diff options
Diffstat (limited to 'include')
55 files changed, 613 insertions, 77 deletions
diff --git a/include/kunit/test.h b/include/kunit/test.h index db1b0ae666c4..df60be7e22ca 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -1105,7 +1105,7 @@ do { \ KUNIT_ASSERTION(test, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \ + KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \ assert_type, \ #op, \ #left, \ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 639cae2c158b..033eb5f73b65 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1073,12 +1073,15 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, * file system requests. */ static inline unsigned int blk_max_size_offset(struct request_queue *q, - sector_t offset) -{ - unsigned int chunk_sectors = q->limits.chunk_sectors; - - if (!chunk_sectors) - return q->limits.max_sectors; + sector_t offset, + unsigned int chunk_sectors) +{ + if (!chunk_sectors) { + if (q->limits.chunk_sectors) + chunk_sectors = q->limits.chunk_sectors; + else + return q->limits.max_sectors; + } if (likely(is_power_of_2(chunk_sectors))) chunk_sectors -= offset & (chunk_sectors - 1); @@ -1101,7 +1104,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); - return min(blk_max_size_offset(q, offset), + return min(blk_max_size_offset(q, offset, 0), blk_queue_get_max_sectors(q, req_op(rq))); } diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 9903088891fa..2696eb0fc149 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -12,6 +12,9 @@ #define BOOTCONFIG_MAGIC "#BOOTCONFIG\n" #define BOOTCONFIG_MAGIC_LEN 12 +#define BOOTCONFIG_ALIGN_SHIFT 2 +#define BOOTCONFIG_ALIGN (1 << BOOTCONFIG_ALIGN_SHIFT) +#define BOOTCONFIG_ALIGN_MASK (BOOTCONFIG_ALIGN - 1) /* XBC tree node */ struct xbc_node { diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index e3a0be2c90ad..7bb66e15b481 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -77,4 +77,9 @@ #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr) #define __static_assert(expr, msg, ...) _Static_assert(expr, msg) +#ifdef __GENKSYMS__ +/* genksyms gets confused by _Static_assert */ +#define _Static_assert(expr, ...) +#endif + #endif /* _LINUX_BUILD_BUG_H */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index dd7233c48bf3..98cff1b4b088 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -8,8 +8,10 @@ + __clang_patchlevel__) #if CLANG_VERSION < 100001 +#ifndef __BPF_TRACING__ # error Sorry, your version of Clang is too old - please use 10.0.1 or newer. #endif +#endif /* Compiler specific definitions for Clang compiler */ diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 46c3d691f677..de51c1bef27d 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -104,6 +104,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } +#if defined(CONFIG_UM) || defined(CONFIG_IA64) /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its @@ -118,5 +119,26 @@ elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset); extern int elf_core_write_extra_data(struct coredump_params *cprm); extern size_t elf_core_extra_data_size(void); +#else +static inline Elf_Half elf_core_extra_phdrs(void) +{ + return 0; +} + +static inline int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) +{ + return 1; +} + +static inline int elf_core_write_extra_data(struct coredump_params *cprm) +{ + return 1; +} + +static inline size_t elf_core_extra_data_size(void) +{ + return 0; +} +#endif #endif /* _LINUX_ELFCORE_H */ diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index dc4fd8a6644d..fa0a524baed0 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -41,6 +41,7 @@ struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); +void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); DECLARE_PER_CPU(int, eventfd_wake_count); @@ -82,6 +83,11 @@ static inline bool eventfd_signal_count(void) return false; } +static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) +{ + +} + #endif #endif /* _LINUX_EVENTFD_H */ diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 5968df82b991..41a1bab98b7e 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -50,10 +50,6 @@ #define ZYNQMP_PM_CAPABILITY_WAKEUP 0x4U #define ZYNQMP_PM_CAPABILITY_UNUSABLE 0x8U -/* Feature check status */ -#define PM_FEATURE_INVALID -1 -#define PM_FEATURE_UNCHECKED 0 - /* * Firmware FPGA Manager flags * XILINX_ZYNQMP_PM_FPGA_FULL: FPGA full reconfiguration diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index fbf5b3e7707e..d956987ed032 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -798,7 +798,6 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; extern int intel_iommu_enabled; -extern int intel_iommu_tboot_noforce; extern int intel_iommu_gfx_mapped; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 71535e87109f..ea5a337e0f8b 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -384,11 +384,19 @@ extern void irq_domain_associate_many(struct irq_domain *domain, extern void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq); -extern unsigned int irq_create_mapping(struct irq_domain *host, - irq_hw_number_t hwirq); +extern unsigned int irq_create_mapping_affinity(struct irq_domain *host, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity); extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec); extern void irq_dispose_mapping(unsigned int virq); +static inline unsigned int irq_create_mapping(struct irq_domain *host, + irq_hw_number_t hwirq) +{ + return irq_create_mapping_affinity(host, hwirq, NULL); +} + + /** * irq_linear_revmap() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 1c49fd62ff2e..578ff196b3ce 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -401,7 +401,7 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** - * struct jbd_inode - The jbd_inode type is the structure linking inodes in + * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h new file mode 100644 index 000000000000..120e5e90fa1d --- /dev/null +++ b/include/linux/kvm_dirty_ring.h @@ -0,0 +1,103 @@ +#ifndef KVM_DIRTY_RING_H +#define KVM_DIRTY_RING_H + +#include <linux/kvm.h> + +/** + * kvm_dirty_ring: KVM internal dirty ring structure + * + * @dirty_index: free running counter that points to the next slot in + * dirty_ring->dirty_gfns, where a new dirty page should go + * @reset_index: free running counter that points to the next dirty page + * in dirty_ring->dirty_gfns for which dirty trap needs to + * be reenabled + * @size: size of the compact list, dirty_ring->dirty_gfns + * @soft_limit: when the number of dirty pages in the list reaches this + * limit, vcpu that owns this ring should exit to userspace + * to allow userspace to harvest all the dirty pages + * @dirty_gfns: the array to keep the dirty gfns + * @index: index of this dirty ring + */ +struct kvm_dirty_ring { + u32 dirty_index; + u32 reset_index; + u32 size; + u32 soft_limit; + struct kvm_dirty_gfn *dirty_gfns; + int index; +}; + +#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0) +/* + * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should + * not be included as well, so define these nop functions for the arch. + */ +static inline u32 kvm_dirty_ring_get_rsvd_entries(void) +{ + return 0; +} + +static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, + int index, u32 size) +{ + return 0; +} + +static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm) +{ + return NULL; +} + +static inline int kvm_dirty_ring_reset(struct kvm *kvm, + struct kvm_dirty_ring *ring) +{ + return 0; +} + +static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, + u32 slot, u64 offset) +{ +} + +static inline struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, + u32 offset) +{ + return NULL; +} + +static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) +{ +} + +static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) +{ + return true; +} + +#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ + +u32 kvm_dirty_ring_get_rsvd_entries(void); +int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); +struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm); + +/* + * called with kvm->slots_lock held, returns the number of + * processed pages. + */ +int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring); + +/* + * returns =0: successfully pushed + * <0: unable to push, need to wait + */ +void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset); + +/* for use in vm_operations_struct */ +struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset); + +void kvm_dirty_ring_free(struct kvm_dirty_ring *ring); +bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring); + +#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ + +#endif /* KVM_DIRTY_RING_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7f2e2a09ebbd..f3b1013fb22c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -34,6 +34,7 @@ #include <linux/kvm_types.h> #include <asm/kvm_host.h> +#include <linux/kvm_dirty_ring.h> #ifndef KVM_MAX_VCPU_ID #define KVM_MAX_VCPU_ID KVM_MAX_VCPUS @@ -319,6 +320,7 @@ struct kvm_vcpu { bool preempted; bool ready; struct kvm_vcpu_arch arch; + struct kvm_dirty_ring dirty_ring; }; static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) @@ -349,6 +351,11 @@ struct kvm_memory_slot { u16 as_id; }; +static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot) +{ + return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; +} + static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) { return ALIGN(memslot->npages, BITS_PER_LONG) / 8; @@ -505,6 +512,7 @@ struct kvm { struct srcu_struct irq_srcu; pid_t userspace_pid; unsigned int max_halt_poll_ns; + u32 dirty_ring_size; }; #define kvm_err(fmt, ...) \ @@ -792,13 +800,12 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, offset_in_page(__gpa), v); \ }) -int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); -void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); @@ -1478,4 +1485,14 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ +/* + * This defines how many reserved entries we want to keep before we + * kick the vcpu to the userspace to avoid dirty ring full. This + * value can be tuned to higher if e.g. PML is enabled on the host. + */ +#define KVM_DIRTY_RING_RSVD_ENTRIES 64 + +/* Max number of entries allowed for each kvm dirty ring */ +#define KVM_DIRTY_RING_MAX_ENTRIES 65536 + #endif diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a80c59af2c60..922a7f600465 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -282,20 +282,6 @@ struct mem_cgroup { MEMCG_PADDING(_pad1_); - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - struct task_struct *move_lock_task; - - /* Legacy local VM stats and events */ - struct memcg_vmstats_percpu __percpu *vmstats_local; - - /* Subtree VM stats and events (batched updates) */ - struct memcg_vmstats_percpu __percpu *vmstats_percpu; - - MEMCG_PADDING(_pad2_); - atomic_long_t vmstats[MEMCG_NR_STAT]; atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; @@ -317,6 +303,20 @@ struct mem_cgroup { struct list_head objcg_list; /* list of inherited objcgs */ #endif + MEMCG_PADDING(_pad2_); + + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + struct task_struct *move_lock_task; + + /* Legacy local VM stats and events */ + struct memcg_vmstats_percpu __percpu *vmstats_local; + + /* Subtree VM stats and events (batched updates) */ + struct memcg_vmstats_percpu __percpu *vmstats_percpu; + #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index d65c6fdc5cfc..551093b74596 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -281,20 +281,6 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ -#ifdef CONFIG_NUMA -extern int memory_add_physaddr_to_nid(u64 start); -extern int phys_to_target_node(u64 start); -#else -static inline int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -static inline int phys_to_target_node(u64 start) -{ - return 0; -} -#endif - #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a092346c7b2d..233352447b1a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1223,6 +1223,11 @@ enum mlx5_fc_bulk_alloc_bitmask { #define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum)) +enum { + MLX5_STEERING_FORMAT_CONNECTX_5 = 0, + MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, +}; + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1521,7 +1526,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 general_obj_types[0x40]; - u8 reserved_at_440[0x20]; + u8 reserved_at_440[0x4]; + u8 steering_format_version[0x4]; + u8 create_qp_start_hint[0x18]; u8 reserved_at_460[0x3]; u8 log_max_uctx[0x5]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 964b494b0e8d..7c3da0e1ea9d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2813,9 +2813,21 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); + int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); + +static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +{ + int ret; + + ret = __dev_direct_xmit(skb, queue_id); + if (!dev_xmit_complete(ret)) + kfree_skb(skb); + return ret; +} + int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); @@ -3137,6 +3149,11 @@ static inline bool dev_validate_header(const struct net_device *dev, return false; } +static inline bool dev_has_header(const struct net_device *dev) +{ + return dev->header_ops && dev->header_ops->create; +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len, int size); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5deb099d156d..8ebb64193757 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -227,7 +227,7 @@ struct xt_table { unsigned int valid_hooks; /* Man behind the curtain... */ - struct xt_table_info *private; + struct xt_table_info __rcu *private; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -448,6 +448,9 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); +struct xt_table_info +*xt_table_get_private_protected(const struct xt_table *table); + #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index c32c15216da3..f0373a6cb5fb 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -55,6 +55,7 @@ struct nfs_page { unsigned short wb_nio; /* Number of I/O attempts */ }; +struct nfs_pgio_mirror; struct nfs_pageio_descriptor; struct nfs_pageio_ops { void (*pg_init)(struct nfs_pageio_descriptor *, struct nfs_page *); @@ -64,6 +65,9 @@ struct nfs_pageio_ops { unsigned int (*pg_get_mirror_count)(struct nfs_pageio_descriptor *, struct nfs_page *); void (*pg_cleanup)(struct nfs_pageio_descriptor *); + struct nfs_pgio_mirror * + (*pg_get_mirror)(struct nfs_pageio_descriptor *, u32); + u32 (*pg_set_mirror)(struct nfs_pageio_descriptor *, u32); }; struct nfs_rw_ops { diff --git a/include/linux/numa.h b/include/linux/numa.h index 8cb33ccfb671..cb44cfe2b725 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -21,13 +21,41 @@ #endif #ifdef CONFIG_NUMA +#include <linux/printk.h> +#include <asm/sparsemem.h> + /* Generic implementation available */ int numa_map_to_online_node(int node); -#else + +#ifndef memory_add_physaddr_to_nid +static inline int memory_add_physaddr_to_nid(u64 start) +{ + pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#ifndef phys_to_target_node +static inline int phys_to_target_node(u64 start) +{ + pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#else /* !CONFIG_NUMA */ static inline int numa_map_to_online_node(int node) { return NUMA_NO_NODE; } +static inline int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +static inline int phys_to_target_node(u64 start) +{ + return 0; +} #endif #endif /* _LINUX_NUMA_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e1e19c1f9ec9..d5570deff400 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -906,6 +906,8 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { + if (xas_retry(&xas, page)) + continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 71125a4676c4..e237004d498d 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,6 +1427,19 @@ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ +#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) +#ifdef CONFIG_PHYS_ADDR_T_64BIT +/* + * ZSMALLOC needs to know the highest PFN on 32-bit architectures + * with physical address space extension, but falls back to + * BITS_PER_LONG otherwise. + */ +#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition +#else +#define MAX_POSSIBLE_PHYSMEM_BITS 32 +#endif +#endif + #ifndef has_transparent_hugepage #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index c59999ce044e..240dce553a0b 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -50,6 +50,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_MODULE_QUIRK_ENA_RESETDONE BIT(25) #define SYSC_MODULE_QUIRK_PRUSS BIT(24) #define SYSC_MODULE_QUIRK_DSS_RESET BIT(23) #define SYSC_MODULE_QUIRK_RTC_UNLOCK BIT(22) diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 4b708f4e8eed..b492ae00cc90 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -387,6 +387,27 @@ static inline int pm_runtime_get_sync(struct device *dev) } /** + * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. + * @dev: Target device. + * + * Resume @dev synchronously and if that is successful, increment its runtime + * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been + * incremented or a negative error code otherwise. + */ +static inline int pm_runtime_resume_and_get(struct device *dev) +{ + int ret; + + ret = __pm_runtime_resume(dev, RPM_GET_PUT); + if (ret < 0) { + pm_runtime_put_noidle(dev); + return ret; + } + + return 0; +} + +/** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * diff --git a/include/linux/sched.h b/include/linux/sched.h index 063cd120b459..76cd21fa5501 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -552,7 +552,6 @@ struct sched_dl_entity { * overruns. */ unsigned int dl_throttled : 1; - unsigned int dl_boosted : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; @@ -571,6 +570,15 @@ struct sched_dl_entity { * time. */ struct hrtimer inactive_timer; + +#ifdef CONFIG_RT_MUTEXES + /* + * Priority Inheritance. When a DEADLINE scheduling entity is boosted + * pi_se points to the donor, otherwise points to the dl_se it belongs + * to (the original one/itself). + */ + struct sched_dl_entity *pi_se; +#endif }; #ifdef CONFIG_UCLAMP_TASK @@ -770,7 +778,6 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; - unsigned sched_remote_wakeup:1; #ifdef CONFIG_PSI unsigned sched_psi_wake_requeue:1; #endif @@ -780,6 +787,21 @@ struct task_struct { /* Unserialized, strictly 'current' */ + /* + * This field must not be in the scheduler word above due to wakelist + * queueing no longer being serialized by p->on_cpu. However: + * + * p->XXX = X; ttwu() + * schedule() if (p->on_rq && ..) // false + * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true + * deactivate_task() ttwu_queue_wakelist()) + * p->on_rq = 0; p->sched_remote_wakeup = Y; + * + * guarantees all stores of 'current' are visible before + * ->sched_remote_wakeup gets used, so it can be in this word. + */ + unsigned sched_remote_wakeup:1; + /* Bit to tell LSMs we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; diff --git a/include/linux/security.h b/include/linux/security.h index bc2725491560..39642626a707 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -869,7 +869,7 @@ static inline int security_inode_killpriv(struct dentry *dentry) static inline int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { - return -EOPNOTSUPP; + return cap_inode_getsecurity(inode, name, buffer, alloc); } static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 99380c0825db..b390fdac1587 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -734,6 +734,25 @@ static inline struct spi_controller *spi_alloc_slave(struct device *host, return __spi_alloc_controller(host, size, true); } +struct spi_controller *__devm_spi_alloc_controller(struct device *dev, + unsigned int size, + bool slave); + +static inline struct spi_controller *devm_spi_alloc_master(struct device *dev, + unsigned int size) +{ + return __devm_spi_alloc_controller(dev, size, false); +} + +static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev, + unsigned int size) +{ + if (!IS_ENABLED(CONFIG_SPI_SLAVE)) + return NULL; + + return __devm_spi_alloc_controller(dev, size, true); +} + extern int spi_register_controller(struct spi_controller *ctlr); extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 628e28903b8b..15ca6b4167cc 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -170,6 +170,7 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; + u32 addr64; u32 rx_queues_to_use; u32 tx_queues_to_use; u8 rx_sched_algorithm; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 3bb72266a75a..fbdc65782195 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -5,6 +5,7 @@ #include <linux/dma-direction.h> #include <linux/init.h> #include <linux/types.h> +#include <linux/limits.h> struct device; struct page; diff --git a/include/linux/tty.h b/include/linux/tty.h index a99e9b8e4e31..eb33d948788c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -306,6 +306,10 @@ struct tty_struct { struct termiox *termiox; /* May be NULL for unsupported */ char name[64]; struct pid *pgrp; /* Protected by ctrl lock */ + /* + * Writes protected by both ctrl lock and legacy mutex, readers must use + * at least one of them. + */ struct pid *session; unsigned long flags; int count; diff --git a/include/linux/wait.h b/include/linux/wait.h index 27fb99cfeb02..fe10e8570a52 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -22,6 +22,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int #define WQ_FLAG_BOOKMARK 0x04 #define WQ_FLAG_CUSTOM 0x08 #define WQ_FLAG_DONE 0x10 +#define WQ_FLAG_PRIORITY 0x20 /* * A single wait-queue entry structure: @@ -164,11 +165,20 @@ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_add(&wq_entry->entry, &wq_head->head); + struct list_head *head = &wq_head->head; + struct wait_queue_entry *wq; + + list_for_each_entry(wq, &wq_head->head, entry) { + if (!(wq->flags & WQ_FLAG_PRIORITY)) + break; + head = &wq->entry; + } + list_add(&wq_entry->entry, head); } /* diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 0fdbf653b173..4807ca4d52e0 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -20,7 +20,6 @@ * zsmalloc mapping modes * * NOTE: These only make a difference when a mapped object spans pages. - * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected. */ enum zs_mapmode { ZS_MM_RW, /* normal read-write mapping */ diff --git a/include/net/bonding.h b/include/net/bonding.h index 7d132cc1e584..adc3da776970 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -86,10 +86,8 @@ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) -#ifdef CONFIG_XFRM_OFFLOAD #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) -#endif /* CONFIG_XFRM_OFFLOAD */ #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; @@ -185,6 +183,11 @@ struct slave { struct rtnl_link_stats64 slave_stats; }; +static inline struct slave *to_slave(struct kobject *kobj) +{ + return container_of(kobj, struct slave, kobj); +} + struct bond_up_slave { unsigned int count; struct rcu_head rcu; @@ -750,6 +753,9 @@ extern struct bond_parm_tbl ad_select_tbl[]; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; +/* exported from bond_sysfs_slave.c */ +extern const struct sysfs_ops slave_sysfs_ops; + static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { atomic_long_inc(&dev->tx_dropped); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index e1eaf1780288..563457fec557 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -107,7 +107,7 @@ static inline int IP_ECN_set_ect1(struct iphdr *iph) if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) return 0; - check += (__force u16)htons(0x100); + check += (__force u16)htons(0x1); iph->check = (__force __sum16)(check + (check>=0xFFFF)); iph->tos ^= INET_ECN_MASK; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 92560974ea67..ca6a3ea9057e 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -247,8 +247,9 @@ void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long high_limit); int inet_hashinfo2_init_mod(struct inet_hashinfo *h); -bool inet_ehash_insert(struct sock *sk, struct sock *osk); -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); +bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk); +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, + bool *found_dup_sk); int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 02ccd32542d0..61620677b034 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -478,9 +478,11 @@ static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { - memcpy(ip_tunnel_info_opts(info), from, len); info->options_len = len; - info->key.tun_flags |= flags; + if (len > 0) { + memcpy(ip_tunnel_info_opts(info), from, len); + info->key.tun_flags |= flags; + } } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) @@ -526,7 +528,6 @@ static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, __be16 flags) { info->options_len = 0; - info->key.tun_flags |= flags; } #endif /* CONFIG_INET */ diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index a21e8b1381a1..851029ecff13 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -108,5 +108,35 @@ out_rcu_unlock: rcu_read_unlock(); inet_frag_put(&fq->q); } + +/* Check if the upper layer header is truncated in the first fragment. */ +static inline bool +ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp) +{ + u8 nexthdr = *nexthdrp; + __be16 frag_off; + int offset; + + offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); + if (offset < 0 || (frag_off & htons(IP6_OFFSET))) + return false; + switch (nexthdr) { + case NEXTHDR_TCP: + offset += sizeof(struct tcphdr); + break; + case NEXTHDR_UDP: + offset += sizeof(struct udphdr); + break; + case NEXTHDR_ICMP: + offset += sizeof(struct icmp6hdr); + break; + default: + offset += 1; + } + if (offset > skb->len) + return true; + return false; +} + #endif #endif diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 81ee17594c32..22ced1381ede 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -204,6 +204,7 @@ struct neigh_table { int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); + int (*is_multicast)(const void *pkey); bool (*allow_add)(const struct net_device *dev, struct netlink_ext_ack *extack); char *id; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 55b4cadf290a..c1c0a4ff92ae 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1524,4 +1524,8 @@ void __init nft_chain_route_init(void); void nft_chain_route_fini(void); void nf_tables_trans_destroy_flush_work(void); + +int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); +__be64 nf_jiffies64_to_msecs(u64 input); + #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index ea7d1d78b92d..1d34fe154fe0 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -37,6 +37,7 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx, struct nft_flow_key { struct flow_dissector_key_basic basic; + struct flow_dissector_key_control control; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; @@ -62,6 +63,9 @@ struct nft_flow_rule { #define NFT_OFFLOAD_F_ACTION (1 << 0) +void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, + enum flow_dissector_key_id addr_type); + struct nft_rule; struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule); void nft_flow_rule_destroy(struct nft_flow_rule *flow); @@ -74,6 +78,9 @@ int nft_flow_rule_offload_commit(struct net *net); offsetof(struct nft_flow_key, __base.__field); \ (__reg)->len = __len; \ (__reg)->key = __key; \ + +#define NFT_OFFLOAD_MATCH_EXACT(__key, __base, __field, __len, __reg) \ + NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ memset(&(__reg)->mask, 0xff, (__reg)->len); int nft_chain_offload_priority(struct nft_base_chain *basechain); diff --git a/include/net/tls.h b/include/net/tls.h index baf1e99d8193..2bdd802212fe 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -199,6 +199,12 @@ enum tls_context_flags { * to be atomic. */ TLS_TX_SYNC_SCHED = 1, + /* tls_dev_del was called for the RX side, device state was released, + * but tls_ctx->netdev might still be kept, because TX-side driver + * resources might not be released yet. Used to prevent the second + * tls_dev_del call in tls_device_down if it happens simultaneously. + */ + TLS_RX_DEV_CLOSED = 2, }; struct cipher_context { @@ -300,7 +306,8 @@ enum tls_offload_sync_type { #define TLS_DEVICE_RESYNC_ASYNC_LOGMAX 13 struct tls_offload_resync_async { atomic64_t req; - u32 loglen; + u16 loglen; + u16 rcd_delta; u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX]; }; @@ -471,6 +478,18 @@ static inline bool tls_bigint_increment(unsigned char *seq, int len) return (i == -1); } +static inline void tls_bigint_subtract(unsigned char *seq, int n) +{ + u64 rcd_sn; + __be64 *p; + + BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8); + + p = (__be64 *)seq; + rcd_sn = be64_to_cpu(*p); + *p = cpu_to_be64(rcd_sn - n); +} + static inline struct tls_context *tls_get_ctx(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -639,6 +658,7 @@ tls_offload_rx_resync_async_request_start(struct sock *sk, __be32 seq, u16 len) atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) | ((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC); rx_ctx->resync_async->loglen = 0; + rx_ctx->resync_async->rcd_delta = 0; } static inline void diff --git a/include/net/xdp.h b/include/net/xdp.h index 3814fb631d52..9dab2bc6f187 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -240,8 +240,6 @@ struct xdp_attachment_info { }; struct netdev_bpf; -bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, - struct netdev_bpf *bpf); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 1a9559c0cbdd..4f4e93bf814c 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -31,6 +31,7 @@ struct xdp_umem { struct page **pgs; int id; struct list_head xsk_dma_list; + struct work_struct work; }; struct xsk_map { diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index c25fb86ffae9..b3bbd10eb3f0 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -132,6 +132,9 @@ struct iscsi_task { void *dd_data; /* driver/transport data */ }; +/* invalid scsi_task pointer */ +#define INVALID_SCSI_TASK (struct iscsi_task *)-1l + static inline int iscsi_task_has_unsol_data(struct iscsi_task *task) { return task->unsol_r2t.data_length > task->unsol_r2t.sent; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 1e9db9577441..49b46df476f2 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -618,6 +618,9 @@ struct ocelot { /* Keep track of the vlan port masks */ u32 vlan_mask[VLAN_N_VID]; + /* Switches like VSC9959 have flooding per traffic class */ + int num_flooding_pgids; + /* In tables like ANA:PORT and the ANA:PGID:PGID mask, * the CPU is located after the physical ports (at the * num_phys_ports index). diff --git a/include/sound/rt1015.h b/include/sound/rt1015.h new file mode 100644 index 000000000000..70a7538d4c89 --- /dev/null +++ b/include/sound/rt1015.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/sound/rt1015.h -- Platform data for RT1015 + * + * Copyright 2020 Realtek Microelectronics + */ + +#ifndef __LINUX_SND_RT1015_H +#define __LINUX_SND_RT1015_H + +struct rt1015_platform_data { + unsigned int power_up_delay_ms; +}; + +#endif diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 26cfb0fa8e7e..49d7d0fe29f6 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -399,6 +399,69 @@ TRACE_EVENT(kvm_halt_poll_ns, #define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \ trace_kvm_halt_poll_ns(false, vcpu_id, new, old) +TRACE_EVENT(kvm_dirty_ring_push, + TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset), + TP_ARGS(ring, slot, offset), + + TP_STRUCT__entry( + __field(int, index) + __field(u32, dirty_index) + __field(u32, reset_index) + __field(u32, slot) + __field(u64, offset) + ), + + TP_fast_assign( + __entry->index = ring->index; + __entry->dirty_index = ring->dirty_index; + __entry->reset_index = ring->reset_index; + __entry->slot = slot; + __entry->offset = offset; + ), + + TP_printk("ring %d: dirty 0x%x reset 0x%x " + "slot %u offset 0x%llx (used %u)", + __entry->index, __entry->dirty_index, + __entry->reset_index, __entry->slot, __entry->offset, + __entry->dirty_index - __entry->reset_index) +); + +TRACE_EVENT(kvm_dirty_ring_reset, + TP_PROTO(struct kvm_dirty_ring *ring), + TP_ARGS(ring), + + TP_STRUCT__entry( + __field(int, index) + __field(u32, dirty_index) + __field(u32, reset_index) + ), + + TP_fast_assign( + __entry->index = ring->index; + __entry->dirty_index = ring->dirty_index; + __entry->reset_index = ring->reset_index; + ), + + TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)", + __entry->index, __entry->dirty_index, __entry->reset_index, + __entry->dirty_index - __entry->reset_index) +); + +TRACE_EVENT(kvm_dirty_ring_exit, + TP_PROTO(struct kvm_vcpu *vcpu), + TP_ARGS(vcpu), + + TP_STRUCT__entry( + __field(int, vcpu_id) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + ), + + TP_printk("vcpu %d", __entry->vcpu_id) +); + #endif /* _TRACE_KVM_MAIN_H */ /* This part must be outside protection */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 2477014e3fa6..2a03263b5f9d 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -68,7 +68,8 @@ DECLARE_EVENT_CLASS(rpc_xdr_buf_class, TP_fast_assign( __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client->cl_clid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; __entry->head_base = xdr->head[0].iov_base; __entry->head_len = xdr->head[0].iov_len; __entry->tail_base = xdr->tail[0].iov_base; diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index e7cbccc7c14c..57d795365987 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -190,7 +190,7 @@ TRACE_EVENT(inode_foreign_history, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); + strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; @@ -219,7 +219,7 @@ TRACE_EVENT(inode_switch_wbs, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(old_wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); @@ -252,7 +252,7 @@ TRACE_EVENT(track_foreign_dirty, struct address_space *mapping = page_mapping(page); struct inode *inode = mapping ? mapping->host : NULL; - strncpy(__entry->name, bdi_dev_name(wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; @@ -285,7 +285,7 @@ TRACE_EVENT(flush_foreign, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e6ceac3f7d62..556216dc9703 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3897,8 +3897,8 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ - FN(bpf_per_cpu_ptr), \ - FN(bpf_this_cpu_ptr), \ + FN(per_cpu_ptr), \ + FN(this_cpu_ptr), \ FN(redirect_peer), \ /* */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 0113bc4db9f5..5203f54a2be1 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -526,6 +526,8 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_STATS_LIMIT, /* u8 */ DEVLINK_ATTR_RELOAD_STATS_VALUE, /* u32 */ DEVLINK_ATTR_REMOTE_RELOAD_STATS, /* nested */ + DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */ + DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */ /* add new attributes above here, update the policy in devlink.c */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ca41220b40b8..374c67875cdb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -250,6 +250,8 @@ struct kvm_hyperv_exit { #define KVM_EXIT_ARM_NISV 28 #define KVM_EXIT_X86_RDMSR 29 #define KVM_EXIT_X86_WRMSR 30 +#define KVM_EXIT_DIRTY_RING_FULL 31 +#define KVM_EXIT_AP_RESET_HOLD 32 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -572,6 +574,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_CHECK_STOP 6 #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 +#define KVM_MP_STATE_AP_RESET_HOLD 9 struct kvm_mp_state { __u32 mp_state; @@ -1053,6 +1056,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_X86_USER_SPACE_MSR 188 #define KVM_CAP_X86_MSR_FILTER 189 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 +#define KVM_CAP_SYS_HYPERV_CPUID 191 +#define KVM_CAP_DIRTY_LOG_RING 192 #ifdef KVM_CAP_IRQ_ROUTING @@ -1511,7 +1516,7 @@ struct kvm_enc_region { /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */ #define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) -/* Available with KVM_CAP_HYPERV_CPUID */ +/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */ #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2) /* Available with KVM_CAP_ARM_SVE */ @@ -1557,6 +1562,9 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_X86_MSR_FILTER */ #define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter) +/* Available with KVM_CAP_DIRTY_LOG_RING */ +#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ @@ -1710,4 +1718,52 @@ struct kvm_hyperv_eventfd { #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) +/* + * Arch needs to define the macro after implementing the dirty ring + * feature. KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the + * starting page offset of the dirty ring structures. + */ +#ifndef KVM_DIRTY_LOG_PAGE_OFFSET +#define KVM_DIRTY_LOG_PAGE_OFFSET 0 +#endif + +/* + * KVM dirty GFN flags, defined as: + * + * |---------------+---------------+--------------| + * | bit 1 (reset) | bit 0 (dirty) | Status | + * |---------------+---------------+--------------| + * | 0 | 0 | Invalid GFN | + * | 0 | 1 | Dirty GFN | + * | 1 | X | GFN to reset | + * |---------------+---------------+--------------| + * + * Lifecycle of a dirty GFN goes like: + * + * dirtied harvested reset + * 00 -----------> 01 -------------> 1X -------+ + * ^ | + * | | + * +------------------------------------------+ + * + * The userspace program is only responsible for the 01->1X state + * conversion after harvesting an entry. Also, it must not skip any + * dirty bits, so that dirty bits are always harvested in sequence. + */ +#define KVM_DIRTY_GFN_F_DIRTY BIT(0) +#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_MASK 0x3 + +/* + * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of + * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn. The + * size of the gfn buffer is decided by the first argument when + * enabling KVM_CAP_DIRTY_LOG_RING. + */ +struct kvm_dirty_gfn { + __u32 flags; + __u32 slot; + __u64 offset; +}; + #endif /* __LINUX_KVM_H */ diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 8300cc29dec8..8d16744edc31 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -1058,4 +1058,6 @@ enum ovs_dec_ttl_attr { __OVS_DEC_TTL_ATTR_MAX }; +#define OVS_DEC_TTL_ATTR_MAX (__OVS_DEC_TTL_ATTR_MAX - 1) + #endif /* _LINUX_OPENVSWITCH_H */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 82cc58fe9368..1500a0f58041 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -171,9 +171,12 @@ struct statx { * be of use to ordinary userspace programs such as GUIs or ls rather than * specialised tools. * - * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS + * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags * semantically. Where possible, the numerical value is picked to correspond - * also. + * also. Note that the DAX attribute indicates that the file is in the CPU + * direct access state. It does not correspond to the per-inode flag that + * some filesystems support. + * */ #define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */ #define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */ @@ -183,7 +186,7 @@ struct statx { #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ -#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ +#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 9bc5bc07d4d3..b9c937b3a149 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -198,6 +198,23 @@ void gnttab_free_auto_xlat_frames(void); int gnttab_alloc_pages(int nr_pages, struct page **pages); void gnttab_free_pages(int nr_pages, struct page **pages); +struct gnttab_page_cache { + spinlock_t lock; +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC + struct page *pages; +#else + struct list_head pages; +#endif + unsigned int num_pages; +}; + +void gnttab_page_cache_init(struct gnttab_page_cache *cache); +int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page); +void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page, + unsigned int num); +void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, + unsigned int num); + #ifdef CONFIG_XEN_GRANT_DMA_ALLOC struct gnttab_dma_alloc_args { /* Device for which DMA memory will be/was allocated. */ |