summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/gup.c2
-rw-r--r--mm/hugetlb.c14
-rw-r--r--mm/ksm.c12
-rw-r--r--mm/madvise.c18
-rw-r--r--mm/mremap.c13
-rw-r--r--mm/shmem.c13
-rw-r--r--mm/slub.c12
-rw-r--r--mm/vmalloc.c16
8 files changed, 80 insertions, 20 deletions
diff --git a/mm/gup.c b/mm/gup.c
index 6076df8e04a4..50681f0286de 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1088,7 +1088,7 @@ retry:
* potentially allocating memory.
*/
if (fatal_signal_pending(current)) {
- ret = -ERESTARTSYS;
+ ret = -EINTR;
goto out;
}
cond_resched();
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cd459155d28a..bcabbe02192b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5365,8 +5365,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
{
pgd_t *pgd;
p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd;
+ pud_t *pud, pud_entry;
+ pmd_t *pmd, pmd_entry;
pgd = pgd_offset(mm, addr);
if (!pgd_present(*pgd))
@@ -5376,17 +5376,19 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
return NULL;
pud = pud_offset(p4d, addr);
- if (sz != PUD_SIZE && pud_none(*pud))
+ pud_entry = READ_ONCE(*pud);
+ if (sz != PUD_SIZE && pud_none(pud_entry))
return NULL;
/* hugepage or swap? */
- if (pud_huge(*pud) || !pud_present(*pud))
+ if (pud_huge(pud_entry) || !pud_present(pud_entry))
return (pte_t *)pud;
pmd = pmd_offset(pud, addr);
- if (sz != PMD_SIZE && pmd_none(*pmd))
+ pmd_entry = READ_ONCE(*pmd);
+ if (sz != PMD_SIZE && pmd_none(pmd_entry))
return NULL;
/* hugepage or swap? */
- if (pmd_huge(*pmd) || !pmd_present(*pmd))
+ if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry))
return (pte_t *)pmd;
return NULL;
diff --git a/mm/ksm.c b/mm/ksm.c
index a558da9e7177..281c00129a2e 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2112,8 +2112,16 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
down_read(&mm->mmap_sem);
vma = find_mergeable_vma(mm, rmap_item->address);
- err = try_to_merge_one_page(vma, page,
- ZERO_PAGE(rmap_item->address));
+ if (vma) {
+ err = try_to_merge_one_page(vma, page,
+ ZERO_PAGE(rmap_item->address));
+ } else {
+ /*
+ * If the vma is out of date, we do not need to
+ * continue.
+ */
+ err = 0;
+ }
up_read(&mm->mmap_sem);
/*
* In case of failure, the page was not really empty, so we
diff --git a/mm/madvise.c b/mm/madvise.c
index 4bb30ed6c8d2..8cbd8c1bfe15 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -27,6 +27,7 @@
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/mmu_notifier.h>
+#include <linux/sched/mm.h>
#include <asm/tlb.h>
@@ -1090,6 +1091,23 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
if (write) {
if (down_write_killable(&current->mm->mmap_sem))
return -EINTR;
+
+ /*
+ * We may have stolen the mm from another process
+ * that is undergoing core dumping.
+ *
+ * Right now that's io_ring, in the future it may
+ * be remote process management and not "current"
+ * at all.
+ *
+ * We need to fix core dumping to not do this,
+ * but for now we have the mmget_still_valid()
+ * model.
+ */
+ if (!mmget_still_valid(current->mm)) {
+ up_write(&current->mm->mmap_sem);
+ return -EINTR;
+ }
} else {
down_read(&current->mm->mmap_sem);
}
diff --git a/mm/mremap.c b/mm/mremap.c
index a7e282ead438..c881abeba0bf 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -413,9 +413,20 @@ static unsigned long move_vma(struct vm_area_struct *vma,
/* Always put back VM_ACCOUNT since we won't unmap */
vma->vm_flags |= VM_ACCOUNT;
- vm_acct_memory(vma_pages(new_vma));
+ vm_acct_memory(new_len >> PAGE_SHIFT);
}
+ /*
+ * VMAs can actually be merged back together in copy_vma
+ * calling merge_vma. This can happen with anonymous vmas
+ * which have not yet been faulted, so if we were to consider
+ * this VMA split we'll end up adding VM_ACCOUNT on the
+ * next VMA, which is completely unrelated if this VMA
+ * was re-merged.
+ */
+ if (split && new_vma == vma)
+ split = 0;
+
/* We always clear VM_LOCKED[ONFAULT] on the old vma */
vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
diff --git a/mm/shmem.c b/mm/shmem.c
index d722eb830317..bd8840082c94 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -952,7 +952,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
VM_BUG_ON_PAGE(PageWriteback(page), page);
if (shmem_punch_compound(page, start, end))
truncate_inode_page(mapping, page);
- else {
+ else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
/* Wipe the page and don't get stuck */
clear_highpage(page);
flush_dcache_page(page);
@@ -2179,7 +2179,11 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
struct shmem_inode_info *info = SHMEM_I(inode);
int retval = -ENOMEM;
- spin_lock_irq(&info->lock);
+ /*
+ * What serializes the accesses to info->flags?
+ * ipc_lock_object() when called from shmctl_do_lock(),
+ * no serialization needed when called from shm_destroy().
+ */
if (lock && !(info->flags & VM_LOCKED)) {
if (!user_shm_lock(inode->i_size, user))
goto out_nomem;
@@ -2194,7 +2198,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
retval = 0;
out_nomem:
- spin_unlock_irq(&info->lock);
return retval;
}
@@ -2399,11 +2402,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
lru_cache_add_anon(page);
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
info->alloced++;
inode->i_blocks += BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
inc_mm_counter(dst_mm, mm_counter_file(page));
page_add_file_rmap(page, false);
diff --git a/mm/slub.c b/mm/slub.c
index 332d4b459a90..9bf44955c4f1 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3533,6 +3533,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
{
slab_flags_t flags = s->flags;
unsigned int size = s->object_size;
+ unsigned int freepointer_area;
unsigned int order;
/*
@@ -3541,6 +3542,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
* the possible location of the free pointer.
*/
size = ALIGN(size, sizeof(void *));
+ /*
+ * This is the area of the object where a freepointer can be
+ * safely written. If redzoning adds more to the inuse size, we
+ * can't use that portion for writing the freepointer, so
+ * s->offset must be limited within this for the general case.
+ */
+ freepointer_area = size;
#ifdef CONFIG_SLUB_DEBUG
/*
@@ -3582,13 +3590,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
*/
s->offset = size;
size += sizeof(void *);
- } else if (size > sizeof(void *)) {
+ } else if (freepointer_area > sizeof(void *)) {
/*
* Store freelist pointer near middle of object to keep
* it away from the edges of the object to avoid small
* sized over/underflows from neighboring allocations.
*/
- s->offset = ALIGN(size / 2, sizeof(void *));
+ s->offset = ALIGN(freepointer_area / 2, sizeof(void *));
}
#ifdef CONFIG_SLUB_DEBUG
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 399f219544f7..9a8227afa073 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -34,6 +34,7 @@
#include <linux/llist.h>
#include <linux/bitops.h>
#include <linux/rbtree_augmented.h>
+#include <linux/overflow.h>
#include <linux/uaccess.h>
#include <asm/tlbflush.h>
@@ -3054,6 +3055,7 @@ finished:
* @vma: vma to cover
* @uaddr: target user address to start at
* @kaddr: virtual address of vmalloc kernel memory
+ * @pgoff: offset from @kaddr to start at
* @size: size of map area
*
* Returns: 0 for success, -Exxx on failure
@@ -3066,9 +3068,15 @@ finished:
* Similar to remap_pfn_range() (see mm/memory.c)
*/
int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
- void *kaddr, unsigned long size)
+ void *kaddr, unsigned long pgoff,
+ unsigned long size)
{
struct vm_struct *area;
+ unsigned long off;
+ unsigned long end_index;
+
+ if (check_shl_overflow(pgoff, PAGE_SHIFT, &off))
+ return -EINVAL;
size = PAGE_ALIGN(size);
@@ -3082,8 +3090,10 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT)))
return -EINVAL;
- if (kaddr + size > area->addr + get_vm_area_size(area))
+ if (check_add_overflow(size, off, &end_index) ||
+ end_index > get_vm_area_size(area))
return -EINVAL;
+ kaddr += off;
do {
struct page *page = vmalloc_to_page(kaddr);
@@ -3122,7 +3132,7 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
unsigned long pgoff)
{
return remap_vmalloc_range_partial(vma, vma->vm_start,
- addr + (pgoff << PAGE_SHIFT),
+ addr, pgoff,
vma->vm_end - vma->vm_start);
}
EXPORT_SYMBOL(remap_vmalloc_range);