diff options
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/blkdev.h | 16 | ||||
-rw-r--r-- | include/linux/bpf.h | 60 | ||||
-rw-r--r-- | include/linux/can/dev.h | 16 | ||||
-rw-r--r-- | include/linux/can/platform/sja1000.h | 2 | ||||
-rw-r--r-- | include/linux/cgroup.h | 1 | ||||
-rw-r--r-- | include/linux/efi.h | 3 | ||||
-rw-r--r-- | include/linux/fault-inject.h | 7 | ||||
-rw-r--r-- | include/linux/fortify-string.h | 13 | ||||
-rw-r--r-- | include/linux/fs.h | 8 | ||||
-rw-r--r-- | include/linux/fscache.h | 2 | ||||
-rw-r--r-- | include/linux/gfp.h | 18 | ||||
-rw-r--r-- | include/linux/intel-svm.h | 13 | ||||
-rw-r--r-- | include/linux/io-pgtable.h | 6 | ||||
-rw-r--r-- | include/linux/io_uring.h | 3 | ||||
-rw-r--r-- | include/linux/iommu.h | 128 | ||||
-rw-r--r-- | include/linux/kvm_host.h | 25 | ||||
-rw-r--r-- | include/linux/maple_tree.h | 7 | ||||
-rw-r--r-- | include/linux/mlx5/driver.h | 1 | ||||
-rw-r--r-- | include/linux/mm.h | 29 | ||||
-rw-r--r-- | include/linux/mmc/mmc.h | 2 | ||||
-rw-r--r-- | include/linux/pgtable.h | 18 | ||||
-rw-r--r-- | include/linux/ring_buffer.h | 2 | ||||
-rw-r--r-- | include/linux/skmsg.h | 2 | ||||
-rw-r--r-- | include/linux/slab.h | 23 | ||||
-rw-r--r-- | include/linux/swapops.h | 8 | ||||
-rw-r--r-- | include/linux/trace.h | 4 | ||||
-rw-r--r-- | include/linux/vfio.h | 1 |
27 files changed, 282 insertions, 136 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 50e358a19d98..891f8cbcd043 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -311,6 +311,13 @@ struct queue_limits { unsigned char discard_misaligned; unsigned char raid_partial_stripes_expensive; enum blk_zoned_model zoned; + + /* + * Drivers that set dma_alignment to less than 511 must be prepared to + * handle individual bvec's that are not a multiple of a SECTOR_SIZE + * due to possible offsets. + */ + unsigned int dma_alignment; }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, @@ -456,12 +463,6 @@ struct request_queue { unsigned long nr_requests; /* Max # of requests */ unsigned int dma_pad_mask; - /* - * Drivers that set dma_alignment to less than 511 must be prepared to - * handle individual bvec's that are not a multiple of a SECTOR_SIZE - * due to possible offsets. - */ - unsigned int dma_alignment; #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct blk_crypto_profile *crypto_profile; @@ -944,7 +945,6 @@ extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); -extern void blk_set_default_limits(struct queue_limits *lim); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); @@ -1324,7 +1324,7 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev) static inline int queue_dma_alignment(const struct request_queue *q) { - return q ? q->dma_alignment : 511; + return q ? q->limits.dma_alignment : 511; } static inline unsigned int bdev_dma_alignment(struct block_device *bdev) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0566705c1d4e..c1bd1bd10506 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -27,7 +27,7 @@ #include <linux/bpfptr.h> #include <linux/btf.h> #include <linux/rcupdate_trace.h> -#include <linux/init.h> +#include <linux/static_call.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -315,7 +315,7 @@ static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, b u32 next_off = map->off_arr->field_off[i]; memcpy(dst + curr_off, src + curr_off, next_off - curr_off); - curr_off += map->off_arr->field_sz[i]; + curr_off = next_off + map->off_arr->field_sz[i]; } memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); } @@ -344,7 +344,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) u32 next_off = map->off_arr->field_off[i]; memset(dst + curr_off, 0, next_off - curr_off); - curr_off += map->off_arr->field_sz[i]; + curr_off = next_off + map->off_arr->field_sz[i]; } memset(dst + curr_off, 0, map->value_size - curr_off); } @@ -954,6 +954,10 @@ struct bpf_dispatcher { void *rw_image; u32 image_off; struct bpf_ksym ksym; +#ifdef CONFIG_HAVE_STATIC_CALL + struct static_call_key *sc_key; + void *sc_tramp; +#endif }; static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( @@ -971,7 +975,33 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); -int __init bpf_arch_init_dispatcher_early(void *ip); + +/* + * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn + * indirection with a direct call to the bpf program. If the architecture does + * not have STATIC_CALL, avoid a double-indirection. + */ +#ifdef CONFIG_HAVE_STATIC_CALL + +#define __BPF_DISPATCHER_SC_INIT(_name) \ + .sc_key = &STATIC_CALL_KEY(_name), \ + .sc_tramp = STATIC_CALL_TRAMP_ADDR(_name), + +#define __BPF_DISPATCHER_SC(name) \ + DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func) + +#define __BPF_DISPATCHER_CALL(name) \ + static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func) + +#define __BPF_DISPATCHER_UPDATE(_d, _new) \ + __static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new)) + +#else +#define __BPF_DISPATCHER_SC_INIT(name) +#define __BPF_DISPATCHER_SC(name) +#define __BPF_DISPATCHER_CALL(name) bpf_func(ctx, insnsi) +#define __BPF_DISPATCHER_UPDATE(_d, _new) +#endif #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ @@ -984,34 +1014,21 @@ int __init bpf_arch_init_dispatcher_early(void *ip); .name = #_name, \ .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ }, \ + __BPF_DISPATCHER_SC_INIT(_name##_call) \ } -#define BPF_DISPATCHER_INIT_CALL(_name) \ - static int __init _name##_init(void) \ - { \ - return bpf_arch_init_dispatcher_early(_name##_func); \ - } \ - early_initcall(_name##_init) - -#ifdef CONFIG_X86_64 -#define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5))) -#else -#define BPF_DISPATCHER_ATTRIBUTES -#endif - #define DEFINE_BPF_DISPATCHER(name) \ - notrace BPF_DISPATCHER_ATTRIBUTES \ + __BPF_DISPATCHER_SC(name); \ noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ { \ - return bpf_func(ctx, insnsi); \ + return __BPF_DISPATCHER_CALL(name); \ } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ - BPF_DISPATCHER_INIT(bpf_dispatcher_##name); \ - BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name); + BPF_DISPATCHER_INIT(bpf_dispatcher_##name); #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ @@ -1019,6 +1036,7 @@ int __init bpf_arch_init_dispatcher_early(void *ip); const struct bpf_insn *insnsi, \ bpf_func_t bpf_func); \ extern struct bpf_dispatcher bpf_dispatcher_##name; + #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 58f5431a5559..982ba245eb41 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -152,6 +152,22 @@ static inline bool can_is_canxl_dev_mtu(unsigned int mtu) return (mtu >= CANXL_MIN_MTU && mtu <= CANXL_MAX_MTU); } +/* drop skb if it does not contain a valid CAN frame for sending */ +static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb) +{ + struct can_priv *priv = netdev_priv(dev); + + if (priv->ctrlmode & CAN_CTRLMODE_LISTENONLY) { + netdev_info_once(dev, + "interface in listen only mode, dropping skb\n"); + kfree_skb(skb); + dev->stats.tx_dropped++; + return true; + } + + return can_dropped_invalid_skb(dev, skb); +} + void can_setup(struct net_device *dev); struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, diff --git a/include/linux/can/platform/sja1000.h b/include/linux/can/platform/sja1000.h index 5755ae5a4712..6a869682c120 100644 --- a/include/linux/can/platform/sja1000.h +++ b/include/linux/can/platform/sja1000.h @@ -14,7 +14,7 @@ #define OCR_MODE_TEST 0x01 #define OCR_MODE_NORMAL 0x02 #define OCR_MODE_CLOCK 0x03 -#define OCR_MODE_MASK 0x07 +#define OCR_MODE_MASK 0x03 #define OCR_TX0_INVERT 0x04 #define OCR_TX0_PULLDOWN 0x08 #define OCR_TX0_PULLUP 0x10 diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 528bd44b59e2..2b7d077de7ef 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -68,6 +68,7 @@ struct css_task_iter { struct list_head iters_node; /* css_set->task_iters */ }; +extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; diff --git a/include/linux/efi.h b/include/linux/efi.h index 80f3c1c7827d..7603fc58c47c 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -389,6 +389,7 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) #define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) +#define EFI_SMBIOS_PROTOCOL_GUID EFI_GUID(0x03583ff6, 0xcb36, 0x4940, 0x94, 0x7e, 0xb9, 0xb3, 0x9f, 0x4a, 0xfa, 0xf7) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -1222,7 +1223,7 @@ efi_status_t efi_random_get_seed(void); arch_efi_call_virt_teardown(); \ }) -#define EFI_RANDOM_SEED_SIZE 64U +#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE struct linux_efi_random_seed { u32 size; diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 9f6e25467844..444236dadcf0 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -20,7 +20,6 @@ struct fault_attr { atomic_t space; unsigned long verbose; bool task_filter; - bool no_warn; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; @@ -32,6 +31,10 @@ struct fault_attr { struct dentry *dname; }; +enum fault_flags { + FAULT_NOWARN = 1 << 0, +}; + #define FAULT_ATTR_INITIALIZER { \ .interval = 1, \ .times = ATOMIC_INIT(1), \ @@ -40,11 +43,11 @@ struct fault_attr { .ratelimit_state = RATELIMIT_STATE_INIT_DISABLED, \ .verbose = 2, \ .dname = NULL, \ - .no_warn = false, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER int setup_fault_attr(struct fault_attr *attr, char *str); +bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags); bool should_fail(struct fault_attr *attr, ssize_t size); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 18a31b125f9d..1067a8450826 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -454,13 +454,18 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ - size_t __fortify_size = (size_t)(size); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, p_size, q_size, \ - p_size_field, q_size_field, #op), \ + const size_t __fortify_size = (size_t)(size); \ + const size_t __p_size = (p_size); \ + const size_t __q_size = (q_size); \ + const size_t __p_size_field = (p_size_field); \ + const size_t __q_size_field = (q_size_field); \ + WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + __q_size, __p_size_field, \ + __q_size_field, #op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ __fortify_size, \ "field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \ - p_size_field); \ + __p_size_field); \ __underlying_##op(p, q, __fortify_size); \ }) diff --git a/include/linux/fs.h b/include/linux/fs.h index e654435f1651..59ae95ddb679 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2089,6 +2089,14 @@ struct dir_context { */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) +/* + * These flags control the behavior of vfs_copy_file_range(). + * They are not available to the user via syscall. + * + * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops + */ +#define COPY_FILE_SPLICE (1 << 0) + struct iov_iter; struct io_uring_cmd; diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 36e5dd84cf59..8e312c8323a8 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -75,7 +75,7 @@ struct fscache_volume { atomic_t n_accesses; /* Number of cache accesses in progress */ unsigned int debug_id; unsigned int key_hash; /* Hash of key string */ - char *key; /* Volume ID, eg. "afs@example.com@1234" */ + u8 *key; /* Volume ID, eg. "afs@example.com@1234" */ struct list_head proc_link; /* Link in /proc/fs/fscache/volumes */ struct hlist_bl_node hash_link; /* Link in hash table */ struct work_struct work; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index ef4aea3b356e..65a78773dcca 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -210,6 +210,20 @@ alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct p return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array); } +static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) +{ + gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); + + if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN)) + return; + + if (node_online(this_node)) + return; + + pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node); + dump_stack(); +} + /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). @@ -218,7 +232,7 @@ 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((gfp_mask & __GFP_THISNODE) && !node_online(nid)); + warn_if_node_offline(nid, gfp_mask); return __alloc_pages(gfp_mask, order, nid, NULL); } @@ -227,7 +241,7 @@ static inline struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); - VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid)); + warn_if_node_offline(nid, gfp); return __folio_alloc(gfp, order, nid, NULL); } diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 207ef06ba3e1..f9a0d44f6fdb 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -13,17 +13,4 @@ #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) #define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) -/* - * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only - * for access to kernel addresses. No IOTLB flushes are automatically done - * for kernel mappings; it is valid only for access to the kernel's static - * 1:1 mapping of physical memory — not to vmalloc or even module mappings. - * A future API addition may permit the use of such ranges, by means of an - * explicit IOTLB flush call (akin to the DMA API's unmap method). - * - * It is unlikely that we will ever hook into flush_tlb_kernel_range() to - * do such IOTLB flushes automatically. - */ -#define SVM_FLAG_SUPERVISOR_MODE BIT(0) - #endif /* __INTEL_SVM_H__ */ diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 1f068dfdb140..1b7a44b35616 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -150,9 +150,7 @@ struct io_pgtable_cfg { /** * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers. * - * @map: Map a physically contiguous memory region. * @map_pages: Map a physically contiguous range of pages of the same size. - * @unmap: Unmap a physically contiguous memory region. * @unmap_pages: Unmap a range of virtually contiguous pages of the same size. * @iova_to_phys: Translate iova to physical address. * @@ -160,13 +158,9 @@ struct io_pgtable_cfg { * the same names. */ struct io_pgtable_ops { - int (*map)(struct io_pgtable_ops *ops, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp); int (*map_pages)(struct io_pgtable_ops *ops, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, int prot, gfp_t gfp, size_t *mapped); - size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, - size_t size, struct iommu_iotlb_gather *gather); size_t (*unmap_pages)(struct io_pgtable_ops *ops, unsigned long iova, size_t pgsize, size_t pgcount, struct iommu_iotlb_gather *gather); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 43bc8a2edccf..0ded9e271523 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -16,6 +16,9 @@ enum io_uring_cmd_flags { IO_URING_F_SQE128 = 4, IO_URING_F_CQE32 = 8, IO_URING_F_IOPOLL = 16, + + /* the request is executed from poll, it should not be freed */ + IO_URING_F_MULTISHOT = 32, }; struct io_uring_cmd { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 3c9da1f8979e..68d7d304cdb7 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -64,6 +64,8 @@ struct iommu_domain_geometry { #define __IOMMU_DOMAIN_PT (1U << 2) /* Domain is identity mapped */ #define __IOMMU_DOMAIN_DMA_FQ (1U << 3) /* DMA-API uses flush queue */ +#define __IOMMU_DOMAIN_SVA (1U << 4) /* Shared process address space */ + /* * This are the possible domain-types * @@ -77,6 +79,8 @@ struct iommu_domain_geometry { * certain optimizations for these domains * IOMMU_DOMAIN_DMA_FQ - As above, but definitely using batched TLB * invalidation. + * IOMMU_DOMAIN_SVA - DMA addresses are shared process addresses + * represented by mm_struct's. */ #define IOMMU_DOMAIN_BLOCKED (0U) #define IOMMU_DOMAIN_IDENTITY (__IOMMU_DOMAIN_PT) @@ -86,15 +90,27 @@ struct iommu_domain_geometry { #define IOMMU_DOMAIN_DMA_FQ (__IOMMU_DOMAIN_PAGING | \ __IOMMU_DOMAIN_DMA_API | \ __IOMMU_DOMAIN_DMA_FQ) +#define IOMMU_DOMAIN_SVA (__IOMMU_DOMAIN_SVA) struct iommu_domain { unsigned type; const struct iommu_domain_ops *ops; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ - iommu_fault_handler_t handler; - void *handler_token; struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; + enum iommu_page_response_code (*iopf_handler)(struct iommu_fault *fault, + void *data); + void *fault_data; + union { + struct { + iommu_fault_handler_t handler; + void *handler_token; + }; + struct { /* IOMMU_DOMAIN_SVA */ + struct mm_struct *mm; + int users; + }; + }; }; static inline bool iommu_is_dma_domain(struct iommu_domain *domain) @@ -214,15 +230,15 @@ struct iommu_iotlb_gather { * driver init to device driver init (default no) * @dev_enable/disable_feat: per device entries to enable/disable * iommu specific features. - * @sva_bind: Bind process address space to device - * @sva_unbind: Unbind process address space from device - * @sva_get_pasid: Get PASID associated to a SVA handle * @page_response: handle page request response * @def_domain_type: device default domain type, return value: * - IOMMU_DOMAIN_IDENTITY: must use an identity domain * - IOMMU_DOMAIN_DMA: must use a dma domain * - 0: use the default setting * @default_domain_ops: the default ops for domains + * @remove_dev_pasid: Remove any translation configurations of a specific + * pasid, so that any DMA transactions with this pasid + * will be blocked by the hardware. * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops */ @@ -247,16 +263,12 @@ struct iommu_ops { int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f); int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f); - struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm, - void *drvdata); - void (*sva_unbind)(struct iommu_sva *handle); - u32 (*sva_get_pasid)(struct iommu_sva *handle); - int (*page_response)(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); int (*def_domain_type)(struct device *dev); + void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid); const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; @@ -266,7 +278,20 @@ struct iommu_ops { /** * struct iommu_domain_ops - domain specific operations * @attach_dev: attach an iommu domain to a device + * Return: + * * 0 - success + * * EINVAL - can indicate that device and domain are incompatible due to + * some previous configuration of the domain, in which case the + * driver shouldn't log an error, since it is legitimate for a + * caller to test reuse of existing domains. Otherwise, it may + * still represent some other fundamental problem + * * ENOMEM - out of memory + * * ENOSPC - non-ENOMEM type of resource allocation failures + * * EBUSY - device is attached to a domain and cannot be changed + * * ENODEV - device specific errors, not able to be attached + * * <others> - treated as ENODEV by the caller. Use is discouraged * @detach_dev: detach an iommu domain from a device + * @set_dev_pasid: set an iommu domain to a pasid of device * @map: map a physically contiguous memory region to an iommu domain * @map_pages: map a physically contiguous set of pages of the same size to * an iommu domain. @@ -287,6 +312,8 @@ struct iommu_ops { struct iommu_domain_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); void (*detach_dev)(struct iommu_domain *domain, struct device *dev); + int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev, + ioasid_t pasid); int (*map)(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp); @@ -322,12 +349,14 @@ struct iommu_domain_ops { * @list: Used by the iommu-core to keep a list of registered iommus * @ops: iommu-ops for talking to this iommu * @dev: struct device for sysfs handling + * @max_pasids: number of supported PASIDs */ struct iommu_device { struct list_head list; const struct iommu_ops *ops; struct fwnode_handle *fwnode; struct device *dev; + u32 max_pasids; }; /** @@ -366,6 +395,7 @@ struct iommu_fault_param { * @fwspec: IOMMU fwspec data * @iommu_dev: IOMMU device this device is linked to * @priv: IOMMU Driver private data + * @max_pasids: number of PASIDs this device can consume * * TODO: migrate other per device data pointers under iommu_dev_data, e.g. * struct iommu_group *iommu_group; @@ -377,6 +407,7 @@ struct dev_iommu { struct iommu_fwspec *fwspec; struct iommu_device *iommu_dev; void *priv; + u32 max_pasids; }; int iommu_device_register(struct iommu_device *iommu, @@ -622,6 +653,7 @@ struct iommu_fwspec { */ struct iommu_sva { struct device *dev; + struct iommu_domain *domain; }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, @@ -663,12 +695,6 @@ void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); -struct iommu_sva *iommu_sva_bind_device(struct device *dev, - struct mm_struct *mm, - void *drvdata); -void iommu_sva_unbind_device(struct iommu_sva *handle); -u32 iommu_sva_get_pasid(struct iommu_sva *handle); - int iommu_device_use_default_domain(struct device *dev); void iommu_device_unuse_default_domain(struct device *dev); @@ -676,6 +702,15 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); void iommu_group_release_dma_owner(struct iommu_group *group); bool iommu_group_dma_owner_claimed(struct iommu_group *group); +struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, + struct mm_struct *mm); +int iommu_attach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); +void iommu_detach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); +struct iommu_domain * +iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, + unsigned int type); #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; @@ -995,21 +1030,6 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) return -ENODEV; } -static inline struct iommu_sva * -iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) -{ - return NULL; -} - -static inline void iommu_sva_unbind_device(struct iommu_sva *handle) -{ -} - -static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) -{ - return IOMMU_PASID_INVALID; -} - static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { return NULL; @@ -1038,6 +1058,30 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) { return false; } + +static inline struct iommu_domain * +iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm) +{ + return NULL; +} + +static inline int iommu_attach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid) +{ + return -ENODEV; +} + +static inline void iommu_detach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid) +{ +} + +static inline struct iommu_domain * +iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, + unsigned int type) +{ + return NULL; +} #endif /* CONFIG_IOMMU_API */ /** @@ -1099,4 +1143,26 @@ static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_m #endif /* CONFIG_IOMMU_DMA */ +#ifdef CONFIG_IOMMU_SVA +struct iommu_sva *iommu_sva_bind_device(struct device *dev, + struct mm_struct *mm); +void iommu_sva_unbind_device(struct iommu_sva *handle); +u32 iommu_sva_get_pasid(struct iommu_sva *handle); +#else +static inline struct iommu_sva * +iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) +{ + return NULL; +} + +static inline void iommu_sva_unbind_device(struct iommu_sva *handle) +{ +} + +static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) +{ + return IOMMU_PASID_INVALID; +} +#endif /* CONFIG_IOMMU_SVA */ + #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 00c3448ba7f8..637a60607c7d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -776,6 +776,7 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + bool override_halt_poll_ns; unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool vm_bugged; @@ -1240,8 +1241,18 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); /** - * kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a - * given guest physical address. + * kvm_gpc_init - initialize gfn_to_pfn_cache. + * + * @gpc: struct gfn_to_pfn_cache object. + * + * This sets up a gfn_to_pfn_cache by initializing locks. Note, the cache must + * be zero-allocated (or zeroed by the caller before init). + */ +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest + * physical address. * * @kvm: pointer to kvm instance. * @gpc: struct gfn_to_pfn_cache object. @@ -1265,9 +1276,9 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before * accessing the target page. */ -int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, - gpa_t gpa, unsigned long len); +int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len); /** * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. @@ -1324,7 +1335,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); /** - * kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache. + * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. * * @kvm: pointer to kvm instance. * @gpc: struct gfn_to_pfn_cache object. @@ -1332,7 +1343,7 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); * This removes a cache from the @kvm's list to be processed on MMU notifier * invocation. */ -void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); +void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 2effab72add1..e594db58a0f1 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -638,6 +638,12 @@ static inline void mt_set_in_rcu(struct maple_tree *mt) } } +static inline unsigned int mt_height(const struct maple_tree *mt) + +{ + return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET; +} + void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max); @@ -664,6 +670,7 @@ extern atomic_t maple_tree_tests_passed; void mt_dump(const struct maple_tree *mt); void mt_validate(struct maple_tree *mt); +void mt_cache_shrink(void); #define MT_BUG_ON(__tree, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index af2ceb4160bc..06cbad166225 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -981,6 +981,7 @@ struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; u16 opcode; /* cmd opcode */ + u16 op_mod; /* cmd op_mod */ void *out; /* pointer to the cmd output buffer */ }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 8bbcccbc5565..974ccca609d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1852,6 +1852,25 @@ static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodem __show_free_areas(flags, nodemask, MAX_NR_ZONES - 1); } +/* + * Parameter block passed down to zap_pte_range in exceptional cases. + */ +struct zap_details { + struct folio *single_folio; /* Locked folio to be unmapped */ + bool even_cows; /* Zap COWed private pages too? */ + zap_flags_t zap_flags; /* Extra flags for zapping */ +}; + +/* + * Whether to drop the pte markers, for example, the uffd-wp information for + * file-backed memory. This should only be specified when we will completely + * drop the page in the mm, either by truncation or unmapping of the vma. By + * default, the flag is not set. + */ +#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) +/* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ +#define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) + #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else @@ -1869,6 +1888,8 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); +void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, + unsigned long size, struct zap_details *details); void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); @@ -3467,12 +3488,4 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif -/* - * Whether to drop the pte markers, for example, the uffd-wp information for - * file-backed memory. This should only be specified when we will completely - * drop the page in the mm, either by truncation or unmapping of the vma. By - * default, the flag is not set. - */ -#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) - #endif /* _LINUX_MM_H */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 9c50bc40f8ff..6f7993803ee7 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -451,7 +451,7 @@ static inline bool mmc_ready_for_data(u32 status) #define MMC_SECURE_TRIM1_ARG 0x80000001 #define MMC_SECURE_TRIM2_ARG 0x80008000 #define MMC_SECURE_ARGS 0x80000000 -#define MMC_TRIM_ARGS 0x00008001 +#define MMC_TRIM_OR_DISCARD_ARGS 0x00008003 #define mmc_driver_type_mask(n) (1 << (n)) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a108b60a6962..5f0d7d0b9471 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -165,6 +165,13 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr) return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); } +#ifndef pmd_young +static inline int pmd_young(pmd_t pmd) +{ + return 0; +} +#endif + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, @@ -260,6 +267,17 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef arch_has_hw_nonleaf_pmd_young +/* + * Return whether the accessed bit in non-leaf PMD entries is supported on the + * local CPU. + */ +static inline bool arch_has_hw_nonleaf_pmd_young(void) +{ + return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG); +} +#endif + #ifndef arch_has_hw_pte_young /* * Return whether the accessed bit is supported on the local CPU. diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 2504df9a0453..3c7d295746f6 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -100,7 +100,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, - struct file *filp, poll_table *poll_table); + struct file *filp, poll_table *poll_table, int full); void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); #define RING_BUFFER_ALL_CPUS -1 diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 48f4b645193b..70d6cb94e580 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -376,7 +376,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) } struct sk_psock *sk_psock_init(struct sock *sk, int node); -void sk_psock_stop(struct sk_psock *psock, bool wait); +void sk_psock_stop(struct sk_psock *psock); #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); diff --git a/include/linux/slab.h b/include/linux/slab.h index 90877fcde70b..45efc6c553b8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -470,35 +470,12 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignm void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; -#ifdef CONFIG_TRACING void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_kmalloc_alignment __alloc_size(4); -#else /* CONFIG_TRACING */ -/* Save a function call when CONFIG_TRACING=n */ -static __always_inline __alloc_size(3) -void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) -{ - void *ret = kmem_cache_alloc(s, flags); - - ret = kasan_kmalloc(s, ret, size, flags); - return ret; -} - -static __always_inline __alloc_size(4) -void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) -{ - void *ret = kmem_cache_alloc_node(s, gfpflags, node); - - ret = kasan_kmalloc(s, ret, size, gfpflags); - return ret; -} -#endif /* CONFIG_TRACING */ - void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 86b95ccb81bb..b07b277d6a16 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -33,11 +33,13 @@ * can use the extra bits to store other information besides PFN. */ #ifdef MAX_PHYSMEM_BITS -#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #else /* MAX_PHYSMEM_BITS */ -#define SWP_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT) +#define SWP_PFN_BITS min_t(int, \ + sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \ + SWP_TYPE_SHIFT) #endif /* MAX_PHYSMEM_BITS */ -#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) +#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) /** * Migration swap entry specific bitfield definitions. Layout: diff --git a/include/linux/trace.h b/include/linux/trace.h index b5e16e438448..80ffda871749 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -26,13 +26,13 @@ struct trace_export { int flags; }; +struct trace_array; + #ifdef CONFIG_TRACING int register_ftrace_export(struct trace_export *export); int unregister_ftrace_export(struct trace_export *export); -struct trace_array; - void trace_printk_init_buffers(void); __printf(3, 4) int trace_array_printk(struct trace_array *tr, unsigned long ip, diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e7cebeb875dd..fdd393f70b19 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -189,6 +189,7 @@ int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); +unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set); int vfio_mig_get_next_state(struct vfio_device *device, enum vfio_device_mig_state cur_fsm, |