diff options
Diffstat (limited to 'include')
48 files changed, 749 insertions, 411 deletions
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h index fcb61b4659b3..8666fe7f35d7 100644 --- a/include/asm-generic/futex.h +++ b/include/asm-generic/futex.h @@ -23,7 +23,9 @@ * * Return: * 0 - On success - * <0 - On error + * -EFAULT - User access resulted in a page fault + * -EAGAIN - Atomic operation was unable to complete due to contention + * -ENOSYS - Operation not supported */ static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr) @@ -85,7 +87,9 @@ out_pagefault_enable: * * Return: * 0 - On success - * <0 - On error + * -EFAULT - User access resulted in a page fault + * -EAGAIN - Atomic operation was unable to complete due to contention + * -ENOSYS - Function not implemented (only if !HAVE_FUTEX_CMPXCHG) */ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 303871651f8a..8f3bf95a36d1 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -19,12 +19,9 @@ #include <asm-generic/iomap.h> #endif +#include <asm/mmiowb.h> #include <asm-generic/pci_iomap.h> -#ifndef mmiowb -#define mmiowb() do {} while (0) -#endif - #ifndef __io_br #define __io_br() barrier() #endif @@ -49,7 +46,7 @@ /* serialize device access against a spin_unlock, usually handled there. */ #ifndef __io_aw -#define __io_aw() barrier() +#define __io_aw() mmiowb_set_pending() #endif #ifndef __io_pbw diff --git a/include/asm-generic/mmiowb.h b/include/asm-generic/mmiowb.h new file mode 100644 index 000000000000..9439ff037b2d --- /dev/null +++ b/include/asm-generic/mmiowb.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_MMIOWB_H +#define __ASM_GENERIC_MMIOWB_H + +/* + * Generic implementation of mmiowb() tracking for spinlocks. + * + * If your architecture doesn't ensure that writes to an I/O peripheral + * within two spinlocked sections on two different CPUs are seen by the + * peripheral in the order corresponding to the lock handover, then you + * need to follow these FIVE easy steps: + * + * 1. Implement mmiowb() (and arch_mmiowb_state() if you're fancy) + * in asm/mmiowb.h, then #include this file + * 2. Ensure your I/O write accessors call mmiowb_set_pending() + * 3. Select ARCH_HAS_MMIOWB + * 4. Untangle the resulting mess of header files + * 5. Complain to your architects + */ +#ifdef CONFIG_MMIOWB + +#include <linux/compiler.h> +#include <asm-generic/mmiowb_types.h> + +#ifndef arch_mmiowb_state +#include <asm/percpu.h> +#include <asm/smp.h> + +DECLARE_PER_CPU(struct mmiowb_state, __mmiowb_state); +#define __mmiowb_state() this_cpu_ptr(&__mmiowb_state) +#else +#define __mmiowb_state() arch_mmiowb_state() +#endif /* arch_mmiowb_state */ + +static inline void mmiowb_set_pending(void) +{ + struct mmiowb_state *ms = __mmiowb_state(); + ms->mmiowb_pending = ms->nesting_count; +} + +static inline void mmiowb_spin_lock(void) +{ + struct mmiowb_state *ms = __mmiowb_state(); + ms->nesting_count++; +} + +static inline void mmiowb_spin_unlock(void) +{ + struct mmiowb_state *ms = __mmiowb_state(); + + if (unlikely(ms->mmiowb_pending)) { + ms->mmiowb_pending = 0; + mmiowb(); + } + + ms->nesting_count--; +} +#else +#define mmiowb_set_pending() do { } while (0) +#define mmiowb_spin_lock() do { } while (0) +#define mmiowb_spin_unlock() do { } while (0) +#endif /* CONFIG_MMIOWB */ +#endif /* __ASM_GENERIC_MMIOWB_H */ diff --git a/include/asm-generic/mmiowb_types.h b/include/asm-generic/mmiowb_types.h new file mode 100644 index 000000000000..8eb0095655e7 --- /dev/null +++ b/include/asm-generic/mmiowb_types.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_MMIOWB_TYPES_H +#define __ASM_GENERIC_MMIOWB_TYPES_H + +#include <linux/types.h> + +struct mmiowb_state { + u16 nesting_count; + u16 mmiowb_pending; +}; + +#endif /* __ASM_GENERIC_MMIOWB_TYPES_H */ diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index fa782fba51ee..75d9d68a6de7 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1126,6 +1126,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, static inline void init_espfix_bsp(void) { } #endif +extern void __init pgd_cache_init(void); + #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) { diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h deleted file mode 100644 index 93e67a055a4d..000000000000 --- a/include/asm-generic/rwsem.h +++ /dev/null @@ -1,140 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_GENERIC_RWSEM_H -#define _ASM_GENERIC_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead." -#endif - -#ifdef __KERNEL__ - -/* - * R/W semaphores originally for PPC using the stuff in lib/rwsem.c. - * Adapted largely from include/asm-i386/rwsem.h - * by Paul Mackerras <paulus@samba.org>. - */ - -/* - * the semaphore definition - */ -#ifdef CONFIG_64BIT -# define RWSEM_ACTIVE_MASK 0xffffffffL -#else -# define RWSEM_ACTIVE_MASK 0x0000ffffL -#endif - -#define RWSEM_UNLOCKED_VALUE 0x00000000L -#define RWSEM_ACTIVE_BIAS 0x00000001L -#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -static inline void __down_read(struct rw_semaphore *sem) -{ - if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) - rwsem_down_read_failed(sem); -} - -static inline int __down_read_killable(struct rw_semaphore *sem) -{ - if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) { - if (IS_ERR(rwsem_down_read_failed_killable(sem))) - return -EINTR; - } - - return 0; -} - -static inline int __down_read_trylock(struct rw_semaphore *sem) -{ - long tmp; - - while ((tmp = atomic_long_read(&sem->count)) >= 0) { - if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, - tmp + RWSEM_ACTIVE_READ_BIAS)) { - return 1; - } - } - return 0; -} - -/* - * lock for writing - */ -static inline void __down_write(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, - &sem->count); - if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) - rwsem_down_write_failed(sem); -} - -static inline int __down_write_killable(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, - &sem->count); - if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) - if (IS_ERR(rwsem_down_write_failed_killable(sem))) - return -EINTR; - return 0; -} - -static inline int __down_write_trylock(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); - return tmp == RWSEM_UNLOCKED_VALUE; -} - -/* - * unlock after reading - */ -static inline void __up_read(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic_long_dec_return_release(&sem->count); - if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)) - rwsem_wake(sem); -} - -/* - * unlock after writing - */ -static inline void __up_write(struct rw_semaphore *sem) -{ - if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS, - &sem->count) < 0)) - rwsem_wake(sem); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - long tmp; - - /* - * When downgrading from exclusive to shared ownership, - * anything inside the write-locked region cannot leak - * into the read side. In contrast, anything in the - * read-locked region is ok to be re-ordered into the - * write side. As such, rely on RELEASE semantics. - */ - tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count); - if (tmp < 0) - rwsem_downgrade_wake(sem); -} - -#endif /* __KERNEL__ */ -#endif /* _ASM_GENERIC_RWSEM_H */ diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index d79abca81a52..d1779d442aa5 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -77,6 +77,20 @@ static inline int arch_is_kernel_data(unsigned long addr) } #endif +/* + * Check if an address is part of freed initmem. This is needed on architectures + * with virt == phys kernel mapping, for code that wants to check if an address + * is part of a static object within [_stext, _end]. After initmem is freed, + * memory can be allocated from it, and such allocations would then have + * addresses within the range [_stext, _end]. + */ +#ifndef arch_is_kernel_initmem_freed +static inline int arch_is_kernel_initmem_freed(unsigned long addr) +{ + return 0; +} +#endif + /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 6be86c1c5c58..480e5b2a5748 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -19,9 +19,140 @@ #include <linux/swap.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> +#include <asm/cacheflush.h> + +/* + * Blindly accessing user memory from NMI context can be dangerous + * if we're in the middle of switching the current user task or switching + * the loaded mm. + */ +#ifndef nmi_uaccess_okay +# define nmi_uaccess_okay() true +#endif #ifdef CONFIG_MMU +/* + * Generic MMU-gather implementation. + * + * The mmu_gather data structure is used by the mm code to implement the + * correct and efficient ordering of freeing pages and TLB invalidations. + * + * This correct ordering is: + * + * 1) unhook page + * 2) TLB invalidate page + * 3) free page + * + * That is, we must never free a page before we have ensured there are no live + * translations left to it. Otherwise it might be possible to observe (or + * worse, change) the page content after it has been reused. + * + * The mmu_gather API consists of: + * + * - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather + * + * Finish in particular will issue a (final) TLB invalidate and free + * all (remaining) queued pages. + * + * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA + * + * Defaults to flushing at tlb_end_vma() to reset the range; helps when + * there's large holes between the VMAs. + * + * - tlb_remove_page() / __tlb_remove_page() + * - tlb_remove_page_size() / __tlb_remove_page_size() + * + * __tlb_remove_page_size() is the basic primitive that queues a page for + * freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a + * boolean indicating if the queue is (now) full and a call to + * tlb_flush_mmu() is required. + * + * tlb_remove_page() and tlb_remove_page_size() imply the call to + * tlb_flush_mmu() when required and has no return value. + * + * - tlb_change_page_size() + * + * call before __tlb_remove_page*() to set the current page-size; implies a + * possible tlb_flush_mmu() call. + * + * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() + * + * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets + * related state, like the range) + * + * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees + * whatever pages are still batched. + * + * - mmu_gather::fullmm + * + * A flag set by tlb_gather_mmu() to indicate we're going to free + * the entire mm; this allows a number of optimizations. + * + * - We can ignore tlb_{start,end}_vma(); because we don't + * care about ranges. Everything will be shot down. + * + * - (RISC) architectures that use ASIDs can cycle to a new ASID + * and delay the invalidation until ASID space runs out. + * + * - mmu_gather::need_flush_all + * + * A flag that can be set by the arch code if it wants to force + * flush the entire TLB irrespective of the range. For instance + * x86-PAE needs this when changing top-level entries. + * + * And allows the architecture to provide and implement tlb_flush(): + * + * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make + * use of: + * + * - mmu_gather::start / mmu_gather::end + * + * which provides the range that needs to be flushed to cover the pages to + * be freed. + * + * - mmu_gather::freed_tables + * + * set when we freed page table pages + * + * - tlb_get_unmap_shift() / tlb_get_unmap_size() + * + * returns the smallest TLB entry size unmapped in this range. + * + * If an architecture does not provide tlb_flush() a default implementation + * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is + * specified, in which case we'll default to flush_tlb_mm(). + * + * Additionally there are a few opt-in features: + * + * HAVE_MMU_GATHER_PAGE_SIZE + * + * This ensures we call tlb_flush() every time tlb_change_page_size() actually + * changes the size and provides mmu_gather::page_size to tlb_flush(). + * + * HAVE_RCU_TABLE_FREE + * + * This provides tlb_remove_table(), to be used instead of tlb_remove_page() + * for page directores (__p*_free_tlb()). This provides separate freeing of + * the page-table pages themselves in a semi-RCU fashion (see comment below). + * Useful if your architecture doesn't use IPIs for remote TLB invalidates + * and therefore doesn't naturally serialize with software page-table walkers. + * + * When used, an architecture is expected to provide __tlb_remove_table() + * which does the actual freeing of these pages. + * + * HAVE_RCU_TABLE_NO_INVALIDATE + * + * This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before + * freeing the page-table pages. This can be avoided if you use + * HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux + * page-tables natively. + * + * MMU_GATHER_NO_RANGE + * + * Use this if your architecture lacks an efficient flush_tlb_range(). + */ + #ifdef CONFIG_HAVE_RCU_TABLE_FREE /* * Semi RCU freeing of the page directories. @@ -60,11 +191,11 @@ struct mmu_table_batch { #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) -extern void tlb_table_flush(struct mmu_gather *tlb); extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #endif +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. @@ -89,14 +220,21 @@ struct mmu_gather_batch { */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) -/* struct mmu_gather is an opaque type used by the mm code for passing around +extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, + int page_size); +#endif + +/* + * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; + #ifdef CONFIG_HAVE_RCU_TABLE_FREE struct mmu_table_batch *batch; #endif + unsigned long start; unsigned long end; /* @@ -124,23 +262,30 @@ struct mmu_gather { unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; + /* + * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma + */ + unsigned int vma_exec : 1; + unsigned int vma_huge : 1; + + unsigned int batch_count; + +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; - unsigned int batch_count; - int page_size; -}; -#define HAVE_GENERIC_MMU_GATHER +#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE + unsigned int page_size; +#endif +#endif +}; void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); void tlb_flush_mmu(struct mmu_gather *tlb); void arch_tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end, bool force); -void tlb_flush_mmu_free(struct mmu_gather *tlb); -extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, - int page_size); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, @@ -163,8 +308,94 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; + /* + * Do not reset mmu_gather::vma_* fields here, we do not + * call into tlb_start_vma() again to set them if there is an + * intermediate flush. + */ +} + +#ifdef CONFIG_MMU_GATHER_NO_RANGE + +#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma) +#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma() +#endif + +/* + * When an architecture does not have efficient means of range flushing TLBs + * there is no point in doing intermediate flushes on tlb_end_vma() to keep the + * range small. We equally don't have to worry about page granularity or other + * things. + * + * All we need to do is issue a full flush for any !0 range. + */ +static inline void tlb_flush(struct mmu_gather *tlb) +{ + if (tlb->end) + flush_tlb_mm(tlb->mm); +} + +static inline void +tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } + +#define tlb_end_vma tlb_end_vma +static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { } + +#else /* CONFIG_MMU_GATHER_NO_RANGE */ + +#ifndef tlb_flush + +#if defined(tlb_start_vma) || defined(tlb_end_vma) +#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma() +#endif + +/* + * When an architecture does not provide its own tlb_flush() implementation + * but does have a reasonably efficient flush_vma_range() implementation + * use that. + */ +static inline void tlb_flush(struct mmu_gather *tlb) +{ + if (tlb->fullmm || tlb->need_flush_all) { + flush_tlb_mm(tlb->mm); + } else if (tlb->end) { + struct vm_area_struct vma = { + .vm_mm = tlb->mm, + .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | + (tlb->vma_huge ? VM_HUGETLB : 0), + }; + + flush_tlb_range(&vma, tlb->start, tlb->end); + } +} + +static inline void +tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + /* + * flush_tlb_range() implementations that look at VM_HUGETLB (tile, + * mips-4k) flush only large pages. + * + * flush_tlb_range() implementations that flush I-TLB also flush D-TLB + * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing + * range. + * + * We rely on tlb_end_vma() to issue a flush, such that when we reset + * these values the batch is empty. + */ + tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB); + tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); } +#else + +static inline void +tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } + +#endif + +#endif /* CONFIG_MMU_GATHER_NO_RANGE */ + static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { if (!tlb->end) @@ -196,21 +427,18 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) return tlb_remove_page_size(tlb, page, PAGE_SIZE); } -#ifndef tlb_remove_check_page_size_change -#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change -static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, +static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { - /* - * We don't care about page size change, just update - * mmu_gather page size here so that debug checks - * doesn't throw false warning. - */ -#ifdef CONFIG_DEBUG_VM +#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE + if (tlb->page_size && tlb->page_size != page_size) { + if (!tlb->fullmm) + tlb_flush_mmu(tlb); + } + tlb->page_size = page_size; #endif } -#endif static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) { @@ -237,17 +465,30 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) * the vmas are adjusted to only cover the region to be torn down. */ #ifndef tlb_start_vma -#define tlb_start_vma(tlb, vma) do { } while (0) -#endif +static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + if (tlb->fullmm) + return; -#define __tlb_end_vma(tlb, vma) \ - do { \ - if (!tlb->fullmm) \ - tlb_flush_mmu_tlbonly(tlb); \ - } while (0) + tlb_update_vma_flags(tlb, vma); + flush_cache_range(vma, vma->vm_start, vma->vm_end); +} +#endif #ifndef tlb_end_vma -#define tlb_end_vma __tlb_end_vma +static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + if (tlb->fullmm) + return; + + /* + * Do a TLB flush and reset the range at VMA boundaries; this avoids + * the ranges growing with the unused space between consecutive VMAs, + * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on + * this. + */ + tlb_flush_mmu_tlbonly(tlb); +} #endif #ifndef __tlb_remove_tlb_entry @@ -372,6 +613,4 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) #endif /* CONFIG_MMU */ -#define tlb_migrate_finish(mm) do {} while (0) - #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 38cd77b39a64..723e4dfa1c14 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -26,6 +26,14 @@ #define IORT_IRQ_MASK(irq) (irq & 0xffffffffULL) #define IORT_IRQ_TRIGGER_MASK(irq) ((irq >> 32) & 0xffffffffULL) +/* + * PMCG model identifiers for use in smmu pmu driver. Please note + * that this is purely for the use of software and has nothing to + * do with hardware or with IORT specification. + */ +#define IORT_SMMU_V3_PMCG_GENERIC 0x00000000 /* Generic SMMUv3 PMCG */ +#define IORT_SMMU_V3_PMCG_HISI_HIP08 0x00000001 /* HiSilicon HIP08 PMCG */ + int iort_register_domain_token(int trans_id, phys_addr_t base, struct fwnode_handle *fw_node); void iort_deregister_domain_token(int trans_id); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f02367faa58d..944ccc310201 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -510,7 +510,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, } \ _out: \ rcu_read_unlock(); \ - preempt_enable_no_resched(); \ + preempt_enable(); \ _ret; \ }) diff --git a/include/linux/clk.h b/include/linux/clk.h index d8bc1a856b39..f689fc58d7be 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -811,6 +811,22 @@ static inline bool clk_has_parent(struct clk *clk, struct clk *parent) return true; } +static inline int clk_set_rate_range(struct clk *clk, unsigned long min, + unsigned long max) +{ + return 0; +} + +static inline int clk_set_min_rate(struct clk *clk, unsigned long rate) +{ + return 0; +} + +static inline int clk_set_max_rate(struct clk *clk, unsigned long rate) +{ + return 0; +} + static inline int clk_set_parent(struct clk *clk, struct clk *parent) { return 0; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 445348facea9..d58aa0db05f9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -67,7 +67,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, .line = __LINE__, \ }; \ ______r = !!(cond); \ - ______f.miss_hit[______r]++; \ + ______r ? ______f.miss_hit[1]++ : ______f.miss_hit[0]++;\ ______r; \ })) #endif /* CONFIG_PROFILE_ALL_BRANCHES */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 5041357d0297..732745f865b7 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -137,9 +137,26 @@ static inline int disable_nonboot_cpus(void) return freeze_secondary_cpus(0); } extern void enable_nonboot_cpus(void); + +static inline int suspend_disable_secondary_cpus(void) +{ + int cpu = 0; + + if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) + cpu = -1; + + return freeze_secondary_cpus(cpu); +} +static inline void suspend_enable_secondary_cpus(void) +{ + return enable_nonboot_cpus(); +} + #else /* !CONFIG_PM_SLEEP_SMP */ static inline int disable_nonboot_cpus(void) { return 0; } static inline void enable_nonboot_cpus(void) {} +static inline int suspend_disable_secondary_cpus(void) { return 0; } +static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ void cpu_startup_entry(enum cpuhp_state state); @@ -175,6 +192,7 @@ enum cpuhp_smt_control { CPU_SMT_DISABLED, CPU_SMT_FORCE_DISABLED, CPU_SMT_NOT_SUPPORTED, + CPU_SMT_NOT_IMPLEMENTED, }; #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) @@ -182,9 +200,33 @@ extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); extern void cpu_smt_check_topology(void); #else -# define cpu_smt_control (CPU_SMT_ENABLED) +# define cpu_smt_control (CPU_SMT_NOT_IMPLEMENTED) static inline void cpu_smt_disable(bool force) { } static inline void cpu_smt_check_topology(void) { } #endif +/* + * These are used for a global "mitigations=" cmdline option for toggling + * optional CPU mitigations. + */ +enum cpu_mitigations { + CPU_MITIGATIONS_OFF, + CPU_MITIGATIONS_AUTO, + CPU_MITIGATIONS_AUTO_NOSMT, +}; + +extern enum cpu_mitigations cpu_mitigations; + +/* mitigations=off */ +static inline bool cpu_mitigations_off(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_OFF; +} + +/* mitigations=auto,nosmt */ +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; +} + #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/dmi.h b/include/linux/dmi.h index c46fdb36700b..8de8c4f15163 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -102,9 +102,7 @@ const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list); extern const char * dmi_get_system_info(int field); extern const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from); -extern void dmi_scan_machine(void); -extern void dmi_memdev_walk(void); -extern void dmi_set_dump_stack_arch_desc(void); +extern void dmi_setup(void); extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp); extern int dmi_get_bios_year(void); extern int dmi_name_in_vendors(const char *str); @@ -122,9 +120,7 @@ static inline int dmi_check_system(const struct dmi_system_id *list) { return 0; static inline const char * dmi_get_system_info(int field) { return NULL; } static inline const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from) { return NULL; } -static inline void dmi_scan_machine(void) { return; } -static inline void dmi_memdev_walk(void) { } -static inline void dmi_set_dump_stack_arch_desc(void) { } +static inline void dmi_setup(void) { } static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp) { if (yearp) diff --git a/include/linux/filter.h b/include/linux/filter.h index 6074aa064b54..7d3abde3f183 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -20,6 +20,7 @@ #include <linux/set_memory.h> #include <linux/kallsyms.h> #include <linux/if_vlan.h> +#include <linux/vmalloc.h> #include <net/sch_generic.h> @@ -503,7 +504,6 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ - undo_set_mem:1, /* Passed set_memory_ro() checkpoint */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -733,24 +733,15 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { - fp->undo_set_mem = 1; + set_vm_flush_reset_perms(fp); set_memory_ro((unsigned long)fp, fp->pages); } -static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) -{ - if (fp->undo_set_mem) - set_memory_rw((unsigned long)fp, fp->pages); -} - static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { + set_vm_flush_reset_perms(hdr); set_memory_ro((unsigned long)hdr, hdr->pages); -} - -static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) -{ - set_memory_rw((unsigned long)hdr, hdr->pages); + set_memory_x((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * @@ -788,7 +779,6 @@ void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { - bpf_prog_unlock_ro(fp); __bpf_prog_free(fp); } diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 730876187344..20899919ead8 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -241,21 +241,11 @@ static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { #ifdef CONFIG_STACK_TRACER -#define STACK_TRACE_ENTRIES 500 - -struct stack_trace; - -extern unsigned stack_trace_index[]; -extern struct stack_trace stack_trace_max; -extern unsigned long stack_trace_max_size; -extern arch_spinlock_t stack_trace_max_lock; - extern int stack_tracer_enabled; -void stack_trace_print(void); -int -stack_trace_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + +int stack_trace_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ DECLARE_PER_CPU(int, disable_stack_tracer); diff --git a/include/linux/ima.h b/include/linux/ima.h index dc12fbcf484c..fd9f7cf4cdf5 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -31,7 +31,7 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern void ima_add_kexec_buffer(struct kimage *image); #endif -#if defined(CONFIG_X86) && defined(CONFIG_EFI) +#if (defined(CONFIG_X86) && defined(CONFIG_EFI)) || defined(CONFIG_S390) extern bool arch_ima_get_secureboot(void); extern const char * const *arch_get_ima_policy(void); #else diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 690b238a44d5..c7eef32e7739 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -668,31 +668,6 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); extern void tasklet_init(struct tasklet_struct *t, void (*func)(unsigned long), unsigned long data); -struct tasklet_hrtimer { - struct hrtimer timer; - struct tasklet_struct tasklet; - enum hrtimer_restart (*function)(struct hrtimer *); -}; - -extern void -tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, - enum hrtimer_restart (*function)(struct hrtimer *), - clockid_t which_clock, enum hrtimer_mode mode); - -static inline -void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time, - const enum hrtimer_mode mode) -{ - hrtimer_start(&ttimer->timer, time, mode); -} - -static inline -void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer) -{ - hrtimer_cancel(&ttimer->timer); - tasklet_kill(&ttimer->tasklet); -} - /* * Autoprobing for irqs: * diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h index a49f2b45b3f0..42710d5949ba 100644 --- a/include/linux/jump_label_ratelimit.h +++ b/include/linux/jump_label_ratelimit.h @@ -12,21 +12,79 @@ struct static_key_deferred { struct delayed_work work; }; -extern void static_key_slow_dec_deferred(struct static_key_deferred *key); -extern void static_key_deferred_flush(struct static_key_deferred *key); +struct static_key_true_deferred { + struct static_key_true key; + unsigned long timeout; + struct delayed_work work; +}; + +struct static_key_false_deferred { + struct static_key_false key; + unsigned long timeout; + struct delayed_work work; +}; + +#define static_key_slow_dec_deferred(x) \ + __static_key_slow_dec_deferred(&(x)->key, &(x)->work, (x)->timeout) +#define static_branch_slow_dec_deferred(x) \ + __static_key_slow_dec_deferred(&(x)->key.key, &(x)->work, (x)->timeout) + +#define static_key_deferred_flush(x) \ + __static_key_deferred_flush((x), &(x)->work) + +extern void +__static_key_slow_dec_deferred(struct static_key *key, + struct delayed_work *work, + unsigned long timeout); +extern void __static_key_deferred_flush(void *key, struct delayed_work *work); extern void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); +extern void jump_label_update_timeout(struct work_struct *work); + +#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl) \ + struct static_key_true_deferred name = { \ + .key = { STATIC_KEY_INIT_TRUE }, \ + .timeout = (rl), \ + .work = __DELAYED_WORK_INITIALIZER((name).work, \ + jump_label_update_timeout, \ + 0), \ + } + +#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl) \ + struct static_key_false_deferred name = { \ + .key = { STATIC_KEY_INIT_FALSE }, \ + .timeout = (rl), \ + .work = __DELAYED_WORK_INITIALIZER((name).work, \ + jump_label_update_timeout, \ + 0), \ + } + +#define static_branch_deferred_inc(x) static_branch_inc(&(x)->key) + #else /* !CONFIG_JUMP_LABEL */ struct static_key_deferred { struct static_key key; }; +struct static_key_true_deferred { + struct static_key_true key; +}; +struct static_key_false_deferred { + struct static_key_false key; +}; +#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl) \ + struct static_key_true_deferred name = { STATIC_KEY_TRUE_INIT } +#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl) \ + struct static_key_false_deferred name = { STATIC_KEY_FALSE_INIT } + +#define static_branch_slow_dec_deferred(x) static_branch_dec(&(x)->key) + static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) { STATIC_KEY_CHECK_USE(key); static_key_slow_dec(&key->key); } -static inline void static_key_deferred_flush(struct static_key_deferred *key) +static inline void static_key_deferred_flush(void *key) { STATIC_KEY_CHECK_USE(key); } diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 79c3873d58ac..6e2377e6c1d6 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -66,6 +66,11 @@ struct lock_class_key { extern struct lock_class_key __lockdep_no_validate__; +struct lock_trace { + unsigned int nr_entries; + unsigned int offset; +}; + #define LOCKSTAT_POINTS 4 /* @@ -100,7 +105,7 @@ struct lock_class { * IRQ/softirq usage tracking bits: */ unsigned long usage_mask; - struct stack_trace usage_traces[XXX_LOCK_USAGE_STATES]; + struct lock_trace usage_traces[XXX_LOCK_USAGE_STATES]; /* * Generation counter, when doing certain classes of graph walking, @@ -188,7 +193,7 @@ struct lock_list { struct list_head entry; struct lock_class *class; struct lock_class *links_to; - struct stack_trace trace; + struct lock_trace trace; int distance; /* @@ -471,7 +476,7 @@ struct pin_cookie { }; #define NIL_COOKIE (struct pin_cookie){ } -#define lockdep_pin_lock(l) ({ struct pin_cookie cookie; cookie; }) +#define lockdep_pin_lock(l) ({ struct pin_cookie cookie = { }; cookie; }) #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) diff --git a/include/linux/mm.h b/include/linux/mm.h index 6b10c21630f5..083d7b4863ed 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2610,37 +2610,31 @@ static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } #endif -#ifdef CONFIG_DEBUG_PAGEALLOC extern bool _debug_pagealloc_enabled; -extern void __kernel_map_pages(struct page *page, int numpages, int enable); static inline bool debug_pagealloc_enabled(void) { - return _debug_pagealloc_enabled; + return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled; } +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) +extern void __kernel_map_pages(struct page *page, int numpages, int enable); + static inline void kernel_map_pages(struct page *page, int numpages, int enable) { - if (!debug_pagealloc_enabled()) - return; - __kernel_map_pages(page, numpages, enable); } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); #endif /* CONFIG_HIBERNATION */ -#else /* CONFIG_DEBUG_PAGEALLOC */ +#else /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } #endif /* CONFIG_HIBERNATION */ -static inline bool debug_pagealloc_enabled(void) -{ - return false; -} -#endif /* CONFIG_DEBUG_PAGEALLOC */ +#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ef764f613..15a82ff0aefe 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -240,7 +240,6 @@ struct perf_event; #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 -#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 @@ -464,7 +463,7 @@ enum perf_addr_filter_action_t { /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage - * @inode: object file's inode for file-based filters + * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop @@ -888,6 +887,9 @@ extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); + +extern void perf_pmu_resched(struct pmu *pmu); + extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); @@ -1055,12 +1057,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo #endif /* - * Take a snapshot of the regs. Skip ip and frame pointer to - * the nth caller. We only need a few of the regs: + * When generating a perf sample in-line, instead of from an interrupt / + * exception, we lack a pt_regs. This is typically used from software events + * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. + * + * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests - * - bp for callchains - * - eflags, for future purposes, just in case + * - sp for PERF_SAMPLE_CALLCHAIN + * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) + * + * NOTE: assumes @regs is otherwise already 0 filled; this is important for + * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index f6165d304b4d..48841e5dab90 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1338,7 +1338,6 @@ static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) } /* Let SB update */ - mmiowb(); return rc; } @@ -1374,7 +1373,6 @@ static inline void qed_sb_ack(struct qed_sb_info *sb_info, /* Both segments (interrupts & acks) are written to same place address; * Need to guarantee all commands will be received (in-order) by HW. */ - mmiowb(); barrier(); } diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 6cdb1db776cf..922bb6848813 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -878,9 +878,11 @@ static inline void rcu_head_init(struct rcu_head *rhp) static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { - if (READ_ONCE(rhp->func) == f) + rcu_callback_t func = READ_ONCE(rhp->func); + + if (func == f) return true; - WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L); + WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 90bfa3279a01..563290fc194f 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -18,7 +18,7 @@ * awoken. */ struct rcuwait { - struct task_struct *task; + struct task_struct __rcu *task; }; #define __RCUWAIT_INITIALIZER(name) \ diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h deleted file mode 100644 index e47568363e5e..000000000000 --- a/include/linux/rwsem-spinlock.h +++ /dev/null @@ -1,47 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* rwsem-spinlock.h: fallback C implementation - * - * Copyright (c) 2001 David Howells (dhowells@redhat.com). - * - Derived partially from ideas by Andrea Arcangeli <andrea@suse.de> - * - Derived also from comments by Linus - */ - -#ifndef _LINUX_RWSEM_SPINLOCK_H -#define _LINUX_RWSEM_SPINLOCK_H - -#ifndef _LINUX_RWSEM_H -#error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ -/* - * the rw-semaphore definition - * - if count is 0 then there are no active readers or writers - * - if count is +ve then that is the number of active readers - * - if count is -1 then there is one active writer - * - if wait_list is not empty, then there are processes waiting for the semaphore - */ -struct rw_semaphore { - __s32 count; - raw_spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - -#define RWSEM_UNLOCKED_VALUE 0x00000000 - -extern void __down_read(struct rw_semaphore *sem); -extern int __must_check __down_read_killable(struct rw_semaphore *sem); -extern int __down_read_trylock(struct rw_semaphore *sem); -extern void __down_write(struct rw_semaphore *sem); -extern int __must_check __down_write_killable(struct rw_semaphore *sem); -extern int __down_write_trylock(struct rw_semaphore *sem); -extern void __up_read(struct rw_semaphore *sem); -extern void __up_write(struct rw_semaphore *sem); -extern void __downgrade_write(struct rw_semaphore *sem); -extern int rwsem_is_locked(struct rw_semaphore *sem); - -#endif /* __KERNEL__ */ -#endif /* _LINUX_RWSEM_SPINLOCK_H */ diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 67dbb57508b1..2ea18a3def04 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -20,25 +20,30 @@ #include <linux/osq_lock.h> #endif -struct rw_semaphore; - -#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK -#include <linux/rwsem-spinlock.h> /* use a generic implementation */ -#define __RWSEM_INIT_COUNT(name) .count = RWSEM_UNLOCKED_VALUE -#else -/* All arch specific implementations share the same struct */ +/* + * For an uncontended rwsem, count and owner are the only fields a task + * needs to touch when acquiring the rwsem. So they are put next to each + * other to increase the chance that they will share the same cacheline. + * + * In a contended rwsem, the owner is likely the most frequently accessed + * field in the structure as the optimistic waiter that holds the osq lock + * will spin on owner. For an embedded rwsem, other hot fields in the + * containing structure should be moved further away from the rwsem to + * reduce the chance that they will share the same cacheline causing + * cacheline bouncing problem. + */ struct rw_semaphore { atomic_long_t count; - struct list_head wait_list; - raw_spinlock_t wait_lock; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER - struct optimistic_spin_queue osq; /* spinner MCS lock */ /* * Write owner. Used as a speculative check to see * if the owner is running on the cpu. */ struct task_struct *owner; + struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif + raw_spinlock_t wait_lock; + struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif @@ -50,24 +55,14 @@ struct rw_semaphore { */ #define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-2L) -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - -/* Include the arch specific part */ -#include <asm/rwsem.h> - /* In all implementations count != 0 means locked */ static inline int rwsem_is_locked(struct rw_semaphore *sem) { return atomic_long_read(&sem->count) != 0; } +#define RWSEM_UNLOCKED_VALUE 0L #define __RWSEM_INIT_COUNT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) -#endif /* Common initializer macros and functions */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 1549584a1538..50606a6e73d6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1057,7 +1057,6 @@ struct task_struct { #ifdef CONFIG_RSEQ struct rseq __user *rseq; - u32 rseq_len; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically @@ -1855,12 +1854,10 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { if (clone_flags & CLONE_THREAD) { t->rseq = NULL; - t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } else { t->rseq = current->rseq; - t->rseq_len = current->rseq_len; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; } @@ -1869,7 +1866,6 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) static inline void rseq_execve(struct task_struct *t) { t->rseq = NULL; - t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 2e97a2227045..f1227f2c38a4 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -76,6 +76,7 @@ extern void exit_itimers(struct signal_struct *); extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); +struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 57c7ed3fe465..cfc0a89a7159 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -76,8 +76,8 @@ struct sched_domain_shared { struct sched_domain { /* These fields must be setup */ - struct sched_domain *parent; /* top domain must be null terminated */ - struct sched_domain *child; /* bottom domain must be null terminated */ + struct sched_domain __rcu *parent; /* top domain must be null terminated */ + struct sched_domain __rcu *child; /* bottom domain must be null terminated */ struct sched_group *groups; /* the balancing groups of the domain */ unsigned long min_interval; /* Minimum balance interval ms */ unsigned long max_interval; /* Maximum balance interval ms */ diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 2a986d282a97..b5071497b8cb 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -17,6 +17,17 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif +#ifndef CONFIG_ARCH_HAS_SET_DIRECT_MAP +static inline int set_direct_map_invalid_noflush(struct page *page) +{ + return 0; +} +static inline int set_direct_map_default_noflush(struct page *page) +{ + return 0; +} +#endif + #ifndef set_mce_nospec static inline int set_mce_nospec(unsigned long pfn) { diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index d0884b525001..9d1bc65d226c 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -29,7 +29,7 @@ struct smpboot_thread_data; * @thread_comm: The base name of the thread */ struct smp_hotplug_thread { - struct task_struct __percpu **store; + struct task_struct * __percpu *store; struct list_head list; int (*thread_should_run)(unsigned int cpu); void (*thread_fn)(unsigned int cpu); diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index e089157dcf97..ed7c4d6b8235 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -57,6 +57,7 @@ #include <linux/stringify.h> #include <linux/bottom_half.h> #include <asm/barrier.h> +#include <asm/mmiowb.h> /* @@ -178,6 +179,7 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); + mmiowb_spin_lock(); } #ifndef arch_spin_lock_flags @@ -189,15 +191,22 @@ do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lo { __acquire(lock); arch_spin_lock_flags(&lock->raw_lock, *flags); + mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { - return arch_spin_trylock(&(lock)->raw_lock); + int ret = arch_spin_trylock(&(lock)->raw_lock); + + if (ret) + mmiowb_spin_lock(); + + return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { + mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } diff --git a/include/linux/srcu.h b/include/linux/srcu.h index c495b2d51569..e432cc92c73d 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -56,45 +56,11 @@ struct srcu_struct { }; void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); -void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced); +void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); -/** - * cleanup_srcu_struct - deconstruct a sleep-RCU structure - * @ssp: structure to clean up. - * - * Must invoke this after you are finished using a given srcu_struct that - * was initialized via init_srcu_struct(), else you leak memory. - */ -static inline void cleanup_srcu_struct(struct srcu_struct *ssp) -{ - _cleanup_srcu_struct(ssp, false); -} - -/** - * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure - * @ssp: structure to clean up. - * - * Must invoke this after you are finished using a given srcu_struct that - * was initialized via init_srcu_struct(), else you leak memory. Also, - * all grace-period processing must have completed. - * - * "Completed" means that the last synchronize_srcu() and - * synchronize_srcu_expedited() calls must have returned before the call - * to cleanup_srcu_struct_quiesced(). It also means that the callback - * from the last call_srcu() must have been invoked before the call to - * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help - * with this last. Violating these rules will get you a WARN_ON() splat - * (with high probability, anyway), and will also cause the srcu_struct - * to be leaked. - */ -static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *ssp) -{ - _cleanup_srcu_struct(ssp, true); -} - #ifdef CONFIG_DEBUG_LOCK_ALLOC /** diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 7978b3e2c1e1..0805dee1b6b8 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -23,10 +23,10 @@ typedef u32 depot_stack_handle_t; -struct stack_trace; +depot_stack_handle_t stack_depot_save(unsigned long *entries, + unsigned int nr_entries, gfp_t gfp_flags); -depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags); - -void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace); +unsigned int stack_depot_fetch(depot_stack_handle_t handle, + unsigned long **entries); #endif diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index ba29a0613e66..f0cfd12cb45e 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -3,11 +3,64 @@ #define __LINUX_STACKTRACE_H #include <linux/types.h> +#include <asm/errno.h> struct task_struct; struct pt_regs; #ifdef CONFIG_STACKTRACE +void stack_trace_print(unsigned long *trace, unsigned int nr_entries, + int spaces); +int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, + unsigned int nr_entries, int spaces); +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_tsk(struct task_struct *task, + unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr); +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); + +/* Internal interfaces. Do not use in generic code */ +#ifdef CONFIG_ARCH_STACKWALK + +/** + * stack_trace_consume_fn - Callback for arch_stack_walk() + * @cookie: Caller supplied pointer handed back by arch_stack_walk() + * @addr: The stack entry address to consume + * @reliable: True when the stack entry is reliable. Required by + * some printk based consumers. + * + * Return: True, if the entry was consumed or skipped + * False, if there is no space left to store + */ +typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr, + bool reliable); +/** + * arch_stack_walk - Architecture specific function to walk the stack + * @consume_entry: Callback which is invoked by the architecture code for + * each entry. + * @cookie: Caller supplied pointer which is handed back to + * @consume_entry + * @task: Pointer to a task struct, can be NULL + * @regs: Pointer to registers, can be NULL + * + * ============ ======= ============================================ + * task regs + * ============ ======= ============================================ + * task NULL Stack trace from task (can be current) + * current regs Stack trace starting on regs->stackpointer + * ============ ======= ============================================ + */ +void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs); +int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task); +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs); + +#else /* CONFIG_ARCH_STACKWALK */ struct stack_trace { unsigned int nr_entries, max_entries; unsigned long *entries; @@ -21,24 +74,20 @@ extern void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace); extern int save_stack_trace_tsk_reliable(struct task_struct *tsk, struct stack_trace *trace); - -extern void print_stack_trace(struct stack_trace *trace, int spaces); -extern int snprint_stack_trace(char *buf, size_t size, - struct stack_trace *trace, int spaces); - -#ifdef CONFIG_USER_STACKTRACE_SUPPORT extern void save_stack_trace_user(struct stack_trace *trace); +#endif /* !CONFIG_ARCH_STACKWALK */ +#endif /* CONFIG_STACKTRACE */ + +#if defined(CONFIG_STACKTRACE) && defined(CONFIG_HAVE_RELIABLE_STACKTRACE) +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size); #else -# define save_stack_trace_user(trace) do { } while (0) +static inline int stack_trace_save_tsk_reliable(struct task_struct *tsk, + unsigned long *store, + unsigned int size) +{ + return -ENOSYS; +} #endif -#else /* !CONFIG_STACKTRACE */ -# define save_stack_trace(trace) do { } while (0) -# define save_stack_trace_tsk(tsk, trace) do { } while (0) -# define save_stack_trace_user(trace) do { } while (0) -# define print_stack_trace(trace, spaces) do { } while (0) -# define snprint_stack_trace(buf, size, trace, spaces) do { } while (0) -# define save_stack_trace_tsk_reliable(tsk, trace) ({ -ENOSYS; }) -#endif /* CONFIG_STACKTRACE */ - #endif /* __LINUX_STACKTRACE_H */ diff --git a/include/linux/tick.h b/include/linux/tick.h index 55388ab45fd4..76acb48acdb7 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -68,6 +68,12 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_offline_cpu(unsigned int cpu); +#else +static inline void tick_offline_cpu(unsigned int cpu) { } +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); #else diff --git a/include/linux/time64.h b/include/linux/time64.h index f38d382ffec1..a620ee610b9f 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -33,6 +33,17 @@ struct itimerspec64 { #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) +/* + * Limits for settimeofday(): + * + * To prevent setting the time close to the wraparound point time setting + * is limited so a reasonable uptime can be accomodated. Uptime of 30 years + * should be really sufficient, which means the cutoff is 2232. At that + * point the cutoff is just a small part of the larger problem. + */ +#define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) +#define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) + static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { @@ -100,6 +111,16 @@ static inline bool timespec64_valid_strict(const struct timespec64 *ts) return true; } +static inline bool timespec64_valid_settod(const struct timespec64 *ts) +{ + if (!timespec64_valid(ts)) + return false; + /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ + if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) + return false; + return true; +} + /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 37b226e8df13..2b70130af585 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -268,6 +268,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); #define user_access_end() do { } while (0) #define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) #define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) +static inline unsigned long user_access_save(void) { return 0UL; } +static inline void user_access_restore(unsigned long flags) { } #endif #ifdef CONFIG_HARDENED_USERCOPY diff --git a/include/linux/uio.h b/include/linux/uio.h index f184af1999a8..2d0131ad4604 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -60,7 +60,7 @@ struct iov_iter { static inline enum iter_type iov_iter_type(const struct iov_iter *i) { - return i->type & ~(READ | WRITE); + return i->type & ~(READ | WRITE | ITER_BVEC_FLAG_NO_REF); } static inline bool iter_is_iovec(const struct iov_iter *i) diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 103a48a48872..12bf0b68ed92 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -115,6 +115,7 @@ struct uprobes_state { struct xol_area *xol_area; }; +extern void __init uprobes_init(void); extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern bool is_swbp_insn(uprobe_opcode_t *insn); @@ -154,6 +155,10 @@ extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, struct uprobes_state { }; +static inline void uprobes_init(void) +{ +} + #define uprobe_get_trap_addr(regs) instruction_pointer(regs) static inline int diff --git a/include/linux/usb.h b/include/linux/usb.h index 5e49e82c4368..ff010d1fd1c7 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -200,7 +200,6 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. - * @pm_usage_cnt: PM usage counter for this interface * @reset_ws: Used for scheduling resets from atomic context. * @resetting_device: USB core reset the device, so use alt setting 0 as * current; needs bandwidth alloc after reset. @@ -257,7 +256,6 @@ struct usb_interface { struct device dev; /* interface specific device info */ struct device *usb_dev; - atomic_t pm_usage_cnt; /* usage counter for autosuspend */ struct work_struct reset_ws; /* for resets in atomic context */ }; #define to_usb_interface(d) container_of(d, struct usb_interface, dev) diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 398e9c95cd61..c6eebb839552 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -21,6 +21,11 @@ struct notifier_block; /* in notifier.h */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ +/* + * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with + * vfree_atomic(). + */ +#define VM_FLUSH_RESET_PERMS 0x00000100 /* Reset direct map and flush TLB on unmap */ /* bits [20..32] reserved for arch specific ioremap internals */ /* @@ -142,6 +147,13 @@ extern int map_kernel_range_noflush(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages); extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); extern void unmap_kernel_range(unsigned long addr, unsigned long size); +static inline void set_vm_flush_reset_perms(void *addr) +{ + struct vm_struct *vm = find_vm_area(addr); + + if (vm) + vm->flags |= VM_FLUSH_RESET_PERMS; +} #else static inline int map_kernel_range_noflush(unsigned long start, unsigned long size, @@ -157,6 +169,9 @@ static inline void unmap_kernel_range(unsigned long addr, unsigned long size) { } +static inline void set_vm_flush_reset_perms(void *addr) +{ +} #endif /* Allocate/destroy a 'vmalloc' VM area. */ diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index 6640f84fe536..6d5beac29bc1 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -105,7 +105,6 @@ enum sctp_verb { SCTP_CMD_T1_RETRAN, /* Mark for retransmission after T1 timeout */ SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */ SCTP_CMD_SEND_MSG, /* Send the whole use message */ - SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */ SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/ SCTP_CMD_SET_ASOC, /* Restore association context */ SCTP_CMD_LAST diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 85386becbaea..99f722c4d804 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -219,7 +219,7 @@ struct xfrm_state { struct xfrm_stats stats; struct xfrm_lifetime_cur curlft; - struct tasklet_hrtimer mtimer; + struct hrtimer mtimer; struct xfrm_state_offload xso; @@ -295,7 +295,8 @@ struct xfrm_replay { }; struct xfrm_if_cb { - struct xfrm_if *(*decode_session)(struct sk_buff *skb); + struct xfrm_if *(*decode_session)(struct sk_buff *skb, + unsigned short family); }; void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); @@ -1404,6 +1405,23 @@ static inline int xfrm_state_kern(const struct xfrm_state *x) return atomic_read(&x->tunnel_users); } +static inline bool xfrm_id_proto_valid(u8 proto) +{ + switch (proto) { + case IPPROTO_AH: + case IPPROTO_ESP: + case IPPROTO_COMP: +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: +#endif + return true; + default: + return false; + } +} + +/* IPSEC_PROTO_ANY only matches 3 IPsec protocols, 0 could match all. */ static inline int xfrm_id_proto_match(u8 proto, u8 userproto) { return (!userproto || proto == userproto || diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index a57e4ee989d6..b7a904825e7d 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -73,7 +73,7 @@ TRACE_EVENT(timer_start, __entry->flags = flags; ), - TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s", + TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->flags & TIMER_CPUMASK, @@ -89,23 +89,27 @@ TRACE_EVENT(timer_start, */ TRACE_EVENT(timer_expire_entry, - TP_PROTO(struct timer_list *timer), + TP_PROTO(struct timer_list *timer, unsigned long baseclk), - TP_ARGS(timer), + TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) + __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; + __entry->baseclk = baseclk; ), - TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now) + TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", + __entry->timer, __entry->function, __entry->now, + __entry->baseclk) ); /** @@ -210,7 +214,7 @@ TRACE_EVENT(hrtimer_start, __entry->mode = mode; ), - TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu " + TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, @@ -243,7 +247,8 @@ TRACE_EVENT(hrtimer_expire_entry, __entry->function = hrtimer->function; ), - TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function, + TP_printk("hrtimer=%p function=%ps now=%llu", + __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 02bb7ad6e986..8f10748dac79 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -353,6 +353,10 @@ struct vfio_region_gfx_edid { #define VFIO_DEVICE_GFX_LINK_STATE_DOWN 2 }; +#define VFIO_REGION_TYPE_CCW (2) +/* ccw sub-types */ +#define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1) + /* * 10de vendor sub-type * diff --git a/include/uapi/linux/vfio_ccw.h b/include/uapi/linux/vfio_ccw.h index 2ec5f367ff78..cbecbf0cd54f 100644 --- a/include/uapi/linux/vfio_ccw.h +++ b/include/uapi/linux/vfio_ccw.h @@ -12,6 +12,7 @@ #include <linux/types.h> +/* used for START SUBCHANNEL, always present */ struct ccw_io_region { #define ORB_AREA_SIZE 12 __u8 orb_area[ORB_AREA_SIZE]; @@ -22,4 +23,15 @@ struct ccw_io_region { __u32 ret_code; } __packed; +/* + * used for processing commands that trigger asynchronous actions + * Note: this is controlled by a capability + */ +#define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0) +#define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1) +struct ccw_cmd_region { + __u32 command; + __u32 ret_code; +} __packed; + #endif |