[PATCH v8 3/7] mm, devm_memremap_pages: Fix shutdown handling

From: Dan Williams
Date: Tue Nov 20 2018 - 18:25:35 EST


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.

Cc: <stable@xxxxxxxxxxxxxxx>
Fixes: e8d513483300 ("memremap: change devm_memremap_pages interface...")
Reviewed-by: "JÃrÃme Glisse" <jglisse@xxxxxxxxxx>
Reported-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Reviewed-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
drivers/dax/pmem.c | 14 +++-----------
drivers/nvdimm/pmem.c | 13 +++++--------
include/linux/memremap.h | 2 ++
kernel/memremap.c | 30 ++++++++++++++----------------
tools/testing/nvdimm/test/iomap.c | 15 ++++++++++++++-
5 files changed, 38 insertions(+), 36 deletions(-)

diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 99e2aace8078..2c1f459c0c63 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -48,9 +48,8 @@ static void dax_pmem_percpu_exit(void *data)
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");
@@ -112,17 +111,10 @@ static int dax_pmem_probe(struct device *dev)
}

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));
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index f7019294740c..bc2f700feef8 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -309,8 +309,11 @@ static void pmem_release_queue(void *q)
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);
}

@@ -402,6 +405,7 @@ static int pmem_attach_disk(struct device *dev,

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;
@@ -427,13 +431,6 @@ static int pmem_attach_disk(struct device *dev,
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);
pmem->virt_addr = addr;
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 0ac69ddf5fc4..55db66b3716f 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -111,6 +111,7 @@ typedef void (*dev_page_free_t)(struct page *page, void *data);
* @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
@@ -122,6 +123,7 @@ struct dev_pagemap {
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;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 99d14940acfa..5e45f0c327a5 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -88,14 +88,10 @@ 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)
@@ -116,7 +112,7 @@ 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
@@ -125,11 +121,8 @@ 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
@@ -145,6 +138,9 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *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)
- align_start;
@@ -170,12 +166,10 @@ 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;

error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
@@ -217,7 +211,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
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);

@@ -228,6 +225,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
err_pfn_remap:
pgmap_array_delete(res);
err_array:
+ pgmap->kill(pgmap->ref);
return ERR_PTR(error);
}
EXPORT_SYMBOL_GPL(devm_memremap_pages);
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index ed18a0cbc0c8..c6635fee27d8 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -104,13 +104,26 @@ void *__wrap_devm_memremap(struct device *dev, resource_size_t offset,
}
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);