diff options
Diffstat (limited to 'kernel/memremap.c')
| -rw-r--r-- | kernel/memremap.c | 103 |
1 files changed, 67 insertions, 36 deletions
diff --git a/kernel/memremap.c b/kernel/memremap.c index 9eced2cc9f94..a856cb5ff192 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -11,6 +11,7 @@ #include <linux/types.h> #include <linux/wait_bit.h> #include <linux/xarray.h> +#include <linux/hmm.h> static DEFINE_XARRAY(pgmap_array); #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) @@ -24,6 +25,9 @@ vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, pmd_t *pmdp) { struct page *page = device_private_entry_to_page(entry); + struct hmm_devmem *devmem; + + devmem = container_of(page->pgmap, typeof(*devmem), pagemap); /* * The page_fault() callback must migrate page back to system memory @@ -39,7 +43,7 @@ vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, * There is a more in-depth description of what that callback can and * cannot do, in include/linux/memremap.h */ - return page->pgmap->page_fault(vma, addr, page, flags, pmdp); + return devmem->page_fault(vma, addr, page, flags, pmdp); } EXPORT_SYMBOL(device_private_entry_fault); #endif /* CONFIG_DEVICE_PRIVATE */ @@ -87,24 +91,29 @@ static void devm_memremap_pages_release(void *data) struct resource *res = &pgmap->res; resource_size_t align_start, align_size; unsigned long pfn; + int nid; + 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) - align_start; + nid = page_to_nid(pfn_to_page(align_start >> PAGE_SHIFT)); + mem_hotplug_begin(); - arch_remove_memory(align_start, align_size, pgmap->altmap_valid ? - &pgmap->altmap : NULL); - kasan_remove_zero_shadow(__va(align_start), align_size); + if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + pfn = align_start >> PAGE_SHIFT; + __remove_pages(page_zone(pfn_to_page(pfn)), pfn, + align_size >> PAGE_SHIFT, NULL); + } else { + arch_remove_memory(nid, align_start, align_size, + pgmap->altmap_valid ? &pgmap->altmap : NULL); + kasan_remove_zero_shadow(__va(align_start), align_size); + } mem_hotplug_done(); untrack_pfn(NULL, PHYS_PFN(align_start), align_size); @@ -116,7 +125,7 @@ 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 +134,8 @@ 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 +151,9 @@ 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; @@ -167,18 +176,13 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) is_ram = region_intersects(align_start, align_size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); - if (is_ram == REGION_MIXED) { - WARN_ONCE(1, "%s attempted on mixed region %pr\n", - __func__, res); - return ERR_PTR(-ENXIO); + if (is_ram != REGION_DISJOINT) { + WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__, + is_ram == REGION_MIXED ? "mixed" : "ram", res); + error = -ENXIO; + goto err_array; } - if (is_ram == REGION_INTERSECTS) - return __va(res->start); - - if (!pgmap->ref) - return ERR_PTR(-EINVAL); - pgmap->dev = dev; error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start), @@ -196,17 +200,40 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) goto err_pfn_remap; mem_hotplug_begin(); - error = kasan_add_zero_shadow(__va(align_start), align_size); - if (error) { - mem_hotplug_done(); - goto err_kasan; + + /* + * For device private memory we call add_pages() as we only need to + * allocate and initialize struct page for the device memory. More- + * over the device memory is un-accessible thus we do not want to + * create a linear mapping for the memory like arch_add_memory() + * would do. + * + * For all other device memory types, which are accessible by + * the CPU, we do want the linear mapping and thus use + * arch_add_memory(). + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + error = add_pages(nid, align_start >> PAGE_SHIFT, + align_size >> PAGE_SHIFT, NULL, false); + } else { + error = kasan_add_zero_shadow(__va(align_start), align_size); + if (error) { + mem_hotplug_done(); + goto err_kasan; + } + + error = arch_add_memory(nid, align_start, align_size, altmap, + false); + } + + if (!error) { + struct zone *zone; + + zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE]; + move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT, + align_size >> PAGE_SHIFT, altmap); } - error = arch_add_memory(nid, align_start, align_size, altmap, false); - if (!error) - move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], - align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT, altmap); mem_hotplug_done(); if (error) goto err_add_memory; @@ -220,7 +247,10 @@ 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); @@ -231,9 +261,10 @@ 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(devm_memremap_pages); +EXPORT_SYMBOL_GPL(devm_memremap_pages); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { |