summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJérôme Glisse <jglisse@redhat.com>2017-09-08 16:11:46 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-09-08 18:26:46 -0700
commit7b2d55d2c8961ae9d456d3133f4ae2f0fbd3e14f (patch)
tree226b098cd8089f23756ca439e9e64d43a66defdb
parent5042db43cc26f51eed51c56192e2c2317e44315f (diff)
downloadlinux-7b2d55d2c8961ae9d456d3133f4ae2f0fbd3e14f.tar.bz2
mm/ZONE_DEVICE: special case put_page() for device private pages
A ZONE_DEVICE page that reach a refcount of 1 is free ie no longer have any user. For device private pages this is important to catch and thus we need to special case put_page() for this. Link: http://lkml.kernel.org/r/20170817000548.32038-9-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/memremap.h13
-rw-r--r--include/linux/mm.h31
-rw-r--r--kernel/memremap.c25
-rw-r--r--mm/hmm.c8
4 files changed, 67 insertions, 10 deletions
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 8e164ec9eed0..8aa6b82679e2 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -126,6 +126,14 @@ struct dev_pagemap {
void *devm_memremap_pages(struct device *dev, struct resource *res,
struct percpu_ref *ref, struct vmem_altmap *altmap);
struct dev_pagemap *find_dev_pagemap(resource_size_t phys);
+
+static inline bool is_zone_device_page(const struct page *page);
+
+static inline bool is_device_private_page(const struct page *page)
+{
+ return is_zone_device_page(page) &&
+ page->pgmap->type == MEMORY_DEVICE_PRIVATE;
+}
#else
static inline void *devm_memremap_pages(struct device *dev,
struct resource *res, struct percpu_ref *ref,
@@ -144,6 +152,11 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
{
return NULL;
}
+
+static inline bool is_device_private_page(const struct page *page)
+{
+ return false;
+}
#endif
/**
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a74c4e954352..eccdab4bb44a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -23,6 +23,7 @@
#include <linux/page_ext.h>
#include <linux/err.h>
#include <linux/page_ref.h>
+#include <linux/memremap.h>
struct mempolicy;
struct anon_vma;
@@ -792,25 +793,25 @@ static inline bool is_zone_device_page(const struct page *page)
{
return page_zonenum(page) == ZONE_DEVICE;
}
-
-static inline bool is_device_private_page(const struct page *page)
-{
- /* See MEMORY_DEVICE_PRIVATE in include/linux/memory_hotplug.h */
- return ((page_zonenum(page) == ZONE_DEVICE) &&
- (page->pgmap->type == MEMORY_DEVICE_PRIVATE));
-}
#else
static inline bool is_zone_device_page(const struct page *page)
{
return false;
}
+#endif
-static inline bool is_device_private_page(const struct page *page)
+#ifdef CONFIG_DEVICE_PRIVATE
+void put_zone_device_private_page(struct page *page);
+#else
+static inline void put_zone_device_private_page(struct page *page)
{
- return false;
}
#endif
+static inline bool is_device_private_page(const struct page *page);
+
+DECLARE_STATIC_KEY_FALSE(device_private_key);
+
static inline void get_page(struct page *page)
{
page = compound_head(page);
@@ -826,6 +827,18 @@ static inline void put_page(struct page *page)
{
page = compound_head(page);
+ /*
+ * For private device pages we need to catch refcount transition from
+ * 2 to 1, when refcount reach one it means the private device page is
+ * free and we need to inform the device driver through callback. See
+ * include/linux/memremap.h and HMM for details.
+ */
+ if (static_branch_unlikely(&device_private_key) &&
+ unlikely(is_device_private_page(page))) {
+ put_zone_device_private_page(page);
+ return;
+ }
+
if (put_page_testzero(page))
__put_page(page);
}
diff --git a/kernel/memremap.c b/kernel/memremap.c
index f1d1e0dfe8b4..1403cf16fa61 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -11,7 +11,6 @@
* 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>
@@ -500,3 +499,27 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
return pgmap ? pgmap->altmap : NULL;
}
#endif /* CONFIG_ZONE_DEVICE */
+
+
+#ifdef CONFIG_DEVICE_PRIVATE
+void put_zone_device_private_page(struct page *page)
+{
+ int count = page_ref_dec_return(page);
+
+ /*
+ * If refcount is 1 then page is freed and refcount is stable as nobody
+ * holds a reference on the page.
+ */
+ if (count == 1) {
+ /* Clear Active bit in case of parallel mark_page_accessed */
+ __ClearPageActive(page);
+ __ClearPageWaiters(page);
+
+ page->mapping = NULL;
+
+ page->pgmap->page_free(page, page->pgmap->data);
+ } else if (!count)
+ __put_page(page);
+}
+EXPORT_SYMBOL(put_zone_device_private_page);
+#endif /* CONFIG_DEVICE_PRIVATE */
diff --git a/mm/hmm.c b/mm/hmm.c
index f6c745b9a25a..3c6265d4254b 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -25,9 +25,17 @@
#include <linux/sched.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
+#include <linux/jump_label.h>
#include <linux/mmu_notifier.h>
+/*
+ * Device private memory see HMM (Documentation/vm/hmm.txt) or hmm.h
+ */
+DEFINE_STATIC_KEY_FALSE(device_private_key);
+EXPORT_SYMBOL(device_private_key);
+
+
#ifdef CONFIG_HMM
static const struct mmu_notifier_ops hmm_mmu_notifier_ops;