[PATCH 07/22] memremap: move dev_pagemap callbacks into a separate structure

From: Christoph Hellwig
Date: Thu Jun 13 2019 - 11:50:02 EST


The dev_pagemap is a growing too many callbacks. Move them into a
separate ops structure so that they are not duplicated for multiple
instances, and an attacker can't easily overwrite them.

Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
drivers/dax/device.c | 6 +++++-
drivers/nvdimm/pmem.c | 18 +++++++++++++-----
drivers/pci/p2pdma.c | 5 ++++-
include/linux/memremap.h | 29 +++++++++++++++--------------
kernel/memremap.c | 12 ++++++------
mm/hmm.c | 8 ++++++--
tools/testing/nvdimm/test/iomap.c | 2 +-
7 files changed, 50 insertions(+), 30 deletions(-)

diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 996d68ff992a..4adab774dade 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -443,6 +443,10 @@ static void dev_dax_kill(void *dev_dax)
kill_dev_dax(dev_dax);
}

+static const struct dev_pagemap_ops dev_dax_pagemap_ops = {
+ .kill = dev_dax_percpu_kill,
+};
+
int dev_dax_probe(struct device *dev)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
@@ -471,7 +475,7 @@ int dev_dax_probe(struct device *dev)
return rc;

dev_dax->pgmap.ref = &dev_dax->ref;
- dev_dax->pgmap.kill = dev_dax_percpu_kill;
+ dev_dax->pgmap.ops = &dev_dax_pagemap_ops;
addr = devm_memremap_pages(dev, &dev_dax->pgmap);
if (IS_ERR(addr)) {
devm_remove_action(dev, dev_dax_percpu_exit, &dev_dax->ref);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index d9d845077b8b..4efbf184ea68 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -316,7 +316,7 @@ static void pmem_release_queue(void *q)
blk_cleanup_queue(q);
}

-static void pmem_freeze_queue(struct percpu_ref *ref)
+static void pmem_kill(struct percpu_ref *ref)
{
struct request_queue *q;

@@ -339,19 +339,27 @@ static void pmem_release_pgmap_ops(void *__pgmap)
dev_pagemap_put_ops();
}

-static void fsdax_pagefree(struct page *page, void *data)
+static void pmem_fsdax_page_free(struct page *page, void *data)
{
wake_up_var(&page->_refcount);
}

+static const struct dev_pagemap_ops fsdax_pagemap_ops = {
+ .page_free = pmem_fsdax_page_free,
+ .kill = pmem_kill,
+};
+
+static const struct dev_pagemap_ops pmem_legacy_pagemap_ops = {
+ .kill = pmem_kill,
+};
+
static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap)
{
dev_pagemap_get_ops();
if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap))
return -ENOMEM;
pgmap->type = MEMORY_DEVICE_FS_DAX;
- pgmap->page_free = fsdax_pagefree;
-
+ pgmap->ops = &fsdax_pagemap_ops;
return 0;
}

@@ -412,7 +420,6 @@ 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;
@@ -433,6 +440,7 @@ static int pmem_attach_disk(struct device *dev,
pmem->pfn_flags |= PFN_MAP;
memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
} else {
+ pmem->pgmap.ops = &pmem_legacy_pagemap_ops;
addr = devm_memremap(dev, pmem->phys_addr,
pmem->size, ARCH_MEMREMAP_PMEM);
memcpy(&bb_res, &nsio->res, sizeof(bb_res));
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 742928d0053e..6e76380f5b97 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -150,6 +150,10 @@ static int pci_p2pdma_setup(struct pci_dev *pdev)
return error;
}

+static const struct dev_pagemap_ops pci_p2pdma_pagemap_ops = {
+ .kill = pci_p2pdma_percpu_kill,
+};
+
/**
* pci_p2pdma_add_resource - add memory for use as p2p memory
* @pdev: the device to add the memory to
@@ -196,7 +200,6 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
pgmap->pci_p2pdma_bus_offset = pci_bus_address(pdev, bar) -
pci_resource_start(pdev, bar);
- pgmap->kill = pci_p2pdma_percpu_kill;

addr = devm_memremap_pages(&pdev->dev, pgmap);
if (IS_ERR(addr)) {
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index f0628660d541..5f7f40875b35 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -63,39 +63,40 @@ enum memory_type {
MEMORY_DEVICE_PCI_P2PDMA,
};

-/*
- * Additional notes about MEMORY_DEVICE_PRIVATE may be found in
- * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief
- * explanation in include/linux/memory_hotplug.h.
- *
- * The page_free() callback is called once the page refcount reaches 1
- * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug.
- * This allows the device driver to implement its own memory management.)
- */
-typedef void (*dev_page_free_t)(struct page *page, void *data);
+struct dev_pagemap_ops {
+ /*
+ * Called once the page refcount reaches 1. (ZONE_DEVICE pages never
+ * reach 0 refcount unless there is a refcount bug. This allows the
+ * device driver to implement its own memory management.)
+ */
+ void (*page_free)(struct page *page, void *data);
+
+ /*
+ * Transition the percpu_ref in struct dev_pagemap to the dead state.
+ */
+ void (*kill)(struct percpu_ref *ref);
+};

/**
* struct dev_pagemap - metadata for ZONE_DEVICE mappings
- * @page_free: free page callback when page refcount reaches 1
* @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
+ * @ops: method table
*/
struct dev_pagemap {
- dev_page_free_t page_free;
struct vmem_altmap altmap;
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;
u64 pci_p2pdma_bus_offset;
+ const struct dev_pagemap_ops *ops;
};

#ifdef CONFIG_ZONE_DEVICE
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 1490e63f69a9..e23286ce0ec4 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -92,7 +92,7 @@ static void devm_memremap_pages_release(void *data)
unsigned long pfn;
int nid;

- pgmap->kill(pgmap->ref);
+ pgmap->ops->kill(pgmap->ref);
for_each_device_pfn(pfn, pgmap)
put_page(pfn_to_page(pfn));

@@ -127,8 +127,8 @@ static void devm_memremap_pages_release(void *data)
* @pgmap: pointer to a struct dev_pagemap
*
* Notes:
- * 1/ At a minimum the res, ref and type members of @pgmap must be initialized
- * by the caller before passing it to this function
+ * 1/ At a minimum the res, ref and type and ops members of @pgmap must be
+ * initialized by the caller before passing it to this function
*
* 2/ The altmap field may optionally be initialized, in which case altmap_valid
* must be set to true
@@ -156,7 +156,7 @@ 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)
+ if (!pgmap->ref || !pgmap->ops || !pgmap->ops->kill)
return ERR_PTR(-EINVAL);

align_start = res->start & ~(SECTION_SIZE - 1);
@@ -266,7 +266,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
err_pfn_remap:
pgmap_array_delete(res);
err_array:
- pgmap->kill(pgmap->ref);
+ pgmap->ops->kill(pgmap->ref);
return ERR_PTR(error);
}
EXPORT_SYMBOL_GPL(devm_memremap_pages);
@@ -353,7 +353,7 @@ void __put_devmap_managed_page(struct page *page)

mem_cgroup_uncharge(page);

- page->pgmap->page_free(page, page->pgmap->data);
+ page->pgmap->ops->page_free(page, page->pgmap->data);
} else if (!count)
__put_page(page);
}
diff --git a/mm/hmm.c b/mm/hmm.c
index 13a16faf0a77..2501ac6045d0 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -1348,6 +1348,11 @@ static void hmm_devmem_free(struct page *page, void *data)
devmem->ops->free(devmem, page);
}

+static const struct dev_pagemap_ops hmm_pagemap_ops = {
+ .page_free = hmm_devmem_free,
+ .kill = hmm_devmem_ref_kill,
+};
+
/*
* hmm_devmem_add() - hotplug ZONE_DEVICE memory for device memory
*
@@ -1406,11 +1411,10 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,

devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
devmem->pagemap.res = *devmem->resource;
- devmem->pagemap.page_free = hmm_devmem_free;
+ devmem->pagemap.ops = &hmm_pagemap_ops;
devmem->pagemap.altmap_valid = false;
devmem->pagemap.ref = &devmem->ref;
devmem->pagemap.data = devmem;
- devmem->pagemap.kill = hmm_devmem_ref_kill;

result = devm_memremap_pages(devmem->device, &devmem->pagemap);
if (IS_ERR(result))
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index c6635fee27d8..7f5ece9b5011 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -108,7 +108,7 @@ static void nfit_test_kill(void *_pgmap)
{
struct dev_pagemap *pgmap = _pgmap;

- pgmap->kill(pgmap->ref);
+ pgmap->ops->kill(pgmap->ref);
}

void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
--
2.20.1