diff options
| author | Paulo Alcantara <pc@manguebit.org> | 2026-09-26 19:20:30 -0300 |
|---|---|---|
| committer | Paulo Alcantara <pc@manguebit.org> | 2026-09-30 14:24:12 -0300 |
| commit | dd05add7b2b6004c5fa3a1f276f56d8668f86b65 (patch) | |
| tree | 23efdcaa0b8031f6ac6f57b6734d18d6c1adc6f2 /include/clocksource/hyperv_timer.h | |
| download | linux-stable-dd05add7b2b6004c5fa3a1f276f56d8668f86b65.tar.gz linux-stable-dd05add7b2b6004c5fa3a1f276f56d8668f86b65.zip | |
netfs: zero the tail of a short DIO/unbuffered readgrafted
The buffered read collector zero-fills the tail of a short read that
stops below the inode's i_size (netfs_clear_unread()), so a read that
races an extending write still returns the expected number of bytes.
The non-buffered collector path does no such thing: it just records
how much was transferred.
Add the same zero-fill for the non-buffered case, gated on
NETFS_SREQ_CLEAR_TAIL: a subreq's source sets that flag when a short
result from it is known to be safe to treat as a hole, as opposed to
NETFS_SREQ_HIT_EOF, which means the read genuinely ran off the end of
the file and should be reported short as-is. Only CLEAR_TAIL should
zero-fill here; a real EOF must stay a real short read.
No source currently sets CLEAR_TAIL on an unbuffered/DIO subrequest,
so this is inert on its own -- a following change teaches cifs to set
it in the one case that needs it.
Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Paulo Alcantara <pc@manguebit.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Cc: Shyam Prasad N <sprasad@microsoft.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: Bharath SM <bharathsm@microsoft.com>
Cc: stable@vger.kernel.org
Diffstat (limited to 'include/clocksource/hyperv_timer.h')
| -rw-r--r-- | include/clocksource/hyperv_timer.h | 111 |
1 files changed, 111 insertions, 0 deletions
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 <mikelley@microsoft.com> + */ + +#ifndef __CLKSOURCE_HYPERV_TIMER_H +#define __CLKSOURCE_HYPERV_TIMER_H + +#include <linux/clocksource.h> +#include <linux/math64.h> +#include <hyperv/hvhdk.h> + +#define HV_MAX_MAX_DELTA_TICKS 0xffffffff +#define HV_MIN_DELTA_TICKS 1 + +#ifdef CONFIG_HYPERV_TIMER + +#include <asm/hyperv_timer.h> + +/* 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 |
