mm, devm_memremap_pages: fix shutdown handling

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/[e-mail]
Signed-off-by: Dan Williams <[e-mail]>
Fixes: e8d513483300 ("memremap: change devm_memremap_pages interface...")
Reviewed-by: "Jérôme Glisse" <[e-mail]>
Reported-by: Logan Gunthorpe <[e-mail]>
Reviewed-by: Logan Gunthorpe <[e-mail]>
Reviewed-by: Christoph Hellwig <[e-mail]>
Cc: Balbir Singh <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

drivers/dax/pmem.c

···
 	percpu_ref_exit(ref);
 }
 
-static void dax_pmem_percpu_kill(void *data)
+static void dax_pmem_percpu_kill(struct percpu_ref *ref)
 {
-	struct percpu_ref *ref = data;
 	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
 
 	dev_dbg(dax_pmem->dev, "trace\n");
···
 	}
 
 	dax_pmem->pgmap.ref = &dax_pmem->ref;
+	dax_pmem->pgmap.kill = dax_pmem_percpu_kill;
 	addr = devm_memremap_pages(dev, &dax_pmem->pgmap);
-	if (IS_ERR(addr)) {
-		devm_remove_action(dev, dax_pmem_percpu_exit, &dax_pmem->ref);
-		percpu_ref_exit(&dax_pmem->ref);
+	if (IS_ERR(addr))
 		return PTR_ERR(addr);
-	}
-
-	rc = devm_add_action_or_reset(dev, dax_pmem_percpu_kill,
-							&dax_pmem->ref);
-	if (rc)
-		return rc;
 
 	/* adjust the dax_region resource to the start of data */
 	memcpy(&res, &dax_pmem->pgmap.res, sizeof(res));

drivers/nvdimm/pmem.c

···
 	blk_cleanup_queue(q);
 }
 
-static void pmem_freeze_queue(void *q)
+static void pmem_freeze_queue(struct percpu_ref *ref)
 {
+	struct request_queue *q;
+
+	q = container_of(ref, typeof(*q), q_usage_counter);
 	blk_freeze_queue_start(q);
 }
 
···
 
 	pmem->pfn_flags = PFN_DEV;
 	pmem->pgmap.ref = &q->q_usage_counter;
+	pmem->pgmap.kill = pmem_freeze_queue;
 	if (is_nd_pfn(dev)) {
 		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
 			return -ENOMEM;
···
 				pmem->size, ARCH_MEMREMAP_PMEM);
 		memcpy(&bb_res, &nsio->res, sizeof(bb_res));
 	}
-
-	/*
-	 * At release time the queue must be frozen before
-	 * devm_memremap_pages is unwound
-	 */
-	if (devm_add_action_or_reset(dev, pmem_freeze_queue, q))
-		return -ENOMEM;
 
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);

include/linux/memremap.h

···
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
  * @res: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
+ * @kill: callback to transition @ref to the dead state
  * @dev: host device of the mapping for debug
  * @data: private data pointer for page_free()
  * @type: memory type: see MEMORY_* in memory_hotplug.h
···
 	bool altmap_valid;
 	struct resource res;
 	struct percpu_ref *ref;
+	void (*kill)(struct percpu_ref *ref);
 	struct device *dev;
 	void *data;
 	enum memory_type type;

kernel/memremap.c

···
 	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);
···
 /**
  * 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
···
  * 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
···
 	struct dev_pagemap *conflict_pgmap;
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
+
+	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)
···
 	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;
 
···
 				align_size >> PAGE_SHIFT, pgmap);
 	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
 
-	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);
 
···
  err_pfn_remap:
 	pgmap_array_delete(res);
  err_array:
+	pgmap->kill(pgmap->ref);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL_GPL(devm_memremap_pages);

tools/testing/nvdimm/test/iomap.c

···
 }
 EXPORT_SYMBOL(__wrap_devm_memremap);
 
+static void nfit_test_kill(void *_pgmap)
+{
+	struct dev_pagemap *pgmap = _pgmap;
+
+	pgmap->kill(pgmap->ref);
+}
+
 void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
 	resource_size_t offset = pgmap->res.start;
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-	if (nfit_res)
+	if (nfit_res) {
+		int rc;
+
+		rc = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
+		if (rc)
+			return ERR_PTR(rc);
 		return nfit_res->buf + offset - nfit_res->res.start;
+	}
 	return devm_memremap_pages(dev, pgmap);
 }
 EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages);