diff options
Diffstat (limited to 'include/linux')
41 files changed, 1311 insertions, 643 deletions
diff --git a/include/linux/damon.h b/include/linux/damon.h index be3d198043ff..d9a3babbafc1 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -55,6 +55,8 @@ struct damon_size_range { * @list: List head for siblings. * @age: Age of this region. * + * For any use case, @ar should be non-zero positive size. + * * @nr_accesses is reset to zero for every &damon_attrs->aggr_interval and be * increased for every &damon_attrs->sample_interval if an access to the region * during the last sampling interval is found. The update of this field should @@ -214,11 +216,22 @@ struct damos_quota_goal { }; /** + * enum damos_quota_goal_tuner - Goal-based quota tuning logic. + * @DAMOS_QUOTA_GOAL_TUNER_CONSIST: Aim long term consistent quota. + * @DAMOS_QUOTA_GOAL_TUNER_TEMPORAL: Aim zero quota asap. + */ +enum damos_quota_goal_tuner { + DAMOS_QUOTA_GOAL_TUNER_CONSIST, + DAMOS_QUOTA_GOAL_TUNER_TEMPORAL, +}; + +/** * struct damos_quota - Controls the aggressiveness of the given scheme. * @reset_interval: Charge reset interval in milliseconds. * @ms: Maximum milliseconds that the scheme can use. * @sz: Maximum bytes of memory that the action can be applied. * @goals: Head of quota tuning goals (&damos_quota_goal) list. + * @goal_tuner: Goal-based @esz tuning algorithm to use. * @esz: Effective size quota in bytes. * * @weight_sz: Weight of the region's size for prioritization. @@ -260,6 +273,7 @@ struct damos_quota { unsigned long ms; unsigned long sz; struct list_head goals; + enum damos_quota_goal_tuner goal_tuner; unsigned long esz; unsigned int weight_sz; @@ -647,8 +661,7 @@ struct damon_operations { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); int (*get_scheme_score)(struct damon_ctx *context, - struct damon_target *t, struct damon_region *r, - struct damos *scheme); + struct damon_region *r, struct damos *scheme); unsigned long (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme, unsigned long *sz_filter_passed); @@ -981,6 +994,7 @@ int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control); int damon_set_region_biggest_system_ram_default(struct damon_target *t, unsigned long *start, unsigned long *end, + unsigned long addr_unit, unsigned long min_region_sz); #endif /* CONFIG_DAMON */ diff --git a/include/linux/dax.h b/include/linux/dax.h index bf103f317cac..10a7cc79aea5 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -69,7 +69,7 @@ static inline bool daxdev_mapping_supported(const struct vm_area_desc *desc, const struct inode *inode, struct dax_device *dax_dev) { - if (!vma_desc_test_flags(desc, VMA_SYNC_BIT)) + if (!vma_desc_test(desc, VMA_SYNC_BIT)) return true; if (!IS_DAX(inode)) return false; @@ -115,7 +115,7 @@ static inline bool daxdev_mapping_supported(const struct vm_area_desc *desc, const struct inode *inode, struct dax_device *dax_dev) { - return !vma_desc_test_flags(desc, VMA_SYNC_BIT); + return !vma_desc_test(desc, VMA_SYNC_BIT); } static inline size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) diff --git a/include/linux/pagevec.h b/include/linux/folio_batch.h index 63be5a451627..b45946adc50b 100644 --- a/include/linux/pagevec.h +++ b/include/linux/folio_batch.h @@ -1,18 +1,18 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * include/linux/pagevec.h + * include/linux/folio_batch.h * * In many places it is efficient to batch an operation up against multiple * folios. A folio_batch is a container which is used for that. */ -#ifndef _LINUX_PAGEVEC_H -#define _LINUX_PAGEVEC_H +#ifndef _LINUX_FOLIO_BATCH_H +#define _LINUX_FOLIO_BATCH_H #include <linux/types.h> /* 31 pointers + header align the folio_batch structure to a power of two */ -#define PAGEVEC_SIZE 31 +#define FOLIO_BATCH_SIZE 31 struct folio; @@ -29,7 +29,7 @@ struct folio_batch { unsigned char nr; unsigned char i; bool percpu_pvec_drained; - struct folio *folios[PAGEVEC_SIZE]; + struct folio *folios[FOLIO_BATCH_SIZE]; }; /** @@ -58,7 +58,7 @@ static inline unsigned int folio_batch_count(const struct folio_batch *fbatch) static inline unsigned int folio_batch_space(const struct folio_batch *fbatch) { - return PAGEVEC_SIZE - fbatch->nr; + return FOLIO_BATCH_SIZE - fbatch->nr; } /** @@ -93,7 +93,7 @@ static inline struct folio *folio_batch_next(struct folio_batch *fbatch) return fbatch->folios[fbatch->i++]; } -void __folio_batch_release(struct folio_batch *pvec); +void __folio_batch_release(struct folio_batch *fbatch); static inline void folio_batch_release(struct folio_batch *fbatch) { @@ -102,4 +102,4 @@ static inline void folio_batch_release(struct folio_batch *fbatch) } void folio_batch_remove_exceptionals(struct folio_batch *fbatch); -#endif /* _LINUX_PAGEVEC_H */ +#endif /* _LINUX_FOLIO_BATCH_H */ diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h index adab609c972e..f6d5f1f127c9 100644 --- a/include/linux/folio_queue.h +++ b/include/linux/folio_queue.h @@ -14,7 +14,7 @@ #ifndef _LINUX_FOLIO_QUEUE_H #define _LINUX_FOLIO_QUEUE_H -#include <linux/pagevec.h> +#include <linux/folio_batch.h> #include <linux/mm.h> /* @@ -29,12 +29,12 @@ */ struct folio_queue { struct folio_batch vec; /* Folios in the queue segment */ - u8 orders[PAGEVEC_SIZE]; /* Order of each folio */ + u8 orders[FOLIO_BATCH_SIZE]; /* Order of each folio */ struct folio_queue *next; /* Next queue segment or NULL */ struct folio_queue *prev; /* Previous queue segment of NULL */ unsigned long marks; /* 1-bit mark per folio */ unsigned long marks2; /* Second 1-bit mark per folio */ -#if PAGEVEC_SIZE > BITS_PER_LONG +#if FOLIO_BATCH_SIZE > BITS_PER_LONG #error marks is not big enough #endif unsigned int rreq_id; @@ -70,7 +70,7 @@ static inline void folioq_init(struct folio_queue *folioq, unsigned int rreq_id) */ static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq) { - return PAGEVEC_SIZE; + return FOLIO_BATCH_SIZE; } /** diff --git a/include/linux/fs.h b/include/linux/fs.h index b5b01bb22d12..e1d257e6da68 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2058,16 +2058,24 @@ static inline bool can_mmap_file(struct file *file) return true; } -int __compat_vma_mmap(const struct file_operations *f_op, - struct file *file, struct vm_area_struct *vma); +void compat_set_desc_from_vma(struct vm_area_desc *desc, const struct file *file, + const struct vm_area_struct *vma); +int __compat_vma_mmap(struct vm_area_desc *desc, struct vm_area_struct *vma); int compat_vma_mmap(struct file *file, struct vm_area_struct *vma); +int __vma_check_mmap_hook(struct vm_area_struct *vma); static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) { + int err; + if (file->f_op->mmap_prepare) return compat_vma_mmap(file, vma); - return file->f_op->mmap(file, vma); + err = file->f_op->mmap(file, vma); + if (err) + return err; + + return __vma_check_mmap_hook(vma); } static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a4d9f964dfde..2949e5acff35 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -27,8 +27,8 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf); bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); -int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr); +bool zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr); int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, @@ -83,7 +83,7 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to * it. Same to PFNMAPs where there's neither page* nor pagecache. */ -#define THP_ORDERS_ALL_SPECIAL \ +#define THP_ORDERS_ALL_SPECIAL_DAX \ (BIT(PMD_ORDER) | BIT(PUD_ORDER)) #define THP_ORDERS_ALL_FILE_DEFAULT \ ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) @@ -92,7 +92,7 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; * Mask of all large folio orders supported for THP. */ #define THP_ORDERS_ALL \ - (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL | THP_ORDERS_ALL_FILE_DEFAULT) + (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL_DAX | THP_ORDERS_ALL_FILE_DEFAULT) enum tva_type { TVA_SMAPS, /* Exposing "THPeligible:" in smaps. */ @@ -771,6 +771,11 @@ static inline bool pmd_is_huge(pmd_t pmd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline bool is_pmd_order(unsigned int order) +{ + return order == HPAGE_PMD_ORDER; +} + static inline int split_folio_to_list_to_order(struct folio *folio, struct list_head *list, int new_order) { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index fc5462fe943f..93418625d3c5 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -778,10 +778,6 @@ static inline unsigned long huge_page_size(const struct hstate *h) return (unsigned long)PAGE_SIZE << h->order; } -extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma); - -extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma); - static inline unsigned long huge_page_mask(struct hstate *h) { return h->mask; @@ -797,6 +793,23 @@ static inline unsigned huge_page_shift(struct hstate *h) return h->order + PAGE_SHIFT; } +/** + * hugetlb_linear_page_index() - linear_page_index() but in hugetlb + * page size granularity. + * @vma: the hugetlb VMA + * @address: the virtual address within the VMA + * + * Return: the page offset within the mapping in huge page units. + */ +static inline pgoff_t hugetlb_linear_page_index(struct vm_area_struct *vma, + unsigned long address) +{ + struct hstate *h = hstate_vma(vma); + + return ((address - vma->vm_start) >> huge_page_shift(h)) + + (vma->vm_pgoff >> huge_page_order(h)); +} + static inline bool order_is_gigantic(unsigned int order) { return order > MAX_PAGE_ORDER; @@ -1178,16 +1191,6 @@ static inline unsigned long huge_page_mask(struct hstate *h) return PAGE_MASK; } -static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) -{ - return PAGE_SIZE; -} - -static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) -{ - return PAGE_SIZE; -} - static inline unsigned int huge_page_order(struct hstate *h) { return 0; diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h index 593f5d4e108b..565b473fd135 100644 --- a/include/linux/hugetlb_inline.h +++ b/include/linux/hugetlb_inline.h @@ -13,7 +13,7 @@ static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags) static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags) { - return vma_flags_test(flags, VMA_HUGETLB_BIT); + return vma_flags_test_any(flags, VMA_HUGETLB_BIT); } #else @@ -30,7 +30,7 @@ static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags) #endif -static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma) +static inline bool is_vm_hugetlb_page(const struct vm_area_struct *vma) { return is_vm_hugetlb_flags(vma->vm_flags); } diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index dfc516c1c719..a26fb8e7cedf 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1015,8 +1015,8 @@ struct vmbus_channel { /* The max size of a packet on this channel */ u32 max_pkt_size; - /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ - int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma); + /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ + int (*mmap_prepare_ring_buffer)(struct vmbus_channel *channel, struct vm_area_desc *desc); /* boolean to control visibility of sysfs for ring buffer */ bool ring_sysfs_visible; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 531f9ebdeeae..2c5685adf3a9 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -9,7 +9,7 @@ #include <linux/types.h> #include <linux/mm_types.h> #include <linux/blkdev.h> -#include <linux/pagevec.h> +#include <linux/folio_batch.h> struct address_space; struct fiemap_extent_info; diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 338a1921a50a..bf233bde68c7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -352,8 +352,8 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip); * kasan_mempool_unpoison_object(). * * This function operates on all slab allocations including large kmalloc - * allocations (the ones returned by kmalloc_large() or by kmalloc() with the - * size > KMALLOC_MAX_SIZE). + * allocations (i.e. the ones backed directly by the buddy allocator rather + * than kmalloc slab caches). * * Return: true if the allocation can be safely reused; false otherwise. */ @@ -381,8 +381,8 @@ void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip); * original tags based on the pointer value. * * This function operates on all slab allocations including large kmalloc - * allocations (the ones returned by kmalloc_large() or by kmalloc() with the - * size > KMALLOC_MAX_SIZE). + * allocations (i.e. the ones backed directly by the buddy allocator rather + * than kmalloc slab caches). */ static __always_inline void kasan_mempool_unpoison_object(void *ptr, size_t size) diff --git a/include/linux/kho/abi/kexec_handover.h b/include/linux/kho/abi/kexec_handover.h index 2201a0d2c159..6b7d8ef550f9 100644 --- a/include/linux/kho/abi/kexec_handover.h +++ b/include/linux/kho/abi/kexec_handover.h @@ -10,8 +10,13 @@ #ifndef _LINUX_KHO_ABI_KEXEC_HANDOVER_H #define _LINUX_KHO_ABI_KEXEC_HANDOVER_H +#include <linux/bits.h> +#include <linux/log2.h> +#include <linux/math.h> #include <linux/types.h> +#include <asm/page.h> + /** * DOC: Kexec Handover ABI * @@ -29,32 +34,32 @@ * compatibility is only guaranteed for kernels supporting the same ABI version. * * FDT Structure Overview: - * The FDT serves as a central registry for physical - * addresses of preserved data structures and sub-FDTs. The first kernel - * populates this FDT with references to memory regions and other FDTs that - * need to persist across the kexec transition. The subsequent kernel then - * parses this FDT to locate and restore the preserved data.:: + * The FDT serves as a central registry for physical addresses of preserved + * data structures. The first kernel populates this FDT with references to + * memory regions and other metadata that need to persist across the kexec + * transition. The subsequent kernel then parses this FDT to locate and + * restore the preserved data.:: * * / { - * compatible = "kho-v1"; + * compatible = "kho-v2"; * * preserved-memory-map = <0x...>; * * <subnode-name-1> { - * fdt = <0x...>; + * preserved-data = <0x...>; * }; * * <subnode-name-2> { - * fdt = <0x...>; + * preserved-data = <0x...>; * }; * ... ... * <subnode-name-N> { - * fdt = <0x...>; + * preserved-data = <0x...>; * }; * }; * * Root KHO Node (/): - * - compatible: "kho-v1" + * - compatible: "kho-v2" * * Indentifies the overall KHO ABI version. * @@ -69,20 +74,20 @@ * is provided by the subsystem that uses KHO for preserving its * data. * - * - fdt: u64 + * - preserved-data: u64 * - * Physical address pointing to a subnode FDT blob that is also + * Physical address pointing to a subnode data blob that is also * being preserved. */ /* The compatible string for the KHO FDT root node. */ -#define KHO_FDT_COMPATIBLE "kho-v1" +#define KHO_FDT_COMPATIBLE "kho-v2" /* The FDT property for the preserved memory map. */ #define KHO_FDT_MEMORY_MAP_PROP_NAME "preserved-memory-map" -/* The FDT property for sub-FDTs. */ -#define KHO_FDT_SUB_TREE_PROP_NAME "fdt" +/* The FDT property for preserved data blobs. */ +#define KHO_FDT_SUB_TREE_PROP_NAME "preserved-data" /** * DOC: Kexec Handover ABI for vmalloc Preservation @@ -160,4 +165,113 @@ struct kho_vmalloc { unsigned short order; }; +/** + * DOC: KHO persistent memory tracker + * + * KHO tracks preserved memory using a radix tree data structure. Each node of + * the tree is exactly a single page. The leaf nodes are bitmaps where each set + * bit is a preserved page of any order. The intermediate nodes are tables of + * physical addresses that point to a lower level node. + * + * The tree hierarchy is shown below:: + * + * root + * +-------------------+ + * | Level 5 | (struct kho_radix_node) + * +-------------------+ + * | + * v + * +-------------------+ + * | Level 4 | (struct kho_radix_node) + * +-------------------+ + * | + * | ... (intermediate levels) + * | + * v + * +-------------------+ + * | Level 0 | (struct kho_radix_leaf) + * +-------------------+ + * + * The tree is traversed using a key that encodes the page's physical address + * (pa) and its order into a single unsigned long value. The encoded key value + * is composed of two parts: the 'order bit' in the upper part and the + * 'shifted physical address' in the lower part.:: + * + * +------------+-----------------------------+--------------------------+ + * | Page Order | Order Bit | Shifted Physical Address | + * +------------+-----------------------------+--------------------------+ + * | 0 | ...000100 ... (at bit 52) | pa >> (PAGE_SHIFT + 0) | + * | 1 | ...000010 ... (at bit 51) | pa >> (PAGE_SHIFT + 1) | + * | 2 | ...000001 ... (at bit 50) | pa >> (PAGE_SHIFT + 2) | + * | ... | ... | ... | + * +------------+-----------------------------+--------------------------+ + * + * Shifted Physical Address: + * The 'shifted physical address' is the physical address normalized for its + * order. It effectively represents the PFN shifted right by the order. + * + * Order Bit: + * The 'order bit' encodes the page order by setting a single bit at a + * specific position. The position of this bit itself represents the order. + * + * For instance, on a 64-bit system with 4KB pages (PAGE_SHIFT = 12), the + * maximum range for the shifted physical address (for order 0) is 52 bits + * (64 - 12). This address occupies bits [0-51]. For order 0, the order bit is + * set at position 52. + * + * The following diagram illustrates how the encoded key value is split into + * indices for the tree levels, with PAGE_SIZE of 4KB:: + * + * 63:60 59:51 50:42 41:33 32:24 23:15 14:0 + * +---------+--------+--------+--------+--------+--------+-----------------+ + * | 0 | Lv 5 | Lv 4 | Lv 3 | Lv 2 | Lv 1 | Lv 0 (bitmap) | + * +---------+--------+--------+--------+--------+--------+-----------------+ + * + * The radix tree stores pages of all orders in a single 6-level hierarchy. It + * efficiently shares higher tree levels, especially due to common zero top + * address bits, allowing a single, efficient algorithm to manage all + * pages. This bitmap approach also offers memory efficiency; for example, a + * 512KB bitmap can cover a 16GB memory range for 0-order pages with PAGE_SIZE = + * 4KB. + * + * The data structures defined here are part of the KHO ABI. Any modification + * to these structures that breaks backward compatibility must be accompanied by + * an update to the "compatible" string. This ensures that a newer kernel can + * correctly interpret the data passed by an older kernel. + */ + +/* + * Defines constants for the KHO radix tree structure, used to track preserved + * memory. These constants govern the indexing, sizing, and depth of the tree. + */ +enum kho_radix_consts { + /* + * The bit position of the order bit (and also the length of the + * shifted physical address) for an order-0 page. + */ + KHO_ORDER_0_LOG2 = 64 - PAGE_SHIFT, + + /* Size of the table in kho_radix_node, in log2 */ + KHO_TABLE_SIZE_LOG2 = const_ilog2(PAGE_SIZE / sizeof(phys_addr_t)), + + /* Number of bits in the kho_radix_leaf bitmap, in log2 */ + KHO_BITMAP_SIZE_LOG2 = PAGE_SHIFT + const_ilog2(BITS_PER_BYTE), + + /* + * The total tree depth is the number of intermediate levels + * and 1 bitmap level. + */ + KHO_TREE_MAX_DEPTH = + DIV_ROUND_UP(KHO_ORDER_0_LOG2 - KHO_BITMAP_SIZE_LOG2, + KHO_TABLE_SIZE_LOG2) + 1, +}; + +struct kho_radix_node { + u64 table[1 << KHO_TABLE_SIZE_LOG2]; +}; + +struct kho_radix_leaf { + DECLARE_BITMAP(bitmap, 1 << KHO_BITMAP_SIZE_LOG2); +}; + #endif /* _LINUX_KHO_ABI_KEXEC_HANDOVER_H */ diff --git a/include/linux/kho/abi/memfd.h b/include/linux/kho/abi/memfd.h index 68cb6303b846..08b10fea2afc 100644 --- a/include/linux/kho/abi/memfd.h +++ b/include/linux/kho/abi/memfd.h @@ -56,10 +56,24 @@ struct memfd_luo_folio_ser { u64 index; } __packed; +/* + * The set of seals this version supports preserving. If support for any new + * seals is needed, add it here and bump version. + */ +#define MEMFD_LUO_ALL_SEALS (F_SEAL_SEAL | \ + F_SEAL_SHRINK | \ + F_SEAL_GROW | \ + F_SEAL_WRITE | \ + F_SEAL_FUTURE_WRITE | \ + F_SEAL_EXEC) + /** * struct memfd_luo_ser - Main serialization structure for a memfd. * @pos: The file's current position (f_pos). * @size: The total size of the file in bytes (i_size). + * @seals: The seals present on the memfd. The seals are uABI so it is safe + * to directly use them in the ABI. + * @flags: Flags for the file. Unused flag bits must be set to 0. * @nr_folios: Number of folios in the folios array. * @folios: KHO vmalloc descriptor pointing to the array of * struct memfd_luo_folio_ser. @@ -67,11 +81,13 @@ struct memfd_luo_folio_ser { struct memfd_luo_ser { u64 pos; u64 size; + u32 seals; + u32 flags; u64 nr_folios; struct kho_vmalloc folios; } __packed; /* The compatibility string for memfd file handler */ -#define MEMFD_LUO_FH_COMPATIBLE "memfd-v1" +#define MEMFD_LUO_FH_COMPATIBLE "memfd-v2" #endif /* _LINUX_KHO_ABI_MEMFD_H */ diff --git a/include/linux/kho_radix_tree.h b/include/linux/kho_radix_tree.h new file mode 100644 index 000000000000..84e918b96e53 --- /dev/null +++ b/include/linux/kho_radix_tree.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_KHO_RADIX_TREE_H +#define _LINUX_KHO_RADIX_TREE_H + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/mutex_types.h> +#include <linux/types.h> + +/** + * DOC: Kexec Handover Radix Tree + * + * This is a radix tree implementation for tracking physical memory pages + * across kexec transitions. It was developed for the KHO mechanism but is + * designed for broader use by any subsystem that needs to preserve pages. + * + * The radix tree is a multi-level tree where leaf nodes are bitmaps + * representing individual pages. To allow pages of different sizes (orders) + * to be stored efficiently in a single tree, it uses a unique key encoding + * scheme. Each key is an unsigned long that combines a page's physical + * address and its order. + * + * Client code is responsible for allocating the root node of the tree, + * initializing the mutex lock, and managing its lifecycle. It must use the + * tree data structures defined in the KHO ABI, + * `include/linux/kho/abi/kexec_handover.h`. + */ + +struct kho_radix_node; + +struct kho_radix_tree { + struct kho_radix_node *root; + struct mutex lock; /* protects the tree's structure and root pointer */ +}; + +typedef int (*kho_radix_tree_walk_callback_t)(phys_addr_t phys, + unsigned int order); + +#ifdef CONFIG_KEXEC_HANDOVER + +int kho_radix_add_page(struct kho_radix_tree *tree, unsigned long pfn, + unsigned int order); + +void kho_radix_del_page(struct kho_radix_tree *tree, unsigned long pfn, + unsigned int order); + +int kho_radix_walk_tree(struct kho_radix_tree *tree, + kho_radix_tree_walk_callback_t cb); + +#else /* #ifdef CONFIG_KEXEC_HANDOVER */ + +static inline int kho_radix_add_page(struct kho_radix_tree *tree, long pfn, + unsigned int order) +{ + return -EOPNOTSUPP; +} + +static inline void kho_radix_del_pa |