diff options
Diffstat (limited to 'include')
46 files changed, 620 insertions, 381 deletions
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/tlb.h b/include/asm-generic/tlb.h index 6be86c1c5c58..b9edc7608d90 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -19,9 +19,131 @@ #include <linux/swap.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> +#include <asm/cacheflush.h> #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 +182,11 @@ 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 +211,21 @@ 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 +253,30 @@ 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 +299,94 @@ 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 +418,18 @@ 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 +456,30 @@ 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 +604,4 @@ 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/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index cbf3180cb612..668ad971cd7b 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -420,7 +420,6 @@ extern struct ttm_bo_global { /** * Protected by ttm_global_mutex. */ - unsigned int use_count; struct list_head device_list; /** diff --git a/include/dt-bindings/clock/sifive-fu540-prci.h b/include/dt-bindings/clock/sifive-fu540-prci.h new file mode 100644 index 000000000000..6a0b70a37d78 --- /dev/null +++ b/include/dt-bindings/clock/sifive-fu540-prci.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018-2019 SiFive, Inc. + * Wesley Terpstra + * Paul Walmsley + */ + +#ifndef __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H +#define __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H + +/* Clock indexes for use by Device Tree data and the PRCI driver */ + +#define PRCI_CLK_COREPLL 0 +#define PRCI_CLK_DDRPLL 1 +#define PRCI_CLK_GEMGXLPLL 2 +#define PRCI_CLK_TLCLK 3 + +#endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c58a3b2bf00..317ab30d2904 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -548,7 +548,6 @@ struct request_queue { struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; struct percpu_ref q_usage_counter; - struct list_head all_q_node; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; 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/bvec.h b/include/linux/bvec.h index 3bc91879e1e2..ff13cbc1887d 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -160,8 +160,9 @@ static inline void bvec_advance(const struct bio_vec *bvec, bv->bv_page = nth_page(bv->bv_page, 1); bv->bv_offset = 0; } else { - bv->bv_page = bvec->bv_page; - bv->bv_offset = bvec->bv_offset; + bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset / + PAGE_SIZE); + bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); 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..2d9c6f4b78f5 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -187,4 +187,28 @@ 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/efi.h b/include/linux/efi.h index 54357a258b35..6ebc2098cfe1 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1611,7 +1611,12 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, struct screen_info *si, efi_guid_t *proto, unsigned long size); -bool efi_runtime_disabled(void); +#ifdef CONFIG_EFI +extern bool efi_runtime_disabled(void); +#else +static inline bool efi_runtime_disabled(void) { return true; } +#endif + extern void efi_call_virt_check_flags(unsigned long flags, const char *call); extern unsigned long efi_call_virt_save_flags(void); diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2e9e2763bf47..6e8bc53740f0 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -31,6 +31,7 @@ struct elevator_mq_ops { void (*exit_sched)(struct elevator_queue *); int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e2f3b21cd72a..aa8bfd6f738c 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -449,6 +449,18 @@ static inline void eth_addr_dec(u8 *addr) } /** + * eth_addr_inc() - Increment the given MAC address. + * @addr: Pointer to a six-byte array containing Ethernet address to increment. + */ +static inline void eth_addr_inc(u8 *addr) +{ + u64 u = ether_addr_to_u64(addr); + + u++; + u64_to_ether_addr(u, addr); +} + +/** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address 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/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/kprobes.h b/include/linux/kprobes.h index 201f0f2683f2..9a897256e481 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -173,6 +173,7 @@ struct kretprobe_instance { struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; + void *fp; char data[0]; }; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9d55c63db09b..640a03642766 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -28,6 +28,7 @@ #include <linux/irqbypass.h> #include <linux/swait.h> #include <linux/refcount.h> +#include <linux/nospec.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -513,10 +514,10 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { - /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case - * the caller has read kvm->online_vcpus before (as is the case - * for kvm_for_each_vcpu, for example). - */ + int num_vcpus = atomic_read(&kvm->online_vcpus); + i = array_index_nospec(i, num_vcpus); + + /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); return kvm->vcpus[i]; } @@ -600,6 +601,7 @@ void kvm_put_kvm(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { + as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); 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/netdevice.h b/include/linux/netdevice.h index 26f69cf763f4..324e872c91d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1500,6 +1500,7 @@ struct net_device_ops { * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device + * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1532,6 +1533,7 @@ enum netdev_priv_flags { IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, + IFF_LIVE_RENAME_OK = 1<<30, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1563,6 +1565,7 @@ enum netdev_priv_flags { #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER +#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK /** * struct net_device - The DEVICE structure. diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index cf023db0e8a2..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 diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index abb2dac3da9b..5c626fdc10db 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -176,6 +176,7 @@ void free_pipe_info(struct pipe_inode_info *); bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); +int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); 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/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/mm.h b/include/linux/sched/mm.h index 0cd9f10423fb..a3fda9f024c3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f3fb1edb3526..20d815a33145 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -21,6 +21,7 @@ struct shmem_inode_info { struct list_head swaplist; /* chain of maybes on swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ + atomic_t stop_eviction; /* hold when working on inode */ struct inode vfs_inode; }; 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/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/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/net/af_rxrpc.h b/include/net/af_rxrpc.h index 2bfb87eb98ce..78c856cba4f5 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -61,10 +61,12 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); -u32 rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *); +bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *, + u32 *); void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *); u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *, ktime_t *); +bool rxrpc_kernel_call_is_complete(struct rxrpc_call *); #endif /* _NET_RXRPC_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index bb307a11ee63..13bfeb712d36 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7183,6 +7183,11 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, #define wiphy_info(wiphy, format, args...) \ dev_info(&(wiphy)->dev, format, ##args) +#define wiphy_err_ratelimited(wiphy, format, args...) \ + dev_err_ratelimited(&(wiphy)->dev, format, ##args) +#define wiphy_warn_ratelimited(wiphy, format, args...) \ + dev_warn_ratelimited(&(wiphy)->dev, format, ##args) + #define wiphy_debug(wiphy, format, args...) \ wiphy_printk(KERN_DEBUG, wiphy, format, ##args) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ac2ed8ec662b..112dc18c658f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6231,8 +6231,6 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, * @hw: pointer as obtained from ieee80211_alloc_hw() * @ac: AC number to return packets from. * - * Should only be called between calls to ieee80211_txq_schedule_start() - * and ieee80211_txq_schedule_end(). * Returns the next txq if successful, %NULL if no queue is eligible. If a txq * is returned, it should be returned with ieee80211_return_txq() after the * driver has finished scheduling it. @@ -6240,51 +6238,58 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac); /** - * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() - * - * @hw: pointer as obtained from ieee80211_alloc_hw() - * @txq: pointer obtained from station or virtual interface - * - * Should only be called between calls to ieee80211_txq_schedule_start() - * and ieee80211_txq_schedule_end(). - */ -void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); - -/** - * ieee80211_txq_schedule_start - acquire locks for safe scheduling of an AC + * ieee80211_txq_schedule_start - start new scheduling round for TXQs * * @hw: pointer as obtained from ieee80211_alloc_hw() * @ac: AC number to acquire locks for * - * Acquire locks needed to schedule TXQs from the given AC. Should be called - * before ieee80211_next_txq() or ieee80211_return_txq(). + * Should be called before ieee80211_next_txq() or ieee80211_return_txq(). + * The driver must not call multiple TXQ scheduling rounds concurrently. */ -void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) - __acquires(txq_lock); +void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac); + +/* (deprecated) */ +static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) +{ +} + +void __ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, bool force); /** - * ieee80211_txq_schedule_end - release locks for safe scheduling of an AC + * ieee80211_schedule_txq - schedule a TXQ for transmission * * @hw: pointer as obtained from ieee80211_alloc_hw() - * @ac: AC number to acquire locks for + * @txq: pointer obtained from station or virtual interface * - * Release locks previously acquired by ieee80211_txq_schedule_end(). + * Schedules a TXQ for transmission if it is not already scheduled, + * even if mac80211 does not have any packets buffered. + * + * The driver may call this function if it has buffered packets for + * this TXQ internally. */ -void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) - __releases(txq_lock); +static inline void +ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) +{ + __ieee80211_schedule_txq(hw, txq, true); +} /** - * ieee80211_schedule_txq - schedule a TXQ for transmission + * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface + * @force: schedule txq even if mac80211 does not have any buffered packets. * - * Schedules a TXQ for transmission if it is not already scheduled. Takes a - * lock, which means it must *not* be called between - * ieee80211_txq_schedule_start() and ieee80211_txq_schedule_end() + * The driver may set force=true if it has buffered packets for this TXQ + * internally. */ -void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) - __acquires(txq_lock) __releases(txq_lock); +static inline void +ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, + bool force) +{ + __ieee80211_schedule_txq(hw, txq, force); +} /** * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5ee7b30b4917..d2bc733a2ef1 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -316,6 +316,8 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, gfp_t flags); void nf_ct_tmpl_free(struct nf_conn *tmpl); +u32 nf_ct_get_id(const struct nf_conn *ct); + static inline void nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) { diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 778087591983..a49edfdf47e8 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -75,6 +75,12 @@ bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); +int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state, + u8 l4proto, + union nf_inet_addr *outer_daddr); + int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, diff --git a/include/net/netrom.h b/include/net/netrom.h index 5a0714ff500f..80f15b1c1a48 100644 --- a/include/net/netrom.h +++ b/include/net/netrom.h @@ -266,7 +266,7 @@ void nr_stop_idletimer(struct sock *); int nr_t1timer_running(struct sock *); /* sysctl_net_netrom.c */ -void nr_register_sysctl(void); +int nr_register_sysctl(void); void nr_unregister_sysctl(void); #endif 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/sock.h b/include/net/sock.h index 8de5ee258b93..341f8bafa0cf 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2084,12 +2084,6 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) * @p: poll_table * * See the comments in the wq_has_sleeper function. - * - * Do not derive sock from filp->private_data here. An SMC socket establishes - * an internal TCP socket that is used in the fallback case. All socket - * operations on the SMC socket are then forwarded to the TCP socket. In case of - * poll, the filp->private_data pointer references the SMC socket because the - * TCP socket has no file assigned. */ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) diff --git a/include/net/tls.h b/include/net/tls.h index a5a938583295..5934246b2c6f 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -307,6 +307,7 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tls_device_sk_destruct(struct sock *sk); +void tls_device_free_resources_tx(struct sock *sk); void tls_device_init(void); void tls_device_cleanup(void); int tls_tx_records(struct sock *sk, int flags); @@ -330,6 +331,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx, int flags); int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, int flags); +bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { @@ -379,7 +381,7 @@ tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) { #ifdef CONFIG_SOCK_VALIDATE_XMIT - return sk_fullsock(sk) & + return sk_fullsock(sk) && (smp_load_acquire(&sk->sk_validate_xmit_skb) == &tls_validate_xmit_skb); #else diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 85386becbaea..c9b0b2b5d672 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -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/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7f14d4a66c28..64cee116928e 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -439,10 +439,12 @@ #define KEY_TITLE 0x171 #define KEY_SUBTITLE 0x172 #define KEY_ANGLE 0x173 -#define KEY_ZOOM 0x174 +#define KEY_FULL_SCREEN 0x174 /* AC View Toggle */ +#define KEY_ZOOM KEY_FULL_SCREEN #define KEY_MODE 0x175 #define KEY_KEYBOARD 0x176 -#define KEY_SCREEN 0x177 +#define KEY_ASPECT_RATIO 0x177 /* HUTRR37: Aspect */ +#define KEY_SCREEN KEY_ASPECT_RATIO #define KEY_PC 0x178 /* Media Select Computer */ #define KEY_TV 0x179 /* Media Select TV */ #define KEY_TV2 0x17a /* Media Select Cable */ diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h index 87b3198f4b5d..f4d4010b7e3e 100644 --- a/include/uapi/rdma/mlx5-abi.h +++ b/include/uapi/rdma/mlx5-abi.h @@ -238,6 +238,7 @@ enum mlx5_ib_query_dev_resp_flags { MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP = 1 << 0, MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD = 1 << 1, MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE = 1 << 2, + MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT = 1 << 3, }; enum mlx5_ib_tunnel_offloads { |