From 3f1fe48a36b0b6722dc3fd421d93512bac138e9a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 2 Oct 2026 12:17:24 -0700 Subject: Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux Pull io_uring fixes from Jens Axboe: - Fix a task_work add use-after-free with SQPOLL. The sqpoll thread could pop and complete the last request while io_req_normal_work_add() was still looking at them after the mpscq push. Use the same approach as DEFER_TASKRUN to protect from that, holding an RCU read lock across the add, and have exit wait for an RCU grace period for SQPOLL rings as well. - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED rings - Mark the source filter table as COW when cloning bpf filters, so registering another filter on the source doesn't modify the shared table in place - Initialize the task context before running the BPF loop - Requeue zcrx multishot receives stopped by a local resource - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit) * tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: io_uring: fix task_work add use-after-free with SQPOLL io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full io_uring/zcrx: requeue multishot receives stopped by a local resource io_uring: initialize task context before running the BPF loop io_uring: zero big_cqe for aux CQEs on CQE32 rings io_uring: fix free entry check for 32b CQEs on CQE32 rings io_uring: only post the dummy skip CQE on CQE_MIXED rings io_uring/bpf_filter: mark source as COW when cloning filters --- include/clocksource/hyperv_timer.h | 111 +++++++++++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+) create mode 100644 include/clocksource/hyperv_timer.h (limited to 'include/clocksource/hyperv_timer.h') diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h new file mode 100644 index 000000000..8d3befb7e --- /dev/null +++ b/include/clocksource/hyperv_timer.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Definitions for the clocksource provided by the Hyper-V + * hypervisor to guest VMs, as described in the Hyper-V Top + * Level Functional Spec (TLFS). + * + * Copyright (C) 2019, Microsoft, Inc. + * + * Author: Michael Kelley + */ + +#ifndef __CLKSOURCE_HYPERV_TIMER_H +#define __CLKSOURCE_HYPERV_TIMER_H + +#include +#include +#include + +#define HV_MAX_MAX_DELTA_TICKS 0xffffffff +#define HV_MIN_DELTA_TICKS 1 + +#ifdef CONFIG_HYPERV_TIMER + +#include + +/* Routines called by the VMbus driver */ +extern int hv_stimer_alloc(bool have_percpu_irqs); +extern int hv_stimer_cleanup(unsigned int cpu); +extern void hv_stimer_global_cleanup(void); + +extern void hv_init_clocksource(void); +extern void hv_remap_tsc_clocksource(void); + +extern unsigned long hv_get_tsc_pfn(void); +extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); + +extern void hv_adj_sched_clock_offset(u64 offset); + +static __always_inline bool +hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, + u64 *cur_tsc, u64 *time) +{ + u64 scale, offset; + u32 sequence; + + /* + * The protocol for reading Hyper-V TSC page is specified in Hypervisor + * Top-Level Functional Specification ver. 3.0 and above. To get the + * reference time we must do the following: + * - READ ReferenceTscSequence + * A special '0' value indicates the time source is unreliable and we + * need to use something else. The currently published specification + * versions (up to 4.0b) contain a mistake and wrongly claim '-1' + * instead of '0' as the special value, see commit c35b82ef0294. + * - ReferenceTime = + * ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset + * - READ ReferenceTscSequence again. In case its value has changed + * since our first reading we need to discard ReferenceTime and repeat + * the whole sequence as the hypervisor was updating the page in + * between. + */ + do { + sequence = READ_ONCE(tsc_pg->tsc_sequence); + if (!sequence) + return false; + /* + * Make sure we read sequence before we read other values from + * TSC page. + */ + smp_rmb(); + + scale = READ_ONCE(tsc_pg->tsc_scale); + offset = READ_ONCE(tsc_pg->tsc_offset); + *cur_tsc = hv_get_raw_timer(); + + /* + * Make sure we read sequence after we read all other values + * from TSC page. + */ + smp_rmb(); + + } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence); + + *time = mul_u64_u64_shr(*cur_tsc, scale, 64) + offset; + return true; +} + +#else /* CONFIG_HYPERV_TIMER */ +static inline unsigned long hv_get_tsc_pfn(void) +{ + return 0; +} + +static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void) +{ + return NULL; +} + +static __always_inline bool +hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time) +{ + return false; +} + +static inline int hv_stimer_cleanup(unsigned int cpu) { return 0; } +static inline void hv_stimer_global_cleanup(void) {} + +#endif /* CONFIG_HYPERV_TIMER */ + +#endif -- cgit v1.3.1