diff options
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/bpf_verifier.h | 3 | ||||
-rw-r--r-- | include/linux/cpu.h | 2 | ||||
-rw-r--r-- | include/linux/dax.h | 7 | ||||
-rw-r--r-- | include/linux/dcache.h | 1 | ||||
-rw-r--r-- | include/linux/efi.h | 8 | ||||
-rw-r--r-- | include/linux/gfp.h | 2 | ||||
-rw-r--r-- | include/linux/kvm_host.h | 8 | ||||
-rw-r--r-- | include/linux/memory_hotplug.h | 3 | ||||
-rw-r--r-- | include/linux/memremap.h | 36 | ||||
-rw-r--r-- | include/linux/mlx5/driver.h | 12 | ||||
-rw-r--r-- | include/linux/mm.h | 80 | ||||
-rw-r--r-- | include/linux/mtd/map.h | 2 | ||||
-rw-r--r-- | include/linux/mtd/rawnand.h | 16 | ||||
-rw-r--r-- | include/linux/node.h | 8 | ||||
-rw-r--r-- | include/linux/nospec.h | 10 | ||||
-rw-r--r-- | include/linux/percpu-rwsem.h | 6 | ||||
-rw-r--r-- | include/linux/rwsem.h | 6 | ||||
-rw-r--r-- | include/linux/sched.h | 10 | ||||
-rw-r--r-- | include/linux/seccomp.h | 5 |
19 files changed, 143 insertions, 82 deletions
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7e61c395fddf..df36b1b08af0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -142,10 +142,11 @@ struct bpf_verifier_state_list { struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ - struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */ + unsigned long map_state; /* pointer/poison value for maps */ s32 call_imm; /* saved imm field of call insn */ }; int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ + int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7b01bc11c692..a97a63eef59f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -53,6 +53,8 @@ extern ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spec_store_bypass(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/dax.h b/include/linux/dax.h index a43b396fb336..b51db4264c83 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -86,6 +86,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev) struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); + +struct page *dax_layout_busy_page(struct address_space *mapping); #else static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { @@ -106,6 +108,11 @@ static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) return NULL; } +static inline struct page *dax_layout_busy_page(struct address_space *mapping) +{ + return NULL; +} + static inline int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc) { diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 94acbde17bb1..66c6e17e61e5 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -224,6 +224,7 @@ extern seqlock_t rename_lock; * These are the low-level FS interfaces to the dcache.. */ extern void d_instantiate(struct dentry *, struct inode *); +extern void d_instantiate_new(struct dentry *, struct inode *); extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *); extern int d_instantiate_no_diralias(struct dentry *, struct inode *); diff --git a/include/linux/efi.h b/include/linux/efi.h index f1b7d68ac460..3016d8c456bc 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -395,8 +395,8 @@ typedef struct { u32 attributes; u32 get_bar_attributes; u32 set_bar_attributes; - uint64_t romsize; - void *romimage; + u64 romsize; + u32 romimage; } efi_pci_io_protocol_32; typedef struct { @@ -415,8 +415,8 @@ typedef struct { u64 attributes; u64 get_bar_attributes; u64 set_bar_attributes; - uint64_t romsize; - void *romimage; + u64 romsize; + u64 romimage; } efi_pci_io_protocol_64; typedef struct { diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 1a4582b44d32..fc5ab85278d5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -464,7 +464,7 @@ static inline struct page * __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); - VM_WARN_ON(!node_online(nid)); + VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); return __alloc_pages(gfp_mask, order, nid); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6930c63126c7..6d6e79c59e68 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1045,13 +1045,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING -#ifdef CONFIG_S390 -#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that... -#elif defined(CONFIG_ARM64) -#define KVM_MAX_IRQ_ROUTES 4096 -#else -#define KVM_MAX_IRQ_ROUTES 1024 -#endif +#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */ bool kvm_arch_can_set_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e0e49b5b1ee1..2b0265265c28 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -216,6 +216,9 @@ void put_online_mems(void); void mem_hotplug_begin(void); void mem_hotplug_done(void); +extern void set_zone_contiguous(struct zone *zone); +extern void clear_zone_contiguous(struct zone *zone); + #else /* ! CONFIG_MEMORY_HOTPLUG */ #define pfn_to_online_page(pfn) \ ({ \ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 7b4899c06f49..5ebfff65da4d 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ -#include <linux/mm.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> @@ -30,13 +29,6 @@ struct vmem_altmap { * Specialize ZONE_DEVICE memory into multiple types each having differents * usage. * - * MEMORY_DEVICE_HOST: - * Persistent device memory (pmem): struct page might be allocated in different - * memory and architecture might want to perform special actions. It is similar - * to regular memory, in that the CPU can access it transparently. However, - * it is likely to have different bandwidth and latency than regular memory. - * See Documentation/nvdimm/nvdimm.txt for more information. - * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages @@ -53,11 +45,19 @@ struct vmem_altmap { * driver can hotplug the device memory using ZONE_DEVICE and with that memory * type. Any page of a process can be migrated to such memory. However no one * should be allow to pin such memory so that it can always be evicted. + * + * MEMORY_DEVICE_FS_DAX: + * Host memory that has similar access semantics as System RAM i.e. DMA + * coherent and supports page pinning. In support of coordinating page + * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a + * wakeup event whenever a page is unpinned and becomes idle. This + * wakeup is used to coordinate physical address space management (ex: + * fs truncate/hole punch) vs pinned pages (ex: device dma). */ enum memory_type { - MEMORY_DEVICE_HOST = 0, - MEMORY_DEVICE_PRIVATE, + MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_PUBLIC, + MEMORY_DEVICE_FS_DAX, }; /* @@ -129,8 +129,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); - -static inline bool is_zone_device_page(const struct page *page); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) @@ -161,20 +159,6 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap, } #endif /* CONFIG_ZONE_DEVICE */ -#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) -static inline bool is_device_private_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PRIVATE; -} - -static inline bool is_device_public_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PUBLIC; -} -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ - static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2a156c5dfadd..d703774982ca 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1286,17 +1286,7 @@ enum { static inline const struct cpumask * mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector) { - struct irq_desc *desc; - unsigned int irq; - int eqn; - int err; - - err = mlx5_vector2eqn(dev, vector, &eqn, &irq); - if (err) - return NULL; - - desc = irq_to_desc(irq); - return desc->affinity_hint; + return dev->priv.irq_info[vector].mask; } #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1ac1f06a4be6..274d5242bd0d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -821,27 +821,65 @@ static inline bool is_zone_device_page(const struct page *page) } #endif -#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) -void put_zone_device_private_or_public_page(struct page *page); -DECLARE_STATIC_KEY_FALSE(device_private_key); -#define IS_HMM_ENABLED static_branch_unlikely(&device_private_key) -static inline bool is_device_private_page(const struct page *page); -static inline bool is_device_public_page(const struct page *page); -#else /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ -static inline void put_zone_device_private_or_public_page(struct page *page) +#ifdef CONFIG_DEV_PAGEMAP_OPS +void dev_pagemap_get_ops(void); +void dev_pagemap_put_ops(void); +void __put_devmap_managed_page(struct page *page); +DECLARE_STATIC_KEY_FALSE(devmap_managed_key); +static inline bool put_devmap_managed_page(struct page *page) +{ + if (!static_branch_unlikely(&devmap_managed_key)) + return false; + if (!is_zone_device_page(page)) + return false; + switch (page->pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + case MEMORY_DEVICE_PUBLIC: + case MEMORY_DEVICE_FS_DAX: + __put_devmap_managed_page(page); + return true; + default: + break; + } + return false; +} + +static inline bool is_device_private_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; +} + +static inline bool is_device_public_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PUBLIC; +} + +#else /* CONFIG_DEV_PAGEMAP_OPS */ +static inline void dev_pagemap_get_ops(void) { } -#define IS_HMM_ENABLED 0 + +static inline void dev_pagemap_put_ops(void) +{ +} + +static inline bool put_devmap_managed_page(struct page *page) +{ + return false; +} + static inline bool is_device_private_page(const struct page *page) { return false; } + static inline bool is_device_public_page(const struct page *page) { return false; } -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ - +#endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline void get_page(struct page *page) { @@ -859,16 +897,13 @@ static inline void put_page(struct page *page) page = compound_head(page); /* - * For private device pages we need to catch refcount transition from - * 2 to 1, when refcount reach one it means the private device page is - * free and we need to inform the device driver through callback. See + * For devmap managed pages we need to catch refcount transition from + * 2 to 1, when refcount reach one it means the page is free and we + * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ - if (IS_HMM_ENABLED && unlikely(is_device_private_page(page) || - unlikely(is_device_public_page(page)))) { - put_zone_device_private_or_public_page(page); + if (put_devmap_managed_page(page)) return; - } if (put_page_testzero(page)) __put_page(page); @@ -2109,7 +2144,6 @@ extern void setup_per_cpu_pageset(void); extern void zone_pcp_update(struct zone *zone); extern void zone_pcp_reset(struct zone *zone); -extern void setup_zone_pageset(struct zone *zone); /* page_alloc.c */ extern int min_free_kbytes; @@ -2466,6 +2500,13 @@ static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } +static inline vm_fault_t vmf_error(int err) +{ + if (err == -ENOMEM) + return VM_FAULT_OOM; + return VM_FAULT_SIGBUS; +} + struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags, unsigned int *page_mask); @@ -2493,6 +2534,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ +#define FOLL_ANON 0x8000 /* don't do file mappings */ static inline int vm_fault_to_errno(int vm_fault, int foll_flags) { diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index b5b43f94f311..01b990e4b228 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -312,7 +312,7 @@ void map_destroy(struct mtd_info *mtd); ({ \ int i, ret = 1; \ for (i = 0; i < map_words(map); i++) { \ - if (((val1).x[i] & (val2).x[i]) != (val2).x[i]) { \ + if (((val1).x[i] & (val2).x[i]) != (val3).x[i]) { \ ret = 0; \ break; \ } \ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5dad59b31244..17c919436f48 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -867,12 +867,18 @@ struct nand_op_instr { * tBERS (during an erase) which all of them are u64 values that cannot be * divided by usual kernel macros and must be handled with the special * DIV_ROUND_UP_ULL() macro. + * + * Cast to type of dividend is needed here to guarantee that the result won't + * be an unsigned long long when the dividend is an unsigned long (or smaller), + * which is what the compiler does when it sees ternary operator with 2 + * different return types (picks the largest type to make sure there's no + * loss). */ -#define __DIVIDE(dividend, divisor) ({ \ - sizeof(dividend) == sizeof(u32) ? \ - DIV_ROUND_UP(dividend, divisor) : \ - DIV_ROUND_UP_ULL(dividend, divisor); \ - }) +#define __DIVIDE(dividend, divisor) ({ \ + (__typeof__(dividend))(sizeof(dividend) <= sizeof(unsigned long) ? \ + DIV_ROUND_UP(dividend, divisor) : \ + DIV_ROUND_UP_ULL(dividend, divisor)); \ + }) #define PSEC_TO_NSEC(x) __DIVIDE(x, 1000) #define PSEC_TO_MSEC(x) __DIVIDE(x, 1000000000) diff --git a/include/linux/node.h b/include/linux/node.h index 41f171861dcc..6d336e38d155 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -32,9 +32,11 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages); +extern int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool check_nid); #else -static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages) +static inline int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool check_nid) { return 0; } @@ -57,7 +59,7 @@ static inline int register_one_node(int nid) if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages); + error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages, true); } return error; diff --git a/include/linux/nospec.h b/include/linux/nospec.h index e791ebc65c9c..0c5ef54fd416 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -7,6 +7,8 @@ #define _LINUX_NOSPEC_H #include <asm/barrier.h> +struct task_struct; + /** * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise * @index: array element index @@ -55,4 +57,12 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, \ (typeof(_i)) (_i & _mask); \ }) + +/* Speculation control prctl */ +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which); +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl); +/* Speculation control for seccomp enforced mitigation */ +void arch_seccomp_spec_mitigate(struct task_struct *task); + #endif /* _LINUX_NOSPEC_H */ diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index b1f37a89e368..79b99d653e03 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -133,7 +133,7 @@ static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, lock_release(&sem->rw_sem.dep_map, 1, ip); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER if (!read) - sem->rw_sem.owner = NULL; + sem->rw_sem.owner = RWSEM_OWNER_UNKNOWN; #endif } @@ -141,6 +141,10 @@ static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip); +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER + if (!read) + sem->rw_sem.owner = current; +#endif } #endif diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 56707d5ff6ad..ab93b6eae696 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -44,6 +44,12 @@ struct rw_semaphore { #endif }; +/* + * Setting bit 0 of the owner field with other non-zero bits will indicate + * that the rwsem is writer-owned with an unknown owner. + */ +#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-1L) + extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); diff --git a/include/linux/sched.h b/include/linux/sched.h index c2413703f45d..ca3f3eae8980 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1433,7 +1433,8 @@ static inline bool is_percpu_thread(void) #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ - +#define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ +#define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1458,6 +1459,13 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) +TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) +TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) +TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) + +TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index c723a5c4e3ff..e5320f6c8654 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -4,8 +4,9 @@ #include <uapi/linux/seccomp.h> -#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ - SECCOMP_FILTER_FLAG_LOG) +#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ + SECCOMP_FILTER_FLAG_LOG | \ + SECCOMP_FILTER_FLAG_SPEC_ALLOW) #ifdef CONFIG_SECCOMP |