From caab277b1de0a22b675c4c95fc7b285ec2eb5bf5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 3 Jun 2019 07:44:50 +0200 Subject: treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 234 Based on 1 normalized pattern(s): this program is free software you can redistribute it and or modify it under the terms of the gnu general public license version 2 as published by the free software foundation this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details you should have received a copy of the gnu general public license along with this program if not see http www gnu org licenses extracted by the scancode license scanner the SPDX license identifier GPL-2.0-only has been chosen to replace the boilerplate/reference in 503 file(s). Signed-off-by: Thomas Gleixner Reviewed-by: Alexios Zavras Reviewed-by: Allison Randal Reviewed-by: Enrico Weigelt Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190602204653.811534538@linutronix.de Signed-off-by: Greg Kroah-Hartman --- include/clocksource/arm_arch_timer.h | 13 +------------ include/clocksource/samsung_pwm.h | 13 +------------ 2 files changed, 2 insertions(+), 24 deletions(-) (limited to 'include/clocksource') diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h index 702967d996bb..1d68d5613dae 100644 --- a/include/clocksource/arm_arch_timer.h +++ b/include/clocksource/arm_arch_timer.h @@ -1,17 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see . */ #ifndef __CLKSOURCE_ARM_ARCH_TIMER_H #define __CLKSOURCE_ARM_ARCH_TIMER_H diff --git a/include/clocksource/samsung_pwm.h b/include/clocksource/samsung_pwm.h index 0c7d48b8b396..c395238d0922 100644 --- a/include/clocksource/samsung_pwm.h +++ b/include/clocksource/samsung_pwm.h @@ -1,17 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2013 Samsung Electronics Co., Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see . */ #ifndef __CLOCKSOURCE_SAMSUNG_PWM_H #define __CLOCKSOURCE_SAMSUNG_PWM_H -- cgit v1.2.3 From 721154f972aa68772f410401ebfae795b7b4c5f8 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 24 Jun 2019 11:50:55 +0200 Subject: clocksource/drivers/davinci: Add support for clockevents Currently the clocksource and clockevent support for davinci platforms lives in mach-davinci. It hard-codes many things, uses global variables, implements functionalities unused by any platform and has code fragments scattered across many (often unrelated) files. Implement a new, modern and simplified timer driver and put it into drivers/clocksource. We still need to support legacy board files so export a config structure and a function that allows machine code to register the timer. The timer we're using is 64-bit but can be programmed in dual 32-bit mode (both chained and unchained). On all davinci SoCs except for da830 we're using both halves. Lower half for clockevents and upper half for clocksource. On da830 we're using the lower half for both with the help of a compare register. This patch contains the core code and support for clockevent. The clocksource code will be included in a subsequent patch. Signed-off-by: Bartosz Golaszewski Signed-off-by: Daniel Lezcano --- drivers/clocksource/Kconfig | 5 + drivers/clocksource/Makefile | 1 + drivers/clocksource/timer-davinci.c | 284 ++++++++++++++++++++++++++++++++++++ include/clocksource/timer-davinci.h | 44 ++++++ 4 files changed, 334 insertions(+) create mode 100644 drivers/clocksource/timer-davinci.c create mode 100644 include/clocksource/timer-davinci.h (limited to 'include/clocksource') diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index e9936992934a..5e9317dc3d39 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -43,6 +43,11 @@ config BCM_KONA_TIMER help Enables the support for the BCM Kona mobile timer driver. +config DAVINCI_TIMER + bool "Texas Instruments DaVinci timer driver" if COMPILE_TEST + help + Enables the support for the TI DaVinci timer driver. + config DIGICOLOR_TIMER bool "Digicolor timer driver" if COMPILE_TEST select CLKSRC_MMIO diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 0939886b305f..5582252efb31 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_SH_TIMER_TMU) += sh_tmu.o obj-$(CONFIG_EM_TIMER_STI) += em_sti.o obj-$(CONFIG_CLKBLD_I8253) += i8253.o obj-$(CONFIG_CLKSRC_MMIO) += mmio.o +obj-$(CONFIG_DAVINCI_TIMER) += timer-davinci.o obj-$(CONFIG_DIGICOLOR_TIMER) += timer-digicolor.o obj-$(CONFIG_OMAP_DM_TIMER) += timer-ti-dm.o obj-$(CONFIG_DW_APB_TIMER) += dw_apb_timer.o diff --git a/drivers/clocksource/timer-davinci.c b/drivers/clocksource/timer-davinci.c new file mode 100644 index 000000000000..246a5564495d --- /dev/null +++ b/drivers/clocksource/timer-davinci.c @@ -0,0 +1,284 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * TI DaVinci clocksource driver + * + * Copyright (C) 2019 Texas Instruments + * Author: Bartosz Golaszewski + * (with tiny parts adopted from code by Kevin Hilman ) + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#undef pr_fmt +#define pr_fmt(fmt) "%s: " fmt "\n", __func__ + +#define DAVINCI_TIMER_REG_TIM12 0x10 +#define DAVINCI_TIMER_REG_TIM34 0x14 +#define DAVINCI_TIMER_REG_PRD12 0x18 +#define DAVINCI_TIMER_REG_PRD34 0x1c +#define DAVINCI_TIMER_REG_TCR 0x20 +#define DAVINCI_TIMER_REG_TGCR 0x24 + +#define DAVINCI_TIMER_TIMMODE_MASK GENMASK(3, 2) +#define DAVINCI_TIMER_RESET_MASK GENMASK(1, 0) +#define DAVINCI_TIMER_TIMMODE_32BIT_UNCHAINED BIT(2) +#define DAVINCI_TIMER_UNRESET GENMASK(1, 0) + +#define DAVINCI_TIMER_ENAMODE_MASK GENMASK(1, 0) +#define DAVINCI_TIMER_ENAMODE_DISABLED 0x00 +#define DAVINCI_TIMER_ENAMODE_ONESHOT BIT(0) +#define DAVINCI_TIMER_ENAMODE_PERIODIC BIT(1) + +#define DAVINCI_TIMER_ENAMODE_SHIFT_TIM12 6 +#define DAVINCI_TIMER_ENAMODE_SHIFT_TIM34 22 + +#define DAVINCI_TIMER_MIN_DELTA 0x01 +#define DAVINCI_TIMER_MAX_DELTA 0xfffffffe + +#define DAVINCI_TIMER_TGCR_DEFAULT \ + (DAVINCI_TIMER_TIMMODE_32BIT_UNCHAINED | DAVINCI_TIMER_UNRESET) + +struct davinci_clockevent { + struct clock_event_device dev; + void __iomem *base; + unsigned int cmp_off; +}; + +static struct davinci_clockevent * +to_davinci_clockevent(struct clock_event_device *clockevent) +{ + return container_of(clockevent, struct davinci_clockevent, dev); +} + +static unsigned int +davinci_clockevent_read(struct davinci_clockevent *clockevent, + unsigned int reg) +{ + return readl_relaxed(clockevent->base + reg); +} + +static void davinci_clockevent_write(struct davinci_clockevent *clockevent, + unsigned int reg, unsigned int val) +{ + writel_relaxed(val, clockevent->base + reg); +} + +static void davinci_tim12_shutdown(void __iomem *base) +{ + unsigned int tcr; + + tcr = DAVINCI_TIMER_ENAMODE_DISABLED << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM12; + /* + * This function is only ever called if we're using both timer + * halves. In this case TIM34 runs in periodic mode and we must + * not modify it. + */ + tcr |= DAVINCI_TIMER_ENAMODE_PERIODIC << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM34; + + writel_relaxed(tcr, base + DAVINCI_TIMER_REG_TCR); +} + +static void davinci_tim12_set_oneshot(void __iomem *base) +{ + unsigned int tcr; + + tcr = DAVINCI_TIMER_ENAMODE_ONESHOT << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM12; + /* Same as above. */ + tcr |= DAVINCI_TIMER_ENAMODE_PERIODIC << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM34; + + writel_relaxed(tcr, base + DAVINCI_TIMER_REG_TCR); +} + +static int davinci_clockevent_shutdown(struct clock_event_device *dev) +{ + struct davinci_clockevent *clockevent; + + clockevent = to_davinci_clockevent(dev); + + davinci_tim12_shutdown(clockevent->base); + + return 0; +} + +static int davinci_clockevent_set_oneshot(struct clock_event_device *dev) +{ + struct davinci_clockevent *clockevent = to_davinci_clockevent(dev); + + davinci_clockevent_write(clockevent, DAVINCI_TIMER_REG_TIM12, 0x0); + + davinci_tim12_set_oneshot(clockevent->base); + + return 0; +} + +static int +davinci_clockevent_set_next_event_std(unsigned long cycles, + struct clock_event_device *dev) +{ + struct davinci_clockevent *clockevent = to_davinci_clockevent(dev); + + davinci_clockevent_shutdown(dev); + + davinci_clockevent_write(clockevent, DAVINCI_TIMER_REG_TIM12, 0x0); + davinci_clockevent_write(clockevent, DAVINCI_TIMER_REG_PRD12, cycles); + + davinci_clockevent_set_oneshot(dev); + + return 0; +} + +static int +davinci_clockevent_set_next_event_cmp(unsigned long cycles, + struct clock_event_device *dev) +{ + struct davinci_clockevent *clockevent = to_davinci_clockevent(dev); + unsigned int curr_time; + + curr_time = davinci_clockevent_read(clockevent, + DAVINCI_TIMER_REG_TIM12); + davinci_clockevent_write(clockevent, + clockevent->cmp_off, curr_time + cycles); + + return 0; +} + +static irqreturn_t davinci_timer_irq_timer(int irq, void *data) +{ + struct davinci_clockevent *clockevent = data; + + if (!clockevent_state_oneshot(&clockevent->dev)) + davinci_tim12_shutdown(clockevent->base); + + clockevent->dev.event_handler(&clockevent->dev); + + return IRQ_HANDLED; +} + +static void davinci_timer_init(void __iomem *base) +{ + /* Set clock to internal mode and disable it. */ + writel_relaxed(0x0, base + DAVINCI_TIMER_REG_TCR); + /* + * Reset both 32-bit timers, set no prescaler for timer 34, set the + * timer to dual 32-bit unchained mode, unreset both 32-bit timers. + */ + writel_relaxed(DAVINCI_TIMER_TGCR_DEFAULT, + base + DAVINCI_TIMER_REG_TGCR); + /* Init both counters to zero. */ + writel_relaxed(0x0, base + DAVINCI_TIMER_REG_TIM12); + writel_relaxed(0x0, base + DAVINCI_TIMER_REG_TIM34); +} + +int __init davinci_timer_register(struct clk *clk, + const struct davinci_timer_cfg *timer_cfg) +{ + struct davinci_clockevent *clockevent; + unsigned int tick_rate; + void __iomem *base; + int rv; + + rv = clk_prepare_enable(clk); + if (rv) { + pr_err("Unable to prepare and enable the timer clock"); + return rv; + } + + if (!request_mem_region(timer_cfg->reg.start, + resource_size(&timer_cfg->reg), + "davinci-timer")) { + pr_err("Unable to request memory region"); + return -EBUSY; + } + + base = ioremap(timer_cfg->reg.start, resource_size(&timer_cfg->reg)); + if (!base) { + pr_err("Unable to map the register range"); + return -ENOMEM; + } + + davinci_timer_init(base); + tick_rate = clk_get_rate(clk); + + clockevent = kzalloc(sizeof(*clockevent), GFP_KERNEL | __GFP_NOFAIL); + if (!clockevent) { + pr_err("Error allocating memory for clockevent data"); + return -ENOMEM; + } + + clockevent->dev.name = "tim12"; + clockevent->dev.features = CLOCK_EVT_FEAT_ONESHOT; + clockevent->dev.cpumask = cpumask_of(0); + clockevent->base = base; + + if (timer_cfg->cmp_off) { + clockevent->cmp_off = timer_cfg->cmp_off; + clockevent->dev.set_next_event = + davinci_clockevent_set_next_event_cmp; + } else { + clockevent->dev.set_next_event = + davinci_clockevent_set_next_event_std; + clockevent->dev.set_state_oneshot = + davinci_clockevent_set_oneshot; + clockevent->dev.set_state_shutdown = + davinci_clockevent_shutdown; + } + + rv = request_irq(timer_cfg->irq[DAVINCI_TIMER_CLOCKEVENT_IRQ].start, + davinci_timer_irq_timer, IRQF_TIMER, + "clockevent/tim12", clockevent); + if (rv) { + pr_err("Unable to request the clockevent interrupt"); + return rv; + } + + clockevents_config_and_register(&clockevent->dev, tick_rate, + DAVINCI_TIMER_MIN_DELTA, + DAVINCI_TIMER_MAX_DELTA); + + return 0; +} + +static int __init of_davinci_timer_register(struct device_node *np) +{ + struct davinci_timer_cfg timer_cfg = { }; + struct clk *clk; + int rv; + + rv = of_address_to_resource(np, 0, &timer_cfg.reg); + if (rv) { + pr_err("Unable to get the register range for timer"); + return rv; + } + + rv = of_irq_to_resource_table(np, timer_cfg.irq, + DAVINCI_TIMER_NUM_IRQS); + if (rv != DAVINCI_TIMER_NUM_IRQS) { + pr_err("Unable to get the interrupts for timer"); + return rv; + } + + clk = of_clk_get(np, 0); + if (IS_ERR(clk)) { + pr_err("Unable to get the timer clock"); + return PTR_ERR(clk); + } + + rv = davinci_timer_register(clk, &timer_cfg); + if (rv) + clk_put(clk); + + return rv; +} +TIMER_OF_DECLARE(davinci_timer, "ti,da830-timer", of_davinci_timer_register); diff --git a/include/clocksource/timer-davinci.h b/include/clocksource/timer-davinci.h new file mode 100644 index 000000000000..1dcc1333fbc8 --- /dev/null +++ b/include/clocksource/timer-davinci.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * TI DaVinci clocksource driver + * + * Copyright (C) 2019 Texas Instruments + * Author: Bartosz Golaszewski + */ + +#ifndef __TIMER_DAVINCI_H__ +#define __TIMER_DAVINCI_H__ + +#include +#include + +enum { + DAVINCI_TIMER_CLOCKEVENT_IRQ, + DAVINCI_TIMER_CLOCKSOURCE_IRQ, + DAVINCI_TIMER_NUM_IRQS, +}; + +/** + * struct davinci_timer_cfg - davinci clocksource driver configuration struct + * @reg: register range resource + * @irq: clockevent and clocksource interrupt resources + * @cmp_off: if set - it specifies the compare register used for clockevent + * + * Note: if the compare register is specified, the driver will use the bottom + * clock half for both clocksource and clockevent and the compare register + * to generate event irqs. The user must supply the correct compare register + * interrupt number. + * + * This is only used by da830 the DSP of which uses the top half. The timer + * driver still configures the top half to run in free-run mode. + */ +struct davinci_timer_cfg { + struct resource reg; + struct resource irq[DAVINCI_TIMER_NUM_IRQS]; + unsigned int cmp_off; +}; + +int __init davinci_timer_register(struct clk *clk, + const struct davinci_timer_cfg *data); + +#endif /* __TIMER_DAVINCI_H__ */ -- cgit v1.2.3 From fd1fea6834d0f9f93062ae6685862908a9baed39 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 1 Jul 2019 04:25:56 +0000 Subject: clocksource/drivers: Make Hyper-V clocksource ISA agnostic Hyper-V clock/timer code and data structures are currently mixed in with other code in the ISA independent drivers/hv directory as well as the ISA dependent Hyper-V code under arch/x86. Consolidate this code and data structures into a Hyper-V clocksource driver to better follow the Linux model. In doing so, separate out the ISA dependent portions so the new clocksource driver works for x86 and for the in-process Hyper-V on ARM64 code. To start, move the existing clockevents code to create the new clocksource driver. Update the VMbus driver to call initialization and cleanup routines since the Hyper-V synthetic timers are not independently enumerated in ACPI. No behavior is changed and no new functionality is added. Suggested-by: Marc Zyngier Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Reviewed-by: Vitaly Kuznetsov Cc: "bp@alien8.de" Cc: "will.deacon@arm.com" Cc: "catalin.marinas@arm.com" Cc: "mark.rutland@arm.com" Cc: "linux-arm-kernel@lists.infradead.org" Cc: "gregkh@linuxfoundation.org" Cc: "linux-hyperv@vger.kernel.org" Cc: "olaf@aepfle.de" Cc: "apw@canonical.com" Cc: "jasowang@redhat.com" Cc: "marcelo.cerri@canonical.com" Cc: Sunil Muthuswamy Cc: KY Srinivasan Cc: "sashal@kernel.org" Cc: "vincenzo.frascino@arm.com" Cc: "linux-arch@vger.kernel.org" Cc: "linux-mips@vger.kernel.org" Cc: "linux-kselftest@vger.kernel.org" Cc: "arnd@arndb.de" Cc: "linux@armlinux.org.uk" Cc: "ralf@linux-mips.org" Cc: "paul.burton@mips.com" Cc: "daniel.lezcano@linaro.org" Cc: "salyzyn@android.com" Cc: "pcc@google.com" Cc: "shuah@kernel.org" Cc: "0x7f454c46@gmail.com" <0x7f454c46@gmail.com> Cc: "linux@rasmusvillemoes.dk" Cc: "huw@codeweavers.com" Cc: "sfr@canb.auug.org.au" Cc: "pbonzini@redhat.com" Cc: "rkrcmar@redhat.com" Cc: "kvm@vger.kernel.org" Link: https://lkml.kernel.org/r/1561955054-1838-2-git-send-email-mikelley@microsoft.com --- MAINTAINERS | 2 + arch/x86/include/asm/hyperv-tlfs.h | 6 ++ arch/x86/kernel/cpu/mshyperv.c | 4 +- drivers/clocksource/Makefile | 1 + drivers/clocksource/hyperv_timer.c | 200 +++++++++++++++++++++++++++++++++++++ drivers/hv/Kconfig | 3 + drivers/hv/hv.c | 156 +---------------------------- drivers/hv/hyperv_vmbus.h | 3 - drivers/hv/vmbus_drv.c | 42 ++++---- include/clocksource/hyperv_timer.h | 27 +++++ 10 files changed, 268 insertions(+), 176 deletions(-) create mode 100644 drivers/clocksource/hyperv_timer.c create mode 100644 include/clocksource/hyperv_timer.h (limited to 'include/clocksource') diff --git a/MAINTAINERS b/MAINTAINERS index a2812972b7b0..bfde42a76a95 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7313,6 +7313,7 @@ F: arch/x86/include/asm/trace/hyperv.h F: arch/x86/include/asm/hyperv-tlfs.h F: arch/x86/kernel/cpu/mshyperv.c F: arch/x86/hyperv +F: drivers/clocksource/hyperv_timer.c F: drivers/hid/hid-hyperv.c F: drivers/hv/ F: drivers/input/serio/hyperv-keyboard.c @@ -7323,6 +7324,7 @@ F: drivers/uio/uio_hv_generic.c F: drivers/video/fbdev/hyperv_fb.c F: drivers/iommu/hyperv_iommu.c F: net/vmw_vsock/hyperv_transport.c +F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h F: include/uapi/linux/hyperv.h F: tools/hv/ diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index cdf44aa9a501..af78cd72b8f3 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -401,6 +401,12 @@ enum HV_GENERIC_SET_FORMAT { #define HV_STATUS_INVALID_CONNECTION_ID 18 #define HV_STATUS_INSUFFICIENT_BUFFERS 19 +/* + * The Hyper-V TimeRefCount register and the TSC + * page provide a guest VM clock with 100ns tick rate + */ +#define HV_CLOCK_HZ (NSEC_PER_SEC/100) + typedef struct _HV_REFERENCE_TSC_PAGE { __u32 tsc_sequence; __u32 res1; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 7df29f08871b..1e5f7a03ddf5 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -80,6 +81,7 @@ __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs) inc_irq_stat(hyperv_stimer0_count); if (hv_stimer0_handler) hv_stimer0_handler(); + add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0); ack_APIC_irq(); exiting_irq(); @@ -89,7 +91,7 @@ __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs) int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void)) { *vector = HYPERV_STIMER0_VECTOR; - *irq = 0; /* Unused on x86/x64 */ + *irq = -1; /* Unused on x86/x64 */ hv_stimer0_handler = handler; return 0; } diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 5582252efb31..2e7936e7833f 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -86,3 +86,4 @@ obj-$(CONFIG_ATCPIT100_TIMER) += timer-atcpit100.o obj-$(CONFIG_RISCV_TIMER) += timer-riscv.o obj-$(CONFIG_CSKY_MP_TIMER) += timer-mp-csky.o obj-$(CONFIG_GX6605S_TIMER) += timer-gx6605s.o +obj-$(CONFIG_HYPERV_TIMER) += hyperv_timer.o diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c new file mode 100644 index 000000000000..68a28af31561 --- /dev/null +++ b/drivers/clocksource/hyperv_timer.c @@ -0,0 +1,200 @@ +// 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 + */ + +#include +#include +#include +#include +#include +#include +#include + +static struct clock_event_device __percpu *hv_clock_event; + +/* + * 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. + */ +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 = hyperv_cs->read(NULL); + 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 + */ +void hv_stimer_init(unsigned int cpu) +{ + struct clock_event_device *ce; + + /* + * Synthetic timers are always available except on old versions of + * Hyper-V on x86. In that case, just return as Linux will use a + * clocksource based on emulated PIT or LAPIC timer hardware. + */ + if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)) + return; + + 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); +} +EXPORT_SYMBOL_GPL(hv_stimer_init); + +/* + * hv_stimer_cleanup - Per-cpu cleanup of the clockevent + */ +void hv_stimer_cleanup(unsigned int cpu) +{ + struct clock_event_device *ce; + + /* Turn off clockevent device */ + if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) { + ce = per_cpu_ptr(hv_clock_event, cpu); + hv_ce_shutdown(ce); + } +} +EXPORT_SYMBOL_GPL(hv_stimer_cleanup); + +/* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */ +int hv_stimer_alloc(int sint) +{ + int ret; + + 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) { + free_percpu(hv_clock_event); + hv_clock_event = NULL; + return ret; + } + } + + stimer0_message_sint = sint; + return 0; +} +EXPORT_SYMBOL_GPL(hv_stimer_alloc); + +/* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */ +void hv_stimer_free(void) +{ + if (direct_mode_enabled && (stimer0_irq != 0)) { + 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; + struct clock_event_device *ce; + + if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) { + for_each_present_cpu(cpu) { + ce = per_cpu_ptr(hv_clock_event, cpu); + clockevents_unbind_device(ce, cpu); + } + } + hv_stimer_free(); +} +EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup); diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 1c1a2514d6f3..c423e57ae888 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -10,6 +10,9 @@ config HYPERV Select this option to run Linux as a Hyper-V client operating system. +config HYPERV_TIMER + def_bool HYPERV + config HYPERV_TSCPAGE def_bool HYPERV && X86_64 diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index a1ea482183e8..6188fb7dda42 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -16,27 +16,13 @@ #include #include #include +#include #include #include "hyperv_vmbus.h" /* The one and only */ struct hv_context hv_context; -/* - * 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. - */ -static bool direct_mode_enabled; -static int stimer0_irq; -static int stimer0_vector; - -#define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */ -#define HV_MAX_MAX_DELTA_TICKS 0xffffffff -#define HV_MIN_DELTA_TICKS 1 - /* * hv_init - Main initialization routine. * @@ -47,9 +33,6 @@ int hv_init(void) hv_context.cpu_context = alloc_percpu(struct hv_per_cpu_context); if (!hv_context.cpu_context) return -ENOMEM; - - direct_mode_enabled = ms_hyperv.misc_features & - HV_STIMER_DIRECT_MODE_AVAILABLE; return 0; } @@ -88,89 +71,6 @@ int hv_post_message(union hv_connection_id connection_id, return status & 0xFFFF; } -/* - * 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. - */ - -static void hv_stimer0_isr(void) -{ - struct hv_per_cpu_context *hv_cpu; - - hv_cpu = this_cpu_ptr(hv_context.cpu_context); - hv_cpu->clk_evt->event_handler(hv_cpu->clk_evt); - add_interrupt_randomness(stimer0_vector, 0); -} - -static int hv_ce_set_next_event(unsigned long delta, - struct clock_event_device *evt) -{ - u64 current_tick; - - WARN_ON(!clockevent_state_oneshot(evt)); - - current_tick = hyperv_cs->read(NULL); - 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 = VMBUS_MESSAGE_SINT; - } - hv_init_timer_config(0, timer_cfg.as_uint64); - return 0; -} - -static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu) -{ - dev->name = "Hyper-V clockevent"; - dev->features = CLOCK_EVT_FEAT_ONESHOT; - dev->cpumask = cpumask_of(cpu); - dev->rating = 1000; - /* - * Avoid settint dev->owner = THIS_MODULE deliberately as doing so will - * result in clockevents_config_and_register() taking additional - * references to the hv_vmbus module making it impossible to unload. - */ - - dev->set_state_shutdown = hv_ce_shutdown; - dev->set_state_oneshot = hv_ce_set_oneshot; - dev->set_next_event = hv_ce_set_next_event; -} - - int hv_synic_alloc(void) { int cpu; @@ -199,14 +99,6 @@ int hv_synic_alloc(void) tasklet_init(&hv_cpu->msg_dpc, vmbus_on_msg_dpc, (unsigned long) hv_cpu); - hv_cpu->clk_evt = kzalloc(sizeof(struct clock_event_device), - GFP_KERNEL); - if (hv_cpu->clk_evt == NULL) { - pr_err("Unable to allocate clock event device\n"); - goto err; - } - hv_init_clockevent_device(hv_cpu->clk_evt, cpu); - hv_cpu->synic_message_page = (void *)get_zeroed_page(GFP_ATOMIC); if (hv_cpu->synic_message_page == NULL) { @@ -229,11 +121,6 @@ int hv_synic_alloc(void) INIT_LIST_HEAD(&hv_cpu->chan_list); } - if (direct_mode_enabled && - hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector, - hv_stimer0_isr)) - goto err; - return 0; err: /* @@ -252,7 +139,6 @@ void hv_synic_free(void) struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); - kfree(hv_cpu->clk_evt); free_page((unsigned long)hv_cpu->synic_event_page); free_page((unsigned long)hv_cpu->synic_message_page); free_page((unsigned long)hv_cpu->post_msg_page); @@ -311,36 +197,9 @@ int hv_synic_init(unsigned int cpu) hv_set_synic_state(sctrl.as_uint64); - /* - * Register the per-cpu clockevent source. - */ - if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) - clockevents_config_and_register(hv_cpu->clk_evt, - HV_TIMER_FREQUENCY, - HV_MIN_DELTA_TICKS, - HV_MAX_MAX_DELTA_TICKS); - return 0; -} - -/* - * hv_synic_clockevents_cleanup - Cleanup clockevent devices - */ -void hv_synic_clockevents_cleanup(void) -{ - int cpu; + hv_stimer_init(cpu); - if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)) - return; - - if (direct_mode_enabled) - hv_remove_stimer0_irq(stimer0_irq); - - for_each_present_cpu(cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); - - clockevents_unbind_device(hv_cpu->clk_evt, cpu); - } + return 0; } /* @@ -388,14 +247,7 @@ int hv_synic_cleanup(unsigned int cpu) if (channel_found && vmbus_connection.conn_state == CONNECTED) return -EBUSY; - /* Turn off clockevent device */ - if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) { - struct hv_per_cpu_context *hv_cpu - = this_cpu_ptr(hv_context.cpu_context); - - clockevents_unbind_device(hv_cpu->clk_evt, cpu); - hv_ce_shutdown(hv_cpu->clk_evt); - } + hv_stimer_cleanup(cpu); hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64); diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index b8e1ff05f110..362e70e9d145 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -138,7 +138,6 @@ struct hv_per_cpu_context { * per-cpu list of the channels based on their CPU affinity. */ struct list_head chan_list; - struct clock_event_device *clk_evt; }; struct hv_context { @@ -176,8 +175,6 @@ extern int hv_synic_init(unsigned int cpu); extern int hv_synic_cleanup(unsigned int cpu); -extern void hv_synic_clockevents_cleanup(void); - /* Interface */ void hv_ringbuffer_pre_init(struct vmbus_channel *channel); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 92b1874b3eb3..72d5a7cde7ea 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "hyperv_vmbus.h" struct vmbus_dynid { @@ -955,17 +956,6 @@ static void vmbus_onmessage_work(struct work_struct *work) kfree(ctx); } -static void hv_process_timer_expiration(struct hv_message *msg, - struct hv_per_cpu_context *hv_cpu) -{ - struct clock_event_device *dev = hv_cpu->clk_evt; - - if (dev->event_handler) - dev->event_handler(dev); - - vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED); -} - void vmbus_on_msg_dpc(unsigned long data) { struct hv_per_cpu_context *hv_cpu = (void *)data; @@ -1159,9 +1149,10 @@ static void vmbus_isr(void) /* Check if there are actual msgs to be processed */ if (msg->header.message_type != HVMSG_NONE) { - if (msg->header.message_type == HVMSG_TIMER_EXPIRED) - hv_process_timer_expiration(msg, hv_cpu); - else + if (msg->header.message_type == HVMSG_TIMER_EXPIRED) { + hv_stimer0_isr(); + vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED); + } else tasklet_schedule(&hv_cpu->msg_dpc); } @@ -1263,14 +1254,19 @@ static int vmbus_bus_init(void) ret = hv_synic_alloc(); if (ret) goto err_alloc; + + ret = hv_stimer_alloc(VMBUS_MESSAGE_SINT); + if (ret < 0) + goto err_alloc; + /* - * Initialize the per-cpu interrupt state and - * connect to the host. + * Initialize the per-cpu interrupt state and stimer state. + * Then connect to the host. */ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online", hv_synic_init, hv_synic_cleanup); if (ret < 0) - goto err_alloc; + goto err_cpuhp; hyperv_cpuhp_online = ret; ret = vmbus_connect(); @@ -1318,6 +1314,8 @@ static int vmbus_bus_init(void) err_connect: cpuhp_remove_state(hyperv_cpuhp_online); +err_cpuhp: + hv_stimer_free(); err_alloc: hv_synic_free(); hv_remove_vmbus_irq(); @@ -2064,7 +2062,7 @@ static struct acpi_driver vmbus_acpi_driver = { static void hv_kexec_handler(void) { - hv_synic_clockevents_cleanup(); + hv_stimer_global_cleanup(); vmbus_initiate_unload(false); vmbus_connection.conn_state = DISCONNECTED; /* Make sure conn_state is set as hv_synic_cleanup checks for it */ @@ -2075,6 +2073,8 @@ static void hv_kexec_handler(void) static void hv_crash_handler(struct pt_regs *regs) { + int cpu; + vmbus_initiate_unload(true); /* * In crash handler we can't schedule synic cleanup for all CPUs, @@ -2082,7 +2082,9 @@ static void hv_crash_handler(struct pt_regs *regs) * for kdump. */ vmbus_connection.conn_state = DISCONNECTED; - hv_synic_cleanup(smp_processor_id()); + cpu = smp_processor_id(); + hv_stimer_cleanup(cpu); + hv_synic_cleanup(cpu); hyperv_cleanup(); }; @@ -2131,7 +2133,7 @@ static void __exit vmbus_exit(void) hv_remove_kexec_handler(); hv_remove_crash_handler(); vmbus_connection.conn_state = DISCONNECTED; - hv_synic_clockevents_cleanup(); + hv_stimer_global_cleanup(); vmbus_disconnect(); hv_remove_vmbus_irq(); for_each_online_cpu(cpu) { diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h new file mode 100644 index 000000000000..0cd73f7bc992 --- /dev/null +++ b/include/clocksource/hyperv_timer.h @@ -0,0 +1,27 @@ +/* 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 + +#define HV_MAX_MAX_DELTA_TICKS 0xffffffff +#define HV_MIN_DELTA_TICKS 1 + +/* Routines called by the VMbus driver */ +extern int hv_stimer_alloc(int sint); +extern void hv_stimer_free(void); +extern void hv_stimer_init(unsigned int cpu); +extern void hv_stimer_cleanup(unsigned int cpu); +extern void hv_stimer_global_cleanup(void); +extern void hv_stimer0_isr(void); + +#endif -- cgit v1.2.3 From dd2cb348613b44f9d948b068775e159aad298599 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 1 Jul 2019 04:26:06 +0000 Subject: clocksource/drivers: Continue making Hyper-V clocksource ISA agnostic Continue consolidating Hyper-V clock and timer code into an ISA independent Hyper-V clocksource driver. Move the existing clocksource code under drivers/hv and arch/x86 to the new clocksource driver while separating out the ISA dependencies. Update Hyper-V initialization to call initialization and cleanup routines since the Hyper-V synthetic clock is not independently enumerated in ACPI. Update Hyper-V clocksource users in KVM and VDSO to get definitions from the new include file. No behavior is changed and no new functionality is added. Suggested-by: Marc Zyngier Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Reviewed-by: Vitaly Kuznetsov Cc: "bp@alien8.de" Cc: "will.deacon@arm.com" Cc: "catalin.marinas@arm.com" Cc: "mark.rutland@arm.com" Cc: "linux-arm-kernel@lists.infradead.org" Cc: "gregkh@linuxfoundation.org" Cc: "linux-hyperv@vger.kernel.org" Cc: "olaf@aepfle.de" Cc: "apw@canonical.com" Cc: "jasowang@redhat.com" Cc: "marcelo.cerri@canonical.com" Cc: Sunil Muthuswamy Cc: KY Srinivasan Cc: "sashal@kernel.org" Cc: "vincenzo.frascino@arm.com" Cc: "linux-arch@vger.kernel.org" Cc: "linux-mips@vger.kernel.org" Cc: "linux-kselftest@vger.kernel.org" Cc: "arnd@arndb.de" Cc: "linux@armlinux.org.uk" Cc: "ralf@linux-mips.org" Cc: "paul.burton@mips.com" Cc: "daniel.lezcano@linaro.org" Cc: "salyzyn@android.com" Cc: "pcc@google.com" Cc: "shuah@kernel.org" Cc: "0x7f454c46@gmail.com" <0x7f454c46@gmail.com> Cc: "linux@rasmusvillemoes.dk" Cc: "huw@codeweavers.com" Cc: "sfr@canb.auug.org.au" Cc: "pbonzini@redhat.com" Cc: "rkrcmar@redhat.com" Cc: "kvm@vger.kernel.org" Link: https://lkml.kernel.org/r/1561955054-1838-3-git-send-email-mikelley@microsoft.com --- arch/x86/entry/vdso/vma.c | 2 +- arch/x86/hyperv/hv_init.c | 91 +------------------- arch/x86/include/asm/mshyperv.h | 81 +++--------------- arch/x86/include/asm/vdso/gettimeofday.h | 2 +- arch/x86/kvm/x86.c | 1 + drivers/clocksource/hyperv_timer.c | 139 +++++++++++++++++++++++++++++++ drivers/hv/hv_util.c | 1 + include/clocksource/hyperv_timer.h | 80 ++++++++++++++++++ 8 files changed, 237 insertions(+), 160 deletions(-) (limited to 'include/clocksource') diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 8db1f594e8b1..349a61d8bf34 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 1608050e9df9..0e033ef11a9f 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -17,64 +17,13 @@ #include #include #include -#include #include #include #include - -#ifdef CONFIG_HYPERV_TSCPAGE - -static struct ms_hyperv_tsc_page *tsc_pg; - -struct ms_hyperv_tsc_page *hv_get_tsc_page(void) -{ - return tsc_pg; -} -EXPORT_SYMBOL_GPL(hv_get_tsc_page); - -static u64 read_hv_clock_tsc(struct clocksource *arg) -{ - u64 current_tick = hv_read_tsc_page(tsc_pg); - - if (current_tick == U64_MAX) - rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); - - return current_tick; -} - -static struct clocksource hyperv_cs_tsc = { - .name = "hyperv_clocksource_tsc_page", - .rating = 400, - .read = read_hv_clock_tsc, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; -#endif - -static u64 read_hv_clock_msr(struct clocksource *arg) -{ - 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. - */ - rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); - return current_tick; -} - -static struct clocksource hyperv_cs_msr = { - .name = "hyperv_clocksource_msr", - .rating = 400, - .read = read_hv_clock_msr, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; +#include void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); -struct clocksource *hyperv_cs; -EXPORT_SYMBOL_GPL(hyperv_cs); u32 *hv_vp_index; EXPORT_SYMBOL_GPL(hv_vp_index); @@ -343,42 +292,8 @@ void __init hyperv_init(void) x86_init.pci.arch_init = hv_pci_init; - /* - * Register Hyper-V specific clocksource. - */ -#ifdef CONFIG_HYPERV_TSCPAGE - if (ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE) { - union hv_x64_msr_hypercall_contents tsc_msr; - - tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL); - if (!tsc_pg) - goto register_msr_cs; - - hyperv_cs = &hyperv_cs_tsc; - - rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); - - tsc_msr.enable = 1; - tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg); - - wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); - - hyperv_cs_tsc.archdata.vclock_mode = VCLOCK_HVCLOCK; - - clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100); - return; - } -register_msr_cs: -#endif - /* - * For 32 bit guests just use the MSR based mechanism for reading - * the partition counter. - */ - - hyperv_cs = &hyperv_cs_msr; - if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE) - clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); - + /* Register Hyper-V specific clocksource */ + hv_init_clocksource(); return; remove_cpuhp_state: diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index cc60e617931c..f4fa8a9d5d0b 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -105,6 +105,17 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) #define hv_get_crash_ctl(val) \ rdmsrl(HV_X64_MSR_CRASH_CTL, val) +#define hv_get_time_ref_count(val) \ + rdmsrl(HV_X64_MSR_TIME_REF_COUNT, val) + +#define hv_get_reference_tsc(val) \ + rdmsrl(HV_X64_MSR_REFERENCE_TSC, val) +#define hv_set_reference_tsc(val) \ + wrmsrl(HV_X64_MSR_REFERENCE_TSC, val) +#define hv_set_clocksource_vdso(val) \ + ((val).archdata.vclock_mode = VCLOCK_HVCLOCK) +#define hv_get_raw_timer() rdtsc_ordered() + void hyperv_callback_vector(void); void hyperv_reenlightenment_vector(void); #ifdef CONFIG_TRACING @@ -133,7 +144,6 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {} #if IS_ENABLED(CONFIG_HYPERV) -extern struct clocksource *hyperv_cs; extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; @@ -387,73 +397,4 @@ static inline int hyperv_flush_guest_mapping_range(u64 as, } #endif /* CONFIG_HYPERV */ -#ifdef CONFIG_HYPERV_TSCPAGE -struct ms_hyperv_tsc_page *hv_get_tsc_page(void); -static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, - u64 *cur_tsc) -{ - 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 U64_MAX; - /* - * 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 = rdtsc_ordered(); - - /* - * Make sure we read sequence after we read all other values - * from TSC page. - */ - smp_rmb(); - - } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence); - - return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset; -} - -static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) -{ - u64 cur_tsc; - - return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc); -} - -#else -static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void) -{ - return NULL; -} - -static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, - u64 *cur_tsc) -{ - BUG(); - return U64_MAX; -} -#endif #endif diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index a14039a59abd..ae91429129a6 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -18,7 +18,7 @@ #include #include #include -#include +#include #define __vdso_data (VVAR(_vdso_data)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8ec676029365..5e1db26b5e15 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -67,6 +67,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 68a28af31561..ba2c79e6a0ee 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include #include #include #include @@ -198,3 +200,140 @@ void hv_stimer_global_cleanup(void) 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. + */ + +struct clocksource *hyperv_cs; +EXPORT_SYMBOL_GPL(hyperv_cs); + +#ifdef CONFIG_HYPERV_TSCPAGE + +static struct ms_hyperv_tsc_page *tsc_pg; + +struct ms_hyperv_tsc_page *hv_get_tsc_page(void) +{ + return tsc_pg; +} +EXPORT_SYMBOL_GPL(hv_get_tsc_page); + +static u64 notrace read_hv_sched_clock_tsc(void) +{ + u64 current_tick = hv_read_tsc_page(tsc_pg); + + if (current_tick == U64_MAX) + hv_get_time_ref_count(current_tick); + + return current_tick; +} + +static u64 read_hv_clock_tsc(struct clocksource *arg) +{ + return read_hv_sched_clock_tsc(); +} + +static struct clocksource hyperv_cs_tsc = { + .name = "hyperv_clocksource_tsc_page", + .rating = 400, + .read = read_hv_clock_tsc, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; +#endif + +static u64 notrace read_hv_sched_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 read_hv_clock_msr(struct clocksource *arg) +{ + return read_hv_sched_clock_msr(); +} + +static struct clocksource hyperv_cs_msr = { + .name = "hyperv_clocksource_msr", + .rating = 400, + .read = read_hv_clock_msr, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +#ifdef CONFIG_HYPERV_TSCPAGE +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; + + tsc_pg = vmalloc(PAGE_SIZE); + if (!tsc_pg) + return false; + + hyperv_cs = &hyperv_cs_tsc; + phys_addr = page_to_phys(vmalloc_to_page(tsc_pg)); + + /* + * 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); + + /* sched_clock_register is needed on ARM64 but is a no-op on x86 */ + sched_clock_register(read_hv_sched_clock_tsc, 64, HV_CLOCK_HZ); + return true; +} +#else +static bool __init hv_init_tsc_clocksource(void) +{ + return false; +} +#endif + + +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; + + hyperv_cs = &hyperv_cs_msr; + clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); + + /* sched_clock_register is needed on ARM64 but is a no-op on x86 */ + sched_clock_register(read_hv_sched_clock_msr, 64, HV_CLOCK_HZ); +} +EXPORT_SYMBOL_GPL(hv_init_clocksource); diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 7d3d31f099ea..e32681ee7b9f 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include "hyperv_vmbus.h" diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 0cd73f7bc992..a821deb8ecb2 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -13,6 +13,10 @@ #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 @@ -24,4 +28,80 @@ extern void hv_stimer_cleanup(unsigned int cpu); extern void hv_stimer_global_cleanup(void); extern void hv_stimer0_isr(void); +#if IS_ENABLED(CONFIG_HYPERV) +extern struct clocksource *hyperv_cs; +extern void hv_init_clocksource(void); +#endif /* CONFIG_HYPERV */ + +#ifdef CONFIG_HYPERV_TSCPAGE +extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); + +static inline notrace u64 +hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc) +{ + 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 U64_MAX; + /* + * 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); + + return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset; +} + +static inline notrace u64 +hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) +{ + u64 cur_tsc; + + return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc); +} + +#else /* CONFIG_HYPERV_TSC_PAGE */ +static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void) +{ + return NULL; +} + +static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, + u64 *cur_tsc) +{ + return U64_MAX; +} +#endif /* CONFIG_HYPERV_TSCPAGE */ + #endif -- cgit v1.2.3