path: root/include/linux/hmm.h

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * Copyright 2013 Red Hat Inc.
 *
 * Authors: Jérôme Glisse <jglisse@redhat.com>
 */
/*
 * Heterogeneous Memory Management (HMM)
 *
 * See Documentation/vm/hmm.rst for reasons and overview of what HMM is and it
 * is for. Here we focus on the HMM API description, with some explanation of
 * the underlying implementation.
 *
 * Short description: HMM provides a set of helpers to share a virtual address
 * space between CPU and a device, so that the device can access any valid
 * address of the process (while still obeying memory protection). HMM also
 * provides helpers to migrate process memory to device memory, and back. Each
 * set of functionality (address space mirroring, and migration to and from
 * device memory) can be used independently of the other.
 *
 *
 * HMM address space mirroring API:
 *
 * Use HMM address space mirroring if you want to mirror range of the CPU page
 * table of a process into a device page table. Here, "mirror" means "keep
 * synchronized". Prerequisites: the device must provide the ability to write-
 * protect its page tables (at PAGE_SIZE granularity), and must be able to
 * recover from the resulting potential page faults.
 *
 * HMM guarantees that at any point in time, a given virtual address points to
 * either the same memory in both CPU and device page tables (that is: CPU and
 * device page tables each point to the same pages), or that one page table (CPU
 * or device) points to no entry, while the other still points to the old page
 * for the address. The latter case happens when the CPU page table update
 * happens first, and then the update is mirrored over to the device page table.
 * This does not cause any issue, because the CPU page table cannot start
 * pointing to a new page until the device page table is invalidated.
 *
 * HMM uses mmu_notifiers to monitor the CPU page tables, and forwards any
 * updates to each device driver that has registered a mirror. It also provides
 * some API calls to help with taking a snapshot of the CPU page table, and to
 * synchronize with any updates that might happen concurrently.
 *
 *
 * HMM migration to and from device memory:
 *
 * HMM provides a set of helpers to hotplug device memory as ZONE_DEVICE, with
 * a new MEMORY_DEVICE_PRIVATE type. This provides a struct page for each page
 * of the device memory, and allows the device driver to manage its memory
 * using those struct pages. Having struct pages for device memory makes
 * migration easier. Because that memory is not addressable by the CPU it must
 * never be pinned to the device; in other words, any CPU page fault can always
 * cause the device memory to be migrated (copied/moved) back to regular memory.
 *
 * A new migrate helper (migrate_vma()) has been added (see mm/migrate.c) that
 * allows use of a device DMA engine to perform the copy operation between
 * regular system memory and device memory.
 */
#ifndef LINUX_HMM_H
#define LINUX_HMM_H

#include <linux/kconfig.h>
#include <asm/pgtable.h>

#if IS_ENABLED(CONFIG_HMM)

#include <linux/device.h>
#include <linux/migrate.h>
#include <linux/memremap.h>
#include <linux/completion.h>
#include <linux/mmu_notifier.h>


/*
 * struct hmm - HMM per mm struct
 *
 * @mm: mm struct this HMM struct is bound to
 * @lock: lock protecting ranges list
 * @ranges: list of range being snapshotted
 * @mirrors: list of mirrors for this mm
 * @mmu_notifier: mmu notifier to track updates to CPU page table
 * @mirrors_sem: read/write semaphore protecting the mirrors list
 * @wq: wait queue for user waiting on a range invalidation
 * @notifiers: count of active mmu notifiers
 * @dead: is the mm dead ?
 */
struct hmm {
	struct mm_struct	*mm;
	struct kref		kref;
	struct mutex		lock;
	struct list_head	ranges;
	struct list_head	mirrors;
	struct mmu_notifier	mmu_notifier;
	struct rw_semaphore	mirrors_sem;
	wait_queue_head_t	wq;
	long			notifiers;
	bool			dead;
};

/*
 * hmm_pfn_flag_e - HMM flag enums
 *
 * Flags:
 * HMM_PFN_VALID: pfn is valid. It has, at least, read permission.
 * HMM_PFN_WRITE: CPU page table has write permission set
 * HMM_PFN_DEVICE_PRIVATE: private device memory (ZONE_DEVICE)
 *
 * The driver provide a flags array, if driver valid bit for an entry is bit
 * 3 ie (entry & (1 << 3)) is true if entry is valid then driver must provide
 * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3.
 * Same logic apply to all flags. This is same idea as vm_page_prot in vma
 * except that this is per device driver rather than per architecture.
 */
enum hmm_pfn_flag_e {
	HMM_PFN_VALID = 0,
	HMM_PFN_WRITE,
	HMM_PFN_DEVICE_PRIVATE,
	HMM_PFN_FLAG_MAX
};

/*
 * hmm_pfn_value_e - HMM pfn special value
 *
 * Flags:
 * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory
 * HMM_PFN_NONE: corresponding CPU page table entry is pte_none()
 * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the
 *      result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not
 *      be mirrored by a device, because the entry will never have HMM_PFN_VALID
 *      set and the pfn value is undefined.
 *
 * Driver provide entry value for none entry, error entry and special entry,
 * driver can alias (ie use same value for error and special for instance). It
 * should not alias none and error or special.
 *
 * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be:
 * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous,
 * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table
 * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one
 */
enum hmm_pfn_value_e {
	HMM_PFN_ERROR,
	HMM_PFN_NONE,
	HMM_PFN_SPECIAL,
	HMM_PFN_VALUE_MAX
};

/*
 * struct hmm_range - track invalidation lock on virtual address range
 *
 * @hmm: the core HMM structure this range is active against
 * @vma: the vm area struct for the range
 * @list: all range lock are on a list
 * @start: range virtual start address (inclusive)
 * @end: range virtual end address (exclusive)
 * @pfns: array of pfns (big enough for the range)
 * @flags: pfn flags to match device driver page table
 * @values: pfn value for some special case (none, special, error, ...)
 * @default_flags: default flags for the range (write, read, ... see hmm doc)
 * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter
 * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT)
 * @valid: pfns array did not change since it has been fill by an HMM function
 */
struct hmm_range {
	struct hmm		*hmm;
	struct vm_area_struct	*vma;
	struct list_head	list;
	unsigned long		start;
	unsigned long		end;
	uint64_t		*pfns;
	const uint64_t		*flags;
	const uint64_t		*values;
	uint64_t		default_flags;
	uint64_t		pfn_flags_mask;
	uint8_t			page_shift;
	uint8_t			pfn_shift;
	bool			valid;
};

/*
 * hmm_range_page_shift() - return the page shift for the range
 * @range: range being queried
 * Returns: page shift (page size = 1 << page shift) for the range
 */
static inline unsigned hmm_range_page_shift(const struct hmm_range *range)
{
	return range->page_shift;
}

/*
 * hmm_range_page_size() - return the page size for the range
 * @range: range being queried
 * Returns: page size for the range in bytes
 */
static inline unsigned long hmm_range_page_size(const struct hmm_range *range)
{
	return 1UL << hmm_range_page_shift(range);
}

/*
 * hmm_range_wait_until_valid() - wait for range to be valid
 * @range: range affected by invalidation to wait on
 * @timeout: time out for wait in ms (ie abort wait after that period of time)
 * Returns: true if the range is valid, false otherwise.
 */
static inline bool hmm_range_wait_until_valid(struct hmm_range *range,
					      unsigned long timeout)
{
	/* Check if mm is dead ? */
	if (range->hmm == NULL || range->hmm->dead || range->hmm->mm == NULL) {
		range->valid = false;
		return false;
	}
	if (range->valid)
		return true;
	wait_event_timeout(range->hmm->wq, range->valid || range->hmm->dead,
			   msecs_to_jiffies(timeout));
	/* Return current valid status just in case we get lucky */
	return range->valid;
}

/*
 * hmm_range_valid() - test if a range is valid or not
 * @range: range
 * Returns: true if the range is valid, false otherwise.
 */
static inline bool hmm_range_valid(struct hmm_range *range)
{
	return range->valid;
}

/*
 * hmm_device_entry_to_page() - return struct page pointed to by a device entry
 * @range: range use to decode device entry value
 * @entry: device entry value to get corresponding struct page from
 * Returns: struct page pointer if entry is a valid, NULL otherwise
 *
 * If the device entry is valid (ie valid flag set) then return the struct page
 * matching the entry value. Otherwise return NULL.
 */
static inline struct page *hmm_device_entry_to_page(const struct hmm_range *range,
						    uint64_t entry)
{
	if (entry == range->values[HMM_PFN_NONE])
		return NULL;
	if (entry == range->values[HMM_PFN_ERROR])
		return NULL;
	if (entry == range->values[HMM_PFN_SPECIAL])
		return NULL;
	if (!(entry & range->flags[HMM_PFN_VALID]))
		return NULL;
	return pfn_to_page(entry >> range->pfn_shift);
}

/*
 * hmm_device_entry_to_pfn() - return pfn value store in a device entry
 * @range: range use to decode device entry value
 * @entry: device entry to extract pfn from
 * Returns: pfn value if device entry is valid, -1UL otherwise
 */
static inline unsigned long
hmm_device_entry_to_pfn(const struct hmm_range *range, uint64_t pfn)
{
	if (pfn == range->values[HMM_PFN_NONE])
		return -1UL;
	if (pfn == range->values[HMM_PFN_ERROR])
		return -1UL;
	if (pfn == range->values[HMM_PFN_SPECIAL])
		return -1UL;
	if (!(pfn & range->flags[HMM_PFN_VALID]))
		return -1UL;
	return (pfn >> range->pfn_shift);
}

/*
 * hmm_device_entry_from_page() - create a valid device entry for a page
 * @range: range use to encode HMM pfn value
 * @page: page for which to create the device entry
 * Returns: valid device entry for the page
 */
static inline uint64_t hmm_device_entry_from_page(const struct hmm_range *range,
						  struct page *page)
{
	return (page_to_pfn(page) << range->pfn_shift) |
		range->flags[HMM_PFN_VALID];
}

/*
 * hmm_device_entry_from_pfn() - create a valid device entry value from pfn
 * @range: range use to encode HMM pfn value
 * @pfn: pfn value for which to create the device entry
 * Returns: valid device entry for the pfn
 */
static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range,
						 unsigned long pfn)
{
	return (pfn << range->pfn_shift) |
		range->flags[HMM_PFN_VALID];
}

/*
 * Old API:
 * hmm_pfn_to_page()
 * hmm_pfn_to_pfn()
 * hmm_pfn_from_page()
 * hmm_pfn_from_pfn()
 *
 * This are the OLD API please use new API, it is here to avoid cross-tree
 * merge painfullness ie we convert things to new API in stages.
 */
static inline struct page *hmm_pfn_to_page(const struct hmm_range *range,
					   uint64_t pfn)
{
	return hmm_device_entry_to_page(range, pfn);
}

static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range,
					   uint64_t pfn)
{
	return hmm_device_entry_to_pfn(range, pfn);
}

static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range,
					 struct page *page)
{
	return hmm_device_entry_from_page(range, page);
}

static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range,
					unsigned long pfn)
{
	return hmm_device_entry_from_pfn(range, pfn);
}



#if IS_ENABLED(CONFIG_HMM_MIRROR)