aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c21
-rw-r--r--mm/gup_benchmark.c8
-rw-r--r--mm/hugetlb.c51
-rw-r--r--mm/internal.h21
-rw-r--r--mm/memory.c38
-rw-r--r--mm/migrate.c25
-rw-r--r--mm/mmap.c6
-rw-r--r--mm/shmem.c11
-rw-r--r--mm/zsmalloc.c5
9 files changed, 133 insertions, 53 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 39ba6d939cc3..536be508ce4c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2350,27 +2350,6 @@ EXPORT_SYMBOL(generic_file_read_iter);
#ifdef CONFIG_MMU
#define MMAP_LOTSAMISS (100)
-static struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
- struct file *fpin)
-{
- int flags = vmf->flags;
-
- if (fpin)
- return fpin;
-
- /*
- * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
- * anything, so we only pin the file and drop the mmap_sem if only
- * FAULT_FLAG_ALLOW_RETRY is set.
- */
- if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
- FAULT_FLAG_ALLOW_RETRY) {
- fpin = get_file(vmf->vma->vm_file);
- up_read(&vmf->vma->vm_mm->mmap_sem);
- }
- return fpin;
-}
-
/*
* lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem
* @vmf - the vm_fault for this fault.
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 7dd602d7f8db..ad9d5b1c4473 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -26,6 +26,7 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
unsigned long i, nr_pages, addr, next;
int nr;
struct page **pages;
+ int ret = 0;
if (gup->size > ULONG_MAX)
return -EINVAL;
@@ -63,7 +64,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
NULL);
break;
default:
- return -1;
+ kvfree(pages);
+ ret = -EINVAL;
+ goto out;
}
if (nr <= 0)
@@ -85,7 +88,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
gup->put_delta_usec = ktime_us_delta(end_time, start_time);
kvfree(pages);
- return 0;
+out:
+ return ret;
}
static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4c842adf14e0..205acd58dbe7 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -27,6 +27,7 @@
#include <linux/swapops.h>
#include <linux/jhash.h>
#include <linux/numa.h>
+#include <linux/llist.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -1255,7 +1256,7 @@ static inline void ClearPageHugeTemporary(struct page *page)
page[2].mapping = NULL;
}
-void free_huge_page(struct page *page)
+static void __free_huge_page(struct page *page)
{
/*
* Can't pass hstate in here because it is called from the
@@ -1318,6 +1319,54 @@ void free_huge_page(struct page *page)
spin_unlock(&hugetlb_lock);
}
+/*
+ * As free_huge_page() can be called from a non-task context, we have
+ * to defer the actual freeing in a workqueue to prevent potential
+ * hugetlb_lock deadlock.
+ *
+ * free_hpage_workfn() locklessly retrieves the linked list of pages to
+ * be freed and frees them one-by-one. As the page->mapping pointer is
+ * going to be cleared in __free_huge_page() anyway, it is reused as the
+ * llist_node structure of a lockless linked list of huge pages to be freed.
+ */
+static LLIST_HEAD(hpage_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+ struct llist_node *node;
+ struct page *page;
+
+ node = llist_del_all(&hpage_freelist);
+
+ while (node) {
+ page = container_of((struct address_space **)node,
+ struct page, mapping);
+ node = node->next;
+ __free_huge_page(page);
+ }
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+void free_huge_page(struct page *page)
+{
+ /*
+ * Defer freeing if in non-task context to avoid hugetlb_lock deadlock.
+ */
+ if (!in_task()) {
+ /*
+ * Only call schedule_work() if hpage_freelist is previously
+ * empty. Otherwise, schedule_work() had been called but the
+ * workfn hasn't retrieved the list yet.
+ */
+ if (llist_add((struct llist_node *)&page->mapping,
+ &hpage_freelist))
+ schedule_work(&free_hpage_work);
+ return;
+ }
+
+ __free_huge_page(page);
+}
+
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
INIT_LIST_HEAD(&page->lru);
diff --git a/mm/internal.h b/mm/internal.h
index e32390802fd3..5d91f9e90741 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -362,6 +362,27 @@ vma_address(struct page *page, struct vm_area_struct *vma)
return max(start, vma->vm_start);
}
+static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
+ struct file *fpin)
+{
+ int flags = vmf->flags;
+
+ if (fpin)
+ return fpin;
+
+ /*
+ * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
+ * anything, so we only pin the file and drop the mmap_sem if only
+ * FAULT_FLAG_ALLOW_RETRY is set.
+ */
+ if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
+ FAULT_FLAG_ALLOW_RETRY) {
+ fpin = get_file(vmf->vma->vm_file);
+ up_read(&vmf->vma->vm_mm->mmap_sem);
+ }
+ return fpin;
+}
+
#else /* !CONFIG_MMU */
static inline void clear_page_mlock(struct page *page) { }
static inline void mlock_vma_page(struct page *page) { }
diff --git a/mm/memory.c b/mm/memory.c
index b0efc69b2634..339f8ba20470 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2257,10 +2257,11 @@ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf)
*
* The function expects the page to be locked and unlocks it.
*/
-static void fault_dirty_shared_page(struct vm_area_struct *vma,
- struct page *page)
+static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
struct address_space *mapping;
+ struct page *page = vmf->page;
bool dirtied;
bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite;
@@ -2275,16 +2276,30 @@ static void fault_dirty_shared_page(struct vm_area_struct *vma,
mapping = page_rmapping(page);
unlock_page(page);
+ if (!page_mkwrite)
+ file_update_time(vma->vm_file);
+
+ /*
+ * Throttle page dirtying rate down to writeback speed.
+ *
+ * mapping may be NULL here because some device drivers do not
+ * set page.mapping but still dirty their pages
+ *
+ * Drop the mmap_sem before waiting on IO, if we can. The file
+ * is pinning the mapping, as per above.
+ */
if ((dirtied || page_mkwrite) && mapping) {
- /*
- * Some device drivers do not set page.mapping
- * but still dirty their pages
- */
+ struct file *fpin;
+
+ fpin = maybe_unlock_mmap_for_io(vmf, NULL);
balance_dirty_pages_ratelimited(mapping);
+ if (fpin) {
+ fput(fpin);
+ return VM_FAULT_RETRY;
+ }
}
- if (!page_mkwrite)
- file_update_time(vma->vm_file);
+ return 0;
}
/*
@@ -2527,6 +2542,7 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf)
__releases(vmf->ptl)
{
struct vm_area_struct *vma = vmf->vma;
+ vm_fault_t ret = VM_FAULT_WRITE;
get_page(vmf->page);
@@ -2550,10 +2566,10 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf)
wp_page_reuse(vmf);
lock_page(vmf->page);
}
- fault_dirty_shared_page(vma, vmf->page);
+ ret |= fault_dirty_shared_page(vmf);
put_page(vmf->page);
- return VM_FAULT_WRITE;
+ return ret;
}
/*
@@ -3615,7 +3631,7 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
return ret;
}
- fault_dirty_shared_page(vma, vmf->page);
+ ret |= fault_dirty_shared_page(vmf);
return ret;
}
diff --git a/mm/migrate.c b/mm/migrate.c
index dbb3b5bee4ee..812c18c48704 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1522,9 +1522,11 @@ static int do_move_pages_to_node(struct mm_struct *mm,
/*
* Resolves the given address to a struct page, isolates it from the LRU and
* puts it to the given pagelist.
- * Returns -errno if the page cannot be found/isolated or 0 when it has been
- * queued or the page doesn't need to be migrated because it is already on
- * the target node
+ * Returns:
+ * errno - if the page cannot be found/isolated
+ * 0 - when it doesn't have to be migrated because it is already on the
+ * target node
+ * 1 - when it has been queued
*/
static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
int node, struct list_head *pagelist, bool migrate_all)
@@ -1563,7 +1565,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
if (PageHuge(page)) {
if (PageHead(page)) {
isolate_huge_page(page, pagelist);
- err = 0;
+ err = 1;
}
} else {
struct page *head;
@@ -1573,7 +1575,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
if (err)
goto out_putpage;
- err = 0;
+ err = 1;
list_add_tail(&head->lru, pagelist);
mod_node_page_state(page_pgdat(head),
NR_ISOLATED_ANON + page_is_file_cache(head),
@@ -1650,8 +1652,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
*/
err = add_page_for_migration(mm, addr, current_node,
&pagelist, flags & MPOL_MF_MOVE_ALL);
- if (!err)
+
+ if (!err) {
+ /* The page is already on the target node */
+ err = store_status(status, i, current_node, 1);
+ if (err)
+ goto out_flush;
continue;
+ } else if (err > 0) {
+ /* The page is successfully queued for migration */
+ continue;
+ }
err = store_status(status, i, err, 1);
if (err)
@@ -1675,7 +1686,7 @@ out_flush:
err1 = do_move_pages_to_node(mm, &pagelist, current_node);
if (!err1)
err1 = store_status(status, start, current_node, i - start);
- if (!err)
+ if (err >= 0)
err = err1;
out:
return err;
diff --git a/mm/mmap.c b/mm/mmap.c
index d8a903f61262..b0c80b19898b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -90,12 +90,6 @@ static void unmap_region(struct mm_struct *mm,
* MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes
* w: (no) no w: (no) no w: (copy) copy w: (no) no
* x: (no) no x: (no) yes x: (no) yes x: (yes) yes
- *
- * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
- * MAP_PRIVATE:
- * r: (no) no
- * w: (no) no
- * x: (yes) yes
*/
pgprot_t protection_map[16] __ro_after_init = {
__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
diff --git a/mm/shmem.c b/mm/shmem.c
index 32c30ad3573d..9fedf2805291 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2005,16 +2005,14 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
shmem_falloc->waitq &&
vmf->pgoff >= shmem_falloc->start &&
vmf->pgoff < shmem_falloc->next) {
+ struct file *fpin;
wait_queue_head_t *shmem_falloc_waitq;
DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function);
ret = VM_FAULT_NOPAGE;
- if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
- !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
- /* It's polite to up mmap_sem if we can */
- up_read(&vma->vm_mm->mmap_sem);
+ fpin = maybe_unlock_mmap_for_io(vmf, NULL);
+ if (fpin)
ret = VM_FAULT_RETRY;
- }
shmem_falloc_waitq = shmem_falloc->waitq;
prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
@@ -2032,6 +2030,9 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
spin_lock(&inode->i_lock);
finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
spin_unlock(&inode->i_lock);
+
+ if (fpin)
+ fput(fpin);
return ret;
}
spin_unlock(&inode->i_lock);
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 7d62ef2daf83..b85492d25ba2 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2092,6 +2092,11 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
zs_pool_dec_isolated(pool);
}
+ if (page_zone(newpage) != page_zone(page)) {
+ dec_zone_page_state(page, NR_ZSPAGES);
+ inc_zone_page_state(newpage, NR_ZSPAGES);
+ }
+
reset_page(page);
put_page(page);
page = newpage;
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-27 05:38:34 +0000