diff options
author | Jason Gunthorpe <jgg@nvidia.com> | 2024-11-22 14:37:25 -0400 |
---|---|---|
committer | Jason Gunthorpe <jgg@nvidia.com> | 2024-11-22 14:37:25 -0400 |
commit | 2d762281950877eb450ac98bc77a6d340f6b5249 (patch) | |
tree | b4ce2d3983483d4f44c6014a548b4e66c719a772 /include | |
parent | 6d026e6d48cd2a95407c8fdd8d6187b871401c23 (diff) | |
parent | 42f0cbb2a253bcd7d4f20e80462014622f19d88e (diff) | |
download | lwn-2d762281950877eb450ac98bc77a6d340f6b5249.tar.gz lwn-2d762281950877eb450ac98bc77a6d340f6b5249.zip |
Merge tag 'iommu-updates-v6.13' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/iommu/linux into iommufd.git
Merge with Joerg's tree for dependencies on the next patches.
======================================
IOMMU Updates for Linux v6.13:
Including:
- Core Updates:
- Convert call-sites using iommu_domain_alloc() to more specific
versions and remove function.
- Introduce iommu_paging_domain_alloc_flags().
- Extend support for allocating PASID-capable domains to more
drivers.
- Remove iommu_present().
- Some smaller improvements.
- New IOMMU driver for RISC-V.
- Intel VT-d Updates:
- Add domain_alloc_paging support.
- Enable user space IOPFs in non-PASID and non-svm cases.
- Small code refactoring and cleanups.
- Add domain replacement support for pasid.
- AMD-Vi Updates:
- Adapt to iommu_paging_domain_alloc_flags() interface and alloc V2
page-tables by default.
- Replace custom domain ID allocator with IDA allocator.
- Add ops->release_domain() support.
- Other improvements to device attach and domain allocation code
paths.
- ARM-SMMU Updates:
- SMMUv2:
- Return -EPROBE_DEFER for client devices probing before their SMMU.
- Devicetree binding updates for Qualcomm MMU-500 implementations.
- SMMUv3:
- Minor fixes and cleanup for NVIDIA's virtual command queue driver.
- IO-PGTable:
- Fix indexing of concatenated PGDs and extend selftest coverage.
- Remove unused block-splitting support.
- S390 IOMMU:
- Implement support for blocking domain.
- Mediatek IOMMU:
- Enable 35-bit physical address support for mt8186.
- OMAP IOMMU driver:
- Adapt to recent IOMMU core changes and unbreak driver.
======================================
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Diffstat (limited to 'include')
61 files changed, 412 insertions, 253 deletions
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 76e44e102780..62d368bcd9ec 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -65,7 +65,7 @@ struct cpc_desc { int write_cmd_status; int write_cmd_id; /* Lock used for RMW operations in cpc_write() */ - spinlock_t rmw_lock; + raw_spinlock_t rmw_lock; struct cpc_register_resource cpc_regs[MAX_CPC_REG_ENT]; struct acpi_psd_package domain_info; struct kobject kobj; diff --git a/include/acpi/processor.h b/include/acpi/processor.h index e6f6074eadbf..a17e97e634a6 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -465,4 +465,6 @@ extern int acpi_processor_ffh_lpi_probe(unsigned int cpu); extern int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi); #endif +void acpi_processor_init_invariance_cppc(void); + #endif diff --git a/include/drm/drm_kunit_helpers.h b/include/drm/drm_kunit_helpers.h index e7cc17ee4934..afdd46ef04f7 100644 --- a/include/drm/drm_kunit_helpers.h +++ b/include/drm/drm_kunit_helpers.h @@ -120,4 +120,8 @@ drm_kunit_helper_create_crtc(struct kunit *test, const struct drm_crtc_funcs *funcs, const struct drm_crtc_helper_funcs *helper_funcs); +struct drm_display_mode * +drm_kunit_display_mode_from_cea_vic(struct kunit *test, struct drm_device *dev, + u8 video_code); + #endif // DRM_KUNIT_HELPERS_H_ diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 1f0a9ff23a2c..941deffc590d 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -135,18 +135,21 @@ static inline void alloc_tag_sub_check(union codetag_ref *ref) {} #endif /* Caller should verify both ref and tag to be valid */ -static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { alloc_tag_add_check(ref, tag); if (!ref || !tag) - return; + return false; ref->ct = &tag->ct; + return true; } -static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { - __alloc_tag_ref_set(ref, tag); + if (unlikely(!__alloc_tag_ref_set(ref, tag))) + return false; + /* * We need in increment the call counter every time we have a new * allocation or when we split a large allocation into smaller ones. @@ -154,12 +157,13 @@ static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *t * counter because when we free each part the counter will be decremented. */ this_cpu_inc(tag->counters->calls); + return true; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) { - alloc_tag_ref_set(ref, tag); - this_cpu_add(tag->counters->bytes, bytes); + if (likely(alloc_tag_ref_set(ref, tag))) + this_cpu_add(tag->counters->bytes, bytes); } static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index b721f360d759..4a952c4885ed 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -11,10 +11,6 @@ void topology_normalize_cpu_scale(void); int topology_update_cpu_topology(void); -#ifdef CONFIG_ACPI_CPPC_LIB -void topology_init_cpu_capacity_cppc(void); -#endif - struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index f59099a213d0..67f6fdf2e7cd 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -315,8 +315,6 @@ u32 arm_smccc_get_version(void); void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); -extern u64 smccc_has_sve_hint; - /** * arm_smccc_get_soc_id_version() * @@ -415,15 +413,6 @@ struct arm_smccc_quirk { }; /** - * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls - * - * Sets the SMCCC hint bit to indicate if there is live state in the SVE - * registers, this modifies x0 in place and should never be called from C - * code. - */ -asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0); - -/** * __arm_smccc_smc() - make SMC calls * @a0-a7: arguments passed in registers 0 to 7 * @res: result values from registers 0 to 3 @@ -490,20 +479,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #endif -/* nVHE hypervisor doesn't have a current thread so needs separate checks */ -#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__) - -#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n", "bl __arm_smccc_sve_check \n", \ - ARM64_SVE) -#define smccc_sve_clobbers "x16", "x30", "cc", - -#else - -#define SMCCC_SVE_CHECK -#define smccc_sve_clobbers - -#endif - #define __constraint_read_2 "r" (arg0) #define __constraint_read_3 __constraint_read_2, "r" (arg1) #define __constraint_read_4 __constraint_read_3, "r" (arg2) @@ -574,12 +549,11 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, register unsigned long r3 asm("r3"); \ CONCATENATE(__declare_arg_, \ COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__); \ - asm volatile(SMCCC_SVE_CHECK \ - inst "\n" : \ + asm volatile(inst "\n" : \ "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3) \ : CONCATENATE(__constraint_read_, \ COUNT_ARGS(__VA_ARGS__)) \ - : smccc_sve_clobbers "memory"); \ + : "memory"); \ if (___res) \ *___res = (typeof(*___res)){r0, r1, r2, r3}; \ } while (0) @@ -628,7 +602,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, asm ("" : \ : CONCATENATE(__constraint_read_, \ COUNT_ARGS(__VA_ARGS__)) \ - : smccc_sve_clobbers "memory"); \ + : "memory"); \ if (___res) \ ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ } while (0) diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h index 4b61b0e57720..2eed0ffb5e8f 100644 --- a/include/linux/backing-file.h +++ b/include/linux/backing-file.h @@ -16,7 +16,7 @@ struct backing_file_ctx { const struct cred *cred; struct file *user_file; void (*accessed)(struct file *); - void (*end_write)(struct file *); + void (*end_write)(struct file *, loff_t, ssize_t); }; struct file *backing_file_open(const struct path *user_path, int flags, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 19d8ca8ac960..bdadb0bb6cec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -635,6 +635,7 @@ enum bpf_type_flag { */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + /* MEM can be uninitialized. */ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ @@ -700,6 +701,13 @@ enum bpf_type_flag { */ MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), + /* MEM is being written to, often combined with MEM_UNINIT. Non-presence + * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the + * MEM_UNINIT means that memory needs to be initialized since it is also + * read. + */ + MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -758,10 +766,10 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, - /* pointer to memory does not need to be initialized, helper function must fill - * all bytes or clear them in error case. + /* Pointer to memory does not need to be initialized, since helper function + * fills all bytes or clears them in error case. */ - ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index aaf004d94322..e45162ef59bb 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +/* Check the allocation size for kmalloc equivalent allocator */ +int bpf_mem_alloc_check_size(bool percpu, size_t size); + /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9f2a6b83b49e..fa78f49d4a9a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -146,6 +146,7 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter) BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx) BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit) +BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap) #endif #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) diff --git a/include/linux/closure.h b/include/linux/closure.h index 2af44427107d..880fe85e35e9 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -454,4 +454,39 @@ do { \ __closure_wait_event(waitlist, _cond); \ } while (0) +#define __closure_wait_event_timeout(waitlist, _cond, _until) \ +({ \ + struct closure cl; \ + long _t; \ + \ + closure_init_stack(&cl); \ + \ + while (1) { \ + closure_wait(waitlist, &cl); \ + if (_cond) { \ + _t = max_t(long, 1L, _until - jiffies); \ + break; \ + } \ + _t = max_t(long, 0L, _until - jiffies); \ + if (!_t) \ + break; \ + closure_sync_timeout(&cl, _t); \ + } \ + closure_wake_up(waitlist); \ + closure_sync(&cl); \ + _t; \ +}) + +/* + * Returns 0 if timeout expired, remaining time in jiffies (at least 1) if + * condition became true + */ +#define closure_wait_event_timeout(waitlist, _cond, _timeout) \ +({ \ + unsigned long _until = jiffies + _timeout; \ + (_cond) \ + ? max_t(long, 1L, _until - jiffies) \ + : __closure_wait_event_timeout(waitlist, _cond, _until);\ +}) + #endif /* _LINUX_CLOSURE_H */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index f805adaa316e..cd6f9aae311f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -80,7 +80,11 @@ #define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif +#ifdef __SANITIZE_HWADDRESS__ +#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress"))) +#else #define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#endif #if defined(__SANITIZE_THREAD__) #define __no_sanitize_thread __attribute__((__no_sanitize_thread__)) diff --git a/include/linux/device.h b/include/linux/device.h index b4bde8d22697..667cb6db9019 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1078,6 +1078,9 @@ int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); +int device_for_each_child_reverse_from(struct device *parent, + struct device *from, const void *data, + int (*fn)(struct device *, const void *)); struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 499bb2c63483..692b2b445761 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -292,7 +292,6 @@ static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src) struct irq_data; extern void dmar_msi_unmask(struct irq_data *data); extern void dmar_msi_mask(struct irq_data *data); -extern void dmar_msi_read(int irq, struct msi_msg *msg); extern void dmar_msi_write(int irq, struct msi_msg *msg); extern int dmar_set_interrupt(struct intel_iommu *iommu); extern irqreturn_t dmar_fault(int irq, void *dev_id); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index c13e99cbbf81..4b4bfef6f053 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc, int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc); + +#define GET_TREE_BDEV_QUIET_LOOKUP 0x0001 +int get_tree_bdev_flags(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc), unsigned int flags); + extern int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h index df25fffdc0ae..623ccfcbf39c 100644 --- a/include/linux/fsl/enetc_mdio.h +++ b/include/linux/fsl/enetc_mdio.h @@ -59,7 +59,8 @@ static inline int enetc_mdio_read_c45(struct mii_bus *bus, int phy_id, static inline int enetc_mdio_write_c45(struct mii_bus *bus, int phy_id, int devad, int regnum, u16 value) { return -EINVAL; } -struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) +static inline struct enetc_hw *enetc_hw_alloc(struct device *dev, + void __iomem *port_regs) { return ERR_PTR(-EINVAL); } #endif diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 9c8119ed13a4..c4dde3aafcac 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -466,6 +466,7 @@ struct host1x_memory_context { refcount_t ref; struct pid *owner; + struct device_dma_parameters dma_parms; struct device dev; u64 dma_mask; u32 stream_id; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 67d0ab3c3bba..ef5b80e48599 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -322,6 +322,24 @@ struct thpsize { (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) +static inline bool vma_thp_disabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* + * Explicitly disabled through madvise or prctl, or some + * architectures may disable THP for some mappings, for + * example, s390 kvm. + */ + return (vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags); +} + +static inline bool thp_disabled_by_hw(void) +{ + /* If the hardware/firmware marked hugepage support disabled. */ + return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); +} + unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, diff --git a/include/linux/input.h b/include/linux/input.h index 89a0be6ee0e2..cd866b020a01 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -339,12 +339,16 @@ struct input_handler { * @name: name given to the handle by handler that created it * @dev: input device the handle is attached to * @handler: handler that works with the device through this handle + * @handle_events: event sequence handler. It is set up by the input core + * according to event handling method specified in the @handler. See + * input_handle_setup_event_handler(). + * This method is being called by the input core with interrupts disabled + * and dev->event_lock spinlock held and so it may not sleep. * @d_node: used to put the handle on device's list of attached handles * @h_node: used to put the handle on handler's list of handles from which * it gets events */ struct input_handle { - void *private; int open; @@ -353,6 +357,10 @@ struct input_handle { struct input_dev *dev; struct input_handler *handler; + unsigned int (*handle_events)(struct input_handle *handle, + struct input_value *vals, + unsigned int count); + struct list_head d_node; struct list_head h_node; }; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 4ad12a3c8bae..f61407e3b121 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -256,6 +256,39 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) return &i->iomap; } +/* + * Return the file offset for the first unchanged block after a short write. + * + * If nothing was written, round @pos down to point at the first block in + * the range, else round up to include the partially written block. + */ +static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos, + ssize_t written) +{ + if (unlikely(!written)) + return round_down(pos, i_blocksize(inode)); + return round_up(pos + written, i_blocksize(inode)); +} + +/* + * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE + * operation. + * + * Don't bother with blocks that are not shared to start with; or mappings that + * cannot be shared, such as inline data, delalloc reservations, holes or + * unwritten extents. + * + * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing + * requires providing a separate source map, and the presence of one is a good + * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set + * for any data that goes into the COW fork for XFS. + */ +static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) +{ + return (iter->iomap.flags & IOMAP_F_SHARED) && + iter->srcmap.type == IOMAP_MAPPED; +} + ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops, void *private); int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); @@ -276,9 +309,9 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, struct iomap *iomap); -void iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, - loff_t length, ssize_t written, unsigned flag, - struct iomap *iomap, iomap_punch_t punch); +void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, + loff_t end_byte, unsigned flags, struct iomap *iomap, + iomap_punch_t punch); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, const struct iomap_ops *ops); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 8b02adbd14f7..d6aaaec3caf4 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -559,8 +559,6 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size, * the caller iommu_domain_alloc() returns. * @domain_alloc_user: Allocate an iommu domain corresponding to the input * parameters as defined in include/uapi/linux/iommufd.h. - * Unlike @domain_alloc, it is called only by IOMMUFD and - * must fully initialize the new domain before return. * Upon success, if the @user_data is valid and the @parent * points to a kernel-managed domain, the new domain must be * IOMMU_DOMAIN_NESTED type; otherwise, the @parent must be @@ -676,7 +674,8 @@ struct iommu_ops { * * 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 - * @set_dev_pasid: set an iommu domain to a pasid of device + * @set_dev_pasid: set or replace an iommu domain to a pasid of device. The pasid of + * the device should be left in the old config in error case. * @map_pages: map a physically contiguous set of pages of the same size to * an iommu domain. * @unmap_pages: unmap a number of pages of the same size from an iommu domain @@ -701,7 +700,7 @@ struct iommu_ops { struct iommu_domain_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev, - ioasid_t pasid); + ioasid_t pasid, struct iommu_domain *old); int (*map_pages)(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, @@ -842,12 +841,14 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) }; } -extern int bus_iommu_probe(const struct bus_type *bus); extern bool iommu_present(const struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_group_has_isolated_msi(struct iommu_group *group); -extern struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus); -struct iommu_domain *iommu_paging_domain_alloc(struct device *dev); +struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, unsigned int flags); +static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev) +{ + return iommu_paging_domain_alloc_flags(dev, 0); +} extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); @@ -1140,19 +1141,15 @@ struct iommu_iotlb_gather {}; struct iommu_dirty_bitmap {}; struct iommu_dirty_ops {}; -static inline bool iommu_present(const struct bus_type *bus) -{ - return false; -} - static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) { return false; } -static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus) +static inline struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, + unsigned int flags) { - return NULL; + return ERR_PTR(-ENODEV); } static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev) diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index ecabed6d3307..7f1f11a5e4e4 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -66,10 +66,12 @@ struct its_vpe { bool enabled; bool group; } sgi_config[16]; - atomic_t vmapp_count; }; }; + /* Track the VPE being mapped */ + atomic_t vmapp_count; + /* * Ensures mutual exclusion between affinity setting of the * vPE and vLPI operations using vpe->col_idx. diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 11690dacd986..ec9c05044d4f 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm) return atomic_long_read(&mm->ksm_zero_pages); } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { + /* Adding mm to ksm is best effort on fork. */ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); - - return 0; + __ksm_enter(mm); } static inline int ksm_execve(struct mm_struct *mm) @@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm) return 0; } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline int ksm_execve(struct mm_struct *mm) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index db567d26f7b9..45be36e5285f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1313,8 +1313,6 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); diff --git a/include/linux/mm.h b/include/linux/mm.h index f9de33ac2add..75ccdc96ebfa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3819,8 +3819,9 @@ void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); -void pmd_init(void *addr); void pud_init(void *addr); +void pmd_init(void *addr); +void kernel_pte_init(void *addr); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); diff --git a/include/linux/mman.h b/include/linux/mman.h index bcb201ab7a41..a842783ffa62 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H +#include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> @@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages) #endif #ifndef arch_calc_vm_flag_bits -#define arch_calc_vm_flag_bits(flags) 0 +#define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot @@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey) * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_flag_bits(unsigned long flags) +calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | - arch_calc_vm_flag_bits(flags); + arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); @@ -188,16 +189,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 17506e4a2835..80bc5640bb60 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -458,9 +458,7 @@ struct lru_gen_folio { enum { MM_LEAF_TOTAL, /* total leaf entries */ - MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ - MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS @@ -557,7 +555,7 @@ struct lru_gen_memcg { void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); @@ -576,8 +574,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } -static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { + return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) @@ -824,6 +823,7 @@ struct zone { unsigned long watermark_boost; unsigned long nr_reserved_highatomic; + unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4d20c776a4ff..8896705ccd63 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3325,6 +3325,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -3451,6 +3457,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, if (likely(dql_avail(&dev_queue->dql) >= 0)) return; + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); /* diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index b0dd9b1eef4f..3982fea79919 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -32,7 +32,8 @@ typedef struct { struct auth_domain *dom; /* auth_domain for localio */ } nfs_uuid_t; -void nfs_uuid_begin(nfs_uuid_t *); +void nfs_uuid_init(nfs_uuid_t *); +bool nfs_uuid_begin(nfs_uuid_t *); void nfs_uuid_end(nfs_uuid_t *); void nfs_uuid_is_local(const uuid_t *, struct list_head *, struct net *, struct auth_domain *, struct module *); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1b3a76710487..cc839e4365c1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -975,12 +975,16 @@ static __always_inline bool folio_test_##fname(const struct folio *folio) \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ + if (folio_test_##fname(folio)) \ + return; \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ + if (folio->page.page_type == UINT_MAX) \ + return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } @@ -993,11 +997,15 @@ static __always_inline int Page##uname(const struct page *page) \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ + if (Page##uname(page)) \ + return; \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ + if (page->page_type == UINT_MAX) \ + return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } diff --git a/include/linux/percpu.h b/include/linux/percpu.h index b6321fc49159..52b5ea663b9f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -41,7 +41,11 @@ PCPU_MIN_ALLOC_SHIFT) #ifdef CONFIG_RANDOM_KMALLOC_CACHES -#define PERCPU_DYNAMIC_SIZE_SHIFT 12 +# if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PAGE_SIZE_4KB) +# define PERCPU_DYNAMIC_SIZE_SHIFT 13 +# else +# define PERCPU_DYNAMIC_SIZE_SHIFT 12 +#endif /* LOCKDEP and PAGE_SIZE > 4KiB */ #else #define PERCPU_DYNAMIC_SIZE_SHIFT 10 #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 449dd64ed9ac..bb343136ddd0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2133,6 +2133,11 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +static inline bool task_is_runnable(struct task_struct *p) +{ + return p->on_rq && !p->se.sched_delayed; +} + extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index c3bca9c0bf2c..2996a3c28ef3 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -258,8 +258,8 @@ struct geni_se { #define RX_DMA_PARITY_ERR BIT(5) #define RX_DMA_BREAK GENMASK(8, 7) #define RX_GENI_GP_IRQ GENMASK(10, 5) -#define RX_GENI_CANCEL_IRQ BIT(11) #define RX_GENI_GP_IRQ_EXT GENMASK(13, 12) +#define RX_GENI_CANCEL_IRQ BIT(14) /* SE_HW_PARAM_0 fields */ #define TX_FIFO_WIDTH_MSK GENMASK(29, 24) diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 9e9f528b1370..2f20281d4ad4 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -125,6 +125,7 @@ struct llcc_edac_reg_offset { * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @ecc_irq: interrupt for llcc cache error detection and reporting + * @ecc_irq_configured: 'True' if firmware has already configured the irq propagation * @version: Indicates the LLCC version */ struct llcc_drv_data { @@ -139,6 +140,7 @@ struct llcc_drv_data { u32 num_banks; unsigned long *bitmap; int ecc_irq; + bool ecc_irq_configured; u32 version; }; diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 37ae69365fe2..734dc1fa3b5b 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -227,7 +227,7 @@ struct sdw_intel_ops { /** * struct sdw_intel_acpi_info - Soundwire Intel information found in ACPI tables * @handle: ACPI controller handle - * @count: link count found with "sdw-master-count" property + * @count: link count found with "sdw-master-count" or "sdw-manager-list" property * @link_mask: bit-wise mask listing links enabled by BIOS menu * * this structure could be expanded to e.g. provide all the _ADR diff --git a/include/linux/swap.h b/include/linux/swap.h index ca533b478c21..f3e0ac20c2e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,6 +335,7 @@ struct swap_info_struct { * list. */ struct work_struct discard_work; /* discard worker */ + struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one diff --git a/include/linux/task_work.h b/include/linux/task_work.h index cf5e7e891a77..2964171856e0 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -14,11 +14,14 @@ init_task_work(struct callback_head *twork, task_work_func_t func) } enum task_work_notify_mode { - TWA_NONE, + TWA_NONE = 0, TWA_RESUME, TWA_SIGNAL, TWA_SIGNAL_NO_IPI, TWA_NMI_CURRENT, + + TWA_FLAGS = 0xff00, + TWAF_NO_ALLOC = 0x0100, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/include/linux/tick.h b/include/linux/tick.h index 72744638c5b0..99c9c5a7252a 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -251,12 +251,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk, if (tick_nohz_full_enabled()) tick_nohz_dep_set_task(tsk, bit); } + static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_clear_task(tsk, bit); } + +static inline void tick_dep_init_task(struct task_struct *tsk) +{ + atomic_set(&tsk->tick_dep_mask, 0); +} + static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { @@ -290,6 +297,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { } +static inline void tick_dep_init_task(struct task_struct *tsk) { } static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_signal(struct signal_struct *signal, diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 39c7cf82b0c2..43844510d5d0 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -38,6 +38,7 @@ #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL + #define mask_user_address(src) (src) #endif /* @@ -159,19 +160,27 @@ _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); - if (!should_fail_usercopy() && likely(access_ok(from, n))) { + if (should_fail_usercopy()) + goto fail; + if (can_do_masked_user_access()) + from = mask_user_address(from); + else { + if (!access_ok(from, n)) + goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); - instrument_copy_from_user_before(to, from, n); - res = raw_copy_from_user(to, from, n); - instrument_copy_from_user_after(to, from, n, res); } - if (unlikely(res)) - memset(to + (n - res), 0, res); + instrument_copy_from_user_before(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + if (likely(!res)) + return 0; +fail: + memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 3625096d5f85..7183e5aca282 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -141,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, + bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 9fc6ce15c499..cb40f1a1d081 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); +void dup_userfaultfd_fail(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); @@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l) { } +static inline void dup_userfaultfd_fail(struct list_head *l) +{ +} + static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 5d655e109b2c..f66bc85c6411 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -403,6 +403,7 @@ int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); +bool bt_sock_linked(struct bt_sock_list *l, struct sock *s); struct sock *bt_sock_alloc(struct net *net, struct socket *sock, struct proto *prot, int proto, gfp_t prio, int kern); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 69ec1eb41a09..941dc62f3027 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6130,6 +6130,50 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); /** + * wiphy_delayed_work_pending - Find out whether a wiphy delayable + * work item is currently pending. + * + * @wiphy: the wiphy, for debug purposes + * @dwork: the delayed work in question + * + * Return: true if timer is pending, false otherwise + * + * How wiphy_delayed_work_queue() works is by setting a timer which + * when it expires calls wiphy_work_queue() to queue the wiphy work. + * Because wiphy_delayed_work_queue() uses mod_timer(), if it is + * called twice and the second call happens before the first call + * deadline, the work will rescheduled for the second deadline and + * won't run before that. + * + * wiphy_delayed_work_pending() can be used to detect if calling + * wiphy_work_delayed_work_queue() would start a new work schedule + * or delayed a previous one. As seen below it cannot be used to + * detect precisely if the work has finished to execute nor if it + * is currently executing. + * + * CPU0 CPU1 + * wiphy_delayed_work_queue(wk) + * mod_timer(wk->timer) + * wiphy_delayed_work_pending(wk) -> true + * + * [...] + * expire_timers(wk->timer) + * detach_timer(wk->timer) + * wiphy_delayed_work_pending(wk) -> false + * wk->timer->function() | + * wiphy_work_queue(wk) | delayed work pending + * list_add_tail() | returns false but + * queue_work(cfg80211_wiphy_work) | wk->func() has not + * | been run yet + * [...] | + * cfg80211_wiphy_work() | + * wk->func() V + * + */ +bool wiphy_delayed_work_pending(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork); + +/** * enum ieee80211_ap_reg_power - regulatory power for an Access Point * * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9ab49bfeae78..c1d91f1d20f6 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -531,13 +531,12 @@ static inline int genlmsg_multicast(const struct genl_family *family, * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array - * @flags: allocation flags * * This function must hold the RTNL or rcu_read_lock(). */ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, - unsigned int group, gfp_t flags); + unsigned int group); /** * genlmsg_unicast - unicast a netlink message diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 02fbc036f34e..813e163ce27c 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -24,25 +24,27 @@ * struct ieee80211_radiotap_header - base radiotap header */ struct ieee80211_radiotap_header { - /** - * @it_version: radiotap version, always 0 - */ - uint8_t it_version; - - /** - * @it_pad: padding (or alignment) - */ - uint8_t it_pad; - - /** - * @it_len: overall radiotap header length - */ - __le16 it_len; - - /** - * @it_present: (first) present word - */ - __le32 it_present; + __struct_group(ieee80211_radiotap_header_fixed, hdr, __packed, + /** + * @it_version: radiotap version, always 0 + */ + uint8_t it_version; + + /** + * @it_pad: padding (or alignment) + */ + uint8_t it_pad; + + /** + * @it_len: overall radiotap header length + */ + __le16 it_len; + + /** + * @it_present: (first) present word + */ + __le32 it_present; + ); /** * @it_optional: all remaining presence bitmaps @@ -50,6 +52,9 @@ struct ieee80211_radiotap_header { __le32 it_optional[]; } __packed; +static_assert(offsetof(struct ieee80211_radiotap_header, it_optional) == sizeof(struct ieee80211_radiotap_header_fixed), + "struct member likely outside of __struct_group()"); + /* version is always 0 */ #define PKTHDR_RADIOTAP_VERSION 0 diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 6194fbb564c6..6a070478254d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -354,7 +354,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); if (oif) { - fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif); /* Legacy VRF/l3mdev use case */ fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; } diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 91ae20cb7648..066a3ea33b12 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1103,6 +1103,7 @@ struct nft_rule_blob { * @name: name of the chain * @udlen: user data length * @udata: user data in the chain + * @rcu_head: rcu head for deferred release * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { @@ -1120,6 +1121,7 @@ struct nft_chain { char *name; u16 udlen; u8 *udata; + struct rcu_head rcu_head; /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; @@ -1263,6 +1265,7 @@ static inline void nft_use_inc_restore(u32 *use) * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table + * @net: netnamespace this table belongs to * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table @@ -1282,6 +1285,7 @@ struct nft_table { struct list_head sets; struct list_head objects; struct list_head flowtables; + possible_net_t net; u64 hgenerator; u64 handle; u32 use; diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index d489d9250bff..ae60d6664095 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -51,7 +51,6 @@ struct netns_xfrm { struct hlist_head *policy_byidx; unsigned int policy_idx_hmask; unsigned int idx_generator; - struct hlist_head policy_inexact[XFRM_POLICY_MAX]; struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX]; unsigned int policy_count[XFRM_POLICY_MAX * 2]; struct work_struct policy_hash_work; diff --git a/include/net/sock.h b/include/net/sock.h index db29c39e19a7..f29c14448938 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2717,6 +2717,11 @@ static inline bool sk_is_stream_unix(const struct sock *sk) return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; } +static inline bool sk_is_vsock(const struct sock *sk) +{ + return sk->sk_family == AF_VSOCK; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b6bfdc6416c7..a0bdd58f401c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -349,20 +349,25 @@ struct xfrm_if_cb { void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); void xfrm_if_unregister_cb(void); +struct xfrm_dst_lookup_params { + struct net *net; + int tos; + int oif; + xfrm_address_t *saddr; + xfrm_address_t *daddr; + u32 mark; + __u8 ipproto; + union flowi_uli uli; +}; + struct net_device; struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { struct dst_ops *dst_ops; - struct dst_entry *(*dst_lookup)(struct net *net, - int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - u32 mark); - int (*get_saddr)(struct net *net, int oif, - xfrm_address_t *saddr, - xfrm_address_t *daddr, - u32 mark); + struct dst_entry *(*dst_lookup)(const struct xfrm_dst_lookup_params *params); + int (*get_saddr)(xfrm_address_t *saddr, + const struct xfrm_dst_lookup_params *params); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); @@ -1764,10 +1769,7 @@ static inline int xfrm_user_policy(struct sock *sk, int optname, } #endif -struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - int family, u32 mark); +struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params); struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 450c44c83a5d..a0aed1a428a1 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -331,7 +331,11 @@ enum yfs_cm_operation { EM(afs_edit_dir_delete, "delete") \ EM(afs_edit_dir_delete_error, "d_err ") \ EM(afs_edit_dir_delete_inval, "d_invl") \ - E_(afs_edit_dir_delete_noent, "d_nent") + EM(afs_edit_dir_delete_noent, "d_nent") \ + EM(afs_edit_dir_update_dd, "u_ddot") \ + EM(afs_edit_dir_update_error, "u_fail") \ + EM(afs_edit_dir_update_inval, "u_invl") \ + E_(afs_edit_dir_update_nodd, "u_nodd") #define afs_edit_dir_reasons \ EM(afs_edit_dir_for_create, "Create") \ @@ -340,6 +344,7 @@ enum yfs_cm_operation { EM(afs_edit_dir_for_rename_0, "Renam0") \ EM(afs_edit_dir_for_rename_1, "Renam1") \ EM(afs_edit_dir_for_rename_2, "Renam2") \ + EM(afs_edit_dir_for_rename_sub, "RnmSub") \ EM(afs_edit_dir_for_rmdir, "RmDir ") \ EM(afs_edit_dir_for_silly_0, "S_Ren0") \ EM(afs_edit_dir_for_silly_1, "S_Ren1") \ diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index 569f86a44aaa..b0f41265191c 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -121,7 +121,7 @@ TRACE_EVENT(dma_alloc, TP_STRUCT__entry( __string(device, dev_name(dev)) - __field(u64, phys_addr) + __field(void *, virt_addr) __field(u64, dma_addr) __field(size_t, size) __field(gfp_t, flags) @@ -130,18 +130,18 @@ TRACE_EVENT(dma_alloc, TP_fast_assign( __assign_str(device); - __entry->phys_addr = virt_to_phys(virt_addr); + __entry->virt_addr = virt_addr; __entry->dma_addr = dma_addr; __entry->size = size; __entry->flags = flags; __entry->attrs = attrs; ), - TP_printk("%s dma_addr=%llx size=%zu phys_addr=%llx flags=%s attrs=%s", + TP_printk("%s dma_addr=%llx size=%zu virt_addr=%p flags=%s attrs=%s", __get_str(device), __entry->dma_addr, __entry->size, - __entry->phys_addr, + __entry->virt_addr, show_gfp_flags(__entry->flags), decode_dma_attrs(__entry->attrs)) ); @@ -153,7 +153,7 @@ TRACE_EVENT(dma_free, TP_STRUCT__entry( __string(device, dev_name(dev)) - __field(u64, phys_addr) + __field(void *, virt_addr) __field(u64, dma_addr) __field(size_t, size) __field(unsigned long, attrs) @@ -161,17 +161,17 @@ TRACE_EVENT(dma_free, TP_fast_assign( __assign_str(device); - __entry->phys_addr = virt_to_phys(virt_addr); + __entry->virt_addr = virt_addr; __entry->dma_addr = dma_addr; __entry->size = size; __entry->attrs = attrs; ), - TP_printk("%s dma_addr=%llx size=%zu phys_addr=%llx attrs=%s", + TP_printk("%s dma_addr=%llx size=%zu virt_addr=%p attrs=%s", __get_str(device), __entry->dma_addr, __entry->size, - __entry->phys_addr, + __entry->virt_addr, decode_dma_attrs(__entry->attrs)) ); diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index b5f5369b6300..9d5c00b0285c 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -208,7 +208,7 @@ TRACE_EVENT(mm_khugepaged_scan_file, TRACE_EVENT(mm_khugepaged_collapse_file, TP_PROTO(struct mm_struct *mm, struct folio *new_folio, pgoff_t index, - bool is_shmem, unsigned long addr, struct file *file, + unsigned long addr, bool is_shmem, struct file *file, int nr, int result), TP_ARGS(mm, new_folio, index, addr, is_shmem, file, nr, result), TP_STRUCT__entry( @@ -233,7 +233,7 @@ TRACE_EVENT(mm_khugepaged_collapse_file, __entry->result = result; ), - TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%ld, is_shmem=%d, filename=%s, nr=%d, result=%s", + TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%lx, is_shmem=%d, filename=%s, nr=%d, result=%s", __entry->mm, __entry->hpfn, __entry->index, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 1d7c52821e55..69975c9c6823 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -172,7 +172,6 @@ EM(netfs_folio_trace_read, "read") \ EM(netfs_folio_trace_read_done, "read-done") \ EM(netfs_folio_trace_read_gaps, "read-gaps") \ - EM(netfs_folio_trace_read_put, "read-put") \ EM(netfs_folio_trace_read_unlock, "read-unlock") \ EM(netfs_folio_trace_redirtied, "redirtied") \ EM(netfs_folio_trace_store, "store") \ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a1b126a6b0d7..cc22596c7250 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -287,6 +287,7 @@ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ + EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ E_(rxrpc_call_see_zap, "SEE zap ") #define rxrpc_txqueue_traces \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c6cd7c7aeeee..4a939c90dc2e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1121,6 +1121,9 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[] + * in sync with the definitions below. + */ enum bpf_link_type { BPF_LINK_TYPE_UNSPEC = 0, BPF_LINK_TYPE_RAW_TRACEPOINT = 1, @@ -6047,11 +6050,6 @@ enum { BPF_F_MARK_ENFORCE = (1ULL << 6), }; -/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -enum { - BPF_F_INGRESS = (1ULL << 0), -}; - /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ enum { BPF_F_TUNINFO_IPV6 = (1ULL << 0), @@ -6198,10 +6196,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; -/* Flags for bpf_redirect_map helper */ +/* Flags for bpf_redirect and bpf_redirect_map helpers */ enum { - BPF_F_BROADCAST = (1ULL << 3), - BPF_F_EXCLUDE_INGRESS = (1ULL << 4), + BPF_F_INGRESS = (1ULL << 0), /* used for skb path */ + BPF_F_BROADCAST = (1ULL << 3), /* used for XDP path */ + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), /* used for XDP path */ +#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) }; #define __bpf_md_ptr(type, name) \ diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 4ae8b1ee0444..059b6537f2b7 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -387,11 +387,19 @@ struct iommu_vfio_ioas { * enforced on device attachment * @IOMMU_HWPT_FAULT_ID_VALID: The fault_id field of hwpt allocation data is * valid. + * @IOMMU_HWPT_ALLOC_PASID: Requests a domain that can be used with PASID. The + * domain can be attached to any PASID on the device. + * Any domain attached to the non-PASID part of the + * device must also be flaged, otherwise attaching a + * PASID will blocked. + * If IOMMU does not support PASID it will return + * error (-EOPNOTSUPP). */ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, IOMMU_HWPT_FAULT_ID_VALID = 1 << 2, + IOMMU_HWPT_ALLOC_PASID = 1 << 3, }; /** diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index c8dc5f8ea699..12873639ea96 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -175,7 +175,13 @@ /* use ioctl encoding for uring command */ #define UBLK_F_CMD_IOCTL_ENCODE (1UL << 6) -/* Copy between request and user buffer by pread()/pwrite() */ +/* + * Copy between request and user buffer by pread()/pwrite() + * + * Not available for UBLK_F_UNPRIVILEGED_DEV, otherwise userspace may + * deceive us by not filling request buffer, then kernel uninitialized + * data may be leaked. + */ #define UBLK_F_USER_COPY (1UL << 7) /* diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 99333cbd3114..c117672d4439 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -88,7 +88,7 @@ /* ABI version */ #define SND_SOC_TPLG_ABI_VERSION 0x5 /* current version */ -#define SND_SOC_TPLG_ABI_VERSION_MIN 0x4 /* oldest version supported */ +#define SND_SOC_TPLG_ABI_VERSION_MIN 0x5 /* oldest version supported */ /* Max size of TLV data */ #define SND_SOC_TPLG_TLV_SIZE 32 diff --git a/include/video/da8xx-fb.h b/include/video/da8xx-fb.h deleted file mode 100644 index 1d19ae62b844..000000000000 --- a/include/video/da8xx-fb.h +++ /dev/null @@ -1,94 +0,0 @@ -/* - * Header file for TI DA8XX LCD controller platform data. - * - * Copyright (C) 2008-2009 MontaVista Software Inc. - * Copyright (C) 2008-2009 Texas Instruments Inc - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef DA8XX_FB_H -#define DA8XX_FB_H - -enum panel_shade { - MONOCHROME = 0, - COLOR_ACTIVE, - COLOR_PASSIVE, -}; - -enum raster_load_mode { - LOAD_DATA = 1, - LOAD_PALETTE, -}; - -enum da8xx_frame_complete { - DA8XX_FRAME_WAIT, - DA8XX_FRAME_NOWAIT, -}; - -struct da8xx_lcdc_platform_data { - const char manu_name[10]; - void *controller_data; - const char type[25]; -}; - -struct lcd_ctrl_config { - enum panel_shade panel_shade; - - /* AC Bias Pin Frequency */ - int ac_bias; - - /* AC Bias Pin Transitions per Interrupt */ - int ac_bias_intrpt; - - /* DMA burst size */ - int dma_burst_sz; - - /* Bits per pixel */ - int bpp; - - /* FIFO DMA Request Delay */ - int fdd; - - /* TFT Alternative Signal Mapping (Only for active) */ - unsigned char tft_alt_mode; - - /* 12 Bit Per Pixel (5-6-5) Mode (Only for passive) */ - unsigned char stn_565_mode; - - /* Mono 8-bit Mode: 1=D0-D7 or 0=D0-D3 */ - unsigned char mono_8bit_mode; - - /* Horizontal and Vertical Sync Edge: 0=rising 1=falling */ - unsigned char sync_edge; - - /* Raster Data Order Select: 1=Most-to-least 0=Least-to-most */ - unsigned char raster_order; - - /* DMA FIFO threshold */ - int fifo_th; -}; - -struct lcd_sync_arg { - int back_porch; - int front_porch; - int pulse_width; -}; - -/* ioctls */ -#define FBIOGET_CONTRAST _IOR('F', 1, int) -#define FBIOPUT_CONTRAST _IOW('F', 2, int) -#define FBIGET_BRIGHTNESS _IOR('F', 3, int) -#define FBIPUT_BRIGHTNESS _IOW('F', 3, int) -#define FBIGET_COLOR _IOR('F', 5, int) -#define FBIPUT_COLOR _IOW('F', 6, int) -#define FBIPUT_HSYNC _IOW('F', 9, int) -#define FBIPUT_VSYNC _IOW('F', 10, int) - -/* Proprietary FB_SYNC_ flags */ -#define FB_SYNC_CLK_INVERT 0x40000000 - -#endif /* ifndef DA8XX_FB_H */ - diff --git a/include/xen/acpi.h b/include/xen/acpi.h index daa96a22d257..c66a8461612e 100644 --- a/include/xen/acpi.h +++ b/include/xen/acpi.h @@ -35,6 +35,8 @@ #include <linux/types.h> +typedef int (*get_gsi_from_sbdf_t)(u32 sbdf); + #ifdef CONFIG_XEN_DOM0 #include <asm/xen/hypervisor.h> #include <xen/xen.h> @@ -72,6 +74,8 @@ int xen_acpi_get_gsi_info(struct pci_dev *dev, int *gsi_out, int *trigger_out, int *polarity_out); +void xen_acpi_register_get_gsi_func(get_gsi_from_sbdf_t func); +int xen_acpi_get_gsi_from_sbdf(u32 sbdf); #else static inline void xen_acpi_sleep_register(void) { @@ -89,12 +93,12 @@ static inline int xen_acpi_get_gsi_info(struct pci_dev *dev, { return -1; } -#endif -#ifdef CONFIG_XEN_PCI_STUB -int pcistub_get_gsi_from_sbdf(unsigned int sbdf); -#else -static inline int pcistub_get_gsi_from_sbdf(unsigned int sbdf) +static inline void xen_acpi_register_get_gsi_func(get_gsi_from_sbdf_t func) +{ +} + +static inline int xen_acpi_get_gsi_from_sbdf(u32 sbdf) { return -1; } |