Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/util.c b/mm/util.c
index ab358c6..8904727 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -69,7 +69,8 @@
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
- * Note: Strings allocated by kstrdup_const should be freed by kfree_const.
+ * Note: Strings allocated by kstrdup_const should be freed by kfree_const and
+ * must not be passed to krealloc().
*
* Return: source string if it is in .rodata section otherwise
* fallback to kstrdup.
@@ -271,7 +272,7 @@
EXPORT_SYMBOL(memdup_user_nul);
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
- struct vm_area_struct *prev, struct rb_node *rb_parent)
+ struct vm_area_struct *prev)
{
struct vm_area_struct *next;
@@ -280,18 +281,28 @@
next = prev->vm_next;
prev->vm_next = vma;
} else {
+ next = mm->mmap;
mm->mmap = vma;
- if (rb_parent)
- next = rb_entry(rb_parent,
- struct vm_area_struct, vm_rb);
- else
- next = NULL;
}
vma->vm_next = next;
if (next)
next->vm_prev = vma;
}
+void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ struct vm_area_struct *prev, *next;
+
+ next = vma->vm_next;
+ prev = vma->vm_prev;
+ if (prev)
+ prev->vm_next = next;
+ else
+ mm->mmap = next;
+ if (next)
+ next->vm_prev = prev;
+}
+
/* Check if the vma is being used as a stack by this task */
int vma_is_stack_for_current(struct vm_area_struct *vma)
{
@@ -415,7 +426,7 @@
* @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped
*
* Assumes @task and @mm are valid (i.e. at least one reference on each), and
- * that mmap_sem is held as writer.
+ * that mmap_lock is held as writer.
*
* Return:
* * 0 on success
@@ -427,7 +438,7 @@
unsigned long locked_vm, limit;
int ret = 0;
- lockdep_assert_held_write(&mm->mmap_sem);
+ mmap_assert_write_locked(mm);
locked_vm = mm->locked_vm;
if (inc) {
@@ -471,10 +482,10 @@
if (pages == 0 || !mm)
return 0;
- down_write(&mm->mmap_sem);
+ mmap_write_lock(mm);
ret = __account_locked_vm(mm, pages, inc, current,
capable(CAP_IPC_LOCK));
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
return ret;
}
@@ -491,11 +502,11 @@
ret = security_mmap_file(file, prot, flag);
if (!ret) {
- if (down_write_killable(&mm->mmap_sem))
+ if (mmap_write_lock_killable(mm))
return -EINTR;
- ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
- &populate, &uf);
- up_write(&mm->mmap_sem);
+ ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate,
+ &uf);
+ mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
if (populate)
mm_populate(ret, populate);
@@ -570,7 +581,13 @@
if (ret || size <= PAGE_SIZE)
return ret;
- return __vmalloc_node_flags_caller(size, node, flags,
+ /* Don't even allow crazy sizes */
+ if (unlikely(size > INT_MAX)) {
+ WARN_ON_ONCE(!(flags & __GFP_NOWARN));
+ return NULL;
+ }
+
+ return __vmalloc_node(size, 1, flags, node,
__builtin_return_address(0));
}
EXPORT_SYMBOL(kvmalloc_node);
@@ -725,9 +742,8 @@
unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
-int overcommit_ratio_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
+int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
int ret;
@@ -737,9 +753,49 @@
return ret;
}
-int overcommit_kbytes_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
+static void sync_overcommit_as(struct work_struct *dummy)
+{
+ percpu_counter_sync(&vm_committed_as);
+}
+
+int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table t;
+ int new_policy = -1;
+ int ret;
+
+ /*
+ * The deviation of sync_overcommit_as could be big with loose policy
+ * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to
+ * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply
+ * with the strict "NEVER", and to avoid possible race condtion (even
+ * though user usually won't too frequently do the switching to policy
+ * OVERCOMMIT_NEVER), the switch is done in the following order:
+ * 1. changing the batch
+ * 2. sync percpu count on each CPU
+ * 3. switch the policy
+ */
+ if (write) {
+ t = *table;
+ t.data = &new_policy;
+ ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+ if (ret || new_policy == -1)
+ return ret;
+
+ mm_compute_batch(new_policy);
+ if (new_policy == OVERCOMMIT_NEVER)
+ schedule_on_each_cpu(sync_overcommit_as);
+ sysctl_overcommit_memory = new_policy;
+ } else {
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ }
+
+ return ret;
+}
+
+int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
int ret;
@@ -779,10 +835,15 @@
* balancing memory across competing virtual machines that are hosted.
* Several metrics drive this policy engine including the guest reported
* memory commitment.
+ *
+ * The time cost of this is very low for small platforms, and for big
+ * platform like a 2S/36C/72T Skylake server, in worst case where
+ * vm_committed_as's spinlock is under severe contention, the time cost
+ * could be about 30~40 microseconds.
*/
unsigned long vm_memory_committed(void)
{
- return percpu_counter_read_positive(&vm_committed_as);
+ return percpu_counter_sum_positive(&vm_committed_as);
}
EXPORT_SYMBOL_GPL(vm_memory_committed);
@@ -806,10 +867,6 @@
{
long allowed;
- VM_WARN_ONCE(percpu_counter_read(&vm_committed_as) <
- -(s64)vm_committed_as_batch * num_online_cpus(),
- "memory commitment underflow");
-
vm_acct_memory(pages);
/*
@@ -907,7 +964,7 @@
return res;
}
-int memcmp_pages(struct page *page1, struct page *page2)
+int __weak memcmp_pages(struct page *page1, struct page *page2)
{
char *addr1, *addr2;
int ret;