diff options
| -rw-r--r-- | include/linux/hmm.h | 24 | ||||
| -rw-r--r-- | include/linux/memremap.h | 32 | ||||
| -rw-r--r-- | kernel/memremap.c | 6 | ||||
| -rw-r--r-- | mm/hmm.c | 4 |
4 files changed, 31 insertions, 35 deletions
diff --git a/include/linux/hmm.h b/include/linux/hmm.h index ed89fbc525d2..66f9ebbb1df3 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -69,6 +69,7 @@ #define LINUX_HMM_H #include <linux/kconfig.h> +#include <asm/pgtable.h> #if IS_ENABLED(CONFIG_HMM) @@ -486,6 +487,7 @@ struct hmm_devmem_ops { * @device: device to bind resource to * @ops: memory operations callback * @ref: per CPU refcount + * @page_fault: callback when CPU fault on an unaddressable device page * * This an helper structure for device drivers that do not wish to implement * the gory details related to hotplugging new memoy and allocating struct @@ -493,7 +495,28 @@ struct hmm_devmem_ops { * * Device drivers can directly use ZONE_DEVICE memory on their own if they * wish to do so. + * + * The page_fault() callback must migrate page back, from device memory to + * system memory, so that the CPU can access it. This might fail for various + * reasons (device issues, device have been unplugged, ...). When such error + * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and + * set the CPU page table entry to "poisoned". + * + * Note that because memory cgroup charges are transferred to the device memory, + * this should never fail due to memory restrictions. However, allocation + * of a regular system page might still fail because we are out of memory. If + * that happens, the page_fault() callback must return VM_FAULT_OOM. + * + * The page_fault() callback can also try to migrate back multiple pages in one + * chunk, as an optimization. It must, however, prioritize the faulting address + * over all the others. */ +typedef int (*dev_page_fault_t)(struct vm_area_struct *vma, + unsigned long addr, + const struct page *page, + unsigned int flags, + pmd_t *pmdp); + struct hmm_devmem { struct completion completion; unsigned long pfn_first; @@ -503,6 +526,7 @@ struct hmm_devmem { struct dev_pagemap pagemap; const struct hmm_devmem_ops *ops; struct percpu_ref ref; + dev_page_fault_t page_fault; }; /* diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 55db66b3716f..f0628660d541 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -4,8 +4,6 @@ #include <linux/ioport.h> #include <linux/percpu-refcount.h> -#include <asm/pgtable.h> - struct resource; struct device; @@ -66,47 +64,18 @@ enum memory_type { }; /* - * For MEMORY_DEVICE_PRIVATE we use ZONE_DEVICE and extend it with two - * callbacks: - * page_fault() - * page_free() - * * 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_fault() callback must migrate page back, from device memory to - * system memory, so that the CPU can access it. This might fail for various - * reasons (device issues, device have been unplugged, ...). When such error - * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and - * set the CPU page table entry to "poisoned". - * - * Note that because memory cgroup charges are transferred to the device memory, - * this should never fail due to memory restrictions. However, allocation - * of a regular system page might still fail because we are out of memory. If - * that happens, the page_fault() callback must return VM_FAULT_OOM. - * - * The page_fault() callback can also try to migrate back multiple pages in one - * chunk, as an optimization. It must, however, prioritize the faulting address - * over all the others. - * - * * 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.) - * - * For MEMORY_DEVICE_PUBLIC only the page_free() callback matter. */ -typedef int (*dev_page_fault_t)(struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp); typedef void (*dev_page_free_t)(struct page *page, void *data); /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings - * @page_fault: callback when CPU fault on an unaddressable device page * @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 @@ -117,7 +86,6 @@ typedef void (*dev_page_free_t)(struct page *page, void *data); * @type: memory type: see MEMORY_* in memory_hotplug.h */ struct dev_pagemap { - dev_page_fault_t page_fault; dev_page_free_t page_free; struct vmem_altmap altmap; bool altmap_valid; diff --git a/kernel/memremap.c b/kernel/memremap.c index 0d5603d76c37..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 */ @@ -1087,10 +1087,10 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT; devmem->pfn_last = devmem->pfn_first + (resource_size(devmem->resource) >> PAGE_SHIFT); + devmem->page_fault = hmm_devmem_fault; devmem->pagemap.type = MEMORY_DEVICE_PRIVATE; devmem->pagemap.res = *devmem->resource; - devmem->pagemap.page_fault = hmm_devmem_fault; devmem->pagemap.page_free = hmm_devmem_free; devmem->pagemap.altmap_valid = false; devmem->pagemap.ref = &devmem->ref; @@ -1141,10 +1141,10 @@ struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT; devmem->pfn_last = devmem->pfn_first + (resource_size(devmem->resource) >> PAGE_SHIFT); + devmem->page_fault = hmm_devmem_fault; devmem->pagemap.type = MEMORY_DEVICE_PUBLIC; devmem->pagemap.res = *devmem->resource; - devmem->pagemap.page_fault = hmm_devmem_fault; devmem->pagemap.page_free = hmm_devmem_free; devmem->pagemap.altmap_valid = false; devmem->pagemap.ref = &devmem->ref; |