1660,7 +1661,7 @@ asmlinkage int vprintk_emit(int facility, int level,
const char *dict, size_t dictlen,
const char *fmt, va_list args)
{
- static int recursion_bug;
+ static bool recursion_bug;
static char textbuf[LOG_LINE_MAX];
char *text = textbuf;
size_t text_len = 0;
@@ -1696,7 +1697,7 @@ asmlinkage int vprintk_emit(int facility, int level,
* it can be printed at the next appropriate moment:
*/
if (!oops_in_progress && !lockdep_recursing(current)) {
- recursion_bug = 1;
+ recursion_bug = true;
local_irq_restore(flags);
return 0;
}
@@ -1711,7 +1712,7 @@ asmlinkage int vprintk_emit(int facility, int level,
static const char recursion_msg[] =
"BUG: recent printk recursion!";
- recursion_bug = 0;
+ recursion_bug = false;
/* emit KERN_CRIT message */
printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0,
NULL, 0, recursion_msg,
@@ -2233,13 +2234,24 @@ void console_unlock(void)
static u64 seen_seq;
unsigned long flags;
bool wake_klogd = false;
- bool retry;
+ bool do_cond_resched, retry;
if (console_suspended) {
up_console_sem();
return;
}
+ /*
+ * Console drivers are called under logbuf_lock, so
+ * @console_may_schedule should be cleared before; however, we may
+ * end up dumping a lot of lines, for example, if called from
+ * console registration path, and should invoke cond_resched()
+ * between lines if allowable. Not doing so can cause a very long
+ * scheduling stall on a slow console leading to RCU stall and
+ * softlockup warnings which exacerbate the issue with more
+ * messages practically incapacitating the system.
+ */
+ do_cond_resched = console_may_schedule;
console_may_schedule = 0;
/* flush buffered message fragment immediately to console */
@@ -2311,6 +2323,9 @@ skip:
call_console_drivers(level, ext_text, ext_len, text, len);
start_critical_timings();
local_irq_restore(flags);
+
+ if (do_cond_resched)
+ cond_resched();
}
console_locked = 0;
@@ -2378,6 +2393,25 @@ void console_unblank(void)
console_unlock();
}
+/**
+ * console_flush_on_panic - flush console content on panic
+ *
+ * Immediately output all pending messages no matter what.
+ */
+void console_flush_on_panic(void)
+{
+ /*
+ * If someone else is holding the console lock, trylock will fail
+ * and may_schedule may be set. Ignore and proceed to unlock so
+ * that messages are flushed out. As this can be called from any
+ * context and we don't want to get preempted while flushing,
+ * ensure may_schedule is cleared.
+ */
+ console_trylock();
+ console_may_schedule = 0;
+ console_unlock();
+}
+
/*
* Return the console tty driver structure and its associated index
*/
@@ -2658,13 +2692,36 @@ int unregister_console(struct console *console)
}
EXPORT_SYMBOL(unregister_console);
+/*
+ * Some boot consoles access data that is in the init section and which will
+ * be discarded after the initcalls have been run. To make sure that no code
+ * will access this data, unregister the boot consoles in a late initcall.
+ *
+ * If for some reason, such as deferred probe or the driver being a loadable
+ * module, the real console hasn't registered yet at this point, there will
+ * be a brief interval in which no messages are logged to the console, which
+ * makes it difficult to diagnose problems that occur during this time.
+ *
+ * To mitigate this problem somewhat, only unregister consoles whose memory
+ * intersects with the init section. Note that code exists elsewhere to get
+ * rid of the boot console as soon as the proper console shows up, so there
+ * won't be side-effects from postponing the removal.
+ */
static int __init printk_late_init(void)
{
struct console *con;
for_each_console(con) {
if (!keep_bootcon && con->flags & CON_BOOT) {
- unregister_console(con);
+ /*
+ * Make sure to unregister boot consoles whose data
+ * resides in the init section before the init section
+ * is discarded. Boot consoles whose data will stick
+ * around will automatically be unregistered when the
+ * proper console replaces them.
+ */
+ if (init_section_intersects(con, sizeof(*con)))
+ unregister_console(con);
}
}
hotcpu_notifier(console_cpu_notify, 0);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index b760bae64cf1..2341efe7fe02 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -219,6 +219,14 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
{
const struct cred *cred = current_cred(), *tcred;
+ int dumpable = 0;
+ kuid_t caller_uid;
+ kgid_t caller_gid;
+
+ if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) {
+ WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n");
+ return -EPERM;
+ }
/* May we inspect the given task?
* This check is used both for attaching with ptrace
@@ -228,18 +236,33 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
* because setting up the necessary parent/child relationship
* or halting the specified task is impossible.
*/
- int dumpable = 0;
+
/* Don't let security modules deny introspection */
if (same_thread_group(task, current))
return 0;
rcu_read_lock();
+ if (mode & PTRACE_MODE_FSCREDS) {
+ caller_uid = cred->fsuid;
+ caller_gid = cred->fsgid;
+ } else {
+ /*
+ * Using the euid would make more sense here, but something
+ * in userland might rely on the old behavior, and this
+ * shouldn't be a security problem since
+ * PTRACE_MODE_REALCREDS implies that the caller explicitly
+ * used a syscall that requests access to another process
+ * (and not a filesystem syscall to procfs).
+ */
+ caller_uid = cred->uid;
+ caller_gid = cred->gid;
+ }
tcred = __task_cred(task);
- if (uid_eq(cred->uid, tcred->euid) &&
- uid_eq(cred->uid, tcred->suid) &&
- uid_eq(cred->uid, tcred->uid) &&
- gid_eq(cred->gid, tcred->egid) &&
- gid_eq(cred->gid, tcred->sgid) &&
- gid_eq(cred->gid, tcred->gid))
+ if (uid_eq(caller_uid, tcred->euid) &&
+ uid_eq(caller_uid, tcred->suid) &&
+ uid_eq(caller_uid, tcred->uid) &&
+ gid_eq(caller_gid, tcred->egid) &&
+ gid_eq(caller_gid, tcred->sgid) &&
+ gid_eq(caller_gid, tcred->gid))
goto ok;
if (ptrace_has_cap(tcred->user_ns, mode))
goto ok;
@@ -306,7 +329,7 @@ static int ptrace_attach(struct task_struct *task, long request,
goto out;
task_lock(task);
- retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
+ retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
task_unlock(task);
if (retval)
goto unlock_creds;
@@ -364,8 +387,14 @@ unlock_creds:
mutex_unlock(&task->signal->cred_guard_mutex);
out:
if (!retval) {
- wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT,
- TASK_UNINTERRUPTIBLE);
+ /*
+ * We do not bother to change retval or clear JOBCTL_TRAPPING
+ * if wait_on_bit() was interrupted by SIGKILL. The tracer will
+ * not return to user-mode, it will exit and clear this bit in
+ * __ptrace_unlink() if it wasn't already cleared by the tracee;
+ * and until then nobody can ptrace this task.
+ */
+ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
proc_ptrace_connector(task, PTRACE_ATTACH);
}
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 2489140a7c51..de0e786b2667 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -97,12 +97,6 @@ void default_idle_call(void)
static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
int next_state)
{
- /* Fall back to the default arch idle method on errors. */
- if (next_state < 0) {
- default_idle_call();
- return next_state;
- }
-
/*
* The idle task must be scheduled, it is pointless to go to idle, just
* update no idle residency and return.
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index edb6de4f5908..a467e6c28a3b 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -529,8 +529,6 @@ static int __init cpu_stop_init(void)
}
early_initcall(cpu_stop_init);
-#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
-
static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
{
struct multi_stop_data msdata = {
@@ -628,5 +626,3 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
mutex_unlock(&stop_cpus_mutex);
return ret ?: done.ret;
}
-
-#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
diff --git a/kernel/sys.c b/kernel/sys.c
index 6af9212ab5aa..78947de6f969 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1853,11 +1853,13 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
}
- if (prctl_map.exe_fd != (u32)-1)
+ if (prctl_map.exe_fd != (u32)-1) {
error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd);
- down_read(&mm->mmap_sem);
- if (error)
- goto out;
+ if (error)
+ return error;
+ }
+
+ down_write(&mm->mmap_sem);
/*
* We don't validate if these members are pointing to
@@ -1894,10 +1896,8 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
if (prctl_map.auxv_size)
memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
- error = 0;
-out:
- up_read(&mm->mmap_sem);
- return error;
+ up_write(&mm->mmap_sem);
+ return 0;
}
#endif /* CONFIG_CHECKPOINT_RESTORE */
@@ -1963,7 +1963,7 @@ static int prctl_set_mm(int opt, unsigned long addr,
error = -EINVAL;
- down_read(&mm->mmap_sem);
+ down_write(&mm->mmap_sem);
vma = find_vma(mm, addr);
prctl_map.start_code = mm->start_code;
@@ -2056,7 +2056,7 @@ static int prctl_set_mm(int opt, unsigned long addr,
error = 0;
out:
- up_read(&mm->mmap_sem);
+ up_write(&mm->mmap_sem);
return error;
}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f6fd236429bd..97715fd9e790 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -173,7 +173,7 @@ extern int no_unaligned_warning;
#define SYSCTL_WRITES_WARN 0
#define SYSCTL_WRITES_STRICT 1
-static int sysctl_writes_strict = SYSCTL_WRITES_WARN;
+static int 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);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 9cc20af58c76..9d7a053545f5 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -387,7 +387,7 @@ void __init tick_nohz_init(void)
/*
* NO HZ enabled ?
*/
-static int tick_nohz_enabled __read_mostly = 1;
+int tick_nohz_enabled __read_mostly = 1;
unsigned long tick_nohz_active __read_mostly;
/*
* Enable / Disable tickless mode
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-18 23:13:06 +0000