[tip:x86/mm] mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash

[tip-bot for Dan Williams <tipbot@zytor.com>]

Commit-ID:  71389703839ebe9cb426c72d5f0bd549592e583c
Gitweb:     http://git.kernel.org/tip/71389703839ebe9cb426c72d5f0bd549592e583c
Author:     Dan Williams <dan.j.williams@intel.com>
AuthorDate: Fri, 28 Apr 2017 10:23:37 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Mon, 1 May 2017 09:15:53 +0200

mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash

The x86 conversion to the generic GUP code included a small change which causes
crashes and data corruption in the pmem code - not good.

The root cause is that the /dev/pmem driver code implicitly relies on the x86
get_user_pages() implementation doing a get_page() on the page refcount, because
get_page() does a get_zone_device_page() which properly refcounts pmem's separate
page struct arrays that are not present in the regular page struct structures.
(The pmem driver does this because it can cover huge memory areas.)

But the x86 conversion to the generic GUP code changed the get_page() to
page_cache_get_speculative() which is faster but doesn't do the
get_zone_device_page() call the pmem code relies on.

One way to solve the regression would be to change the generic GUP code to use
get_page(), but that would slow things down a bit and punish other generic-GUP
using architectures for an x86-ism they did not care about. (Arguably the pmem
driver was probably not working reliably for them: but nvdimm is an Intel
feature, so non-x86 exposure is probably still limited.)

So restructure the pmem code's interface with the MM instead: get rid of the
get/put_zone_device_page() distinction, integrate put_zone_device_page() into
__put_page() and and restructure the pmem completion-wait and teardown machinery:

Kirill points out that the calls to {get,put}_dev_pagemap() can be
removed from the mm fast path if we take a single get_dev_pagemap()
reference to signify that the page is alive and use the final put of the
page to drop that reference.

This does require some care to make sure that any waits for the
percpu_ref to drop to zero occur *after* devm_memremap_page_release(),
since it now maintains its own elevated reference.

This speeds up things while also making the pmem refcounting more robust going
forward.

Suggested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/149339998297.24933.1129582806028305912.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/dax/pmem.c    |  2 +-
 drivers/nvdimm/pmem.c | 13 +++++++++++--
 include/linux/mm.h    | 14 --------------
 kernel/memremap.c     | 22 +++++++++-------------
 mm/swap.c             | 10 ++++++++++
 5 files changed, 31 insertions(+), 30 deletions(-)

diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 033f49b3..cb0d742 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -43,6 +43,7 @@ static void dax_pmem_percpu_exit(void *data)
 	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
 
 	dev_dbg(dax_pmem->dev, "%s\n", __func__);
+	wait_for_completion(&dax_pmem->cmp);
 	percpu_ref_exit(ref);
 }
 
@@ -53,7 +54,6 @@ static void dax_pmem_percpu_kill(void *data)
 
 	dev_dbg(dax_pmem->dev, "%s\n", __func__);
 	percpu_ref_kill(ref);
-	wait_for_completion(&dax_pmem->cmp);
 }
 
 static int dax_pmem_probe(struct device *dev)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 5b536be..fb7bbc7 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -25,6 +25,7 @@
 #include <linux/badblocks.h>
 #include <linux/memremap.h>
 #include <linux/vmalloc.h>
+#include <linux/blk-mq.h>
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/pmem.h>
@@ -231,6 +232,11 @@ static void pmem_release_queue(void *q)
 	blk_cleanup_queue(q);
 }
 
+static void pmem_freeze_queue(void *q)
+{
+	blk_mq_freeze_queue_start(q);
+}
+
 static void pmem_release_disk(void *disk)
 {
 	del_gendisk(disk);
@@ -284,6 +290,9 @@ static int pmem_attach_disk(struct device *dev,
 	if (!q)
 		return -ENOMEM;
 
+	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
+		return -ENOMEM;
+
 	pmem->pfn_flags = PFN_DEV;
 	if (is_nd_pfn(dev)) {
 		addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter,
@@ -303,10 +312,10 @@ static int pmem_attach_disk(struct device *dev,
 				pmem->size, ARCH_MEMREMAP_PMEM);
 
 	/*
-	 * At release time the queue must be dead before
+	 * At release time the queue must be frozen before
 	 * devm_memremap_pages is unwound
 	 */
-	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
+	if (devm_add_action_or_reset(dev, pmem_freeze_queue, q))
 		return -ENOMEM;
 
 	if (IS_ERR(addr))
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a835edd..695da2a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -762,19 +762,11 @@ static inline enum zone_type page_zonenum(const struct page *page)
 }
 
 #ifdef CONFIG_ZONE_DEVICE
-void get_zone_device_page(struct page *page);
-void put_zone_device_page(struct page *page);
 static inline bool is_zone_device_page(const struct page *page)
 {
 	return page_zonenum(page) == ZONE_DEVICE;
 }
 #else
-static inline void get_zone_device_page(struct page *page)
-{
-}
-static inline void put_zone_device_page(struct page *page)
-{
-}
 static inline bool is_zone_device_page(const struct page *page)
 {
 	return false;
@@ -790,9 +782,6 @@ static inline void get_page(struct page *page)
 	 */
 	VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
 	page_ref_inc(page);
-
-	if (unlikely(is_zone_device_page(page)))
-		get_zone_device_page(page);
 }
 
 static inline void put_page(struct page *page)
@@ -801,9 +790,6 @@ static inline void put_page(struct page *page)
 
 	if (put_page_testzero(page))
 		__put_page(page);
-
-	if (unlikely(is_zone_device_page(page)))
-		put_zone_device_page(page);
 }
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 07e85e5..23a6483 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -182,18 +182,6 @@ struct page_map {
 	struct vmem_altmap altmap;
 };
 
-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, align_start, align_size, align_end;
@@ -237,6 +225,10 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	struct resource *res = &page_map->res;
 	resource_size_t align_start, align_size;
 	struct dev_pagemap *pgmap = &page_map->pgmap;
+	unsigned long pfn;
+
+	for_each_device_pfn(pfn, page_map)
+		put_page(pfn_to_page(pfn));
 
 	if (percpu_ref_tryget_live(pgmap->ref)) {
 		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
@@ -277,7 +269,10 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
  *
  * Notes:
  * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time
- *    (or devm release event).
+ *    (or devm release event). The expected order of events is that @ref has
+ *    been through percpu_ref_kill() before devm_memremap_pages_release(). The
+ *    wait for the completion of all references being dropped and
+ *    percpu_ref_exit() must occur after devm_memremap_pages_release().
  *
  * 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
@@ -379,6 +374,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		 */
 		list_del(&page->lru);
 		page->pgmap = pgmap;
+		percpu_ref_get(ref);
 	}
 	devres_add(dev, page_map);
 	return __va(res->start);
diff --git a/mm/swap.c b/mm/swap.c
index c4910f1..a4e6113 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -97,6 +97,16 @@ static void __put_compound_page(struct page *page)
 
 void __put_page(struct page *page)
 {
+	if (is_zone_device_page(page)) {
+		put_dev_pagemap(page->pgmap);
+
+		/*
+		 * The page belongs to the device that created pgmap. Do
+		 * not return it to page allocator.
+		 */
+		return;
+	}
+
 	if (unlikely(PageCompound(page)))
 		__put_compound_page(page);
 	else