linux-kernel - RE: [PATCH v5 06/16] x86/hyperv: allocate output arg pages if required

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Tue, 26 Jan 2021 00:41:05 +0000
From:   Michael Kelley <mikelley@...rosoft.com>
To:     Wei Liu <wei.liu@...nel.org>,
        Linux on Hyper-V List <linux-hyperv@...r.kernel.org>
CC:     "virtualization@...ts.linux-foundation.org" 
        <virtualization@...ts.linux-foundation.org>,
        Linux Kernel List <linux-kernel@...r.kernel.org>,
        Vineeth Pillai <viremana@...ux.microsoft.com>,
        Sunil Muthuswamy <sunilmut@...rosoft.com>,
        Nuno Das Neves <nunodasneves@...ux.microsoft.com>,
        "pasha.tatashin@...een.com" <pasha.tatashin@...een.com>,
        Lillian Grassin-Drake <Lillian.GrassinDrake@...rosoft.com>,
        KY Srinivasan <kys@...rosoft.com>,
        Haiyang Zhang <haiyangz@...rosoft.com>,
        Stephen Hemminger <sthemmin@...rosoft.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        "maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)" <x86@...nel.org>,
        "H. Peter Anvin" <hpa@...or.com>
Subject: RE: [PATCH v5 06/16] x86/hyperv: allocate output arg pages if
 required

From: Wei Liu <wei.liu@...nel.org> Sent: Wednesday, January 20, 2021 4:01 AM
> 
> When Linux runs as the root partition, it will need to make hypercalls
> which return data from the hypervisor.
> 
> Allocate pages for storing results when Linux runs as the root
> partition.
> 
> Signed-off-by: Lillian Grassin-Drake <ligrassi@...rosoft.com>
> Co-Developed-by: Lillian Grassin-Drake <ligrassi@...rosoft.com>
> Signed-off-by: Wei Liu <wei.liu@...nel.org>
> ---
> v3: Fix hv_cpu_die to use free_pages.
> v2: Address Vitaly's comments
> ---
>  arch/x86/hyperv/hv_init.c       | 35 ++++++++++++++++++++++++++++-----
>  arch/x86/include/asm/mshyperv.h |  1 +
>  2 files changed, 31 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
> index e04d90af4c27..6f4cb40e53fe 100644
> --- a/arch/x86/hyperv/hv_init.c
> +++ b/arch/x86/hyperv/hv_init.c
> @@ -41,6 +41,9 @@ EXPORT_SYMBOL_GPL(hv_vp_assist_page);
>  void  __percpu **hyperv_pcpu_input_arg;
>  EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
> 
> +void  __percpu **hyperv_pcpu_output_arg;
> +EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg);
> +
>  u32 hv_max_vp_index;
>  EXPORT_SYMBOL_GPL(hv_max_vp_index);
> 
> @@ -73,12 +76,19 @@ static int hv_cpu_init(unsigned int cpu)
>  	void **input_arg;
>  	struct page *pg;
> 
> -	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
>  	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
> -	pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
> +	pg = alloc_pages(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL, hv_root_partition ?
> 1 : 0);
>  	if (unlikely(!pg))
>  		return -ENOMEM;
> +
> +	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
>  	*input_arg = page_address(pg);
> +	if (hv_root_partition) {
> +		void **output_arg;
> +
> +		output_arg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
> +		*output_arg = page_address(pg + 1);
> +	}
> 
>  	hv_get_vp_index(msr_vp_index);
> 
> @@ -205,14 +215,23 @@ static int hv_cpu_die(unsigned int cpu)
>  	unsigned int new_cpu;
>  	unsigned long flags;
>  	void **input_arg;
> -	void *input_pg = NULL;
> +	void *pg;
> 
>  	local_irq_save(flags);
>  	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
> -	input_pg = *input_arg;
> +	pg = *input_arg;
>  	*input_arg = NULL;
> +
> +	if (hv_root_partition) {
> +		void **output_arg;
> +
> +		output_arg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
> +		*output_arg = NULL;
> +	}
> +
>  	local_irq_restore(flags);
> -	free_page((unsigned long)input_pg);
> +
> +	free_pages((unsigned long)pg, hv_root_partition ? 1 : 0);
> 
>  	if (hv_vp_assist_page && hv_vp_assist_page[cpu])
>  		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
> @@ -346,6 +365,12 @@ void __init hyperv_init(void)
> 
>  	BUG_ON(hyperv_pcpu_input_arg == NULL);
> 
> +	/* Allocate the per-CPU state for output arg for root */
> +	if (hv_root_partition) {
> +		hyperv_pcpu_output_arg = alloc_percpu(void *);
> +		BUG_ON(hyperv_pcpu_output_arg == NULL);
> +	}
> +
>  	/* Allocate percpu VP index */
>  	hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
>  				    GFP_KERNEL);
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index ac2b0d110f03..62d9390f1ddf 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -76,6 +76,7 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
>  #if IS_ENABLED(CONFIG_HYPERV)
>  extern void *hv_hypercall_pg;
>  extern void  __percpu  **hyperv_pcpu_input_arg;
> +extern void  __percpu  **hyperv_pcpu_output_arg;
> 
>  static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
>  {
> --
> 2.20.1

I think this all works OK.  But a meta question:  Do we need a separate
per-cpu output argument page?  From the Hyper-V hypercall standpoint, I
don't think input and output args need to be in separate pages.  They both
just need to not cross a page boundary.  As long as we don't have a hypercall
where the sum of the sizes of the input and output args exceeds a page,
we could just have a single page, and split it up in any manner that works
for the particular hypercall.

Thoughts?

Michael