RE: [PATCH v4] drivers/clocksource/hyper-v: Add TSC page support for root partition

[Michael Kelley (LINUX)]

From: Stanislav Kinsburskii <skinsburskii@xxxxxxxxxxxxxxxxxxx> Sent: Friday, November 4, 2022 1:41 PM
> 
> Microsoft Hypervisor root partition has to map the TSC page specified
> by the hypervisor, instead of providing the page to the hypervisor like
> it's done in the guest partitions.
> 
> However, it's too early to map the page when the clock is initialized, so, the
> actual mapping is happening later.
> 
> Signed-off-by: Stanislav Kinsburskiy <stanislav.kinsburskiy@xxxxxxxxx>
> CC: "K. Y. Srinivasan" <kys@xxxxxxxxxxxxx>
> CC: Haiyang Zhang <haiyangz@xxxxxxxxxxxxx>
> CC: Wei Liu <wei.liu@xxxxxxxxxx>
> CC: Dexuan Cui <decui@xxxxxxxxxxxxx>
> CC: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> CC: Ingo Molnar <mingo@xxxxxxxxxx>
> CC: Borislav Petkov <bp@xxxxxxxxx>
> CC: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
> CC: x86@xxxxxxxxxx
> CC: "H. Peter Anvin" <hpa@xxxxxxxxx>
> CC: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
> CC: linux-hyperv@xxxxxxxxxxxxxxx
> CC: linux-kernel@xxxxxxxxxxxxxxx
> ---
>  arch/x86/hyperv/hv_init.c          |    2 ++
>  drivers/clocksource/hyperv_timer.c |   44 +++++++++++++++++++++++++++++-------
>  include/clocksource/hyperv_timer.h |    1 +
>  3 files changed, 38 insertions(+), 9 deletions(-)
> 
> diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
> index f49bc3ec76e6..89954490af93 100644
> --- a/arch/x86/hyperv/hv_init.c
> +++ b/arch/x86/hyperv/hv_init.c
> @@ -464,6 +464,8 @@ void __init hyperv_init(void)
>  		BUG_ON(!src);
>  		memcpy_to_page(pg, 0, src, HV_HYP_PAGE_SIZE);
>  		memunmap(src);
> +
> +		hv_remap_tsc_clocksource();
>  	} else {
>  		hypercall_msr.guest_physical_address =
> vmalloc_to_pfn(hv_hypercall_pg);
>  		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
> diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
> index 9445a1558fe9..c0cef92b12b8 100644
> --- a/drivers/clocksource/hyperv_timer.c
> +++ b/drivers/clocksource/hyperv_timer.c
> @@ -509,9 +509,6 @@ static bool __init hv_init_tsc_clocksource(void)
>  	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
>  		return false;
> 
> -	if (hv_root_partition)
> -		return false;
> -
>  	/*
>  	 * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly
>  	 * handles frequency and offset changes due to live migration,
> @@ -529,16 +526,28 @@ static bool __init hv_init_tsc_clocksource(void)
>  	}
> 
>  	hv_read_reference_counter = read_hv_clock_tsc;
> -	tsc_pfn = HVPFN_DOWN(virt_to_phys(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.
> +	 * TSC page mapping works differently in root compared to guest.
> +	 * - In guest partition the guest PFN has to be passed to the
> +	 *   hypervisor.
> +	 * - In root partition it's other way around: it has to map the PFN
> +	 *   provided by the hypervisor.
> +	 *   But it can't be mapped right here as it's too early and MMU isn't
> +	 *   ready yet. So, we only set the enable bit here and will remap the
> +	 *   page later in hv_remap_tsc_clocksource().
> +	 *
> +	 * It worth mentioning, that TSC clocksource read function
> +	 * (read_hv_clock_tsc) has a MSR-based fallback mechanism, used when
> +	 * TSC page is zeroed (which is the case until the PFN is remapped) and
> +	 * thus TSC clocksource will work even without the real TSC page
> +	 * mapped.
>  	 */
>  	tsc_msr.as_uint64 = hv_get_register(HV_REGISTER_REFERENCE_TSC);
> +	if (hv_root_partition)
> +		tsc_pfn = tsc_msr.pfn;
> +	else
> +		tsc_pfn = HVPFN_DOWN(virt_to_phys(tsc_page));
>  	tsc_msr.enable = 1;
>  	tsc_msr.pfn = tsc_pfn;
>  	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr.as_uint64);
> @@ -573,3 +582,20 @@ void __init hv_init_clocksource(void)
>  	hv_sched_clock_offset = hv_read_reference_counter();
>  	hv_setup_sched_clock(read_hv_sched_clock_msr);
>  }
> +
> +void __init hv_remap_tsc_clocksource(void)
> +{
> +	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
> +		return;
> +
> +	if (!hv_root_partition) {
> +		WARN(1, "%s: attempt to remap TSC page in guest partition\n",
> +		     __func__);
> +		return;
> +	}
> +
> +	tsc_page = memremap(tsc_pfn << HV_HYP_PAGE_SHIFT, sizeof(tsc_pg),
> +			    MEMREMAP_WB);
> +	if (!tsc_page)
> +		pr_err("Failed to remap Hyper-V TSC page.\n");
> +}
> diff --git a/include/clocksource/hyperv_timer.h
> b/include/clocksource/hyperv_timer.h
> index 3078d23faaea..783701a2102d 100644
> --- a/include/clocksource/hyperv_timer.h
> +++ b/include/clocksource/hyperv_timer.h
> @@ -31,6 +31,7 @@ extern void hv_stimer_global_cleanup(void);
>  extern void hv_stimer0_isr(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);
> 

Reviewed-by: Michael Kelley <mikelley@xxxxxxxxxxxxx>