mm, devm_memremap_pages: fix shutdown handling

commit a95c90f1e2c253b280385ecf3d4ebfe476926b28 upstream.

The last step before devm_memremap_pages() returns success is to allocate
a release action, devm_memremap_pages_release(), to tear the entire setup
down.  However, the result from devm_add_action() is not checked.

Checking the error from devm_add_action() is not enough.  The api
currently relies on the fact that the percpu_ref it is using is killed by
the time the devm_memremap_pages_release() is run.  Rather than continue
this awkward situation, offload the responsibility of killing the
percpu_ref to devm_memremap_pages_release() directly.  This allows
devm_memremap_pages() to do the right thing relative to init failures and
shutdown.

Without this change we could fail to register the teardown of
devm_memremap_pages().  The likelihood of hitting this failure is tiny as
small memory allocations almost always succeed.  However, the impact of
the failure is large given any future reconfiguration, or disable/enable,
of an nvdimm namespace will fail forever as subsequent calls to
devm_memremap_pages() will fail to setup the pgmap_radix since there will
be stale entries for the physical address range.

An argument could be made to require that the ->kill() operation be set in
the @pgmap arg rather than passed in separately.  However, it helps code
readability, tracking the lifetime of a given instance, to be able to grep
the kill routine directly at the devm_memremap_pages() call site.

Link: http://lkml.kernel.org/r/154275558526.76910.7535251937849268605.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Fixes: e8d513483300 ("memremap: change devm_memremap_pages interface...")
Reviewed-by: "Jérôme Glisse" <jglisse@redhat.com>
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 15 insertions, 16 deletions

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 92e838127767..3c0c1a9cef69 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -122,14 +122,10 @@ static void devm_memremap_pages_release(void *data)
 	resource_size_t align_start, align_size;
 	unsigned long pfn;
 
+	pgmap->kill(pgmap->ref);
 	for_each_device_pfn(pfn, pgmap)
 		put_page(pfn_to_page(pfn));
 
-	if (percpu_ref_tryget_live(pgmap->ref)) {
-		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
-		percpu_ref_put(pgmap->ref);
-	}
-
 	/* pages are dead and unused, undo the arch mapping */
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -150,7 +146,7 @@ static void devm_memremap_pages_release(void *data)
 /**
  * devm_memremap_pages - remap and provide memmap backing for the given resource
  * @dev: hosting device for @res
- * @pgmap: pointer to a struct dev_pgmap
+ * @pgmap: pointer to a struct dev_pagemap
  *
  * Notes:
  * 1/ At a minimum the res, ref and type members of @pgmap must be initialized
@@ -159,11 +155,8 @@ static void devm_memremap_pages_release(void *data)
  * 2/ The altmap field may optionally be initialized, in which case altmap_valid
  *    must be set to true
  *
- * 3/ pgmap.ref must be 'live' on entry and 'dead' before devm_memunmap_pages()
- *    time (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().
+ * 3/ pgmap->ref must be 'live' on entry and will be killed at
+ *    devm_memremap_pages_release() time, or if this routine fails.
  *
  * 4/ 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
@@ -180,6 +173,9 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	int error, nid, is_ram;
 	struct dev_pagemap *conflict_pgmap;
 
+	if (!pgmap->ref || !pgmap->kill)
+		return ERR_PTR(-EINVAL);
+
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
 		- align_start;
@@ -205,12 +201,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	if (is_ram != REGION_DISJOINT) {
 		WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
 				is_ram == REGION_MIXED ? "mixed" : "ram", res);
-		return ERR_PTR(-ENXIO);
+		error = -ENXIO;
+		goto err_array;
 	}
 
-	if (!pgmap->ref)
-		return ERR_PTR(-EINVAL);
-
 	pgmap->dev = dev;
 
 	mutex_lock(&pgmap_lock);
@@ -267,7 +261,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		percpu_ref_get(pgmap->ref);
 	}
 
-	devm_add_action(dev, devm_memremap_pages_release, pgmap);
+	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
+			pgmap);
+	if (error)
+		return ERR_PTR(error);
 
 	return __va(res->start);
 
@@ -278,6 +275,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
  err_pfn_remap:
  err_radix:
 	pgmap_radix_release(res, pgoff);
+ err_array:
+	pgmap->kill(pgmap->ref);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL_GPL(devm_memremap_pages);