/** * DOC: Overview * * The DRM pagemap layer is intended to augment the dev_pagemap functionality by * providing a way to populate a struct mm_struct virtual range with device * private pages and to provide helpers to abstract device memory allocations, * to migrate memory back and forth between device memory and system RAM and * to handle access (and in the future migration) between devices implementing * a fast interconnect that is not necessarily visible to the rest of the * system. * * Typically the DRM pagemap receives requests from one or more DRM GPU SVM * instances to populate struct mm_struct virtual ranges with memory, and the * migration is best effort only and may thus fail. The implementation should * also handle device unbinding by blocking (return an -ENODEV) error for new * population requests and after that migrate all device pages to system ram.
*/
/** * DOC: Migration * * Migration granularity typically follows the GPU SVM range requests, but * if there are clashes, due to races or due to the fact that multiple GPU * SVM instances have different views of the ranges used, and because of that * parts of a requested range is already present in the requested device memory, * the implementation has a variety of options. It can fail and it can choose * to populate only the part of the range that isn't already in device memory, * and it can evict the range to system before trying to migrate. Ideally an * implementation would just try to migrate the missing part of the range and * allocate just enough memory to do so. * * When migrating to system memory as a response to a cpu fault or a device * memory eviction request, currently a full device memory allocation is * migrated back to system. Moving forward this might need improvement for * situations where a single page needs bouncing between system memory and * device memory due to, for example, atomic operations. * * Key DRM pagemap components: * * - Device Memory Allocations: * Embedded structure containing enough information for the drm_pagemap to * migrate to / from device memory. * * - Device Memory Operations: * Define the interface for driver-specific device memory operations * release memory, populate pfns, and copy to / from device memory.
*/
/** * struct drm_pagemap_zdd - GPU SVM zone device data * * @refcount: Reference count for the zdd * @devmem_allocation: device memory allocation * @device_private_page_owner: Device private pages owner * * This structure serves as a generic wrapper installed in * page->zone_device_data. It provides infrastructure for looking up a device * memory allocation upon CPU page fault and asynchronously releasing device * memory once the CPU has no page references. Asynchronous release is useful * because CPU page references can be dropped in IRQ contexts, while releasing * device memory likely requires sleeping locks.
*/ struct drm_pagemap_zdd { struct kref refcount; struct drm_pagemap_devmem *devmem_allocation; void *device_private_page_owner;
};
/** * drm_pagemap_zdd_alloc() - Allocate a zdd structure. * @device_private_page_owner: Device private pages owner * * This function allocates and initializes a new zdd structure. It sets up the * reference count and initializes the destroy work. * * Return: Pointer to the allocated zdd on success, ERR_PTR() on failure.
*/ staticstruct drm_pagemap_zdd *
drm_pagemap_zdd_alloc(void *device_private_page_owner)
{ struct drm_pagemap_zdd *zdd;
zdd = kmalloc(sizeof(*zdd), GFP_KERNEL); if (!zdd) return NULL;
/** * drm_pagemap_zdd_get() - Get a reference to a zdd structure. * @zdd: Pointer to the zdd structure. * * This function increments the reference count of the provided zdd structure. * * Return: Pointer to the zdd structure.
*/ staticstruct drm_pagemap_zdd *drm_pagemap_zdd_get(struct drm_pagemap_zdd *zdd)
{
kref_get(&zdd->refcount); return zdd;
}
/** * drm_pagemap_zdd_destroy() - Destroy a zdd structure. * @ref: Pointer to the reference count structure. * * This function queues the destroy_work of the zdd for asynchronous destruction.
*/ staticvoid drm_pagemap_zdd_destroy(struct kref *ref)
{ struct drm_pagemap_zdd *zdd =
container_of(ref, struct drm_pagemap_zdd, refcount); struct drm_pagemap_devmem *devmem = zdd->devmem_allocation;
if (devmem) {
complete_all(&devmem->detached); if (devmem->ops->devmem_release)
devmem->ops->devmem_release(devmem);
}
kfree(zdd);
}
/** * drm_pagemap_zdd_put() - Put a zdd reference. * @zdd: Pointer to the zdd structure. * * This function decrements the reference count of the provided zdd structure * and schedules its destruction if the count drops to zero.
*/ staticvoid drm_pagemap_zdd_put(struct drm_pagemap_zdd *zdd)
{
kref_put(&zdd->refcount, drm_pagemap_zdd_destroy);
}
/** * drm_pagemap_migration_unlock_put_page() - Put a migration page * @page: Pointer to the page to put * * This function unlocks and puts a page.
*/ staticvoid drm_pagemap_migration_unlock_put_page(struct page *page)
{
unlock_page(page);
put_page(page);
}
/** * drm_pagemap_migration_unlock_put_pages() - Put migration pages * @npages: Number of pages * @migrate_pfn: Array of migrate page frame numbers * * This function unlocks and puts an array of pages.
*/ staticvoid drm_pagemap_migration_unlock_put_pages(unsignedlong npages, unsignedlong *migrate_pfn)
{ unsignedlong i;
/** * drm_pagemap_get_devmem_page() - Get a reference to a device memory page * @page: Pointer to the page * @zdd: Pointer to the GPU SVM zone device data * * This function associates the given page with the specified GPU SVM zone * device data and initializes it for zone device usage.
*/ staticvoid drm_pagemap_get_devmem_page(struct page *page, struct drm_pagemap_zdd *zdd)
{
page->zone_device_data = drm_pagemap_zdd_get(zdd);
zone_device_page_init(page);
}
/** * drm_pagemap_migrate_map_pages() - Map migration pages for GPU SVM migration * @dev: The device for which the pages are being mapped * @dma_addr: Array to store DMA addresses corresponding to mapped pages * @migrate_pfn: Array of migrate page frame numbers to map * @npages: Number of pages to map * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL) * * This function maps pages of memory for migration usage in GPU SVM. It * iterates over each page frame number provided in @migrate_pfn, maps the * corresponding page, and stores the DMA address in the provided @dma_addr * array. * * Returns: 0 on success, -EFAULT if an error occurs during mapping.
*/ staticint drm_pagemap_migrate_map_pages(struct device *dev,
dma_addr_t *dma_addr, unsignedlong *migrate_pfn, unsignedlong npages, enum dma_data_direction dir)
{ unsignedlong i;
for (i = 0; i < npages; ++i) { struct page *page = migrate_pfn_to_page(migrate_pfn[i]);
if (!page) continue;
if (WARN_ON_ONCE(is_zone_device_page(page))) return -EFAULT;
/** * drm_pagemap_migrate_unmap_pages() - Unmap pages previously mapped for GPU SVM migration * @dev: The device for which the pages were mapped * @dma_addr: Array of DMA addresses corresponding to mapped pages * @npages: Number of pages to unmap * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL) * * This function unmaps previously mapped pages of memory for GPU Shared Virtual * Memory (SVM). It iterates over each DMA address provided in @dma_addr, checks * if it's valid and not already unmapped, and unmaps the corresponding page.
*/ staticvoid drm_pagemap_migrate_unmap_pages(struct device *dev,
dma_addr_t *dma_addr, unsignedlong npages, enum dma_data_direction dir)
{ unsignedlong i;
for (i = 0; i < npages; ++i) { if (!dma_addr[i] || dma_mapping_error(dev, dma_addr[i])) continue;
/** * drm_pagemap_migrate_to_devmem() - Migrate a struct mm_struct range to device memory * @devmem_allocation: The device memory allocation to migrate to. * The caller should hold a reference to the device memory allocation, * and the reference is consumed by this function unless it returns with * an error. * @mm: Pointer to the struct mm_struct. * @start: Start of the virtual address range to migrate. * @end: End of the virtual address range to migrate. * @timeslice_ms: The time requested for the migrated pagemap pages to * be present in @mm before being allowed to be migrated back. * @pgmap_owner: Not used currently, since only system memory is considered. * * This function migrates the specified virtual address range to device memory. * It performs the necessary setup and invokes the driver-specific operations for * migration to device memory. Expected to be called while holding the mmap lock in * at least read mode. * * Note: The @timeslice_ms parameter can typically be used to force data to * remain in pagemap pages long enough for a GPU to perform a task and to prevent * a migration livelock. One alternative would be for the GPU driver to block * in a mmu_notifier for the specified amount of time, but adding the * functionality to the pagemap is likely nicer to the system as a whole. * * Return: %0 on success, negative error code on failure.
*/ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, struct mm_struct *mm, unsignedlong start, unsignedlong end, unsignedlong timeslice_ms, void *pgmap_owner)
{ conststruct drm_pagemap_devmem_ops *ops = devmem_allocation->ops; struct migrate_vma migrate = {
.start = start,
.end = end,
.pgmap_owner = pgmap_owner,
.flags = MIGRATE_VMA_SELECT_SYSTEM,
}; unsignedlong i, npages = npages_in_range(start, end); struct vm_area_struct *vas; struct drm_pagemap_zdd *zdd = NULL; struct page **pages;
dma_addr_t *dma_addr; void *buf; int err;
mmap_assert_locked(mm);
if (!ops->populate_devmem_pfn || !ops->copy_to_devmem ||
!ops->copy_to_ram) return -EOPNOTSUPP;
vas = vma_lookup(mm, start); if (!vas) {
err = -ENOENT; goto err_out;
}
/** * drm_pagemap_migrate_populate_ram_pfn() - Populate RAM PFNs for a VM area * @vas: Pointer to the VM area structure, can be NULL * @fault_page: Fault page * @npages: Number of pages to populate * @mpages: Number of pages to migrate * @src_mpfn: Source array of migrate PFNs * @mpfn: Array of migrate PFNs to populate * @addr: Start address for PFN allocation * * This function populates the RAM migrate page frame numbers (PFNs) for the * specified VM area structure. It allocates and locks pages in the VM area for * RAM usage. If vas is non-NULL use alloc_page_vma for allocation, if NULL use * alloc_page for allocation. * * Return: 0 on success, negative error code on failure.
*/ staticint drm_pagemap_migrate_populate_ram_pfn(struct vm_area_struct *vas, struct page *fault_page, unsignedlong npages, unsignedlong *mpages, unsignedlong *src_mpfn, unsignedlong *mpfn, unsignedlong addr)
{ unsignedlong i;
for (i = 0; i < npages; ++i, addr += PAGE_SIZE) { struct page *page, *src_page;
if (!(src_mpfn[i] & MIGRATE_PFN_MIGRATE)) continue;
src_page = migrate_pfn_to_page(src_mpfn[i]); if (!src_page) continue;
if (fault_page) { if (src_page->zone_device_data !=
fault_page->zone_device_data) continue;
}
if (vas)
page = alloc_page_vma(GFP_HIGHUSER, vas, addr); else
page = alloc_page(GFP_HIGHUSER);
if (!page) goto free_pages;
mpfn[i] = migrate_pfn(page_to_pfn(page));
}
for (i = 0; i < npages; ++i) { struct page *page = migrate_pfn_to_page(mpfn[i]);
if (!page) continue;
WARN_ON_ONCE(!trylock_page(page));
++*mpages;
}
return 0;
free_pages: for (i = 0; i < npages; ++i) { struct page *page = migrate_pfn_to_page(mpfn[i]);
if (!page) continue;
put_page(page);
mpfn[i] = 0;
} return -ENOMEM;
}
/** * drm_pagemap_evict_to_ram() - Evict GPU SVM range to RAM * @devmem_allocation: Pointer to the device memory allocation * * Similar to __drm_pagemap_migrate_to_ram but does not require mmap lock and * migration done via migrate_device_* functions. * * Return: 0 on success, negative error code on failure.
*/ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation)
{ conststruct drm_pagemap_devmem_ops *ops = devmem_allocation->ops; unsignedlong npages, mpages = 0; struct page **pages; unsignedlong *src, *dst;
dma_addr_t *dma_addr; void *buf; int i, err = 0; unsignedint retry_count = 2;
npages = devmem_allocation->size >> PAGE_SHIFT;
retry: if (!mmget_not_zero(devmem_allocation->mm)) return -EFAULT;
/** * __drm_pagemap_migrate_to_ram() - Migrate GPU SVM range to RAM (internal) * @vas: Pointer to the VM area structure * @device_private_page_owner: Device private pages owner * @page: Pointer to the page for fault handling (can be NULL) * @fault_addr: Fault address * @size: Size of migration * * This internal function performs the migration of the specified GPU SVM range * to RAM. It sets up the migration, populates + dma maps RAM PFNs, and * invokes the driver-specific operations for migration to RAM. * * Return: 0 on success, negative error code on failure.
*/ staticint __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, void *device_private_page_owner, struct page *page, unsignedlong fault_addr, unsignedlong size)
{ struct migrate_vma migrate = {
.vma = vas,
.pgmap_owner = device_private_page_owner,
.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE |
MIGRATE_VMA_SELECT_DEVICE_COHERENT,
.fault_page = page,
}; struct drm_pagemap_zdd *zdd; conststruct drm_pagemap_devmem_ops *ops; struct device *dev = NULL; unsignedlong npages, mpages = 0; struct page **pages;
dma_addr_t *dma_addr; unsignedlong start, end; void *buf; int i, err = 0;
if (page) {
zdd = page->zone_device_data; if (time_before64(get_jiffies_64(),
zdd->devmem_allocation->timeslice_expiration)) return 0;
}
start = ALIGN_DOWN(fault_addr, size);
end = ALIGN(fault_addr + 1, size);
/* Corner where VMA area struct has been partially unmapped */ if (start < vas->vm_start)
start = vas->vm_start; if (end > vas->vm_end)
end = vas->vm_end;
for (i = 0; i < npages; ++i)
pages[i] = migrate_pfn_to_page(migrate.src[i]);
err = ops->copy_to_ram(pages, dma_addr, npages); if (err) goto err_finalize;
err_finalize: if (err)
drm_pagemap_migration_unlock_put_pages(npages, migrate.dst);
migrate_vma_pages(&migrate);
migrate_vma_finalize(&migrate); if (dev)
drm_pagemap_migrate_unmap_pages(dev, dma_addr, npages,
DMA_FROM_DEVICE);
err_free:
kvfree(buf);
err_out:
return err;
}
/** * drm_pagemap_page_free() - Put GPU SVM zone device data associated with a page * @page: Pointer to the page * * This function is a callback used to put the GPU SVM zone device data * associated with a page when it is being released.
*/ staticvoid drm_pagemap_page_free(struct page *page)
{
drm_pagemap_zdd_put(page->zone_device_data);
}
/** * drm_pagemap_migrate_to_ram() - Migrate a virtual range to RAM (page fault handler) * @vmf: Pointer to the fault information structure * * This function is a page fault handler used to migrate a virtual range * to ram. The device memory allocation in which the device page is found is * migrated in its entirety. * * Returns: * VM_FAULT_SIGBUS on failure, 0 on success.
*/ static vm_fault_t drm_pagemap_migrate_to_ram(struct vm_fault *vmf)
{ struct drm_pagemap_zdd *zdd = vmf->page->zone_device_data; int err;
/** * drm_pagemap_devmem_init() - Initialize a drm_pagemap device memory allocation * * @devmem_allocation: The struct drm_pagemap_devmem to initialize. * @dev: Pointer to the device structure which device memory allocation belongs to * @mm: Pointer to the mm_struct for the address space * @ops: Pointer to the operations structure for GPU SVM device memory * @dpagemap: The struct drm_pagemap we're allocating from. * @size: Size of device memory allocation
*/ void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, struct device *dev, struct mm_struct *mm, conststruct drm_pagemap_devmem_ops *ops, struct drm_pagemap *dpagemap, size_t size)
{
init_completion(&devmem_allocation->detached);
devmem_allocation->dev = dev;
devmem_allocation->mm = mm;
devmem_allocation->ops = ops;
devmem_allocation->dpagemap = dpagemap;
devmem_allocation->size = size;
}
EXPORT_SYMBOL_GPL(drm_pagemap_devmem_init);
/** * drm_pagemap_page_to_dpagemap() - Return a pointer the drm_pagemap of a page * @page: The struct page. * * Return: A pointer to the struct drm_pagemap of a device private page that * was populated from the struct drm_pagemap. If the page was *not* populated * from a struct drm_pagemap, the result is undefined and the function call * may result in dereferencing and invalid address.
*/ struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page)
{ struct drm_pagemap_zdd *zdd = page->zone_device_data;
/** * drm_pagemap_populate_mm() - Populate a virtual range with device memory pages * @dpagemap: Pointer to the drm_pagemap managing the device memory * @start: Start of the virtual range to populate. * @end: End of the virtual range to populate. * @mm: Pointer to the virtual address space. * @timeslice_ms: The time requested for the migrated pagemap pages to * be present in @mm before being allowed to be migrated back. * * Attempt to populate a virtual range with device memory pages, * clearing them or migrating data from the existing pages if necessary. * The function is best effort only, and implementations may vary * in how hard they try to satisfy the request. * * Return: %0 on success, negative error code on error. If the hardware * device was removed / unbound the function will return %-ENODEV.
*/ int drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, unsignedlong start, unsignedlong end, struct mm_struct *mm, unsignedlong timeslice_ms)
{ int err;
if (!mmget_not_zero(mm)) return -EFAULT;
mmap_read_lock(mm);
err = dpagemap->ops->populate_mm(dpagemap, start, end, mm,
timeslice_ms);
mmap_read_unlock(mm);
mmput(mm);
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.