diff options
| -rw-r--r-- | MAINTAINERS | 7 | ||||
| -rw-r--r-- | include/linux/hmm.h | 139 | ||||
| -rw-r--r-- | include/linux/mm_types.h | 5 | ||||
| -rw-r--r-- | kernel/fork.c | 2 | ||||
| -rw-r--r-- | mm/Kconfig | 11 | ||||
| -rw-r--r-- | mm/Makefile | 1 | ||||
| -rw-r--r-- | mm/hmm.c | 86 |
7 files changed, 251 insertions, 0 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index f593300e310b..41cd63d56699 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5582,6 +5582,13 @@ S: Supported F: drivers/scsi/hisi_sas/ F: Documentation/devicetree/bindings/scsi/hisilicon-sas.txt +HMM - Heterogeneous Memory Management +M: Jérôme Glisse <jglisse@redhat.com> +L: linux-mm@kvack.org +S: Maintained +F: mm/hmm* +F: include/linux/hmm* + HOST AP DRIVER M: Jouni Malinen <j@w1.fi> L: hostap@shmoo.com (subscribers-only) diff --git a/include/linux/hmm.h b/include/linux/hmm.h new file mode 100644 index 000000000000..54dd529b693d --- /dev/null +++ b/include/linux/hmm.h @@ -0,0 +1,139 @@ +/* + * Copyright 2013 Red Hat Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: Jérôme Glisse <jglisse@redhat.com> + */ +/* + * HMM provides 3 separate functionality : + * - Mirroring: synchronize CPU page table and device page table + * - Device memory: allocating struct page for device memory + * - Migration: migrating regular memory to device memory + * + * Each can be use independently from the others. + * + * + * Mirroring: + * + * HMM provide helpers to mirror process address space on a device. For this it + * provides several helpers to order device page table update in respect to CPU + * page table update. Requirement is that for any given virtual address the CPU + * and device page table can not point to different physical page. It uses the + * mmu_notifier API and introduce virtual address range lock which block CPU + * page table update for a range while the device page table is being updated. + * Usage pattern is: + * + * hmm_vma_range_lock(vma, start, end); + * // snap shot CPU page table + * // update device page table from snapshot + * hmm_vma_range_unlock(vma, start, end); + * + * Any CPU page table update that conflict with a range lock will wait until + * range is unlock. This garanty proper serialization of CPU and device page + * table update. + * + * + * Device memory: + * + * HMM provides helpers to help leverage device memory either addressable like + * regular memory by the CPU or un-addressable at all. In both case the device + * memory is associated to dedicated structs page (which are allocated like for + * hotplug memory). Device memory management is under the responsability of the + * device driver. HMM only allocate and initialize the struct pages associated + * with the device memory. + * + * Allocating struct page for device memory allow to use device memory allmost + * like any regular memory. Unlike regular memory it can not be added to the + * lru, nor can any memory allocation can use device memory directly. Device + * memory will only end up to be use in a process if device driver migrate some + * of the process memory from regular memory to device memory. + * + * + * Migration: + * + * Existing memory migration mechanism (mm/migrate.c) does not allow to use + * something else than the CPU to copy from source to destination memory. More + * over existing code is not tailor to drive migration from process virtual + * address rather than from list of pages. Finaly the migration flow does not + * allow for graceful failure at different step of the migration process. + * + * HMM solves all of the above though simple API : + * + * hmm_vma_migrate(vma, start, end, ops); + * + * With ops struct providing 2 callback alloc_and_copy() which allocated the + * destination memory and initialize it using source memory. Migration can fail + * after this step and thus last callback finalize_and_map() allow the device + * driver to know which page were successfully migrated and which were not. + * + * This can easily be use outside of HMM intended use case. + * + * + * This header file contain all the API related to this 3 functionality and + * each functions and struct are more thouroughly documented in below comments. + */ +#ifndef LINUX_HMM_H +#define LINUX_HMM_H + +#include <linux/kconfig.h> + +#if IS_ENABLED(CONFIG_HMM) + + +/* + * hmm_pfn_t - HMM use its own pfn type to keep several flags per page + * + * Flags: + * HMM_PFN_VALID: pfn is valid + * HMM_PFN_WRITE: CPU page table have the write permission set + */ +typedef unsigned long hmm_pfn_t; + +#define HMM_PFN_VALID (1 << 0) +#define HMM_PFN_WRITE (1 << 1) +#define HMM_PFN_SHIFT 2 + +static inline struct page *hmm_pfn_to_page(hmm_pfn_t pfn) +{ + if (!(pfn & HMM_PFN_VALID)) + return NULL; + return pfn_to_page(pfn >> HMM_PFN_SHIFT); +} + +static inline unsigned long hmm_pfn_to_pfn(hmm_pfn_t pfn) +{ + if (!(pfn & HMM_PFN_VALID)) + return -1UL; + return (pfn >> HMM_PFN_SHIFT); +} + +static inline hmm_pfn_t hmm_pfn_from_page(struct page *page) +{ + return (page_to_pfn(page) << HMM_PFN_SHIFT) | HMM_PFN_VALID; +} + +static inline hmm_pfn_t hmm_pfn_from_pfn(unsigned long pfn) +{ + return (pfn << HMM_PFN_SHIFT) | HMM_PFN_VALID; +} + + +/* Below are for HMM internal use only ! Not to be use by device driver ! */ +void hmm_mm_destroy(struct mm_struct *mm); + +#else /* IS_ENABLED(CONFIG_HMM) */ + +/* Below are for HMM internal use only ! Not to be use by device driver ! */ +static inline void hmm_mm_destroy(struct mm_struct *mm) {} + +#endif /* IS_ENABLED(CONFIG_HMM) */ +#endif /* LINUX_HMM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4a8acedf4b7d..4effdbf364cf 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -23,6 +23,7 @@ struct address_space; struct mem_cgroup; +struct hmm; #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ @@ -516,6 +517,10 @@ struct mm_struct { atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; +#if IS_ENABLED(CONFIG_HMM) + /* HMM need to track few things per mm */ + struct hmm *hmm; +#endif }; static inline void mm_init_cpumask(struct mm_struct *mm) diff --git a/kernel/fork.c b/kernel/fork.c index 690a1aad95e4..af0eec8308fd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -27,6 +27,7 @@ #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> +#include <linux/hmm.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/vmacache.h> @@ -702,6 +703,7 @@ void __mmdrop(struct mm_struct *mm) BUG_ON(mm == &init_mm); mm_free_pgd(mm); destroy_context(mm); + hmm_mm_destroy(mm); mmu_notifier_mm_destroy(mm); check_mm(mm); free_mm(mm); diff --git a/mm/Kconfig b/mm/Kconfig index 0a2141124a50..be18cc2fbde8 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -289,6 +289,17 @@ config MIGRATION config ARCH_ENABLE_HUGEPAGE_MIGRATION bool +config HMM + bool "Heterogeneous memory management (HMM)" + depends on MMU + default n + help + Heterogeneous memory management, set of helpers for: + - mirroring of process address space on a device + - using device memory transparently inside a process + + If unsure, say N to disable HMM. + config PHYS_ADDR_T_64BIT def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT diff --git a/mm/Makefile b/mm/Makefile index 2ca1faf3fa09..6ac128424b34 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -76,6 +76,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_MEMTEST) += memtest.o obj-$(CONFIG_MIGRATION) += migrate.o +obj-$(CONFIG_HMM) += hmm.o obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o obj-$(CONFIG_PAGE_COUNTER) += page_counter.o diff --git a/mm/hmm.c b/mm/hmm.c new file mode 100644 index 000000000000..342b59630e47 --- /dev/null +++ b/mm/hmm.c @@ -0,0 +1,86 @@ +/* + * Copyright 2013 Red Hat Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: Jérôme Glisse <jglisse@redhat.com> + */ +/* + * Refer to include/linux/hmm.h for informations about heterogeneous memory + * management or HMM for short. + */ +#include <linux/mm.h> +#include <linux/hmm.h> +#include <linux/slab.h> +#include <linux/sched.h> + +/* + * struct hmm - HMM per mm struct + * + * @mm: mm struct this HMM struct is bound to + */ +struct hmm { + struct mm_struct *mm; +}; + +/* + * hmm_register - register HMM against an mm (HMM internal) + * + * @mm: mm struct to attach to + * + * This is not intended to be use directly by device driver but by other HMM + * component. It allocates an HMM struct if mm does not have one and initialize + * it. + */ +static struct hmm *hmm_register(struct mm_struct *mm) +{ + struct hmm *hmm = NULL; + + if (!mm->hmm) { + hmm = kmalloc(sizeof(*hmm), GFP_KERNEL); + if (!hmm) + return NULL; + hmm->mm = mm; + } + + spin_lock(&mm->page_table_lock); + if (!mm->hmm) + /* + * The hmm struct can only be free once mm_struct goes away + * hence we should always have pre-allocated an new hmm struct + * above. + */ + mm->hmm = hmm; + else if (hmm) + kfree(hmm); + hmm = mm->hmm; + spin_unlock(&mm->page_table_lock); + + return hmm; +} + +void hmm_mm_destroy(struct mm_struct *mm) +{ + struct hmm *hmm; + + /* + * We should not need to lock here as no one should be able to register + * a new HMM while an mm is being destroy. But just to be safe ... + */ + spin_lock(&mm->page_table_lock); + hmm = mm->hmm; + mm->hmm = NULL; + spin_unlock(&mm->page_table_lock); + if (!hmm) + return; + + kfree(hmm); +} |