diff options
Diffstat (limited to 'include')
52 files changed, 648 insertions, 235 deletions
diff --git a/include/dt-bindings/clock/sifive-fu740-prci.h b/include/dt-bindings/clock/sifive-fu740-prci.h index cd7706ea5677..7899b7fee7db 100644 --- a/include/dt-bindings/clock/sifive-fu740-prci.h +++ b/include/dt-bindings/clock/sifive-fu740-prci.h @@ -19,5 +19,6 @@ #define PRCI_CLK_CLTXPLL 5 #define PRCI_CLK_TLCLK 6 #define PRCI_CLK_PCLK 7 +#define PRCI_CLK_PCIE_AUX 8 #endif /* __DT_BINDINGS_CLOCK_SIFIVE_FU740_PRCI_H */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 70a932470b2d..73d039476fa4 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -4,10 +4,12 @@ #ifndef __ASSEMBLY__ -#include <linux/types.h> #include <linux/bitops.h> -#include <linux/string.h> #include <linux/kernel.h> +#include <linux/string.h> +#include <linux/types.h> + +struct device; /* * bitmaps provide bit arrays that consume one or more unsigned @@ -118,54 +120,59 @@ * Allocation and deallocation of bitmap. * Provided in lib/bitmap.c to avoid circular dependency. */ -extern unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); -extern unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); -extern void bitmap_free(const unsigned long *bitmap); +unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); +unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); +void bitmap_free(const unsigned long *bitmap); + +/* Managed variants of the above. */ +unsigned long *devm_bitmap_alloc(struct device *dev, + unsigned int nbits, gfp_t flags); +unsigned long *devm_bitmap_zalloc(struct device *dev, + unsigned int nbits, gfp_t flags); /* * lib/bitmap.c provides these functions: */ -extern int __bitmap_equal(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern bool __pure __bitmap_or_equal(const unsigned long *src1, - const unsigned long *src2, - const unsigned long *src3, - unsigned int nbits); -extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, - unsigned int nbits); -extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits); -extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits); -extern void bitmap_cut(unsigned long *dst, const unsigned long *src, - unsigned int first, unsigned int cut, - unsigned int nbits); -extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +int __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +bool __pure __bitmap_or_equal(const unsigned long *src1, + const unsigned long *src2, + const unsigned long *src3, + unsigned int nbits); +void __bitmap_complement(unsigned long *dst, const unsigned long *src, + unsigned int nbits); +void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits); +void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits); +void bitmap_cut(unsigned long *dst, const unsigned long *src, + unsigned int first, unsigned int cut, unsigned int nbits); +int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +void __bitmap_replace(unsigned long *dst, + const unsigned long *old, const unsigned long *new, + const unsigned long *mask, unsigned int nbits); +int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); -extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern void __bitmap_replace(unsigned long *dst, - const unsigned long *old, const unsigned long *new, - const unsigned long *mask, unsigned int nbits); -extern int __bitmap_intersects(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern int __bitmap_subset(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); -extern void __bitmap_set(unsigned long *map, unsigned int start, int len); -extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); - -extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, - unsigned long size, - unsigned long start, - unsigned int nr, - unsigned long align_mask, - unsigned long align_offset); +int __bitmap_subset(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); +void __bitmap_set(unsigned long *map, unsigned int start, int len); +void __bitmap_clear(unsigned long *map, unsigned int start, int len); + +unsigned long bitmap_find_next_zero_area_off(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned int nr, + unsigned long align_mask, + unsigned long align_offset); /** * bitmap_find_next_zero_area - find a contiguous aligned zero area @@ -190,33 +197,33 @@ bitmap_find_next_zero_area(unsigned long *map, align_mask, 0); } -extern int bitmap_parse(const char *buf, unsigned int buflen, +int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits); -extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, +int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); -extern int bitmap_parselist(const char *buf, unsigned long *maskp, +int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits); -extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, +int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); -extern void bitmap_remap(unsigned long *dst, const unsigned long *src, +void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits); -extern int bitmap_bitremap(int oldbit, +int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); -extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, +void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits); -extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, +void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits); -extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); -extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); -extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); +int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); +void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); +int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); #ifdef __BIG_ENDIAN -extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); +void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else #define bitmap_copy_le bitmap_copy #endif -extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); -extern int bitmap_print_to_pagebuf(bool list, char *buf, +unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); +int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) @@ -265,9 +272,9 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, * therefore conversion is not needed when copying data from/to arrays of u32. */ #if BITS_PER_LONG == 64 -extern void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, +void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits); -extern void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, +void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits); #else #define bitmap_from_arr32(bitmap, buf, nbits) \ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6b47f94378c5..e7e99da31349 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -194,6 +194,8 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); +void invalidate_bh_lrus_cpu(int cpu); +bool has_bh_in_lru(int cpu, void *dummy); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); @@ -406,6 +408,8 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +static inline void invalidate_bh_lrus_cpu(int cpu) {} +static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; } #define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ diff --git a/include/linux/cma.h b/include/linux/cma.h index 217999c8a762..53fd8c3cdbd0 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -44,9 +44,9 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, const char *name, struct cma **res_cma); -extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, +extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align, bool no_warn); -extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count); +extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); #endif diff --git a/include/linux/compaction.h b/include/linux/compaction.h index ed4070ed41ef..4221888bdcd6 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -81,7 +81,6 @@ static inline unsigned long compact_gap(unsigned int order) } #ifdef CONFIG_COMPACTION -extern int sysctl_compact_memory; extern unsigned int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index a370af3c08f0..4a62b3980642 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -169,6 +169,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_RAPL_ONLINE, CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, + CPUHP_AP_PERF_X86_IDXD_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_CFD_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 51872e736e7b..0d53a96a3d64 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -22,6 +22,11 @@ struct dma_map_ops { gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); + struct sg_table *(*alloc_noncontiguous)(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, + unsigned long attrs); + void (*free_noncontiguous)(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); @@ -198,6 +203,20 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_DMA_DECLARE_COHERENT */ +/* + * This is the actual return value from the ->alloc_noncontiguous method. + * The users of the DMA API should only care about the sg_table, but to make + * the DMA-API internal vmaping and freeing easier we stash away the page + * array as well (except for the fallback case). This can go away any time, + * e.g. when a vmap-variant that takes a scatterlist comes along. + */ +struct dma_sgt_handle { + struct sg_table sgt; + struct page **pages; +}; +#define sgt_handle(sgt) \ + container_of((sgt), struct dma_sgt_handle, sgt) + int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2a984cb4d1e0..183e7103a66d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -95,7 +95,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { debug_dma_mapping_error(dev, dma_addr); - if (dma_addr == DMA_MAPPING_ERROR) + if (unlikely(dma_addr == DMA_MAPPING_ERROR)) return -ENOMEM; return 0; } @@ -144,6 +144,15 @@ u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); +struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); +void dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir); +void *dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt); +void dma_vunmap_noncontiguous(struct device *dev, void *vaddr); +int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt); #else /* CONFIG_HAS_DMA */ static inline dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, size_t offset, size_t size, @@ -257,12 +266,37 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; } +static inline struct sg_table *dma_alloc_noncontiguous(struct device *dev, + size_t size, enum dma_data_direction dir, gfp_t gfp, + unsigned long attrs) +{ + return NULL; +} +static inline void dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir) +{ +} +static inline void *dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt) +{ + return NULL; +} +static inline void dma_vunmap_noncontiguous(struct device *dev, void *vaddr) +{ +} +static inline int dma_mmap_noncontiguous(struct device *dev, + struct vm_area_struct *vma, size_t size, struct sg_table *sgt) +{ + return -EINVAL; +} #endif /* CONFIG_HAS_DMA */ struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir); +int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma, + size_t size, struct page *page); static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) @@ -401,7 +435,6 @@ static inline void dma_sync_sgtable_for_device(struct device *dev, static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - return dma_alloc_attrs(dev, size, dma_handle, gfp, (gfp & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0); } diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index c6cc0a566ef5..5487a80617a3 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -168,7 +168,7 @@ struct f2fs_checkpoint { unsigned char alloc_type[MAX_ACTIVE_LOGS]; /* SIT and NAT version bitmap */ - unsigned char sit_nat_version_bitmap[1]; + unsigned char sit_nat_version_bitmap[]; } __packed; #define CP_CHKSUM_OFFSET 4092 /* default chksum offset in checkpoint */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 12766edee81f..acef282b97c6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -442,7 +442,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping, * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. - * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). @@ -463,7 +462,6 @@ struct address_space { struct rb_root_cached i_mmap; struct rw_semaphore i_mmap_rwsem; unsigned long nrpages; - unsigned long nrexceptional; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 26f4d907254a..8a5f6c3d7dba 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -657,7 +657,7 @@ extern int alloc_contig_range(unsigned long start, unsigned long end, extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #endif -void free_contig_range(unsigned long pfn, unsigned int nr_pages); +void free_contig_range(unsigned long pfn, unsigned long nr_pages); #ifdef CONFIG_CMA /* CMA stuff */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index ecf0032a0995..3a268781fcec 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -227,7 +227,7 @@ struct gpio_irq_chip { /** * @valid_mask: * - * If not %NULL holds bitmask of GPIOs which are valid to be included + * If not %NULL, holds bitmask of GPIOs which are valid to be included * in IRQ domain of the chip. */ unsigned long *valid_mask; @@ -346,7 +346,7 @@ struct gpio_irq_chip { * output. * * A gpio_chip can help platforms abstract various sources of GPIOs so - * they can all be accessed through a common programing interface. + * they can all be accessed through a common programming interface. * Example sources would be SOC controllers, FPGAs, multifunction * chips, dedicated GPIO expanders, and so on. * @@ -435,15 +435,15 @@ struct gpio_chip { /** * @valid_mask: * - * If not %NULL holds bitmask of GPIOs which are valid to be used + * If not %NULL, holds bitmask of GPIOs which are valid to be used * from the chip. */ unsigned long *valid_mask; #if defined(CONFIG_OF_GPIO) /* - * If CONFIG_OF is enabled, then all GPIO controllers described in the - * device tree automatically may have an OF translation + * If CONFIG_OF_GPIO is enabled, then all GPIO controllers described in + * the device tree automatically may have an OF translation */ /** @@ -508,7 +508,7 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, * for GPIOs will fail rudely. * * gpiochip_add_data() must only be called after gpiolib initialization, - * ie after core_initcall(). + * i.e. after core_initcall(). * * If gc->base is negative, this requests dynamic assignment of * a range of valid GPIOs. diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 44170f312ae7..832b49b50c7b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -332,4 +332,11 @@ static inline void memcpy_to_page(struct page *page, size_t offset, kunmap_local(to); } +static inline void memzero_page(struct page *page, size_t offset, size_t len) +{ + char *addr = kmap_atomic(page); + memset(addr + offset, 0, len); + kunmap_atomic(addr); +} + #endif /* _LINUX_HIGHMEM_H */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ba973efcd369..9626fda5efce 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -87,9 +87,6 @@ enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, -#ifdef CONFIG_DEBUG_VM - TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, -#endif }; struct kobject; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index cccd1aab69dd..b92f25ccef58 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -11,6 +11,7 @@ #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> +#include <linux/userfaultfd_k.h> struct ctl_table; struct user_struct; @@ -134,11 +135,14 @@ void hugetlb_show_meminfo(void); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); +#ifdef CONFIG_USERFAULTFD int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + enum mcopy_atomic_mode mode, struct page **pagep); +#endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); @@ -152,7 +156,8 @@ void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); -pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); +pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pud_t *pud); struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage); @@ -161,7 +166,7 @@ extern struct list_head huge_boot_pages; /* arch callbacks */ -pte_t *huge_pte_alloc(struct mm_struct *mm, +pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); @@ -187,6 +192,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); bool is_hugetlb_entry_migration(pte_t pte); +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -308,16 +314,19 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, BUG(); } +#ifdef CONFIG_USERFAULTFD static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + enum mcopy_atomic_mode mode, struct page **pagep) { BUG(); return 0; } +#endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) @@ -368,6 +377,8 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, return 0; } +static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } + #endif /* !CONFIG_HUGETLB_PAGE */ /* * hugepages at page global directory. If arch support @@ -555,6 +566,7 @@ HPAGEFLAG(Freed, freed) #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { + struct mutex resize_lock; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; @@ -583,6 +595,7 @@ struct huge_bootmem_page { struct hstate *hstate; }; +int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, @@ -865,6 +878,12 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline int isolate_or_dissolve_huge_page(struct page *page, + struct list_head *list) +{ + return -ENOMEM; +} + static inline struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) @@ -1039,4 +1058,14 @@ static inline __init void hugetlb_cma_check(void) } #endif +bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); + +#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +/* + * ARCHes with special requirements for evicting HUGETLB backing TLB entries can + * implement this. + */ +#define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#endif + #endif /* _LINUX_HUGETLB_H */ diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 7a1dd7b969b6..62a8e3d23829 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -256,11 +256,11 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data); -struct irq_domain *irq_domain_add_simple(struct device_node *of_node, - unsigned int size, - unsigned int first_irq, - const struct irq_domain_ops *ops, - void *host_data); +struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data); struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, unsigned int size, unsigned int first_irq, @@ -325,6 +325,15 @@ static inline struct irq_domain *irq_find_host(struct device_node *node) return d; } +static inline struct irq_domain *irq_domain_add_simple(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data) +{ + return irq_domain_create_simple(of_node_to_fwnode(of_node), size, first_irq, ops, host_data); +} + /** * irq_domain_add_linear() - Allocate and register a linear revmap irq_domain. * @of_node: pointer to interrupt controller's device tree node. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5904716f29ba..c193be760709 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -114,12 +114,13 @@ struct batched_lruvec_stat { }; /* - * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, - * which have elements charged to this memcg. + * Bitmap and deferred work of shrinker::id corresponding to memcg-aware + * shrinkers, which have elements charged to this memcg. */ -struct memcg_shrinker_map { +struct shrinker_info { struct rcu_head rcu; - unsigned long map[]; + atomic_long_t *nr_deferred; + unsigned long *map; }; /* @@ -145,7 +146,7 @@ struct mem_cgroup_per_node { struct mem_cgroup_reclaim_iter iter; - struct memcg_shrinker_map __rcu *shrinker_map; + struct shrinker_info __rcu *shrinker_info; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ @@ -1610,10 +1611,10 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) return false; } -extern int memcg_expand_shrinker_maps(int new_id); - -extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id); +int alloc_shrinker_info(struct mem_cgroup *memcg); +void free_shrinker_info(struct mem_cgroup *memcg); +void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); +void reparent_shrinker_deferred(struct mem_cgroup *memcg); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; @@ -1623,8 +1624,8 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) return false; } -static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id) +static inline void set_shrinker_bit(struct mem_cgroup *memcg, + int nid, int shrinker_id) { } #endif diff --git a/include/linux/memory.h b/include/linux/memory.h index 4da95e684e20..97e92e8b556a 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -29,6 +29,11 @@ struct memory_block { int online_type; /* for passing data to online routine */ int nid; /* NID for this memory block */ struct device dev; + /* + * Number of vmemmap pages. These pages + * lay at the beginning of the memory block. + */ + unsigned long nr_vmemmap_pages; }; int arch_get_memory_phys_device(unsigned long start_pfn); @@ -80,7 +85,8 @@ static inline int memory_notify(unsigned long val, void *v) #else extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); -int create_memory_block_devices(unsigned long start, unsigned long size); +int create_memory_block_devices(unsigned long start, unsigned long size, + unsigned long vmemmap_pages); void remove_memory_block_devices(unsigned long start, unsigned long size); extern void memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7288aa5ef73b..28f32fd00fe9 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -56,6 +56,14 @@ typedef int __bitwise mhp_t; #define MHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) /* + * We want memmap (struct page array) to be self contained. + * To do so, we will use the beginning of the hot-added range to build + * the page tables for the memmap array that describes the entire range. + * Only selected architectures support it with SPARSE_VMEMMAP. + */ +#define MHP_MEMMAP_ON_MEMORY ((__force mhp_t)BIT(1)) + +/* * Extended parameters for memory hotplug: * altmap: alternative allocator for memmap array (optional) * pgprot: page protection flags to apply to newly created page tables @@ -99,9 +107,13 @@ static inline void zone_seqlock_init(struct zone *zone) extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); +extern void adjust_present_page_count(struct zone *zone, long nr_pages); /* VM interface that may be used by firmware interface */ +extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, + struct zone *zone); +extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, - int online_type, int nid); + struct zone *zone); extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn); extern void __offline_isolated_pages(unsigned long start_pfn, @@ -359,6 +371,7 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_ extern int arch_create_linear_mapping(int nid, u64 start, u64 size, struct mhp_params *params); void arch_remove_linear_mapping(u64 start, u64 size); +extern bool mhp_supports_memmap_on_memory(unsigned long size); #endif /* CONFIG_MEMORY_HOTPLUG */ #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index f5b464daeeca..45a79da89c5f 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -17,7 +17,7 @@ struct device; * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { - const unsigned long base_pfn; + unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3a389633b68f..4bb4e519e3f5 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -27,6 +27,7 @@ enum migrate_reason { MR_MEMPOLICY_MBIND, MR_NUMA_MISPLACED, MR_CONTIG_RANGE, + MR_LONGTERM_PIN, MR_TYPES }; @@ -43,10 +44,7 @@ extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); extern struct page *alloc_migration_target(struct page *page, unsigned long private); extern int isolate_movable_page(struct page *page, isolate_mode_t mode); -extern void putback_movable_page(struct page *page); -extern void migrate_prep(void); -extern void migrate_prep_local(void); extern void migrate_page_states(struct page *newpage, struct page *page); extern void migrate_page_copy(struct page *newpage, struct page *page); extern int migrate_huge_page_move_mapping(struct address_space *mapping, @@ -66,9 +64,6 @@ static inline struct page *alloc_migration_target(struct page *page, static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) { return -EBUSY; } -static inline int migrate_prep(void) { return -ENOSYS; } -static inline int migrate_prep_local(void) { return -ENOSYS; } - static inline void migrate_page_states(struct page *newpage, struct page *page) { } diff --git a/include/linux/mm.h b/include/linux/mm.h index 011f43605807..76e27ebb28a3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -372,6 +372,13 @@ extern unsigned int kobjsize(const void *objp); # define VM_GROWSUP VM_NONE #endif +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR +# define VM_UFFD_MINOR_BIT 37 +# define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ +#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ +# define VM_UFFD_MINOR VM_NONE +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) @@ -1134,6 +1141,11 @@ static inline bool is_zone_device_page(const struct page *page) } #endif +static inline bool is_zone_movable_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_MOVABLE; +} + #ifdef CONFIG_DEV_PAGEMAP_OPS void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); @@ -1543,6 +1555,20 @@ static inline unsigned long page_to_section(const struct page *page) } #endif +/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ +#ifdef CONFIG_MIGRATION +static inline bool is_pinnable_page(struct page *page) +{ + return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) || + is_zero_pfn(page_to_pfn(page)); +} +#else +static inline bool is_pinnable_page(struct page *page) +{ + return true; +} +#endif + static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3b2205741048..917bd6c604d5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -407,8 +407,13 @@ enum zone_type { * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might - * essentially turn such pages unmovable. Memory offlining might - * retry a long time. + * essentially turn such pages unmovable. Therefore, we do not allow + * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and + * faulted, they come from the right zone right away. However, it is + * still possible that address space already has pages in + * ZONE_MOVABLE at the time when pages are pinned (i.e. user has + * touches that memory before pinning). In such case we migrate them + * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. @@ -427,6 +432,15 @@ enum zone_type { * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). + * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create + * situations where ZERO_PAGE(0) which is allocated differently + * on different platforms may end up in a movable zone. ZERO_PAGE(0) + * cannot be migrated. + * 7. Memory-hotplug: when using memmap_on_memory and onlining the + * memory to the MOVABLE zone, the vmemmap pages are also placed in + * such zone. Such pages cannot be really moved around as they are + * self-stored in the range, but they are treated as movable when + * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) @@ -1383,10 +1397,8 @@ static inline int online_section_nr(unsigned long nr) #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); -#ifdef CONFIG_MEMORY_HOTREMOVE void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif -#endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { diff --git a/include/linux/msi.h b/include/linux/msi.h index aef35fd1cf11..6aff469e511d 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -240,8 +240,7 @@ void pci_msi_unmask_irq(struct irq_data *data); /* * The arch hooks to setup up msi irqs. Default functions are implemented * as weak symbols so that they /can/ be overriden by architecture specific - * code if needed. These hooks must be enabled by the architecture or by - * drivers which depend on them via msi_controller based MSI handling. + * code if needed. These hooks can only be enabled by the architecture. * * If CONFIG_PCI_MSI_ARCH_FALLBACKS is not selected they are replaced by * stubs with warnings. @@ -251,7 +250,6 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); -void default_teardown_msi_irqs(struct pci_dev *dev); #else static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { @@ -272,19 +270,6 @@ static inline void arch_teardown_msi_irqs(struct pci_dev *dev) void arch_restore_msi_irqs(struct pci_dev *dev); void default_restore_msi_irqs(struct pci_dev *dev); -struct msi_controller { - struct module *owner; - struct device *dev; - struct device_node *of_node; - struct list_head list; - - int (*setup_irq)(struct msi_controller *chip, struct pci_dev *dev, - struct msi_desc *desc); - int (*setup_irqs)(struct msi_controller *chip, struct pci_dev *dev, - int nvec, int type); - void (*teardown_irq)(struct msi_controller *chip, unsigned int irq); -}; - #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN #include <linux/irqhandler.h> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 469fa7ffcf96..a4bd41128bf3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -18,6 +18,11 @@ struct pagevec; +static inline bool mapping_empty(struct address_space *mapping) +{ + return xa_empty(&mapping->i_pages); +} + /* * Bits in mapping->flags. */ diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 65d3d83015c3..fbdadd4d8377 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -85,6 +85,7 @@ extern const struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ extern const struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 */ extern const struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ +extern const struct pci_ecam_ops tegra194_pcie_ops; /* Tegra194 PCIe */ #endif #if IS_ENABLED(CONFIG_PCI_HOST_COMMON) diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fa104ee13d9..c20211e59a57 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -458,7 +458,6 @@ struct pci_dev { u32 saved_config_space[16]; /* Config space saved at suspend time */ struct hlist_head saved_cap_space; - struct bin_attribute *rom_attr; /* Attribute descriptor for sysfs ROM entry */ int rom_attr_enabled; /* Display of ROM attribute enabled? */ struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */ struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */ @@ -540,7 +539,6 @@ struct pci_host_bridge { int (*map_irq)(const struct pci_dev *, u8, u8); void (*release_fn)(struct pci_host_bridge *); void *release_data; - struct msi_controller *msi; unsigned int ignore_reset_delay:1; /* For entire hierarchy */ unsigned int no_ext_tags:1; /* No Extended Tags */ unsigned int native_aer:1; /* OS may use PCIe AER */ @@ -551,6 +549,7 @@ struct pci_host_bridge { unsigned int native_dpc:1; /* OS may use PCIe DPC */ unsigned int preserve_config:1; /* Preserve FW resource setup */ unsigned int size_windows:1; /* Enable root bus sizing */ + unsigned int msi_domain:1; /* Bridge wants MSI domain */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, @@ -621,7 +620,6 @@ struct pci_bus { struct resource busn_res; /* Bus numbers routed to this bus */ struct pci_ops *ops; /* Configuration access functions */ - struct msi_controller *msi; /* MSI controller */ void *sysdata; /* Hook for sys-specific extension */ struct proc_dir_entry *procdir; /* Directory entry in /proc/bus/pci */ @@ -1085,6 +1083,7 @@ u8 pci_find_next_ht_capability(struct pci_dev *dev, u8 pos, int ht_cap); u16 pci_find_ext_capability(struct pci_dev *dev, int cap); u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 pos, int cap); struct pci_bus *pci_find_next_bus(const struct pci_bus *from); +u16 pci_find_vsec_capability(struct pci_dev *dev, u16 vendor, int cap); u64 pci_get_dsn(struct pci_dev *dev); @@ -1209,6 +1208,7 @@ int __must_check pci_set_mwi(struct pci_dev *dev); int __must_check pcim_set_mwi(struct pci_dev *dev); int pci_try_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); +void pci_disable_parity(struct pci_dev *dev); void pci_intx(struct pci_dev *dev, int enable); bool pci_check_and_mask_intx(struct pci_dev *dev); bool pci_check_and_unmask_intx(struct pci_dev *dev); @@ -1310,7 +1310,6 @@ void pci_unlock_rescan_remove(void); /* Vital Product Data routines */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf); ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); -int pci_set_vpd_size(struct pci_dev *dev, size_t len); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); @@ -2319,14 +2318,13 @@ static inline u8 pci_vpd_info_field_size(const u8 *info_field) /** * pci_vpd_find_tag - Locates the Resource Data Type tag provided * @buf: Pointer to buffered vpd data - * @off: The offset into the buffer at which to begin the search * @len: The length of the vpd buffer * @rdt: The Resource Data Type to search for * * Returns the index where the Resource Data Type was found or * -ENOENT otherwise. */ -int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt); +int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt); /** * pci_vpd_find_info_keyword - Locates an information field keyword in the VPD diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 5e772392a379..2194a9cd885c 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1111,6 +1111,7 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, extern void untrack_pfn_moved(struct vm_area_struct *vma); #endif +#ifdef CONFIG_MMU #ifdef __HAVE_COLOR_ZERO_PAGE static inline int is_zero_pfn(unsigned long pfn) { @@ -1134,6 +1135,17 @@ static inline unsigned long my_zero_pfn(unsigned long addr) return zero_pfn; } #endif +#else +static inline int is_zero_pfn(unsigned long pfn) +{ + return 0; +} + +static inline unsigned long my_zero_pfn(unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_MMU */ #ifdef CONFIG_MMU diff --git a/include/linux/pwm.h b/include/linux/pwm.h index e4d84d4db293..5bb90af4997e 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -91,6 +91,11 @@ struct pwm_device { * pwm_get_state() - retrieve the current PWM state * @pwm: PWM device * @state: state to fill with the current PWM state + * + * The returned PWM state represents the state that was applied by a previous call to + * pwm_apply_state(). Drivers may have to slightly tweak that state before programming it to + * hardware. If pwm_apply_state() was never called, this returns either the current hardware + * state (if supported) or the default settings. */ static inline void pwm_get_state(const struct pwm_device *pwm, struct pwm_state *state) @@ -392,8 +397,6 @@ int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); -int pwmchip_add_with_polarity(struct pwm_chip *chip, - enum pwm_polarity polarity); int pwmchip_add(struct pwm_chip *chip); int pwmchip_remove(struct pwm_chip *chip); struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index f28ee75d1005..8b795b544f75 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -315,6 +315,7 @@ struct rproc; /** * struct rproc_mem_entry - memory entry descriptor * @va: virtual address + * @is_iomem: io memory * @dma: dma address * @len: length, in bytes * @da: device address @@ -329,6 +330,7 @@ struct rproc; */ struct rproc_mem_entry { void *va; + bool is_iomem; dma_addr_t dma; size_t len; u32 da; @@ -361,6 +363,7 @@ enum rsc_handling_status { * @start: power on the device and boot it * @stop: power off the device * @attach: attach to a device that his already powered up + * @detach: detach from a device, leaving it powered up * @kick: kick a virtqueue (virtqueue id given as a parameter) * @da_to_va: optional platform hook to perform address translations * @parse_fw: parse firmware to extract information (e.g. resource table) @@ -368,7 +371,9 @@ enum rsc_handling_status { * RSC_HANDLED if resource was handled, RSC_IGNORED if not handled and a * negative value on error * @load_rsc_table: load resource table from firmware image - * @find_loaded_rsc_table: find the loaded resouce table + * @find_loaded_rsc_table: find the loaded resource table from firmware image + * @get_loaded_rsc_table: get resource table installed in memory + * by external entity * @load: load firmware to memory, where the remote processor * expects to find it * @sanity_check: sanity check the fw image @@ -383,13 +388,16 @@ struct rproc_ops { int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); int (*attach)(struct rproc *rproc); + int (*detach)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); - void * (*da_to_va)(struct rproc *rproc, u64 da, size_t len); + void * (*da_to_va)(struct rproc *rproc, u64 da, size_t len, bool *is_iomem); int (*parse_fw)(struct rproc *rproc, const struct firmware *fw); int (*handle_rsc)(struct rproc *rproc, u32 rsc_type, void *rsc, int offset, int avail); struct resource_table *(*find_loaded_rsc_table)( struct rproc *rproc, const struct firmware *fw); + struct resource_table *(*get_loaded_rsc_table)( + struct rproc *rproc, size_t *size); int (*load)(struct rproc *rproc, const struct firmware *fw); int (*sanity_check)(struct rproc *rproc, const struct firmware *fw); u64 (*get_boot_addr)(struct rproc *rproc, const struct firmware *fw); @@ -405,6 +413,8 @@ struct rproc_ops { * @RPROC_RUNNING: device is up and running * @RPROC_CRASHED: device has crashed; need to start recovery * @RPROC_DELETED: device is deleted + * @RPROC_ATTACHED: device has been booted by another entity and the core + * has attached to it * @RPROC_DETACHED: device has been booted by another entity and waiting * for the core to attach to it * @RPROC_LAST: just keep this one at the end @@ -421,8 +431,9 @@ enum rproc_state { RPROC_RUNNING = 2, RPROC_CRASHED = 3, RPROC_DELETED = 4, - RPROC_DETACHED = 5, - RPROC_LAST = 6, + RPROC_ATTACHED = 5, + RPROC_DETACHED = 6, + RPROC_LAST = 7, }; /** @@ -505,11 +516,12 @@ struct rproc_dump_segment { * @recovery_disabled: flag that state if recovery was disabled * @max_notifyid: largest allocated notify id. * @table_ptr: pointer to the resource table in effect + * @clean_table: copy of the resource table without modifications. Used + * when a remote processor is attached or detached from the core * @cached_table: copy of the resource table * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started - * @autonomous: true if an external entity has booted the remote processor * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc * @char_dev: character device of the rproc @@ -542,11 +554,11 @@ struct rproc { bool recovery_disabled; int max_notifyid; struct resource_table *table_ptr; + struct resource_table *clean_table; struct resource_table *cached_table; size_t table_sz; bool has_iommu; bool auto_boot; - bool autonomous; struct list_head dump_segments; int nb_vdev; u8 elf_class; @@ -655,6 +667,7 @@ rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, size_t len, int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); +int rproc_detach(struct rproc *rproc); int rproc_set_firmware(struct rproc *rproc, const char *fw_name); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); void rproc_coredump_using_sections(struct rproc *rproc); diff --git a/include/linux/reset.h b/include/linux/reset.h index 46e6372cb431..db0e6115a2f6 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -76,6 +76,11 @@ static inline int reset_control_reset(struct reset_control *rstc) return 0; } +static inline int reset_control_rearm(struct reset_control *rstc) +{ + return 0; +} + static inline int reset_control_assert(struct reset_control *rstc) { return 0; diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index a5db828b2420..d97dcd049f18 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -18,8 +18,7 @@ #include <linux/mutex.h> #include <linux/poll.h> #include <linux/rpmsg/byteorder.h> - -#define RPMSG_ADDR_ANY 0xFFFFFFFF +#include <uapi/linux/rpmsg.h> struct rpmsg_device; struct rpmsg_endpoint; diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c25c8e67030..d2c881384517 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1583,7 +1583,7 @@ extern struct pid *cad_pid; #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ -#define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ +#define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 90b2a0bce11c..e24b1fe348e3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -151,12 +151,13 @@ static inline bool in_vfork(struct task_struct *tsk) * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS + * PF_MEMALLOC_PIN implies !GFP_MOVABLE */ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); - if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) { + if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence @@ -165,6 +166,9 @@ static inline gfp_t current_gfp_context(gfp_t flags) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; + + if (pflags & PF_MEMALLOC_PIN) + flags &= ~__GFP_MOVABLE; } return flags; } @@ -271,29 +275,18 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } -#ifdef CONFIG_CMA -static inline unsigned int memalloc_nocma_save(void) +static inline unsigned int memalloc_pin_save(void) { - unsigned int flags = current->flags & PF_MEMALLOC_NOCMA; + unsigned int flags = current->flags & PF_MEMALLOC_PIN; - current->flags |= PF_MEMALLOC_NOCMA; + current->flags |= PF_MEMALLOC_PIN; return flags; } -static inline void memalloc_nocma_restore(unsigned int flags) -{ - current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags; -} -#else -static inline unsigned int memalloc_nocma_save(void) -{ - return 0; -} - -static inline void memalloc_nocma_restore(unsigned int flags) +static inline void memalloc_pin_restore(unsigned int flags) { + current->flags = (current->flags & ~PF_MEMALLOC_PIN) | flags; } -#endif #ifdef CONFIG_MEMCG DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 0f80123650e2..1eac79ce57d4 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -79,13 +79,14 @@ struct shrinker { #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ /* Flags */ -#define SHRINKER_NUMA_AWARE (1 << 0) -#define SHRINKER_MEMCG_AWARE (1 << 1) +#define SHRINKER_REGISTERED (1 << 0) +#define SHRINKER_NUMA_AWARE (1 << 1) +#define SHRINKER_MEMCG_AWARE (1 << 2) /* * It just makes sense when the shrinker is also MEMCG_AWARE for now, * non-MEMCG_AWARE shrinker should not have this flag set. */ -#define SHRINKER_NONSLAB (1 << 2) +#define SHRINKER_NONSLAB (1 << 3) extern int prealloc_shrinker(struct shrinker *shrinker); extern void register_shrinker_prepared(struct shrinker *shrinker); diff --git a/include/linux/swap.h b/include/linux/swap.h index 4cc6ec3bf0ab..f69e0f67651d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -12,6 +12,7 @@ #include <linux/fs.h> #include <linux/atomic.h> #include <linux/page-flags.h> +#include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; @@ -339,6 +340,20 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file, extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void mark_page_accessed(struct page *); + +extern atomic_t lru_disable_count; + +static inline bool lru_cache_disabled(void) +{ + return atomic_read(&lru_disable_count); +} + +static inline void lru_cache_enable(void) +{ + atomic_dec(&lru_disable_count); +} + +extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); @@ -378,6 +393,12 @@ extern int sysctl_min_slab_ratio; #define node_reclaim_mode 0 #endif +static inline bool node_reclaim_enabled(void) +{ + /* Is any node_reclaim_mode bit set? */ + return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); +} + extern void check_move_unevictable_pages(struct pagevec *pvec); extern int kswapd_run(int nid); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 5857a937c637..216854a5e513 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -6,6 +6,7 @@ #include <linux/init.h> #include <linux/types.h> #include <linux/limits.h> +#include <linux/spinlock.h> struct device; struct page; @@ -36,20 +37,11 @@ enum swiotlb_force { extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); -extern unsigned long swiotlb_nr_tbl(void); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); extern int swiotlb_late_init_with_default_size(size_t default_size); extern void __init swiotlb_update_mem_attributes(void); -/* - * Enumeration for sync targets - */ -enum dma_sync_target { - SYNC_FOR_CPU = 0, - SYNC_FOR_DEVICE = 1, -}; - phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, size_t mapping_size, size_t alloc_size, enum dma_data_direction dir, unsigned long attrs); @@ -57,32 +49,70 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, size_t mapping_size, - size_t alloc_size, enum dma_data_direction dir, unsigned long attrs); -extern void swiotlb_tbl_sync_single(struct device *hwdev, - phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir, - enum dma_sync_target target); - +void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir); +void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir); dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs); #ifdef CONFIG_SWIOTLB extern enum swiotlb_force swiotlb_force; -extern phys_addr_t io_tlb_start, io_tlb_end; + +/** + * struct io_tlb_mem - IO TLB Memory Pool Descriptor + * + * @start: The start address of the swiotlb memory pool. Used to do a quick + * range check to see if the memory was in fact allocated by this + * API. + * @end: The end address of the swiotlb memory pool. Used to do a quick + * range check to see if the memory was in fact allocated by this + * API. + * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and + * @end. This is command line adjustable via setup_io_tlb_npages. + * @used: The number of used IO TLB block. + * @list: The free list describing the number of free entries available + * from each index. + * @index: The index to start searching in the next round. + * @orig_addr: The original address corresponding to a mapped entry. + * @alloc_size: Size of the allocated buffer. + * @lock: The lock to protect the above data structures in the map and + * unmap calls. + * @debugfs: The dentry to debugfs. + * @late_alloc: %true if allocated using the page allocator + */ +struct io_tlb_mem { + phys_addr_t start; + phys_addr_t end; + unsigned long nslabs; + unsigned long used; + unsigned int index; + spinlock_t lock; + struct dentry *debugfs; + bool late_alloc; + struct io_tlb_slot { + phys_addr_t orig_addr; + size_t alloc_size; + unsigned int list; + } slots[]; +}; +extern struct io_tlb_mem *io_tlb_default_mem; static inline bool is_swiotlb_buffer(phys_addr_t paddr) { - return paddr >= io_tlb_start && paddr < io_tlb_end; + struct io_tlb_mem *mem = io_tlb_default_mem; + + return mem && paddr >= mem->start && paddr < mem->end; } void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); bool is_swiotlb_active(void); -void __init swiotlb_adjust_size(unsigned long new_size); +void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE static inline bool is_swiotlb_buffer(phys_addr_t paddr) @@ -106,7 +136,7 @@ static inline bool is_swiotlb_active(void) return false; } -static inline void swiotlb_adjust_size(unsigned long new_size) +static inline void swiotlb_adjust_size(unsigned long size) { } #endif /* CONFIG_SWIOTLB */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 6ac7bb1d2b1f..d296f3b88fb9 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -91,7 +91,7 @@ struct thermal_cooling_device_ops { struct thermal_cooling_device { int id; - char type[THERMAL_NAME_LENGTH]; + char *type; struct device device; struct device_node *np; void *devdata; @@ -390,7 +390,6 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int thermal_zone_get_slope(struct thermal_zone_device *tz); int thermal_zone_get_offset(struct thermal_zone_device *tz); -void thermal_notify_framework(struct thermal_zone_device *, int); int thermal_zone_device_enable(struct thermal_zone_device *tz); int thermal_zone_device_disable(struct thermal_zone_device *tz); void thermal_zone_device_critical(struct thermal_zone_device *tz); @@ -436,10 +435,6 @@ static inline int thermal_zone_get_offset( struct thermal_zone_device *tz) { return -ENODEV; } -static inline void thermal_notify_framework(struct thermal_zone_device *tz, - int trip) -{ } - static inline int thermal_zone_device_enable(struct thermal_zone_device *tz) { return -ENODEV; } diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index a8e5f3ea9bb2..794d1538b8ba 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -17,6 +17,9 @@ #include <linux/mm.h> #include <asm-generic/pgtable_uffd.h> +/* The set of all possible UFFD-related VM flags. */ +#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) + /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want @@ -34,6 +37,22 @@ extern int sysctl_unprivileged_userfaultfd; extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); +/* + * The mode of operation for __mcopy_atomic and its helpers. + * + * This is almost an implementation detail (mcopy_atomic below doesn't take this + * as a parameter), but it's exposed here because memory-kind-specific + * implementations (e.g. hugetlbfs) need to know the mode of operation. + */ +enum mcopy_atomic_mode { + /* A normal copy_from_user into the destination range. */ + MCOPY_ATOMIC_NORMAL, + /* Don't copy; map the destination range to the zero page. */ + MCOPY_ATOMIC_ZEROPAGE, + /* Just install pte(s) with the existing page(s) in the page cache. */ + MCOPY_ATOMIC_CONTINUE, +}; + extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, bool *mmap_changing, __u64 mode); @@ -41,6 +60,8 @@ extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len, bool *mmap_changing); +extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long len, bool *mmap_changing); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, bool *mmap_changing); @@ -52,6 +73,22 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx; } +/* + * Never enable huge pmd sharing on some uffd registered vmas: + * + * - VM_UFFD_WP VMAs, because write protect information is per pgtable entry. + * + * - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for + * VMAs which share huge pmds. (If you have two mappings to the same + * underlying pages, and fault in the non-UFFD-registered one with a write, + * with huge pmd sharing this would *also* setup the second UFFD-registered + * mapping, and we'd not get minor faults.) + */ +static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); +} + static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; @@ -62,6 +99,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma) return vma->vm_flags & VM_UFFD_WP; } +static inline bool userfaultfd_minor(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_UFFD_MINOR; +} + static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { @@ -76,7 +118,7 @@ static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, static inline bool userfaultfd_armed(struct vm_area_struct *vma) { - return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP); + return vma->vm_flags & __VM_UFFD_FLAGS; } extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); @@ -123,6 +165,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_minor(struct vm_area_struct *vma) +{ + return false; +} + static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 15fa085fab05..f311d227aa1b 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -8,7 +8,7 @@ #include <linux/vhost_iotlb.h> /** - * vDPA callback definition. + * struct vdpa_calllback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function */ @@ -18,7 +18,7 @@ struct vdpa_callback { }; /** - * vDPA notification area + * struct vdpa_notification_area - vDPA notification area * @addr: base address of the notification area * @size: size of the notification area */ @@ -28,7 +28,7 @@ struct vdpa_notification_area { }; /** - * vDPA vq_state definition + * struct vdpa_vq_state - vDPA vq_state definition * @avail_index: available index */ struct vdpa_vq_state { @@ -38,7 +38,7 @@ struct vdpa_vq_state { struct vdpa_mgmt_dev; /** - * vDPA device - representation of a vDPA device + * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA * @config: the configuration ops for this device. @@ -59,7 +59,7 @@ struct vdpa_device { }; /** - * vDPA IOVA range - the IOVA range support by the device + * struct vdpa_iova_range - the IOVA range support by the device * @first: start of the IOVA range * @last: end of the IOVA range */ @@ -69,7 +69,7 @@ struct vdpa_iova_range { }; /** - * vDPA_config_ops - operations for configuring a vDPA device. + * struct vdpa_config_ops - operations for configuring a vDPA device. * Note: vDPA device drivers are required to implement all of the * operations unless it is mentioned to be optional in the following * list. @@ -150,6 +150,9 @@ struct vdpa_iova_range { * @set_status: Set the device status * @vdev: vdpa device * @status: virtio device status + * @get_config_size: Get the size of the configuration space + * @vdev: vdpa device + * Returns size_t: configuration size * @get_config: Read from device specific configuration space * @vdev: vdpa device * @offset: offset from the beginning of @@ -231,6 +234,7 @@ struct vdpa_config_ops { u32 (*get_vendor_id)(struct vdpa_device *vdev); u8 (*get_status)(struct vdpa_device *vdev); void (*set_status)(struct vdpa_device *vdev, u8 status); + size_t (*get_config_size)(struct vdpa_device *vdev); void (*get_config)(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); void (*set_config)(struct vdpa_device *vdev, unsigned int offset, @@ -267,7 +271,7 @@ int _vdpa_register_device(struct vdpa_device *vdev, int nvqs); void _vdpa_unregister_device(struct vdpa_device *vdev); /** - * vdpa_driver - operations for a vDPA driver + * struct vdpa_driver - operations for a vDPA driver * @driver: underlying device driver * @probe: the function to call when a device is found. Returns 0 or -errno. * @remove: the function to call when a device is removed. @@ -344,18 +348,18 @@ static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, } /** - * vdpa_mgmtdev_ops - vdpa device ops - * @dev_add: Add a vdpa device using alloc and register - * @mdev: parent device to use for device addition - * @name: name of the new vdpa device - * Driver need to add a new device using _vdpa_register_device() - * after fully initializing the vdpa device. Driver must return 0 - * on success or appropriate error code. - * @dev_del: Remove a vdpa device using unregister - * @mdev: parent device to use for device removal - * @dev: vdpa device to remove - * Driver need to remove the specified device by calling - * _vdpa_unregister_device(). + * struct vdpa_mgmtdev_ops - vdpa device ops + * @dev_add: Add a vdpa device using alloc and register + * @mdev: parent device to use for device addition + * @name: name of the new vdpa device + * Driver need to add a new device using _vdpa_register_device() + * after fully initializing the vdpa device. Driver must return 0 + * on success or appropriate error code. + * @dev_del: Remove a vdpa device using unregister + * @mdev: parent device to use for device removal + * @dev: vdpa device to remove + * Driver need to remove the specified device by calling + * _vdpa_unregister_device(). */ struct vdpa_mgmtdev_ops { int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name); diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index f26acbeec965..6a95b58fd0f4 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -13,6 +13,8 @@ struct virtio_pci_modern_device { void __iomem *device; /* Base of vq notifications (non-legacy mode). */ void __iomem *notify_base; + /* Physical base of vq notifications */ + resource_size_t notify_pa; /* Where to read and clear interrupt */ u8 __iomem *isr; @@ -99,13 +101,8 @@ void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, u16 idx); u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev); -u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, - u16 idx); -void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, - size_t minlen, - u32 align, - u32 start, u32 size, - size_t *len); +void __iomem * vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev, + u16 index, resource_size_t *pa); int vp_modern_probe(struct virtio_pci_modern_device *mdev); void vp_modern_remove(struct virtio_pci_modern_device *mdev); #endif diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 18e75974d4e3..ae0dd1948c2b 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -71,6 +71,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, #endif +#ifdef CONFIG_CMA + CMA_ALLOC_SUCCESS, + CMA_ALLOC_FAIL, +#endif UNEVICTABLE_PGCULLED, /* culled to noreclaim list */ UNEVICTABLE_PGSCANNED, /* scanned for reclaimability */ UNEVICTABLE_PGRESCUED, /* rescued from noreclaim list */ @@ -121,6 +125,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, SWAP_RA, SWAP_RA_HIT, #endif +#ifdef CONFIG_X86 + DIRECT_MAP_LEVEL2_SPLIT, + DIRECT_MAP_LEVEL3_SPLIT, +#endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 59bd50f99291..84db7b8f912f 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -46,6 +46,9 @@ struct vringh { /* IOTLB for this vring */ struct vhost_iotlb *iotlb; + /* spinlock to synchronize IOTLB accesses */ + spinlock_t *iotlb_lock; + /* The function to call to notify the guest about added buffers */ void (*notify)(struct vringh *); }; @@ -196,6 +199,19 @@ static inline void vringh_kiov_cleanup(struct vringh_kiov *kiov) kiov->iov = NULL; } +static inline size_t vringh_kiov_length(struct vringh_kiov *kiov) +{ + size_t len = 0; + int i; + + for (i = kiov->i; i < kiov->used; i++) + len += kiov->iov[i].iov_len; + + return len; +} + +void vringh_kiov_advance(struct vringh_kiov *kiov, size_t len); + int vringh_getdesc_kern(struct vringh *vrh, struct vringh_kiov *riov, struct vringh_kiov *wiov, @@ -258,7 +274,8 @@ static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val) #if IS_REACHABLE(CONFIG_VHOST_IOTLB) -void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb); +void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb, + spinlock_t *iotlb_lock); int vringh_init_iotlb(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, diff --git a/include/trace/events/cma.h b/include/trace/events/cma.h index 5017a8829270..c3d354702cb0 100644 --- a/include/trace/events/cma.h +++ b/include/trace/events/cma.h @@ -8,28 +8,31 @@ #include <linux/types.h> #include <linux/tracepoint.h> -TRACE_EVENT(cma_alloc, +DECLARE_EVENT_CLASS(cma_alloc_class, - TP_PROTO(unsigned long pfn, const struct page *page, - unsigned int count, unsigned int align), + TP_PROTO(const char *name, unsigned long pfn, const struct page *page, + unsigned long count, unsigned int align), - TP_ARGS(pfn, page, count, align), + TP_ARGS(name, pfn, page, count, align), TP_STRUCT__entry( + __string(name, name) __field(unsigned long, pfn) __field(const struct page *, page) - __field(unsigned int, count) + __field(unsigned long, count) __field(unsigned int, align) ), TP_fast_assign( + __assign_str(name, name); __entry->pfn = pfn; __entry->page = page; __entry->count = count; __entry->align = align; ), - TP_printk("pfn=%lx page=%p count=%u align=%u", + TP_printk("name=%s pfn=%lx page=%p count=%lu align=%u", + __get_str(name), __entry->pfn, __entry->page, __entry->count, @@ -38,29 +41,72 @@ TRACE_EVENT(cma_alloc, TRACE_EVENT(cma_release, - TP_PROTO(unsigned long pfn, const struct page *page, - unsigned int count), + TP_PROTO(const char *name, unsigned long pfn, const struct page *page, + unsigned long count), - TP_ARGS(pfn, page, count), + TP_ARGS(name, pfn, page, count), TP_STRUCT__entry( + __string(name, name) __field(unsigned long, pfn) __field(const struct page *, page) - __field(unsigned int, count) + __field(unsigned long, count) ), TP_fast_assign( + __assign_str(name, name); __entry->pfn = pfn; __entry->page = page; __entry->count = count; ), - TP_printk("pfn=%lx page=%p count=%u", + TP_printk("name=%s pfn=%lx page=%p count=%lu", + __get_str(name), __entry->pfn, __entry->page, __entry->count) ); +TRACE_EVENT(cma_alloc_start, + + TP_PROTO(const char *name, unsigned long count, unsigned int align), + + TP_ARGS(name, count, align), + + TP_STRUCT__entry( + __string(name, name) + __field(unsigned long, count) + __field(unsigned int, align) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->count = count; + __entry->align = align; + ), + + TP_printk("name=%s count=%lu align=%u", + __get_str(name), + __entry->count, + __entry->align) +); + +DEFINE_EVENT(cma_alloc_class, cma_alloc_finish, + + TP_PROTO(const char *name, unsigned long pfn, const struct page *page, + unsigned long count, unsigned int align), + + TP_ARGS(name, pfn, page, count, align) +); + +DEFINE_EVENT(cma_alloc_class, cma_alloc_busy_retry, + + TP_PROTO(const char *name, unsigned long pfn, const struct page *page, + unsigned long count, unsigned int align), + + TP_ARGS(name, pfn, page, count, align) +); + #endif /* _TRACE_CMA_H */ /* This part must be outside protection */ diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 4d434398d64d..9fb2a3bbcdfb 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -20,7 +20,8 @@ EM( MR_SYSCALL, "syscall_or_cpuset") \ EM( MR_MEMPOLICY_MBIND, "mempolicy_mbind") \ EM( MR_NUMA_MISPLACED, "numa_misplaced") \ - EMe(MR_CONTIG_RANGE, "contig_range") + EM( MR_CONTIG_RANGE, "contig_range") \ + EMe(MR_LONGTERM_PIN, "longterm_pin") /* * First define the enums in the above macros to be exported to userspace @@ -81,6 +82,28 @@ TRACE_EVENT(mm_migrate_pages, __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); + +TRACE_EVENT(mm_migrate_pages_start, + + TP_PROTO(enum migrate_mode mode, int reason), + + TP_ARGS(mode, reason), + + TP_STRUCT__entry( + __field(enum migrate_mode, mode) + __field(int, reason) + ), + + TP_fast_assign( + __entry->mode = mode; + __entry->reason = reason; + ), + + TP_printk("mode=%s reason=%s", + __print_symbolic(__entry->mode, MIGRATE_MODE), + __print_symbolic(__entry->reason, MIGRATE_REASON)) +); + #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 67018d367b9f..629c7a0eaff2 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -137,6 +137,12 @@ IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) #define IF_HAVE_VM_SOFTDIRTY(flag,name) #endif +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR +# define IF_HAVE_UFFD_MINOR(flag, name) {flag, name}, +#else +# define IF_HAVE_UFFD_MINOR(flag, name) +#endif + #define __def_vmaflag_names \ {VM_READ, "read" }, \ {VM_WRITE, "write" }, \ @@ -148,6 +154,7 @@ IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) {VM_MAYSHARE, "mayshare" }, \ {VM_GROWSDOWN, "growsdown" }, \ {VM_UFFD_MISSING, "uffd_missing" }, \ +IF_HAVE_UFFD_MINOR(VM_UFFD_MINOR, "uffd_minor" ) \ {VM_PFNMAP, "pfnmap" }, \ {VM_DENYWRITE, "denywrite" }, \ {VM_UFFD_WP, "uffd_wp" }, \ diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 05669c87a0af..778dc191c265 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -42,6 +42,7 @@ #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) #define KEXEC_ARCH_AARCH64 (183 << 16) +#define KEXEC_ARCH_RISCV (243 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 8948467b3992..4832fd0b5642 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -64,5 +64,12 @@ enum { #define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */ #define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */ +/* + * These bit locations are exposed in the vm.zone_reclaim_mode sysctl + * ABI. New bits are OK, but existing bits can never change. + */ +#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ +#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ +#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ #endif /* _UAPI_LINUX_MEMPOLICY_H */ diff --git a/include/uapi/linux/rpmsg.h b/include/uapi/linux/rpmsg.h index e14c6dab4223..f5ca8740f3fb 100644 --- a/include/uapi/linux/rpmsg.h +++ b/include/uapi/linux/rpmsg.h @@ -9,11 +9,13 @@ #include <linux/ioctl.h> #include <linux/types.h> +#define RPMSG_ADDR_ANY 0xFFFFFFFF + /** * struct rpmsg_endpoint_info - endpoint info representation * @name: name of service - * @src: local address - * @dst: destination address + * @src: local address. To set to RPMSG_ADDR_ANY if not used. + * @dst: destination address. To set to RPMSG_ADDR_ANY if not used. */ struct rpmsg_endpoint_info { char name[32]; @@ -21,7 +23,14 @@ struct rpmsg_endpoint_info { __u32 dst; }; +/** + * Instantiate a new rmpsg char device endpoint. + */ #define RPMSG_CREATE_EPT_IOCTL _IOW(0xb5, 0x1, struct rpmsg_endpoint_info) + +/** + * Destroy a rpmsg char device endpoint created by the RPMSG_CREATE_EPT_IOCTL. + */ #define RPMSG_DESTROY_EPT_IOCTL _IO(0xb5, 0x2) #endif diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index c105054cbb57..9aa2fedfa309 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -60,7 +60,7 @@ enum thermal_genl_event { THERMAL_GENL_EVENT_UNSPEC, THERMAL_GENL_EVENT_TZ_CREATE, /* Thermal zone creation */ THERMAL_GENL_EVENT_TZ_DELETE, /* Thermal zone deletion */ - THERMAL_GENL_EVENT_TZ_DISABLE, /* Thermal zone disabed */ + THERMAL_GENL_EVENT_TZ_DISABLE, /* Thermal zone disabled */ THERMAL_GENL_EVENT_TZ_ENABLE, /* Thermal zone enabled */ THERMAL_GENL_EVENT_TZ_TRIP_UP, /* Trip point crossed the way up */ THERMAL_GENL_EVENT_TZ_TRIP_DOWN, /* Trip point crossed the way down */ diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 5f2d88212f7c..bafbeb1a2624 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -19,15 +19,19 @@ * means the userland is reading). */ #define UFFD_API ((__u64)0xAA) +#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \ + UFFDIO_REGISTER_MODE_WP | \ + UFFDIO_REGISTER_MODE_MINOR) #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ - UFFD_FEATURE_EVENT_REMOVE | \ + UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ UFFD_FEATURE_MISSING_HUGETLBFS | \ UFFD_FEATURE_MISSING_SHMEM | \ UFFD_FEATURE_SIGBUS | \ - UFFD_FEATURE_THREAD_ID) + UFFD_FEATURE_THREAD_ID | \ + UFFD_FEATURE_MINOR_HUGETLBFS) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -36,10 +40,12 @@ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ (__u64)1 << _UFFDIO_ZEROPAGE | \ - (__u64)1 << _UFFDIO_WRITEPROTECT) + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE) #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ - (__u64)1 << _UFFDIO_COPY) + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_CONTINUE) /* * Valid ioctl command number range with this API is from 0x00 to @@ -55,6 +61,7 @@ #define _UFFDIO_COPY (0x03) #define _UFFDIO_ZEROPAGE (0x04) #define _UFFDIO_WRITEPROTECT (0x06) +#define _UFFDIO_CONTINUE (0x07) #define _UFFDIO_API (0x3F) /* userfaultfd ioctl ids */ @@ -73,6 +80,8 @@ struct uffdio_zeropage) #define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \ struct uffdio_writeprotect) +#define UFFDIO_CONTINUE _IOR(UFFDIO, _UFFDIO_CONTINUE, \ + struct uffdio_continue) /* read() structure */ struct uffd_msg { @@ -127,6 +136,7 @@ struct uffd_msg { /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ #define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */ +#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */ struct uffdio_api { /* userland asks for an API number and the features to enable */ @@ -171,6 +181,10 @@ struct uffdio_api { * * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will * be returned, if feature is not requested 0 will be returned. + * + * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults + * can be intercepted (via REGISTER_MODE_MINOR) for + * hugetlbfs-backed pages. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -181,6 +195,7 @@ struct uffdio_api { #define UFFD_FEATURE_EVENT_UNMAP (1<<6) #define UFFD_FEATURE_SIGBUS (1<<7) #define UFFD_FEATURE_THREAD_ID (1<<8) +#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) __u64 features; __u64 ioctls; @@ -195,6 +210,7 @@ struct uffdio_register { struct uffdio_range range; #define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0) #define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1) +#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2) __u64 mode; /* @@ -257,6 +273,18 @@ struct uffdio_writeprotect { __u64 mode; }; +struct uffdio_continue { + struct uffdio_range range; +#define UFFDIO_CONTINUE_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 mapped; +}; + /* * Flags for the userfaultfd(2) system call itself. */ diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index dbc4a4b785f6..b3e647f86e3e 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -10,7 +10,8 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir); -extern int xen_swiotlb_init(int verbose, bool early); +int xen_swiotlb_init(void); +void __init xen_swiotlb_init_early(void); extern const struct dma_map_ops xen_swiotlb_dma_ops; #endif /* __LINUX_SWIOTLB_XEN_H */ |