![Mohammed Gamal](/assets/img/avatar_default.png)
When selecting function_graph tracer with the command:
# echo function_graph > /sys/kernel/debug/tracing/current_tracer
The kernel crashes with the following stack trace:
[69703.122389] BUG: stack guard page was hit at 000000001056545c (stack is 00000000fa3f8fed..0000000005d39503)
[69703.122403] kernel stack overflow (double-fault): 0000 [#1] SMP PTI
[69703.122413] CPU: 0 PID: 16982 Comm: bash Kdump: loaded Not tainted 4.18.0-236.el8.x86_64 #1
[69703.122420] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.0 12/17/2019
[69703.122433] RIP: 0010repare_ftrace_return+0xa/0x110
[69703.122458] Code: 05 00 0f 0b 48 c7 c7 10 ca 69 ae 0f b6 f0 e8 4b 52 0c 00 31 c0 eb ca 66 0f 1f 84 00 00 00 00 00 55 48 89 e5 41 56 41 55 41 54 <53> 48 83 ec 18 65 48 8b 04 25 28 00 00 00 48 89 45 d8 31 c0 48 85
[69703.122467] RSP: 0018:ffffbd6d01118000 EFLAGS: 00010086
[69703.122476] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000003
[69703.122484] RDX: 0000000000000000 RSI: ffffbd6d011180d8 RDI: ffffffffadce7550
[69703.122491] RBP: ffffbd6d01118018 R08: 0000000000000000 R09: ffff9d4b09266000
[69703.122498] R10: ffff9d4b0fc04540 R11: ffff9d4b0fc20a00 R12: ffff9d4b6e42aa90
[69703.122506] R13: ffff9d4b0fc20ab8 R14: 00000000000003e8 R15: ffffbd6d0111837c
[69703.122514] FS: 00007fd5f2588740(0000) GS:ffff9d4b6e400000(0000) knlGS:0000000000000000
[69703.122521] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[69703.122528] CR2: ffffbd6d01117ff8 CR3: 00000000565d8001 CR4: 00000000003606f0
[69703.122538] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[69703.122545] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[69703.122552] Call Trace:
[69703.122568] ftrace_graph_caller+0x6b/0xa0
[69703.122589] ? read_hv_sched_clock_tsc+0x5/0x20
[69703.122599] read_hv_sched_clock_tsc+0x5/0x20
[69703.122611] sched_clock+0x5/0x10
[69703.122621] sched_clock_local+0x12/0x80
[69703.122631] sched_clock_cpu+0x8c/0xb0
[69703.122644] trace_clock_global+0x21/0x90
[69703.122655] ring_buffer_lock_reserve+0x100/0x3c0
[69703.122671] trace_buffer_lock_reserve+0x16/0x50
[69703.122683] __trace_graph_entry+0x28/0x90
[69703.122695] trace_graph_entry+0xfd/0x1a0
[69703.122705] ? read_hv_clock_tsc_cs+0x10/0x10
[69703.122714] ? sched_clock+0x5/0x10
[69703.122723] prepare_ftrace_return+0x99/0x110
[69703.122734] ? read_hv_clock_tsc_cs+0x10/0x10
[69703.122743] ? sched_clock+0x5/0x10
[69703.122752] ftrace_graph_caller+0x6b/0xa0
[69703.122768] ? read_hv_clock_tsc_cs+0x10/0x10
[69703.122777] ? sched_clock+0x5/0x10
[69703.122786] ? read_hv_sched_clock_tsc+0x5/0x20
[69703.122796] ? ring_buffer_unlock_commit+0x1d/0xa0
[69703.122805] read_hv_sched_clock_tsc+0x5/0x20
[69703.122814] ftrace_graph_caller+0xa0/0xa0
[ ... recursion snipped ... ]
Setting the notrace attribute for read_hv_sched_clock_msr() and
read_hv_sched_clock_tsc() fixes it.
Fixes: bd00cd52d5
("clocksource/drivers/hyperv: Add Hyper-V specific sched clock function")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
Link: https://lore.kernel.org/r/20200924151117.767442-1-mgamal@redhat.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
476 lines
12 KiB
C
476 lines
12 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
/*
|
|
* Clocksource driver for the synthetic counter and timers
|
|
* provided by the Hyper-V hypervisor to guest VMs, as described
|
|
* in the Hyper-V Top Level Functional Spec (TLFS). This driver
|
|
* is instruction set architecture independent.
|
|
*
|
|
* Copyright (C) 2019, Microsoft, Inc.
|
|
*
|
|
* Author: Michael Kelley <mikelley@microsoft.com>
|
|
*/
|
|
|
|
#include <linux/percpu.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/clockchips.h>
|
|
#include <linux/clocksource.h>
|
|
#include <linux/sched_clock.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/cpuhotplug.h>
|
|
#include <clocksource/hyperv_timer.h>
|
|
#include <asm/hyperv-tlfs.h>
|
|
#include <asm/mshyperv.h>
|
|
|
|
static struct clock_event_device __percpu *hv_clock_event;
|
|
static u64 hv_sched_clock_offset __ro_after_init;
|
|
|
|
/*
|
|
* If false, we're using the old mechanism for stimer0 interrupts
|
|
* where it sends a VMbus message when it expires. The old
|
|
* mechanism is used when running on older versions of Hyper-V
|
|
* that don't support Direct Mode. While Hyper-V provides
|
|
* four stimer's per CPU, Linux uses only stimer0.
|
|
*
|
|
* Because Direct Mode does not require processing a VMbus
|
|
* message, stimer interrupts can be enabled earlier in the
|
|
* process of booting a CPU, and consistent with when timer
|
|
* interrupts are enabled for other clocksource drivers.
|
|
* However, for legacy versions of Hyper-V when Direct Mode
|
|
* is not enabled, setting up stimer interrupts must be
|
|
* delayed until VMbus is initialized and can process the
|
|
* interrupt message.
|
|
*/
|
|
static bool direct_mode_enabled;
|
|
|
|
static int stimer0_irq;
|
|
static int stimer0_vector;
|
|
static int stimer0_message_sint;
|
|
|
|
/*
|
|
* ISR for when stimer0 is operating in Direct Mode. Direct Mode
|
|
* does not use VMbus or any VMbus messages, so process here and not
|
|
* in the VMbus driver code.
|
|
*/
|
|
void hv_stimer0_isr(void)
|
|
{
|
|
struct clock_event_device *ce;
|
|
|
|
ce = this_cpu_ptr(hv_clock_event);
|
|
ce->event_handler(ce);
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_stimer0_isr);
|
|
|
|
static int hv_ce_set_next_event(unsigned long delta,
|
|
struct clock_event_device *evt)
|
|
{
|
|
u64 current_tick;
|
|
|
|
current_tick = hv_read_reference_counter();
|
|
current_tick += delta;
|
|
hv_init_timer(0, current_tick);
|
|
return 0;
|
|
}
|
|
|
|
static int hv_ce_shutdown(struct clock_event_device *evt)
|
|
{
|
|
hv_init_timer(0, 0);
|
|
hv_init_timer_config(0, 0);
|
|
if (direct_mode_enabled)
|
|
hv_disable_stimer0_percpu_irq(stimer0_irq);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int hv_ce_set_oneshot(struct clock_event_device *evt)
|
|
{
|
|
union hv_stimer_config timer_cfg;
|
|
|
|
timer_cfg.as_uint64 = 0;
|
|
timer_cfg.enable = 1;
|
|
timer_cfg.auto_enable = 1;
|
|
if (direct_mode_enabled) {
|
|
/*
|
|
* When it expires, the timer will directly interrupt
|
|
* on the specified hardware vector/IRQ.
|
|
*/
|
|
timer_cfg.direct_mode = 1;
|
|
timer_cfg.apic_vector = stimer0_vector;
|
|
hv_enable_stimer0_percpu_irq(stimer0_irq);
|
|
} else {
|
|
/*
|
|
* When it expires, the timer will generate a VMbus message,
|
|
* to be handled by the normal VMbus interrupt handler.
|
|
*/
|
|
timer_cfg.direct_mode = 0;
|
|
timer_cfg.sintx = stimer0_message_sint;
|
|
}
|
|
hv_init_timer_config(0, timer_cfg.as_uint64);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* hv_stimer_init - Per-cpu initialization of the clockevent
|
|
*/
|
|
static int hv_stimer_init(unsigned int cpu)
|
|
{
|
|
struct clock_event_device *ce;
|
|
|
|
if (!hv_clock_event)
|
|
return 0;
|
|
|
|
ce = per_cpu_ptr(hv_clock_event, cpu);
|
|
ce->name = "Hyper-V clockevent";
|
|
ce->features = CLOCK_EVT_FEAT_ONESHOT;
|
|
ce->cpumask = cpumask_of(cpu);
|
|
ce->rating = 1000;
|
|
ce->set_state_shutdown = hv_ce_shutdown;
|
|
ce->set_state_oneshot = hv_ce_set_oneshot;
|
|
ce->set_next_event = hv_ce_set_next_event;
|
|
|
|
clockevents_config_and_register(ce,
|
|
HV_CLOCK_HZ,
|
|
HV_MIN_DELTA_TICKS,
|
|
HV_MAX_MAX_DELTA_TICKS);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* hv_stimer_cleanup - Per-cpu cleanup of the clockevent
|
|
*/
|
|
int hv_stimer_cleanup(unsigned int cpu)
|
|
{
|
|
struct clock_event_device *ce;
|
|
|
|
if (!hv_clock_event)
|
|
return 0;
|
|
|
|
/*
|
|
* In the legacy case where Direct Mode is not enabled
|
|
* (which can only be on x86/64), stimer cleanup happens
|
|
* relatively early in the CPU offlining process. We
|
|
* must unbind the stimer-based clockevent device so
|
|
* that the LAPIC timer can take over until clockevents
|
|
* are no longer needed in the offlining process. Note
|
|
* that clockevents_unbind_device() eventually calls
|
|
* hv_ce_shutdown().
|
|
*
|
|
* The unbind should not be done when Direct Mode is
|
|
* enabled because we may be on an architecture where
|
|
* there are no other clockevent devices to fallback to.
|
|
*/
|
|
ce = per_cpu_ptr(hv_clock_event, cpu);
|
|
if (direct_mode_enabled)
|
|
hv_ce_shutdown(ce);
|
|
else
|
|
clockevents_unbind_device(ce, cpu);
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_stimer_cleanup);
|
|
|
|
/* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
|
|
int hv_stimer_alloc(void)
|
|
{
|
|
int ret = 0;
|
|
|
|
/*
|
|
* Synthetic timers are always available except on old versions of
|
|
* Hyper-V on x86. In that case, return as error as Linux will use a
|
|
* clockevent based on emulated LAPIC timer hardware.
|
|
*/
|
|
if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
|
|
return -EINVAL;
|
|
|
|
hv_clock_event = alloc_percpu(struct clock_event_device);
|
|
if (!hv_clock_event)
|
|
return -ENOMEM;
|
|
|
|
direct_mode_enabled = ms_hyperv.misc_features &
|
|
HV_STIMER_DIRECT_MODE_AVAILABLE;
|
|
if (direct_mode_enabled) {
|
|
ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
|
|
hv_stimer0_isr);
|
|
if (ret)
|
|
goto free_percpu;
|
|
|
|
/*
|
|
* Since we are in Direct Mode, stimer initialization
|
|
* can be done now with a CPUHP value in the same range
|
|
* as other clockevent devices.
|
|
*/
|
|
ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING,
|
|
"clockevents/hyperv/stimer:starting",
|
|
hv_stimer_init, hv_stimer_cleanup);
|
|
if (ret < 0)
|
|
goto free_stimer0_irq;
|
|
}
|
|
return ret;
|
|
|
|
free_stimer0_irq:
|
|
hv_remove_stimer0_irq(stimer0_irq);
|
|
stimer0_irq = 0;
|
|
free_percpu:
|
|
free_percpu(hv_clock_event);
|
|
hv_clock_event = NULL;
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_stimer_alloc);
|
|
|
|
/*
|
|
* hv_stimer_legacy_init -- Called from the VMbus driver to handle
|
|
* the case when Direct Mode is not enabled, and the stimer
|
|
* must be initialized late in the CPU onlining process.
|
|
*
|
|
*/
|
|
void hv_stimer_legacy_init(unsigned int cpu, int sint)
|
|
{
|
|
if (direct_mode_enabled)
|
|
return;
|
|
|
|
/*
|
|
* This function gets called by each vCPU, so setting the
|
|
* global stimer_message_sint value each time is conceptually
|
|
* not ideal, but the value passed in is always the same and
|
|
* it avoids introducing yet another interface into this
|
|
* clocksource driver just to set the sint in the legacy case.
|
|
*/
|
|
stimer0_message_sint = sint;
|
|
(void)hv_stimer_init(cpu);
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_stimer_legacy_init);
|
|
|
|
/*
|
|
* hv_stimer_legacy_cleanup -- Called from the VMbus driver to
|
|
* handle the case when Direct Mode is not enabled, and the
|
|
* stimer must be cleaned up early in the CPU offlining
|
|
* process.
|
|
*/
|
|
void hv_stimer_legacy_cleanup(unsigned int cpu)
|
|
{
|
|
if (direct_mode_enabled)
|
|
return;
|
|
(void)hv_stimer_cleanup(cpu);
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_stimer_legacy_cleanup);
|
|
|
|
|
|
/* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */
|
|
void hv_stimer_free(void)
|
|
{
|
|
if (!hv_clock_event)
|
|
return;
|
|
|
|
if (direct_mode_enabled) {
|
|
cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING);
|
|
hv_remove_stimer0_irq(stimer0_irq);
|
|
stimer0_irq = 0;
|
|
}
|
|
free_percpu(hv_clock_event);
|
|
hv_clock_event = NULL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_stimer_free);
|
|
|
|
/*
|
|
* Do a global cleanup of clockevents for the cases of kexec and
|
|
* vmbus exit
|
|
*/
|
|
void hv_stimer_global_cleanup(void)
|
|
{
|
|
int cpu;
|
|
|
|
/*
|
|
* hv_stime_legacy_cleanup() will stop the stimer if Direct
|
|
* Mode is not enabled, and fallback to the LAPIC timer.
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
hv_stimer_legacy_cleanup(cpu);
|
|
}
|
|
|
|
/*
|
|
* If Direct Mode is enabled, the cpuhp teardown callback
|
|
* (hv_stimer_cleanup) will be run on all CPUs to stop the
|
|
* stimers.
|
|
*/
|
|
hv_stimer_free();
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
|
|
|
|
/*
|
|
* Code and definitions for the Hyper-V clocksources. Two
|
|
* clocksources are defined: one that reads the Hyper-V defined MSR, and
|
|
* the other that uses the TSC reference page feature as defined in the
|
|
* TLFS. The MSR version is for compatibility with old versions of
|
|
* Hyper-V and 32-bit x86. The TSC reference page version is preferred.
|
|
*
|
|
* The Hyper-V clocksource ratings of 250 are chosen to be below the
|
|
* TSC clocksource rating of 300. In configurations where Hyper-V offers
|
|
* an InvariantTSC, the TSC is not marked "unstable", so the TSC clocksource
|
|
* is available and preferred. With the higher rating, it will be the
|
|
* default. On older hardware and Hyper-V versions, the TSC is marked
|
|
* "unstable", so no TSC clocksource is created and the selected Hyper-V
|
|
* clocksource will be the default.
|
|
*/
|
|
|
|
u64 (*hv_read_reference_counter)(void);
|
|
EXPORT_SYMBOL_GPL(hv_read_reference_counter);
|
|
|
|
static union {
|
|
struct ms_hyperv_tsc_page page;
|
|
u8 reserved[PAGE_SIZE];
|
|
} tsc_pg __aligned(PAGE_SIZE);
|
|
|
|
struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
|
|
{
|
|
return &tsc_pg.page;
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_get_tsc_page);
|
|
|
|
static u64 notrace read_hv_clock_tsc(void)
|
|
{
|
|
u64 current_tick = hv_read_tsc_page(hv_get_tsc_page());
|
|
|
|
if (current_tick == U64_MAX)
|
|
hv_get_time_ref_count(current_tick);
|
|
|
|
return current_tick;
|
|
}
|
|
|
|
static u64 notrace read_hv_clock_tsc_cs(struct clocksource *arg)
|
|
{
|
|
return read_hv_clock_tsc();
|
|
}
|
|
|
|
static u64 notrace read_hv_sched_clock_tsc(void)
|
|
{
|
|
return (read_hv_clock_tsc() - hv_sched_clock_offset) *
|
|
(NSEC_PER_SEC / HV_CLOCK_HZ);
|
|
}
|
|
|
|
static void suspend_hv_clock_tsc(struct clocksource *arg)
|
|
{
|
|
u64 tsc_msr;
|
|
|
|
/* Disable the TSC page */
|
|
hv_get_reference_tsc(tsc_msr);
|
|
tsc_msr &= ~BIT_ULL(0);
|
|
hv_set_reference_tsc(tsc_msr);
|
|
}
|
|
|
|
|
|
static void resume_hv_clock_tsc(struct clocksource *arg)
|
|
{
|
|
phys_addr_t phys_addr = virt_to_phys(&tsc_pg);
|
|
u64 tsc_msr;
|
|
|
|
/* Re-enable the TSC page */
|
|
hv_get_reference_tsc(tsc_msr);
|
|
tsc_msr &= GENMASK_ULL(11, 0);
|
|
tsc_msr |= BIT_ULL(0) | (u64)phys_addr;
|
|
hv_set_reference_tsc(tsc_msr);
|
|
}
|
|
|
|
static int hv_cs_enable(struct clocksource *cs)
|
|
{
|
|
hv_enable_vdso_clocksource();
|
|
return 0;
|
|
}
|
|
|
|
static struct clocksource hyperv_cs_tsc = {
|
|
.name = "hyperv_clocksource_tsc_page",
|
|
.rating = 250,
|
|
.read = read_hv_clock_tsc_cs,
|
|
.mask = CLOCKSOURCE_MASK(64),
|
|
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
|
|
.suspend= suspend_hv_clock_tsc,
|
|
.resume = resume_hv_clock_tsc,
|
|
.enable = hv_cs_enable,
|
|
};
|
|
|
|
static u64 notrace read_hv_clock_msr(void)
|
|
{
|
|
u64 current_tick;
|
|
/*
|
|
* Read the partition counter to get the current tick count. This count
|
|
* is set to 0 when the partition is created and is incremented in
|
|
* 100 nanosecond units.
|
|
*/
|
|
hv_get_time_ref_count(current_tick);
|
|
return current_tick;
|
|
}
|
|
|
|
static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg)
|
|
{
|
|
return read_hv_clock_msr();
|
|
}
|
|
|
|
static u64 notrace read_hv_sched_clock_msr(void)
|
|
{
|
|
return (read_hv_clock_msr() - hv_sched_clock_offset) *
|
|
(NSEC_PER_SEC / HV_CLOCK_HZ);
|
|
}
|
|
|
|
static struct clocksource hyperv_cs_msr = {
|
|
.name = "hyperv_clocksource_msr",
|
|
.rating = 250,
|
|
.read = read_hv_clock_msr_cs,
|
|
.mask = CLOCKSOURCE_MASK(64),
|
|
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
|
|
};
|
|
|
|
static bool __init hv_init_tsc_clocksource(void)
|
|
{
|
|
u64 tsc_msr;
|
|
phys_addr_t phys_addr;
|
|
|
|
if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
|
|
return false;
|
|
|
|
hv_read_reference_counter = read_hv_clock_tsc;
|
|
phys_addr = virt_to_phys(hv_get_tsc_page());
|
|
|
|
/*
|
|
* The Hyper-V TLFS specifies to preserve the value of reserved
|
|
* bits in registers. So read the existing value, preserve the
|
|
* low order 12 bits, and add in the guest physical address
|
|
* (which already has at least the low 12 bits set to zero since
|
|
* it is page aligned). Also set the "enable" bit, which is bit 0.
|
|
*/
|
|
hv_get_reference_tsc(tsc_msr);
|
|
tsc_msr &= GENMASK_ULL(11, 0);
|
|
tsc_msr = tsc_msr | 0x1 | (u64)phys_addr;
|
|
hv_set_reference_tsc(tsc_msr);
|
|
|
|
hv_set_clocksource_vdso(hyperv_cs_tsc);
|
|
clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
|
|
|
|
hv_sched_clock_offset = hv_read_reference_counter();
|
|
hv_setup_sched_clock(read_hv_sched_clock_tsc);
|
|
|
|
return true;
|
|
}
|
|
|
|
void __init hv_init_clocksource(void)
|
|
{
|
|
/*
|
|
* Try to set up the TSC page clocksource. If it succeeds, we're
|
|
* done. Otherwise, set up the MSR clocksoruce. At least one of
|
|
* these will always be available except on very old versions of
|
|
* Hyper-V on x86. In that case we won't have a Hyper-V
|
|
* clocksource, but Linux will still run with a clocksource based
|
|
* on the emulated PIT or LAPIC timer.
|
|
*/
|
|
if (hv_init_tsc_clocksource())
|
|
return;
|
|
|
|
if (!(ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE))
|
|
return;
|
|
|
|
hv_read_reference_counter = read_hv_clock_msr;
|
|
clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
|
|
|
|
hv_sched_clock_offset = hv_read_reference_counter();
|
|
hv_setup_sched_clock(read_hv_sched_clock_msr);
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_init_clocksource);
|