linux_dsm_epyc7002/include/linux/memremap.h
Dan Williams 50f44ee724 mm/devm_memremap_pages: fix final page put race
Logan noticed that devm_memremap_pages_release() kills the percpu_ref
drops all the page references that were acquired at init and then
immediately proceeds to unplug, arch_remove_memory(), the backing pages
for the pagemap.  If for some reason device shutdown actually collides
with a busy / elevated-ref-count page then arch_remove_memory() should
be deferred until after that reference is dropped.

As it stands the "wait for last page ref drop" happens *after*
devm_memremap_pages_release() returns, which is obviously too late and
can lead to crashes.

Fix this situation by assigning the responsibility to wait for the
percpu_ref to go idle to devm_memremap_pages() with a new ->cleanup()
callback.  Implement the new cleanup callback for all
devm_memremap_pages() users: pmem, devdax, hmm, and p2pdma.

Link: http://lkml.kernel.org/r/155727339156.292046.5432007428235387859.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: 41e94a8513 ("add devm_memremap_pages")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-13 17:34:56 -10:00

152 lines
5.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MEMREMAP_H_
#define _LINUX_MEMREMAP_H_
#include <linux/ioport.h>
#include <linux/percpu-refcount.h>
struct resource;
struct device;
/**
* struct vmem_altmap - pre-allocated storage for vmemmap_populate
* @base_pfn: base of the entire dev_pagemap mapping
* @reserve: pages mapped, but reserved for driver use (relative to @base)
* @free: free pages set aside in the mapping for memmap storage
* @align: pages reserved to meet allocation alignments
* @alloc: track pages consumed, private to vmemmap_populate()
*/
struct vmem_altmap {
const unsigned long base_pfn;
const unsigned long reserve;
unsigned long free;
unsigned long align;
unsigned long alloc;
};
/*
* Specialize ZONE_DEVICE memory into multiple types each having differents
* usage.
*
* MEMORY_DEVICE_PRIVATE:
* Device memory that is not directly addressable by the CPU: CPU can neither
* read nor write private memory. In this case, we do still have struct pages
* backing the device memory. Doing so simplifies the implementation, but it is
* important to remember that there are certain points at which the struct page
* must be treated as an opaque object, rather than a "normal" struct page.
*
* A more complete discussion of unaddressable memory may be found in
* include/linux/hmm.h and Documentation/vm/hmm.rst.
*
* MEMORY_DEVICE_PUBLIC:
* Device memory that is cache coherent from device and CPU point of view. This
* is use on platform that have an advance system bus (like CAPI or CCIX). A
* driver can hotplug the device memory using ZONE_DEVICE and with that memory
* type. Any page of a process can be migrated to such memory. However no one
* should be allow to pin such memory so that it can always be evicted.
*
* MEMORY_DEVICE_FS_DAX:
* Host memory that has similar access semantics as System RAM i.e. DMA
* coherent and supports page pinning. In support of coordinating page
* pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
* wakeup event whenever a page is unpinned and becomes idle. This
* wakeup is used to coordinate physical address space management (ex:
* fs truncate/hole punch) vs pinned pages (ex: device dma).
*
* MEMORY_DEVICE_PCI_P2PDMA:
* Device memory residing in a PCI BAR intended for use with Peer-to-Peer
* transactions.
*/
enum memory_type {
MEMORY_DEVICE_PRIVATE = 1,
MEMORY_DEVICE_PUBLIC,
MEMORY_DEVICE_FS_DAX,
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 - 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
* @cleanup: callback to wait for @ref to be idle and reap it
* @dev: host device of the mapping for debug
* @data: private data pointer for page_free()
* @type: memory type: see MEMORY_* in memory_hotplug.h
*/
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);
void (*cleanup)(struct percpu_ref *ref);
struct device *dev;
void *data;
enum memory_type type;
u64 pci_p2pdma_bus_offset;
};
#ifdef CONFIG_ZONE_DEVICE
void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap);
struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
struct dev_pagemap *pgmap);
unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
#else
static inline void *devm_memremap_pages(struct device *dev,
struct dev_pagemap *pgmap)
{
/*
* Fail attempts to call devm_memremap_pages() without
* ZONE_DEVICE support enabled, this requires callers to fall
* back to plain devm_memremap() based on config
*/
WARN_ON_ONCE(1);
return ERR_PTR(-ENXIO);
}
static inline void devm_memunmap_pages(struct device *dev,
struct dev_pagemap *pgmap)
{
}
static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
struct dev_pagemap *pgmap)
{
return NULL;
}
static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
{
return 0;
}
static inline void vmem_altmap_free(struct vmem_altmap *altmap,
unsigned long nr_pfns)
{
}
#endif /* CONFIG_ZONE_DEVICE */
static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
{
if (pgmap)
percpu_ref_put(pgmap->ref);
}
#endif /* _LINUX_MEMREMAP_H_ */